Compare commits

...

144 Commits

Author SHA1 Message Date
Russ Savage
af5017d3dc reviving code from #1447 to a new branch 2018-02-08 15:54:33 -08:00
Daniel Nelson
32dd1b3725 Adjust time of nightly build 2018-02-07 18:37:33 -08:00
Daniel Nelson
1b0e87a8b0 Update changelog 2018-02-07 18:37:32 -08:00
Daniel Nelson
efa9095829 Add TLS support to the mesos input plugin (#3769) 2018-02-07 18:36:38 -08:00
Daniel Nelson
89974d96d7 Install new requirements for fpm gem install 2018-02-06 11:33:18 -08:00
Daniel Nelson
8c51d629eb Update changelog 2018-02-05 12:55:22 -08:00
Andy Cobaugh
ea0be51985 Add additional metrics and reverse metric names option to openldap (#3722) 2018-02-05 12:48:41 -08:00
Daniel Nelson
5639d5608d Update paho mqtt to latest release 2018-02-05 12:20:14 -08:00
Daniel Nelson
9a1d69a2ae Update changelog 2018-02-05 11:17:36 -08:00
Philipp Weber
b7a68eef56 Remove userinfo from url tag in prometheus input (#3743) 2018-02-05 11:16:00 -08:00
Daniel Nelson
be688ec761 Update sample config in contributing docs 2018-02-02 12:31:31 -08:00
Daniel Nelson
3208fc32ee Run nightly build sequentially 2018-02-02 12:31:31 -08:00
Daniel Nelson
1f87c10dd4 Fix Makefile on Windows and use in AppVeyor build (#3748) 2018-02-02 12:25:59 -08:00
Pierre Tessier
281f4d3688 Fix example source_override values in wavefront output (#3744) 2018-02-02 10:51:00 -08:00
Daniel Nelson
3dcf66aed6 Update gitignore 2018-02-01 16:18:01 -08:00
Daniel Nelson
01479af096 Update changelog 2018-02-01 16:12:57 -08:00
Daniel Nelson
23933e1139 Improve procstat readme 2018-02-01 16:12:08 -08:00
Ben Aldrich
a7571d5730 Add native Go method for finding pids to procstat (#3559) 2018-02-01 15:14:27 -08:00
Paul Myjavec
12d62e60b3 Use CircleCI 2.0 for builds (#3731) 2018-02-01 15:05:39 -08:00
Daniel Nelson
4153d2ca42 Update changelog 2018-02-01 12:15:24 -08:00
Daniel Nelson
8c8c9200e7 Update sqlserver readme; enable query_version = 2 in default config
If unset, query_version is still treated as version 1 for compatibility.
2018-02-01 12:13:49 -08:00
Mark Wilkinson - m82labs
426360d61f Add new sql server output data model (#3618) 2018-02-01 11:50:26 -08:00
John Eismeier
86e08e6ce7 Fix spelling mistakes in zipkin and apache inputs (#3741) 2018-02-01 11:15:12 -08:00
Daniel Nelson
a462b555a7 Update changelog 2018-02-01 11:13:14 -08:00
Philipp Weber
a2635573a8 Add TLS and http basic_auth to prometheus_client output (#3719) 2018-02-01 11:12:16 -08:00
Daniel Nelson
ec8e923fda Update documetation style for smart input 2018-02-01 10:51:03 -08:00
Daniel Nelson
d43e8262b7 Update changelog 2018-01-31 12:30:03 -08:00
Laurent Sesquès
7b365180d0 Add Ipset input plugin (#3346) 2018-01-31 12:25:27 -08:00
Daniel Nelson
32732d42f8 Update changelog 2018-01-30 18:08:31 -08:00
Daniel Nelson
10e51e4b49 Set path to / if HOST_MOUNT_PREFIX matches full path (#3736) 2018-01-30 18:06:53 -08:00
Daniel Nelson
3a85e7b1f0 Set release date for 1.5.2 2018-01-30 14:00:34 -08:00
Daniel Nelson
5d87ad85a1 Update changelog 2018-01-30 14:00:33 -08:00
Daniel Nelson
c28d0e1b16 Exclude master_replid fields from redis input (#3725) 2018-01-30 13:58:44 -08:00
Daniel Nelson
1b0a4e49cd Do not build nats input on freebsd
This plugin can work on freebsd, but will only build with cgo
enabled.  For now, disable this plugin to avoid this requirement.
2018-01-30 12:04:21 -08:00
Daniel Nelson
f9c48ee2f0 Update changelog 2018-01-29 14:02:44 -08:00
Philipp Weber
1b84ac08ab Add support for setting bsd source address to the ping input (#3726) 2018-01-29 14:01:00 -08:00
Daniel Nelson
bcefe90846 Update changelog 2018-01-29 12:16:15 -08:00
Ildar Svetlov
da12c64791 Add ability to select which queues will be gathered to rabbitmq input (#3702) 2018-01-29 12:14:49 -08:00
Daniel Nelson
de03ee3caa Update nats readme 2018-01-26 17:15:02 -08:00
Daniel Nelson
fbd3544a9d Add nats input to readme and changelog 2018-01-26 15:18:15 -08:00
Menno Finlay-Smits
fb947e8fe7 Add NATS Monitoring Input Plugin (#3674) 2018-01-26 15:14:54 -08:00
Daniel Nelson
5b130b6ea0 Update changelog 2018-01-26 15:03:19 -08:00
Ivan Lopez
48092ed598 Add RabbitMQ cluster and running nodes count and running node status (#3703) 2018-01-26 15:00:58 -08:00
Daniel Nelson
efb9d5b4cb Return Accumulator interface from NewAccumulator 2018-01-26 11:40:34 -08:00
Peter
c17427631d Expand on tagvalue option in postgresql_extensible (#3720) 2018-01-25 15:38:11 -08:00
Daniel Nelson
8527a1b7b8 Update changelog 2018-01-25 15:05:46 -08:00
Logan
d831dbc51d Allow running as console application on Windows (#2754) 2018-01-25 15:04:09 -08:00
Daniel Nelson
f9c0aa1e23 Update changelog 2018-01-25 13:47:21 -08:00
Pierre Tessier
3e4c91880a Add timeout to wavefront output write (#3711) 2018-01-25 13:44:25 -08:00
Daniel Nelson
899c3a2ae1 Update changelog 2018-01-22 12:06:10 -08:00
Daniel Nelson
4558aeddeb Remove graphite serializer replacement of dot with underscore in field key (#3705) 2018-01-22 12:04:16 -08:00
Daniel Nelson
36c9113917 Update changelog 2018-01-22 12:01:09 -08:00
Daniel Nelson
5270aa451c Avoid loop creation in second processor pass (#3656) 2018-01-22 11:16:07 -08:00
Daniel Nelson
91fc2765b1 Limit wait time for writes in mqtt output (#3699) 2018-01-22 11:15:13 -08:00
Daniel Nelson
ef776f120b Make error loading tls config fatal in mysql input 2018-01-19 12:16:28 -08:00
Daniel Nelson
5bac08662e Update changelog 2018-01-18 17:39:03 -08:00
Piotr Popieluch
601dc99606 Align aggregator period with internal ticker to avoid skipping metrics (#3693)
By the time the aggregator.run() was called about 600ms already passed since setting now which was skewing up the aggregation intervals and skipping metrics.
2018-01-18 17:37:53 -08:00
Daniel Nelson
0f55d9eba2 Update changelog 2018-01-17 15:28:35 -08:00
Piotr Popieluch
f374a295d9 Reconnect before sending graphite metrics if disconnected (#3680) 2018-01-17 15:27:24 -08:00
Daniel Nelson
548157852c Update changelog 2018-01-17 15:14:07 -08:00
Daniel Nelson
822cfbc8e8 Add support for using globs in devices list of diskio input plugin (#3687) 2018-01-17 15:12:05 -08:00
Daniel Nelson
fa5f1bf6d9 Use go-redis for the redis input (#3661) 2018-01-17 14:57:46 -08:00
Daniel Nelson
ad921a3840 Update changelog 2018-01-17 14:38:47 -08:00
Michael Boudreau
9d559292a5 Fix index out of bounds error in solr input plugin (#3683) 2018-01-17 14:37:34 -08:00
Daniel Nelson
6e24056757 Update changelog 2018-01-16 13:46:41 -08:00
Noah Crowley
87830a1c38 Ignore empty lines in Graphite plaintext (#3684) 2018-01-16 13:44:56 -08:00
atzoum
d188b78d9e Add string and boolean support to dropwizard; fix escaping of tags/fields (#3664) 2018-01-16 12:12:14 -08:00
Daniel Nelson
6e4650da3a Update changelog 2018-01-12 17:46:20 -08:00
Jacob McCann
7ab0d50116 Add container health metrics to docker input (#3666) 2018-01-12 17:43:51 -08:00
Daniel Nelson
97f6c9d8e1 Skip intermittent test on CircleCI 2018-01-12 16:49:05 -08:00
Jacob McCann
666eb47613 Listen on localhost interface in tests (#3667) 2018-01-12 12:08:19 -08:00
Daniel Nelson
90b6b760d1 Set 1.5.1 release date 2018-01-10 13:27:58 -08:00
Daniel Nelson
f3147cc44d Skip CircleCI test of tail plugin due to intermittent deadlock 2018-01-09 15:01:20 -08:00
Daniel Nelson
3cf0ba1ccf Pin crate docker image for testing 2018-01-09 13:10:40 -08:00
Daniel Nelson
2b972dcd56 Update release notes 2018-01-08 16:29:59 -08:00
Daniel Nelson
ce06d0cee0 Update changelog 2018-01-08 15:21:20 -08:00
Daniel Nelson
24ae3293bc Update changelog 2018-01-08 15:18:31 -08:00
Daniel Nelson
0ddb1d26a0 Add gjson and match to dependency license file 2018-01-08 15:15:23 -08:00
atzoum
317de40ac4 Add support for dropwizard input format (#2846) 2018-01-08 15:11:36 -08:00
Daniel Nelson
9cfa3b292b Reorder httpjson config to keep variables out of toml table 2018-01-08 15:06:58 -08:00
Daniel Nelson
0bf63a29f1 Update changelog 2018-01-05 16:04:12 -08:00
James
1d86064fb7 Use persistent connection to postgresql database (#2701) 2018-01-05 16:03:09 -08:00
Daniel Nelson
53e7537c5c Fix link to cratedb readme 2018-01-05 16:01:06 -08:00
Daniel Nelson
6dd5c3b2c0 Update changelog 2018-01-05 16:00:44 -08:00
Daniel Nelson
2938c2fa79 Add user privilege level setting to IPMI sensors (#3643) 2018-01-05 15:59:25 -08:00
Daniel Nelson
35f1b9f500 Update changelog 2018-01-05 14:56:54 -08:00
gerardocorea92
ae848e9539 Add available_entropy field to kernel input plugin (#3524) 2018-01-05 14:54:29 -08:00
Daniel Nelson
163f18f959 Update release notes for 1.5 2018-01-04 18:05:21 -08:00
Daniel Nelson
37757b7782 Add link to docs for configuring the openldap monitoring backend 2018-01-04 15:34:55 -08:00
Daniel Nelson
315fd1e987 Update changelog 2018-01-04 15:29:56 -08:00
Daniel Nelson
b0c2bb870e Escape environment variables during config toml parsing (#3637) 2018-01-04 15:28:00 -08:00
Daniel Nelson
11c6a7f9c9 Update changelog 2018-01-03 17:47:13 -08:00
Richard Elling
92acef1664 Add support for additional metrics on Linux in zfs input (#3565) 2018-01-03 17:45:48 -08:00
Daniel Nelson
5397c02570 Update changelog 2018-01-03 17:40:37 -08:00
kerams
87f1d45ee0 Add support for exchanges to RabbitMQ input (#3619) 2018-01-03 17:38:11 -08:00
Daniel Nelson
07cb749e04 Update changelog 2018-01-03 13:44:33 -08:00
kerams
acea7109d4 Fix deliver_get field in rabbitmq input (#3633) 2018-01-03 13:43:17 -08:00
Daniel Nelson
009b649a13 Update changelog 2018-01-02 16:38:20 -08:00
Daniel Nelson
b900967b78 Add wired field to mem input (#3632) 2018-01-02 16:37:11 -08:00
Daniel Nelson
81f42e8b17 Update changelog 2018-01-02 16:36:04 -08:00
Adam Johnson
56be3d3236 Reintroduce AWS credential check to cloudwatch output (#3587) 2018-01-02 16:33:15 -08:00
Daniel Nelson
a440ed8d8c Add information about how to set permissions for postfix input (#3594) 2018-01-02 14:09:14 -08:00
Daniel Nelson
06c21fb9f7 Update changelog 2017-12-28 16:24:04 -08:00
Daniel Nelson
4f7afb8cb5 Set content-type charset in influxdb output and allow it be overridden (#3593) 2017-12-28 16:22:19 -08:00
Daniel Nelson
ef6e5c5a85 Update changelog 2017-12-28 16:19:04 -08:00
Daniel Nelson
005face7c0 Fix DC/OS login expiration time (#3625) 2017-12-28 16:17:40 -08:00
Daniel Nelson
1011cd0c94 Update changelog 2017-12-28 16:12:56 -08:00
Daniel Nelson
6c075c4346 Fix name error in jolokia2_agent sample config (#3624) 2017-12-28 16:10:00 -08:00
Daniel Nelson
7f3f556b39 Fix grammar in haproxy docs 2017-12-21 18:46:03 -08:00
Daniel Nelson
6639f44c17 Fix grammar in dcos readme 2017-12-21 16:26:50 -08:00
Daniel Nelson
801a248668 Update changelog 2017-12-18 20:39:26 -08:00
kerams
496452144c Add messages_delivered_get to rabbitmq_overview (#3596) 2017-12-18 20:36:59 -08:00
Daniel Nelson
3029d58cad Update changelog 2017-12-14 16:59:58 -08:00
Jeff Ashton
fcc9c82d34 Add control over which stats to gather in basicstats aggregator (#3580) 2017-12-14 16:56:10 -08:00
Daniel Nelson
4f1ea13ebf Update bond input description 2017-12-14 16:03:29 -08:00
timhallinflux
b90ee4a43c Improve bond plugin description (#3588) 2017-12-14 15:59:20 -08:00
Daniel Nelson
4537eb2c5d Update haproxy documentation 2017-12-14 15:50:03 -08:00
Daniel Nelson
d6fd9ce738 Set release date for 1.5.0 2017-12-14 10:58:33 -08:00
Daniel Nelson
5b40173bcb Remove AWS credential check from cloudwatch output (#3583)
This method is reported to not work with IAM Instance Profiles, and we
do not want to make any calls that would require additional permissions.
2017-12-13 17:51:55 -08:00
Brian Knight
6638fc68de Update README with missing Redis measurements (#3582) 2017-12-13 11:24:48 -08:00
Antoine Augusti
9ad0297b1f Fix refType documentation for GitHub webhooks (#3579) 2017-12-13 11:22:47 -08:00
Daniel Nelson
15266bb7eb Update changelog 2017-12-13 11:17:36 -08:00
Ildar Svetlov
d935dfa9ed Don't add system input uptime_format as a counter (#3578) 2017-12-13 11:13:56 -08:00
Daniel Nelson
8785c7d78d Update changelog 2017-12-13 10:58:50 -08:00
Logan
fb3d66cdd3 Typo and sentence consistency (#3581) 2017-12-13 10:51:15 -08:00
Daniel Nelson
de180d1e56 Update changelog 2017-12-12 13:32:47 -08:00
Mike Danko
df9c7590b3 Fix various mysql data type conversions (#3554) 2017-12-12 13:22:11 -08:00
Steve Banik
d7d224d511 Fixed typo in README.md (#3574) 2017-12-12 11:21:32 -08:00
Daniel Nelson
abcad439eb Update changelog 2017-12-11 18:01:50 -08:00
Daniel Nelson
8484de6c12 Fix separation of multiple prometheus_client outputs (#3570) 2017-12-11 18:00:19 -08:00
Daniel Nelson
ab8376de03 Update exec plugin documentation 2017-12-11 17:58:06 -08:00
Daniel Nelson
ff634c5056 Update changelog 2017-12-11 15:34:52 -08:00
Daniel Nelson
14b31a2354 Add idle state to processes test 2017-12-11 15:33:44 -08:00
Ted Zlatanov
663a5b1f50 Support I (idle) process state on procfs+Linux (#3530) 2017-12-11 15:31:52 -08:00
Daniel Nelson
93d16a4603 Use auto type detection for scanned devices in smart input (#3561) 2017-12-08 18:03:12 -08:00
Daniel Nelson
88746b01c3 Update changelog 2017-12-08 18:02:01 -08:00
Daniel Nelson
37095ef47d Update sarama-cluster to latest release (#3560) 2017-12-08 17:59:06 -08:00
Daniel Nelson
4f42d8a298 Add benchmark test for single metric 2017-12-08 13:23:08 -08:00
Daniel Nelson
574034c301 Use device name instead of abs path for devices tag in smart input (#3550) 2017-12-08 13:22:41 -08:00
Daniel Nelson
654e953a89 Update changelog 2017-12-07 11:32:54 -08:00
Arkady Emelyanov
4d91162abd Add health status mapping from string to int in elasticsearch input (#3551) 2017-12-07 11:31:03 -08:00
Daniel Nelson
177e7e2c73 Log connect error only in wavefront output (#3549) 2017-12-06 14:55:29 -08:00
Daniel Nelson
d8966d5067 Fix formatting in changelog 2017-12-04 13:18:14 -08:00
Daniel Nelson
bdda6ceb70 Update next version number for dev builds 2017-12-01 11:52:46 -08:00
161 changed files with 7114 additions and 3565 deletions

49
.circleci/config.yml Normal file
View File

@@ -0,0 +1,49 @@
---
defaults: &defaults
docker:
- image: 'circleci/golang:1.9.2'
working_directory: '/go/src/github.com/influxdata/telegraf'
version: 2
jobs:
build:
<<: *defaults
steps:
- checkout
- run: 'make ci-test'
release:
<<: *defaults
steps:
- checkout
- run: './scripts/release.sh'
- store_artifacts:
path: './artifacts'
destination: '.'
nightly:
<<: *defaults
steps:
- checkout
- run: './scripts/release.sh'
- store_artifacts:
path: './artifacts'
destination: '.'
workflows:
version: 2
build_and_release:
jobs:
- 'build'
- 'release':
requires:
- 'build'
nightly:
jobs:
- 'build'
- 'nightly':
requires:
- 'build'
triggers:
- schedule:
cron: "0 18 * * *"
filters:
branches:
only:
- master

4
.gitignore vendored
View File

@@ -1,7 +1,5 @@
build
tivan
.vagrant
/telegraf
.idea
/telegraf.gz
*~
*#

View File

@@ -1,15 +1,111 @@
## v1.5 [unreleased]
## v1.6 [unreleased]
### Release Notes
- The `mysql` input plugin has been updated to convert values to the
correct data type. This may cause a `field type error` when inserting into
InfluxDB due the change of types. It is recommended to drop the `mysql`,
`mysql_variables`, and `mysql_innodb`:
```
DROP MEASUREMENT mysql
DROP MEASUREMENT mysql_variables
DROP MEASUREMENT mysql_innodb
```
- The `postgresql` plugins now defaults to using a persistent connection to the database.
In environments where TCP connections are terminated the `max_lifetime`
setting should be set less than the collection `interval` to prevent errors.
- The `sqlserver` input plugin has a new query and data model that can be enabled
by setting `query_version = 2`. It is encouraged to migrate to the new
model when possible as the old version is deprecated and will be removed in
a future version.
- An option has been added to the `openldap` input plugin that reverses metric
name to improve grouping. This change is enabled when `reverse_metric_names = true`
is set. It is encouraged to enable this option when possible as the old
ordering is deprecated.
### New Plugins
- [ipset](./plugins/inputs/ipset/README.md) - Thanks to @sajoupa
- [nats](./plugins/inputs/nats/README.md) - Thanks to @mjs & @levex
### Features
- [#3551](https://github.com/influxdata/telegraf/pull/3551): Add health status mapping from string to int in elasticsearch input.
- [#3580](https://github.com/influxdata/telegraf/pull/3580): Add control over which stats to gather in basicstats aggregator.
- [#3596](https://github.com/influxdata/telegraf/pull/3596): Add messages_delivered_get to rabbitmq input.
- [#3632](https://github.com/influxdata/telegraf/pull/3632): Add wired field to mem input.
- [#3619](https://github.com/influxdata/telegraf/pull/3619): Add support for gathering exchange metrics to the rabbitmq input.
- [#3565](https://github.com/influxdata/telegraf/pull/3565): Add support for additional metrics on Linux in zfs input.
- [#3524](https://github.com/influxdata/telegraf/pull/3524): Add available_entropy field to kernel input plugin.
- [#3643](https://github.com/influxdata/telegraf/pull/3643): Add user privilege level setting to IPMI sensors.
- [#2701](https://github.com/influxdata/telegraf/pull/2701): Use persistent connection to postgresql database.
- [#2846](https://github.com/influxdata/telegraf/pull/2846): Add support for dropwizard input format.
- [#3666](https://github.com/influxdata/telegraf/pull/3666): Add container health metrics to docker input.
- [#3687](https://github.com/influxdata/telegraf/pull/3687): Add support for using globs in devices list of diskio input plugin.
- [#2754](https://github.com/influxdata/telegraf/pull/2754): Allow running as console application on Windows.
- [#3703](https://github.com/influxdata/telegraf/pull/3703): Add listener counts and node running status to rabbitmq input.
- [#3674](https://github.com/influxdata/telegraf/pull/3674): Add NATS Monitoring Input Plugin.
- [#3702](https://github.com/influxdata/telegraf/pull/3702): Add ability to select which queues will be gathered in rabbitmq input.
- [#3726](https://github.com/influxdata/telegraf/pull/3726): Add support for setting bsd source address to the ping input.
- [#3346](https://github.com/influxdata/telegraf/pull/3346): Add Ipset input plugin.
- [#3719](https://github.com/influxdata/telegraf/pull/3719): Add TLS and HTTP basic auth to prometheus_client output.
- [#3618](https://github.com/influxdata/telegraf/pull/3618): Add new sqlserver output data model.
- [#3559](https://github.com/influxdata/telegraf/pull/3559): Add native Go method for finding pids to procstat.
- [#3722](https://github.com/influxdata/telegraf/pull/3722): Add additional metrics and reverse metric names option to openldap.
- [#3769](https://github.com/influxdata/telegraf/pull/3769): Add TLS support to the mesos input plugin.
### Bugfixes
- [#1896](https://github.com/influxdata/telegraf/issues/1896): Fix various mysql data type conversions.
## v1.5.3 [unreleased]
### Bugfixes
- [#3729](https://github.com/influxdata/telegraf/issues/3729): Set path to / if HOST_MOUNT_PREFIX matches full path.
- [#3739](https://github.com/influxdata/telegraf/issues/3739): Remove userinfo from url tag in prometheus input.
## v1.5.2 [2018-01-30]
### Bugfixes
- [#3684](https://github.com/influxdata/telegraf/pull/3684): Ignore empty lines in Graphite plaintext.
- [#3604](https://github.com/influxdata/telegraf/issues/3604): Fix index out of bounds error in solr input plugin.
- [#3680](https://github.com/influxdata/telegraf/pull/3680): Reconnect before sending graphite metrics if disconnected.
- [#3693](https://github.com/influxdata/telegraf/pull/3693): Align aggregator period with internal ticker to avoid skipping metrics.
- [#3629](https://github.com/influxdata/telegraf/issues/3629): Fix a potential deadlock when using aggregators.
- [#3697](https://github.com/influxdata/telegraf/issues/3697): Limit wait time for writes in mqtt output.
- [#3698](https://github.com/influxdata/telegraf/issues/3698): Revert change in graphite output where dot in field key was replaced by underscore.
- [#3710](https://github.com/influxdata/telegraf/issues/3710): Add timeout to wavefront output write.
- [#3725](https://github.com/influxdata/telegraf/issues/3725): Exclude master_replid fields from redis input.
## v1.5.1 [2018-01-10]
### Bugfixes
- [#3624](https://github.com/influxdata/telegraf/pull/3624): Fix name error in jolokia2_agent sample config.
- [#3625](https://github.com/influxdata/telegraf/pull/3625): Fix DC/OS login expiration time.
- [#3593](https://github.com/influxdata/telegraf/pull/3593): Set Content-Type charset in influxdb output and allow it be overridden.
- [#3594](https://github.com/influxdata/telegraf/pull/3594): Document permissions setup for postfix input.
- [#3633](https://github.com/influxdata/telegraf/pull/3633): Fix deliver_get field in rabbitmq input.
- [#3607](https://github.com/influxdata/telegraf/issues/3607): Escape environment variables during config toml parsing.
## v1.5 [2017-12-14]
### New Plugins
- [basicstats](./plugins/aggregators/basicstats/README.md) - Thanks to @toni-moreno
- [bond](./plugins/inputs/bond/README.md) - Thanks to @ildarsv
- [cratedb](./plugins/outputs/wavefront/README.md) - Thanks to @felixge
- [cratedb](./plugins/outputs/cratedb/README.md) - Thanks to @felixge
- [dcos](./plugins/inputs/dcos/README.md) - Thanks to @influxdata
- [jolokia2](./plugins/inputs/jolokia2/README.md) - Thanks to @dylanmei
- [nginx_plus](./plugins/inputs/nginx_plus/README.md) - Thanks to @mplonka & @poblahblahblah
- [opensmtpd](./plugins/inputs/opensmtpd/README.md) - Thanks to @aromeyer
- [particle](./plugins/inputs/webhooks/particle/README.md) - Thanks to @davidgs
- [pf](./plugins/inputs/pf/README.md) Thanks to @nferch
- [pf](./plugins/inputs/pf/README.md) - Thanks to @nferch
- [postfix](./plugins/inputs/postfix/README.md) - Thanks to @phemmer
- [smart](./plugins/inputs/smart/README.md) - Thanks to @rickard-von-essen
- [solr](./plugins/inputs/solr/README.md) - Thanks to @ljagiello
@@ -28,6 +124,11 @@
plugin is deprecated and will be removed in a future release. Users of this
plugin are encouraged to update to the new `jolokia2` plugin.
- In the `postgresql` and `postgresql_extensible` plugins, the type of the oid
data type has changed from string to integer. It is recommended to drop
affected fields until a new shard is started. For details on how to
workaround this issue please see [#3622](https://github.com/influxdata/telegraf/issues/3622).
### Features
- [#3170](https://github.com/influxdata/telegraf/pull/3170): Add support for sharding based on metric name.
@@ -78,6 +179,7 @@
- [#3140](https://github.com/influxdata/telegraf/pull/3140): Add support for glob patterns in net input plugin.
- [#3405](https://github.com/influxdata/telegraf/pull/3405): Add input plugin for OpenBSD/FreeBSD pf.
- [#3528](https://github.com/influxdata/telegraf/pull/3528): Add option to amqp output to publish persistent messages.
- [#3530](https://github.com/influxdata/telegraf/pull/3530): Support I (idle) process state on procfs+Linux.
### Bugfixes
@@ -92,6 +194,9 @@
- [#3263](https://github.com/influxdata/telegraf/issues/3263): Fix snmp-tools output parsing with Windows EOLs.
- [#3447](https://github.com/influxdata/telegraf/issues/3447): Add shadow-utils dependency to rpm package.
- [#3448](https://github.com/influxdata/telegraf/issues/3448): Use deb-systemd-invoke to restart service.
- [#3553](https://github.com/influxdata/telegraf/issues/3553): Fix kafka_consumer outside range of offsets error.
- [#3568](https://github.com/influxdata/telegraf/issues/3568): Fix separation of multiple prometheus_client outputs.
- [#3577](https://github.com/influxdata/telegraf/issues/3577): Don't add system input uptime_format as a counter.
## v1.4.5 [2017-12-01]

View File

@@ -79,7 +79,10 @@ func (s *Simple) Description() string {
}
func (s *Simple) SampleConfig() string {
return "ok = true # indicate if everything is fine"
return `
## Indicate if everything is fine
ok = true
`
}
func (s *Simple) Gather(acc telegraf.Accumulator) error {
@@ -207,7 +210,9 @@ func (s *Simple) Description() string {
}
func (s *Simple) SampleConfig() string {
return "url = localhost"
return `
ok = true
`
}
func (s *Simple) Connect() error {

10
Godeps
View File

@@ -4,7 +4,7 @@ github.com/amir/raidman c74861fe6a7bb8ede0a010ce4485bdbb4fc4c985
github.com/apache/thrift 4aaa92ece8503a6da9bc6701604f69acf2b99d07
github.com/aws/aws-sdk-go c861d27d0304a79f727e9a8a4e2ac1e74602fdc0
github.com/beorn7/perks 4c0e84591b9aa9e6dcfdf3e020114cd81f89d5f9
github.com/bsm/sarama-cluster ccdc0803695fbce22f1706d04ded46cd518fd832
github.com/bsm/sarama-cluster abf039439f66c1ce78017f560b490612552f6472
github.com/cenkalti/backoff b02f2bbce11d7ea6b97f282ef1771b0fe2f65ef3
github.com/couchbase/go-couchbase bfe555a140d53dc1adf390f1a1d4b0fd4ceadb28
github.com/couchbase/gomemcached 4a25d2f4e1dea9ea7dd76dfd943407abf9b07d29
@@ -16,7 +16,7 @@ github.com/docker/go-connections 990a1a1a70b0da4c4cb70e117971a4f0babfbf1a
github.com/eapache/go-resiliency b86b1ec0dd4209a588dc1285cdd471e73525c0b3
github.com/eapache/go-xerial-snappy bb955e01b9346ac19dc29eb16586c90ded99a98c
github.com/eapache/queue 44cc805cf13205b55f69e14bcb69867d1ae92f98
github.com/eclipse/paho.mqtt.golang d4f545eb108a2d19f9b1a735689dbfb719bc21fb
github.com/eclipse/paho.mqtt.golang aff15770515e3c57fc6109da73d42b0d46f7f483
github.com/go-logfmt/logfmt 390ab7935ee28ec6b286364bba9b4dd6410cb3d5
github.com/go-sql-driver/mysql 2e00b5cd70399450106cec6431c2e2ce3cae5034
github.com/gobwas/glob bea32b9cd2d6f55753d94a28e959b13f0244797a
@@ -27,6 +27,7 @@ github.com/golang/snappy 7db9049039a047d955fe8c19b83c8ff5abd765c7
github.com/go-ole/go-ole be49f7c07711fcb603cff39e1de7c67926dc0ba7
github.com/google/go-cmp f94e52cad91c65a63acc1e75d4be223ea22e99bc
github.com/gorilla/mux 392c28fe23e1c45ddba891b0320b3b5df220beea
github.com/go-redis/redis 73b70592cdaa9e6abdfcfbf97b4a90d80728c836
github.com/go-sql-driver/mysql 2e00b5cd70399450106cec6431c2e2ce3cae5034
github.com/hailocab/go-hostpool e80d13ce29ede4452c43dea11e79b9bc8a15b478
github.com/hashicorp/consul 63d2fc68239b996096a1c55a0d4b400ea4c2583f
@@ -44,6 +45,7 @@ github.com/miekg/dns 99f84ae56e75126dd77e5de4fae2ea034a468ca1
github.com/mitchellh/mapstructure d0303fe809921458f417bcf828397a65db30a7e4
github.com/multiplay/go-ts3 07477f49b8dfa3ada231afc7b7b17617d42afe8e
github.com/naoina/go-stringutil 6b638e95a32d0c1131db0e7fe83775cbea4a0d0b
github.com/nats-io/gnatsd 393bbb7c031433e68707c8810fda0bfcfbe6ab9b
github.com/nats-io/go-nats ea9585611a4ab58a205b9b125ebd74c389a6b898
github.com/nats-io/nats ea9585611a4ab58a205b9b125ebd74c389a6b898
github.com/nats-io/nuid 289cccf02c178dc782430d534e3c1f5b72af807f
@@ -65,13 +67,15 @@ github.com/samuel/go-zookeeper 1d7be4effb13d2d908342d349d71a284a7542693
github.com/satori/go.uuid 5bf94b69c6b68ee1b541973bb8e1144db23a194b
github.com/shirou/gopsutil 384a55110aa5ae052eb93ea94940548c1e305a99
github.com/shirou/w32 3c9377fc6748f222729a8270fe2775d149a249ad
github.com/Shopify/sarama c01858abb625b73a3af51d0798e4ad42c8147093
github.com/Shopify/sarama 3b1b38866a79f06deddf0487d5c27ba0697ccd65
github.com/Sirupsen/logrus 61e43dc76f7ee59a82bdf3d71033dc12bea4c77d
github.com/soniah/gosnmp 5ad50dc75ab389f8a1c9f8a67d3a1cd85f67ed15
github.com/StackExchange/wmi f3e2bae1e0cb5aef83e319133eabfee30013a4a5
github.com/streadway/amqp 63795daa9a446c920826655f26ba31c81c860fd6
github.com/stretchr/objx 1a9d0bb9f541897e62256577b352fdbc1fb4fd94
github.com/stretchr/testify 4d4bfba8f1d1027c4fdbe371823030df51419987
github.com/tidwall/gjson 0623bd8fbdbf97cc62b98d15108832851a658e59
github.com/tidwall/match 173748da739a410c5b0b813b956f89ff94730b4c
github.com/vjeantet/grok d73e972b60935c7fec0b4ffbc904ed39ecaf7efe
github.com/wvanbergen/kafka bc265fedb9ff5b5c5d3c0fdcef4a819b3523d3ee
github.com/wvanbergen/kazoo-go 968957352185472eacb69215fa3dbfcfdbac1096

120
Makefile
View File

@@ -2,6 +2,9 @@ PREFIX := /usr/local
VERSION := $(shell git describe --exact-match --tags 2>/dev/null)
BRANCH := $(shell git rev-parse --abbrev-ref HEAD)
COMMIT := $(shell git rev-parse --short HEAD)
GOFILES ?= $(shell git ls-files '*.go')
GOFMT ?= $(shell gofmt -l $(GOFILES))
ifdef GOBIN
PATH := $(GOBIN):$(PATH)
else
@@ -16,10 +19,18 @@ ifdef VERSION
endif
all:
$(MAKE) fmtcheck
$(MAKE) deps
$(MAKE) telegraf
ci-test:
$(MAKE) deps
$(MAKE) fmtcheck
$(MAKE) vet
$(MAKE) test
deps:
go get -u github.com/golang/lint/golint
go get github.com/sparrc/gdm
gdm restore
@@ -36,98 +47,53 @@ install: telegraf
test:
go test -short ./...
fmt:
@gofmt -w $(GOFILES)
fmtcheck:
@echo '[INFO] running gofmt to identify incorrectly formatted code...'
@if [ ! -z $(GOFMT) ]; then \
echo "[ERROR] gofmt has found errors in the following files:" ; \
echo "$(GOFMT)" ; \
echo "" ;\
echo "Run make fmt to fix them." ; \
exit 1 ;\
fi
@echo '[INFO] done.'
lint:
golint ./...
test-windows:
go test ./plugins/inputs/ping/...
go test ./plugins/inputs/win_perf_counters/...
go test ./plugins/inputs/win_services/...
go test ./plugins/inputs/procstat/...
lint:
go vet ./...
# vet runs the Go source code static analysis tool `vet` to find
# any common errors.
vet:
@echo 'go vet $$(go list ./...)'
@go vet $$(go list ./...) ; if [ $$? -eq 1 ]; then \
echo ""; \
echo "go vet has found suspicious constructs. Please remediate any reported errors"; \
echo "to fix them before submitting code for review."; \
exit 1; \
fi
test-all: lint
test-all: vet
go test ./...
package:
./scripts/build.py --package --platform=all --arch=all
clean:
-rm -f telegraf
-rm -f telegraf.exe
rm -f telegraf
rm -f telegraf.exe
docker-image:
./scripts/build.py --package --platform=linux --arch=amd64
cp build/telegraf*$(COMMIT)*.deb .
docker build -f scripts/dev.docker --build-arg "package=telegraf*$(COMMIT)*.deb" -t "telegraf-dev:$(COMMIT)" .
# Run all docker containers necessary for integration tests
docker-run:
docker run --name aerospike -p "3000:3000" -d aerospike/aerospike-server:3.9.0
docker run --name zookeeper -p "2181:2181" -d wurstmeister/zookeeper
docker run --name kafka \
--link zookeeper:zookeeper \
-e KAFKA_ADVERTISED_HOST_NAME=localhost \
-e KAFKA_ADVERTISED_PORT=9092 \
-e KAFKA_ZOOKEEPER_CONNECT=zookeeper:2181 \
-e KAFKA_CREATE_TOPICS="test:1:1" \
-p "9092:9092" \
-d wurstmeister/kafka
docker run --name elasticsearch -p "9200:9200" -p "9300:9300" -d elasticsearch:5
docker run --name mysql -p "3306:3306" -e MYSQL_ALLOW_EMPTY_PASSWORD=yes -d mysql
docker run --name memcached -p "11211:11211" -d memcached
docker run --name postgres -p "5432:5432" -d postgres
docker run --name rabbitmq -p "15672:15672" -p "5672:5672" -d rabbitmq:3-management
docker run --name redis -p "6379:6379" -d redis
docker run --name nsq -p "4150:4150" -d nsqio/nsq /nsqd
docker run --name mqtt -p "1883:1883" -d ncarlier/mqtt
docker run --name riemann -p "5555:5555" -d stealthly/docker-riemann
docker run --name nats -p "4222:4222" -d nats
docker run --name openldap \
-e SLAPD_CONFIG_ROOTDN="cn=manager,cn=config" \
-e SLAPD_CONFIG_ROOTPW="secret" \
-p "389:389" -p "636:636" \
-d cobaugh/openldap-alpine
docker run --name cratedb \
-p "6543:5432" \
-d crate crate \
-Cnetwork.host=0.0.0.0 \
-Ctransport.host=localhost \
-Clicense.enterprise=false
# Run docker containers necessary for integration tests; skipping services provided
# by CircleCI
docker-run-circle:
docker run --name aerospike -p "3000:3000" -d aerospike/aerospike-server:3.9.0
docker run --name zookeeper -p "2181:2181" -d wurstmeister/zookeeper
docker run --name kafka \
--link zookeeper:zookeeper \
-e KAFKA_ADVERTISED_HOST_NAME=localhost \
-e KAFKA_ADVERTISED_PORT=9092 \
-e KAFKA_ZOOKEEPER_CONNECT=zookeeper:2181 \
-e KAFKA_CREATE_TOPICS="test:1:1" \
-p "9092:9092" \
-d wurstmeister/kafka
docker run --name elasticsearch -p "9200:9200" -p "9300:9300" -d elasticsearch:5
docker run --name nsq -p "4150:4150" -d nsqio/nsq /nsqd
docker run --name mqtt -p "1883:1883" -d ncarlier/mqtt
docker run --name riemann -p "5555:5555" -d stealthly/docker-riemann
docker run --name nats -p "4222:4222" -d nats
docker run --name openldap \
-e SLAPD_CONFIG_ROOTDN="cn=manager,cn=config" \
-e SLAPD_CONFIG_ROOTPW="secret" \
-p "389:389" -p "636:636" \
-d cobaugh/openldap-alpine
docker run --name cratedb \
-p "6543:5432" \
-d crate crate \
-Cnetwork.host=0.0.0.0 \
-Ctransport.host=localhost \
-Clicense.enterprise=false
docker-kill:
-docker kill aerospike elasticsearch kafka memcached mqtt mysql nats nsq \
openldap postgres rabbitmq redis riemann zookeeper cratedb
-docker rm aerospike elasticsearch kafka memcached mqtt mysql nats nsq \
openldap postgres rabbitmq redis riemann zookeeper cratedb
.PHONY: deps telegraf telegraf.exe install test test-windows lint test-all \
package clean docker-run docker-run-circle docker-kill docker-image
.PHONY: deps telegraf install test test-windows lint vet test-all package clean docker-image fmtcheck

View File

@@ -159,6 +159,7 @@ configuration options.
* [interrupts](./plugins/inputs/interrupts)
* [ipmi_sensor](./plugins/inputs/ipmi_sensor)
* [iptables](./plugins/inputs/iptables)
* [ipset](./plugins/inputs/ipset)
* [jolokia](./plugins/inputs/jolokia) (deprecated, use [jolokia2](./plugins/inputs/jolokia2))
* [jolokia2](./plugins/inputs/jolokia2)
* [kapacitor](./plugins/inputs/kapacitor)
@@ -171,6 +172,7 @@ configuration options.
* [minecraft](./plugins/inputs/minecraft)
* [mongodb](./plugins/inputs/mongodb)
* [mysql](./plugins/inputs/mysql)
* [nats](./plugins/inputs/nats)
* [net_response](./plugins/inputs/net_response)
* [nginx](./plugins/inputs/nginx)
* [nginx_plus](./plugins/inputs/nginx_plus)
@@ -256,6 +258,7 @@ formats may be used with input plugins supporting the `data_format` option:
* [Value](./docs/DATA_FORMATS_INPUT.md#value)
* [Nagios](./docs/DATA_FORMATS_INPUT.md#nagios)
* [Collectd](./docs/DATA_FORMATS_INPUT.md#collectd)
* [Dropwizard](./docs/DATA_FORMATS_INPUT.md#dropwizard)
## Processor Plugins

View File

@@ -26,7 +26,7 @@ type MetricMaker interface {
func NewAccumulator(
maker MetricMaker,
metrics chan telegraf.Metric,
) *accumulator {
) telegraf.Accumulator {
acc := accumulator{
maker: maker,
metrics: metrics,

View File

@@ -115,15 +115,15 @@ func TestAddNoIntervalWithPrecision(t *testing.T) {
map[string]interface{}{"value": float64(101)},
map[string]string{"acc": "test"}, now)
testm := <-a.metrics
testm := <-metrics
actual := testm.String()
assert.Contains(t, actual, "acctest value=101")
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Contains(t, actual, "acctest,acc=test value=101")
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Equal(t,
fmt.Sprintf("acctest,acc=test value=101 %d\n", int64(1139572800000000000)),
@@ -147,15 +147,15 @@ func TestAddDisablePrecision(t *testing.T) {
map[string]interface{}{"value": float64(101)},
map[string]string{"acc": "test"}, now)
testm := <-a.metrics
testm := <-metrics
actual := testm.String()
assert.Contains(t, actual, "acctest value=101")
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Contains(t, actual, "acctest,acc=test value=101")
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Equal(t,
fmt.Sprintf("acctest,acc=test value=101 %d\n", int64(1139572800082912748)),
@@ -179,15 +179,15 @@ func TestAddNoPrecisionWithInterval(t *testing.T) {
map[string]interface{}{"value": float64(101)},
map[string]string{"acc": "test"}, now)
testm := <-a.metrics
testm := <-metrics
actual := testm.String()
assert.Contains(t, actual, "acctest value=101")
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Contains(t, actual, "acctest,acc=test value=101")
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Equal(t,
fmt.Sprintf("acctest,acc=test value=101 %d\n", int64(1139572800000000000)),
@@ -204,7 +204,7 @@ func TestDifferentPrecisions(t *testing.T) {
a.AddFields("acctest",
map[string]interface{}{"value": float64(101)},
map[string]string{"acc": "test"}, now)
testm := <-a.metrics
testm := <-metrics
actual := testm.String()
assert.Equal(t,
fmt.Sprintf("acctest,acc=test value=101 %d\n", int64(1139572800000000000)),
@@ -214,7 +214,7 @@ func TestDifferentPrecisions(t *testing.T) {
a.AddFields("acctest",
map[string]interface{}{"value": float64(101)},
map[string]string{"acc": "test"}, now)
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Equal(t,
fmt.Sprintf("acctest,acc=test value=101 %d\n", int64(1139572800083000000)),
@@ -224,7 +224,7 @@ func TestDifferentPrecisions(t *testing.T) {
a.AddFields("acctest",
map[string]interface{}{"value": float64(101)},
map[string]string{"acc": "test"}, now)
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Equal(t,
fmt.Sprintf("acctest,acc=test value=101 %d\n", int64(1139572800082913000)),
@@ -234,7 +234,7 @@ func TestDifferentPrecisions(t *testing.T) {
a.AddFields("acctest",
map[string]interface{}{"value": float64(101)},
map[string]string{"acc": "test"}, now)
testm = <-a.metrics
testm = <-metrics
actual = testm.String()
assert.Equal(t,
fmt.Sprintf("acctest,acc=test value=101 %d\n", int64(1139572800082912748)),

View File

@@ -143,7 +143,7 @@ func (a *Agent) gatherer(
func gatherWithTimeout(
shutdown chan struct{},
input *models.RunningInput,
acc *accumulator,
acc telegraf.Accumulator,
timeout time.Duration,
) {
ticker := time.NewTicker(timeout)
@@ -308,7 +308,13 @@ func (a *Agent) flusher(shutdown chan struct{}, metricC chan telegraf.Metric, ag
metrics = processor.Apply(metrics...)
}
for _, m := range metrics {
outMetricC <- m
for i, o := range a.Config.Outputs {
if i == len(a.Config.Outputs)-1 {
o.AddMetric(m)
} else {
o.AddMetric(m.Copy())
}
}
}
}
}
@@ -364,8 +370,6 @@ func (a *Agent) Run(shutdown chan struct{}) error {
metricC := make(chan telegraf.Metric, 100)
aggC := make(chan telegraf.Metric, 100)
now := time.Now()
// Start all ServicePlugins
for _, input := range a.Config.Inputs {
input.SetDefaultTags(a.Config.Tags)
@@ -406,7 +410,7 @@ func (a *Agent) Run(shutdown chan struct{}) error {
acc := NewAccumulator(agg, aggC)
acc.SetPrecision(a.Config.Agent.Precision.Duration,
a.Config.Agent.Interval.Duration)
agg.Run(acc, now, shutdown)
agg.Run(acc, shutdown)
}(aggregator)
}

View File

@@ -23,7 +23,8 @@ install:
- go env
build_script:
- cmd: C:\GnuWin32\bin\make
- cmd: C:\GnuWin32\bin\make deps
- cmd: C:\GnuWin32\bin\make telegraf
test_script:
- cmd: C:\GnuWin32\bin\make test-windows

View File

@@ -1,19 +0,0 @@
machine:
services:
- docker
- memcached
- redis
- rabbitmq-server
post:
- sudo rm -rf /usr/local/go
- wget https://storage.googleapis.com/golang/go1.9.2.linux-amd64.tar.gz
- sudo tar -C /usr/local -xzf go1.9.2.linux-amd64.tar.gz
- go version
dependencies:
override:
- docker info
test:
override:
- bash scripts/circle-test.sh

View File

@@ -54,9 +54,10 @@ var fUsage = flag.String("usage", "",
"print usage for a plugin, ie, 'telegraf --usage mysql'")
var fService = flag.String("service", "",
"operate on the service")
var fRunAsConsole = flag.Bool("console", false, "run as console application (windows only)")
var (
nextVersion = "1.5.0"
nextVersion = "1.6.0"
version string
commit string
branch string
@@ -358,7 +359,7 @@ func main() {
return
}
if runtime.GOOS == "windows" {
if runtime.GOOS == "windows" && !(*fRunAsConsole) {
svcConfig := &service.Config{
Name: "telegraf",
DisplayName: "Telegraf Data Collector Service",

93
docker-compose.yml Normal file
View File

@@ -0,0 +1,93 @@
version: '3'
services:
aerospike:
image: aerospike/aerospike-server:3.9.0
ports:
- "3000:3000"
zookeeper:
image: wurstmeister/zookeeper
environment:
- JAVA_OPTS="-Xms256m -Xmx256m"
ports:
- "2181:2181"
kafka:
image: wurstmeister/kafka
environment:
- KAFKA_ADVERTISED_HOST_NAME=localhost
- KAFKA_ADVERTISED_PORT=9092
- KAFKA_ZOOKEEPER_CONNECT=zookeeper:2181
- KAFKA_CREATE_TOPICS="test:1:1"
- JAVA_OPTS="-Xms256m -Xmx256m"
ports:
- "9092:9092"
depends_on:
- zookeeper
elasticsearch:
image: elasticsearch:5
environment:
- JAVA_OPTS="-Xms256m -Xmx256m"
ports:
- "9200:9200"
- "9300:9300"
mysql:
image: mysql
environment:
- MYSQL_ALLOW_EMPTY_PASSWORD=yes
ports:
- "3306:3306"
memcached:
image: memcached
ports:
- "11211:11211"
postgres:
image: postgres:alpine
ports:
- "5432:5432"
rabbitmq:
image: rabbitmq:3-management
ports:
- "15672:15672"
- "5672:5672"
redis:
image: redis:alpine
ports:
- "6379:6379"
nsq:
image: nsqio/nsq
ports:
- "4150:4150"
command: "/nsqd"
mqtt:
image: ncarlier/mqtt
ports:
- "1883:1883"
riemann:
image: stealthly/docker-riemann
ports:
- "5555:5555"
nats:
image: nats
ports:
- "4222:4222"
openldap:
image: cobaugh/openldap-alpine
environment:
- SLAPD_CONFIG_ROOTDN="cn=manager,cn=config"
- SLAPD_CONFIG_ROOTPW="secret"
ports:
- "389:389"
- "636:636"
crate:
image: crate/crate
ports:
- "4200:4200"
- "4230:4230"
command:
- crate
- -Cnetwork.host=0.0.0.0
- -Ctransport.host=localhost
- -Clicense.enterprise=false
environment:
- CRATE_HEAP_SIZE=128m
- JAVA_OPTS='-Xms256m -Xmx256m'

View File

@@ -125,7 +125,7 @@ aggregator and will not get sent to the output plugins.
* **name_suffix**: Specifies a suffix to attach to the measurement name.
* **tags**: A map of tags to apply to a specific input's measurements.
The [measurement filtering](#measurement-filtering) parameters be used to
The [measurement filtering](#measurement-filtering) parameters can be used to
limit what metrics are handled by the aggregator. Excluded metrics are passed
downstream to the next aggregator.
@@ -136,7 +136,7 @@ The following config parameters are available for all processors:
* **order**: This is the order in which the processor(s) get executed. If this
is not specified then processor execution order will be random.
The [measurement filtering](#measurement-filtering) can parameters may be used
The [measurement filtering](#measurement-filtering) parameters can be used
to limit what metrics are handled by the processor. Excluded metrics are
passed downstream to the next processor.

View File

@@ -8,6 +8,7 @@ Telegraf is able to parse the following input data formats into metrics:
1. [Value](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#value), ie: 45 or "booyah"
1. [Nagios](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#nagios) (exec input only)
1. [Collectd](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#collectd)
1. [Dropwizard](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#dropwizard)
Telegraf metrics, like InfluxDB
[points](https://docs.influxdata.com/influxdb/v0.10/write_protocols/line/),
@@ -479,3 +480,176 @@ You can also change the path to the typesdb or add additional typesdb using
## Path of to TypesDB specifications
collectd_typesdb = ["/usr/share/collectd/types.db"]
```
# Dropwizard:
The dropwizard format can parse the JSON representation of a single dropwizard metric registry. By default, tags are parsed from metric names as if they were actual influxdb line protocol keys (`measurement<,tag_set>`) which can be overriden by defining custom [measurement & tag templates](./DATA_FORMATS_INPUT.md#measurement--tag-templates). All field value types are supported, `string`, `number` and `boolean`.
A typical JSON of a dropwizard metric registry:
```json
{
"version": "3.0.0",
"counters" : {
"measurement,tag1=green" : {
"count" : 1
}
},
"meters" : {
"measurement" : {
"count" : 1,
"m15_rate" : 1.0,
"m1_rate" : 1.0,
"m5_rate" : 1.0,
"mean_rate" : 1.0,
"units" : "events/second"
}
},
"gauges" : {
"measurement" : {
"value" : 1
}
},
"histograms" : {
"measurement" : {
"count" : 1,
"max" : 1.0,
"mean" : 1.0,
"min" : 1.0,
"p50" : 1.0,
"p75" : 1.0,
"p95" : 1.0,
"p98" : 1.0,
"p99" : 1.0,
"p999" : 1.0,
"stddev" : 1.0
}
},
"timers" : {
"measurement" : {
"count" : 1,
"max" : 1.0,
"mean" : 1.0,
"min" : 1.0,
"p50" : 1.0,
"p75" : 1.0,
"p95" : 1.0,
"p98" : 1.0,
"p99" : 1.0,
"p999" : 1.0,
"stddev" : 1.0,
"m15_rate" : 1.0,
"m1_rate" : 1.0,
"m5_rate" : 1.0,
"mean_rate" : 1.0,
"duration_units" : "seconds",
"rate_units" : "calls/second"
}
}
}
```
Would get translated into 4 different measurements:
```
measurement,metric_type=counter,tag1=green count=1
measurement,metric_type=meter count=1,m15_rate=1.0,m1_rate=1.0,m5_rate=1.0,mean_rate=1.0
measurement,metric_type=gauge value=1
measurement,metric_type=histogram count=1,max=1.0,mean=1.0,min=1.0,p50=1.0,p75=1.0,p95=1.0,p98=1.0,p99=1.0,p999=1.0
measurement,metric_type=timer count=1,max=1.0,mean=1.0,min=1.0,p50=1.0,p75=1.0,p95=1.0,p98=1.0,p99=1.0,p999=1.0,stddev=1.0,m15_rate=1.0,m1_rate=1.0,m5_rate=1.0,mean_rate=1.0
```
You may also parse a dropwizard registry from any JSON document which contains a dropwizard registry in some inner field.
Eg. to parse the following JSON document:
```json
{
"time" : "2017-02-22T14:33:03.662+02:00",
"tags" : {
"tag1" : "green",
"tag2" : "yellow"
},
"metrics" : {
"counters" : {
"measurement" : {
"count" : 1
}
},
"meters" : {},
"gauges" : {},
"histograms" : {},
"timers" : {}
}
}
```
and translate it into:
```
measurement,metric_type=counter,tag1=green,tag2=yellow count=1 1487766783662000000
```
you simply need to use the following additional configuration properties:
```toml
dropwizard_metric_registry_path = "metrics"
dropwizard_time_path = "time"
dropwizard_time_format = "2006-01-02T15:04:05Z07:00"
dropwizard_tags_path = "tags"
## tag paths per tag are supported too, eg.
#[inputs.yourinput.dropwizard_tag_paths]
# tag1 = "tags.tag1"
# tag2 = "tags.tag2"
```
For more information about the dropwizard json format see
[here](http://metrics.dropwizard.io/3.1.0/manual/json/).
#### Dropwizard Configuration:
```toml
[[inputs.exec]]
## Commands array
commands = ["curl http://localhost:8080/sys/metrics"]
timeout = "5s"
## Data format to consume.
## Each data format has its own unique set of configuration options, read
## more about them here:
## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
data_format = "dropwizard"
## Used by the templating engine to join matched values when cardinality is > 1
separator = "_"
## Each template line requires a template pattern. It can have an optional
## filter before the template and separated by spaces. It can also have optional extra
## tags following the template. Multiple tags should be separated by commas and no spaces
## similar to the line protocol format. There can be only one default template.
## Templates support below format:
## 1. filter + template
## 2. filter + template + extra tag(s)
## 3. filter + template with field key
## 4. default template
## By providing an empty template array, templating is disabled and measurements are parsed as influxdb line protocol keys (measurement<,tag_set>)
templates = []
## You may use an appropriate [gjson path](https://github.com/tidwall/gjson#path-syntax)
## to locate the metric registry within the JSON document
# dropwizard_metric_registry_path = "metrics"
## You may use an appropriate [gjson path](https://github.com/tidwall/gjson#path-syntax)
## to locate the default time of the measurements within the JSON document
# dropwizard_time_path = "time"
# dropwizard_time_format = "2006-01-02T15:04:05Z07:00"
## You may use an appropriate [gjson path](https://github.com/tidwall/gjson#path-syntax)
## to locate the tags map within the JSON document
# dropwizard_tags_path = "tags"
## You may even use tag paths per tag
# [inputs.exec.dropwizard_tag_paths]
# tag1 = "tags.tag1"
# tag2 = "tags.tag2"
```

View File

@@ -54,6 +54,7 @@ following works:
- github.com/miekg/dns [BSD](https://github.com/miekg/dns/blob/master/LICENSE)
- github.com/naoina/go-stringutil [MIT](https://github.com/naoina/go-stringutil/blob/master/LICENSE)
- github.com/naoina/toml [MIT](https://github.com/naoina/toml/blob/master/LICENSE)
- github.com/nats-io/gnatsd [MIT](https://github.com/nats-io/gnatsd/blob/master/LICENSE)
- github.com/nats-io/go-nats [MIT](https://github.com/nats-io/go-nats/blob/master/LICENSE)
- github.com/nats-io/nats [MIT](https://github.com/nats-io/nats/blob/master/LICENSE)
- github.com/nats-io/nuid [MIT](https://github.com/nats-io/nuid/blob/master/LICENSE)
@@ -82,6 +83,8 @@ following works:
- github.com/streadway/amqp [BSD](https://github.com/streadway/amqp/blob/master/LICENSE)
- github.com/stretchr/objx [MIT](https://github.com/stretchr/objx/blob/master/LICENSE.md)
- github.com/stretchr/testify [MIT](https://github.com/stretchr/testify/blob/master/LICENCE.txt)
- github.com/tidwall/gjson [MIT](https://github.com/tidwall/gjson/blob/master/LICENSE)
- github.com/tidwall/match [MIT](https://github.com/tidwall/match/blob/master/LICENSE)
- github.com/mitchellh/mapstructure [MIT](https://github.com/mitchellh/mapstructure/blob/master/LICENSE)
- github.com/multiplay/go-ts3 [BSD](https://github.com/multiplay/go-ts3/blob/master/LICENSE)
- github.com/vjeantet/grok [APACHE](https://github.com/vjeantet/grok/blob/master/LICENSE)

View File

@@ -1391,7 +1391,7 @@
# ## By default, some of the fields are renamed from what haproxy calls them.
# ## Setting this option to true results in the plugin keeping the original
# ## field names.
# # keep_field_names = true
# # keep_field_names = false
#
# ## Optional SSL Config
# # ssl_ca = "/etc/telegraf/ca.pem"
@@ -1661,7 +1661,7 @@
# # insecure_skip_verify = false
#
# ## Add metrics to read
# [[inputs.jolokia2.metric]]
# [[inputs.jolokia2_agent.metric]]
# name = "java_runtime"
# mbean = "java.lang:type=Runtime"
# paths = ["Uptime"]

View File

@@ -40,6 +40,11 @@ var (
// envVarRe is a regex to find environment variables in the config file
envVarRe = regexp.MustCompile(`\$\w+`)
envVarEscaper = strings.NewReplacer(
`"`, `\"`,
`\`, `\\`,
)
)
// Config specifies the URL/user/password for the database that telegraf
@@ -689,6 +694,11 @@ func trimBOM(f []byte) []byte {
return bytes.TrimPrefix(f, []byte("\xef\xbb\xbf"))
}
// escapeEnv escapes a value for inserting into a TOML string.
func escapeEnv(value string) string {
return envVarEscaper.Replace(value)
}
// parseFile loads a TOML configuration from a provided path and
// returns the AST produced from the TOML parser. When loading the file, it
// will find environment variables and replace them.
@@ -702,8 +712,9 @@ func parseFile(fpath string) (*ast.Table, error) {
env_vars := envVarRe.FindAll(contents, -1)
for _, env_var := range env_vars {
env_val := os.Getenv(strings.TrimPrefix(string(env_var), "$"))
if env_val != "" {
env_val, ok := os.LookupEnv(strings.TrimPrefix(string(env_var), "$"))
if ok {
env_val = escapeEnv(env_val)
contents = bytes.Replace(contents, env_var, []byte(env_val), 1)
}
}
@@ -1261,6 +1272,47 @@ func buildParser(name string, tbl *ast.Table) (parsers.Parser, error) {
}
}
if node, ok := tbl.Fields["dropwizard_metric_registry_path"]; ok {
if kv, ok := node.(*ast.KeyValue); ok {
if str, ok := kv.Value.(*ast.String); ok {
c.DropwizardMetricRegistryPath = str.Value
}
}
}
if node, ok := tbl.Fields["dropwizard_time_path"]; ok {
if kv, ok := node.(*ast.KeyValue); ok {
if str, ok := kv.Value.(*ast.String); ok {
c.DropwizardTimePath = str.Value
}
}
}
if node, ok := tbl.Fields["dropwizard_time_format"]; ok {
if kv, ok := node.(*ast.KeyValue); ok {
if str, ok := kv.Value.(*ast.String); ok {
c.DropwizardTimeFormat = str.Value
}
}
}
if node, ok := tbl.Fields["dropwizard_tags_path"]; ok {
if kv, ok := node.(*ast.KeyValue); ok {
if str, ok := kv.Value.(*ast.String); ok {
c.DropwizardTagsPath = str.Value
}
}
}
c.DropwizardTagPathsMap = make(map[string]string)
if node, ok := tbl.Fields["dropwizard_tag_paths"]; ok {
if subtbl, ok := node.(*ast.Table); ok {
for name, val := range subtbl.Fields {
if kv, ok := val.(*ast.KeyValue); ok {
if str, ok := kv.Value.(*ast.String); ok {
c.DropwizardTagPathsMap[name] = str.Value
}
}
}
}
}
c.MetricName = name
delete(tbl.Fields, "data_format")
@@ -1271,6 +1323,11 @@ func buildParser(name string, tbl *ast.Table) (parsers.Parser, error) {
delete(tbl.Fields, "collectd_auth_file")
delete(tbl.Fields, "collectd_security_level")
delete(tbl.Fields, "collectd_typesdb")
delete(tbl.Fields, "dropwizard_metric_registry_path")
delete(tbl.Fields, "dropwizard_time_path")
delete(tbl.Fields, "dropwizard_time_format")
delete(tbl.Fields, "dropwizard_tags_path")
delete(tbl.Fields, "dropwizard_tag_paths")
return parsers.NewParser(c)
}

View File

@@ -44,6 +44,9 @@ var (
)
func TestRunTimeout(t *testing.T) {
if testing.Short() {
t.Skip("Skipping test due to random failures.")
}
if sleepbin == "" {
t.Skip("'sleep' binary not available on OS, skipping.")
}
@@ -58,6 +61,8 @@ func TestRunTimeout(t *testing.T) {
}
func TestCombinedOutputTimeout(t *testing.T) {
// TODO: Fix this test
t.Skip("Test failing too often, skip for now and revisit later.")
if sleepbin == "" {
t.Skip("'sleep' binary not available on OS, skipping.")
}
@@ -109,6 +114,8 @@ func TestRunError(t *testing.T) {
}
func TestRandomSleep(t *testing.T) {
// TODO: Fix this test
t.Skip("Test failing too often, skip for now and revisit later.")
// test that zero max returns immediately
s := time.Now()
RandomSleep(time.Duration(0), make(chan struct{}))

View File

@@ -114,7 +114,6 @@ func (r *RunningAggregator) reset() {
// for period ticks to tell it when to push and reset the aggregator.
func (r *RunningAggregator) Run(
acc telegraf.Accumulator,
now time.Time,
shutdown chan struct{},
) {
// The start of the period is truncated to the nearest second.
@@ -133,6 +132,7 @@ func (r *RunningAggregator) Run(
// 2nd interval: 00:10 - 00:20.5
// etc.
//
now := time.Now()
r.periodStart = now.Truncate(time.Second)
truncation := now.Sub(r.periodStart)
r.periodEnd = r.periodStart.Add(r.Config.Period)

View File

@@ -24,7 +24,7 @@ func TestAdd(t *testing.T) {
})
assert.NoError(t, ra.Config.Filter.Compile())
acc := testutil.Accumulator{}
go ra.Run(&acc, time.Now(), make(chan struct{}))
go ra.Run(&acc, make(chan struct{}))
m := ra.MakeMetric(
"RITest",
@@ -55,7 +55,7 @@ func TestAddMetricsOutsideCurrentPeriod(t *testing.T) {
})
assert.NoError(t, ra.Config.Filter.Compile())
acc := testutil.Accumulator{}
go ra.Run(&acc, time.Now(), make(chan struct{}))
go ra.Run(&acc, make(chan struct{}))
// metric before current period
m := ra.MakeMetric(
@@ -113,7 +113,7 @@ func TestAddAndPushOnePeriod(t *testing.T) {
wg.Add(1)
go func() {
defer wg.Done()
ra.Run(&acc, time.Now(), shutdown)
ra.Run(&acc, shutdown)
}()
m := ra.MakeMetric(

View File

@@ -0,0 +1,86 @@
package templating
import (
"sort"
"strings"
)
const (
// DefaultSeparator is the default separation character to use when separating template parts.
DefaultSeparator = "."
)
// Engine uses a Matcher to retrieve the appropriate template and applies the template
// to the input string
type Engine struct {
joiner string
matcher *matcher
}
// Apply extracts the template fields from the given line and returns the measurement
// name, tags and field name
func (e *Engine) Apply(line string) (string, map[string]string, string, error) {
return e.matcher.match(line).Apply(line, e.joiner)
}
// NewEngine creates a new templating engine
func NewEngine(joiner string, defaultTemplate *Template, templates []string) (*Engine, error) {
engine := Engine{
joiner: joiner,
matcher: newMatcher(defaultTemplate),
}
templateSpecs := parseTemplateSpecs(templates)
for _, templateSpec := range templateSpecs {
if err := engine.matcher.addSpec(templateSpec); err != nil {
return nil, err
}
}
return &engine, nil
}
func parseTemplateSpecs(templates []string) templateSpecs {
tmplts := templateSpecs{}
for _, pattern := range templates {
tmplt := templateSpec{
separator: DefaultSeparator,
}
// Format is [separator] [filter] <template> [tag1=value1,tag2=value2]
parts := strings.Fields(pattern)
partsLength := len(parts)
if partsLength < 1 {
// ignore
continue
}
if partsLength == 1 {
tmplt.template = pattern
} else if partsLength == 4 {
tmplt.separator = parts[0]
tmplt.filter = parts[1]
tmplt.template = parts[2]
tmplt.tagstring = parts[3]
} else {
hasTagstring := strings.Contains(parts[partsLength-1], "=")
if hasTagstring {
tmplt.tagstring = parts[partsLength-1]
tmplt.template = parts[partsLength-2]
if partsLength == 3 {
tmplt.filter = parts[0]
}
} else {
tmplt.template = parts[partsLength-1]
if partsLength == 2 {
tmplt.filter = parts[0]
} else { // length == 3
tmplt.separator = parts[0]
tmplt.filter = parts[1]
}
}
}
tmplts = append(tmplts, tmplt)
}
sort.Sort(tmplts)
return tmplts
}

View File

@@ -0,0 +1,58 @@
package templating
import (
"strings"
)
// matcher determines which template should be applied to a given metric
// based on a filter tree.
type matcher struct {
root *node
defaultTemplate *Template
}
// newMatcher creates a new matcher.
func newMatcher(defaultTemplate *Template) *matcher {
return &matcher{
root: &node{},
defaultTemplate: defaultTemplate,
}
}
func (m *matcher) addSpec(tmplt templateSpec) error {
// Parse out the default tags specific to this template
tags := map[string]string{}
if tmplt.tagstring != "" {
for _, kv := range strings.Split(tmplt.tagstring, ",") {
parts := strings.Split(kv, "=")
tags[parts[0]] = parts[1]
}
}
tmpl, err := NewTemplate(tmplt.separator, tmplt.template, tags)
if err != nil {
return err
}
m.add(tmplt.filter, tmpl)
return nil
}
// add inserts the template in the filter tree based the given filter
func (m *matcher) add(filter string, template *Template) {
if filter == "" {
m.defaultTemplate = template
m.root.separator = template.separator
return
}
m.root.insert(filter, template)
}
// match returns the template that matches the given measurement line.
// If no template matches, the default template is returned.
func (m *matcher) match(line string) *Template {
tmpl := m.root.search(line)
if tmpl != nil {
return tmpl
}
return m.defaultTemplate
}

122
internal/templating/node.go Normal file
View File

@@ -0,0 +1,122 @@
package templating
import (
"sort"
"strings"
)
// node is an item in a sorted k-ary tree of filter parts. Each child is sorted by its part value.
// The special value of "*", is always sorted last.
type node struct {
separator string
value string
children nodes
template *Template
}
// insert inserts the given string template into the tree. The filter string is separated
// on the template separator and each part is used as the path in the tree.
func (n *node) insert(filter string, template *Template) {
n.separator = template.separator
n.recursiveInsert(strings.Split(filter, n.separator), template)
}
// recursiveInsert does the actual recursive insertion
func (n *node) recursiveInsert(values []string, template *Template) {
// Add the end, set the template
if len(values) == 0 {
n.template = template
return
}
// See if the the current element already exists in the tree. If so, insert the
// into that sub-tree
for _, v := range n.children {
if v.value == values[0] {
v.recursiveInsert(values[1:], template)
return
}
}
// New element, add it to the tree and sort the children
newNode := &node{value: values[0]}
n.children = append(n.children, newNode)
sort.Sort(&n.children)
// Now insert the rest of the tree into the new element
newNode.recursiveInsert(values[1:], template)
}
// search searches for a template matching the input string
func (n *node) search(line string) *Template {
separator := n.separator
return n.recursiveSearch(strings.Split(line, separator))
}
// recursiveSearch performs the actual recursive search
func (n *node) recursiveSearch(lineParts []string) *Template {
// Nothing to search
if len(lineParts) == 0 || len(n.children) == 0 {
return n.template
}
// If last element is a wildcard, don't include it in this search since it's sorted
// to the end but lexicographically it would not always be and sort.Search assumes
// the slice is sorted.
length := len(n.children)
if n.children[length-1].value == "*" {
length--
}
// Find the index of child with an exact match
i := sort.Search(length, func(i int) bool {
return n.children[i].value >= lineParts[0]
})
// Found an exact match, so search that child sub-tree
if i < len(n.children) && n.children[i].value == lineParts[0] {
return n.children[i].recursiveSearch(lineParts[1:])
}
// Not an exact match, see if we have a wildcard child to search
if n.children[len(n.children)-1].value == "*" {
return n.children[len(n.children)-1].recursiveSearch(lineParts[1:])
}
return n.template
}
// nodes is simply an array of nodes implementing the sorting interface.
type nodes []*node
// Less returns a boolean indicating whether the filter at position j
// is less than the filter at position k. Filters are order by string
// comparison of each component parts. A wildcard value "*" is never
// less than a non-wildcard value.
//
// For example, the filters:
// "*.*"
// "servers.*"
// "servers.localhost"
// "*.localhost"
//
// Would be sorted as:
// "servers.localhost"
// "servers.*"
// "*.localhost"
// "*.*"
func (n *nodes) Less(j, k int) bool {
if (*n)[j].value == "*" && (*n)[k].value != "*" {
return false
}
if (*n)[j].value != "*" && (*n)[k].value == "*" {
return true
}
return (*n)[j].value < (*n)[k].value
}
// Swap swaps two elements of the array
func (n *nodes) Swap(i, j int) { (*n)[i], (*n)[j] = (*n)[j], (*n)[i] }
// Len returns the length of the array
func (n *nodes) Len() int { return len(*n) }

View File

@@ -0,0 +1,148 @@
package templating
import (
"fmt"
"strings"
)
// Template represents a pattern and tags to map a metric string to a influxdb Point
type Template struct {
separator string
parts []string
defaultTags map[string]string
greedyField bool
greedyMeasurement bool
}
// apply extracts the template fields from the given line and returns the measurement
// name, tags and field name
func (t *Template) Apply(line string, joiner string) (string, map[string]string, string, error) {
fields := strings.Split(line, t.separator)
var (
measurement []string
tags = make(map[string][]string)
field []string
)
// Set any default tags
for k, v := range t.defaultTags {
tags[k] = append(tags[k], v)
}
// See if an invalid combination has been specified in the template:
for _, tag := range t.parts {
if tag == "measurement*" {
t.greedyMeasurement = true
} else if tag == "field*" {
t.greedyField = true
}
}
if t.greedyField && t.greedyMeasurement {
return "", nil, "",
fmt.Errorf("either 'field*' or 'measurement*' can be used in each "+
"template (but not both together): %q",
strings.Join(t.parts, joiner))
}
for i, tag := range t.parts {
if i >= len(fields) {
continue
}
if tag == "" {
continue
}
switch tag {
case "measurement":
measurement = append(measurement, fields[i])
case "field":
field = append(field, fields[i])
case "field*":
field = append(field, fields[i:]...)
break
case "measurement*":
measurement = append(measurement, fields[i:]...)
break
default:
tags[tag] = append(tags[tag], fields[i])
}
}
// Convert to map of strings.
outtags := make(map[string]string)
for k, values := range tags {
outtags[k] = strings.Join(values, joiner)
}
return strings.Join(measurement, joiner), outtags, strings.Join(field, joiner), nil
}
func NewDefaultTemplateWithPattern(pattern string) (*Template, error) {
return NewTemplate(DefaultSeparator, pattern, nil)
}
// NewTemplate returns a new template ensuring it has a measurement
// specified.
func NewTemplate(separator string, pattern string, defaultTags map[string]string) (*Template, error) {
parts := strings.Split(pattern, separator)
hasMeasurement := false
template := &Template{
separator: separator,
parts: parts,
defaultTags: defaultTags,
}
for _, part := range parts {
if strings.HasPrefix(part, "measurement") {
hasMeasurement = true
}
if part == "measurement*" {
template.greedyMeasurement = true
} else if part == "field*" {
template.greedyField = true
}
}
if !hasMeasurement {
return nil, fmt.Errorf("no measurement specified for template. %q", pattern)
}
return template, nil
}
// templateSpec is a template string split in its constituent parts
type templateSpec struct {
separator string
filter string
template string
tagstring string
}
// templateSpecs is simply an array of template specs implementing the sorting interface
type templateSpecs []templateSpec
// Less reports whether the element with
// index j should sort before the element with index k.
func (e templateSpecs) Less(j, k int) bool {
if len(e[j].filter) == 0 && len(e[k].filter) == 0 {
jlength := len(strings.Split(e[j].template, e[j].separator))
klength := len(strings.Split(e[k].template, e[k].separator))
return jlength < klength
}
if len(e[j].filter) == 0 {
return true
}
if len(e[k].filter) == 0 {
return false
}
jlength := len(strings.Split(e[j].template, e[j].separator))
klength := len(strings.Split(e[k].template, e[k].separator))
return jlength < klength
}
// Swap swaps the elements with indexes i and j.
func (e templateSpecs) Swap(i, j int) { e[i], e[j] = e[j], e[i] }
// Len is the number of elements in the collection.
func (e templateSpecs) Len() int { return len(e) }

View File

@@ -8,14 +8,26 @@ emitting the aggregate every `period` seconds.
```toml
# Keep the aggregate basicstats of each metric passing through.
[[aggregators.basicstats]]
## General Aggregator Arguments:
## The period on which to flush & clear the aggregator.
period = "30s"
## If true, the original metric will be dropped by the
## aggregator and will not get sent to the output plugins.
drop_original = false
## BasicStats Arguments:
## Configures which basic stats to push as fields
stats = ["count","min","max","mean","stdev","s2"]
```
- stats
- If not specified, all stats are aggregated and pushed as fields
- If empty array, no stats are aggregated
### Measurements & Fields:
- measurement1

View File

@@ -1,6 +1,7 @@
package basicstats
import (
"log"
"math"
"github.com/influxdata/telegraf"
@@ -8,10 +9,22 @@ import (
)
type BasicStats struct {
cache map[uint64]aggregate
Stats []string `toml:"stats"`
cache map[uint64]aggregate
statsConfig *configuredStats
}
func NewBasicStats() telegraf.Aggregator {
type configuredStats struct {
count bool
min bool
max bool
mean bool
variance bool
stdev bool
}
func NewBasicStats() *BasicStats {
mm := &BasicStats{}
mm.Reset()
return mm
@@ -114,25 +127,103 @@ func (m *BasicStats) Add(in telegraf.Metric) {
}
func (m *BasicStats) Push(acc telegraf.Accumulator) {
config := getConfiguredStats(m)
for _, aggregate := range m.cache {
fields := map[string]interface{}{}
for k, v := range aggregate.fields {
fields[k+"_count"] = v.count
fields[k+"_min"] = v.min
fields[k+"_max"] = v.max
fields[k+"_mean"] = v.mean
if config.count {
fields[k+"_count"] = v.count
}
if config.min {
fields[k+"_min"] = v.min
}
if config.max {
fields[k+"_max"] = v.max
}
if config.mean {
fields[k+"_mean"] = v.mean
}
//v.count always >=1
if v.count > 1 {
variance := v.M2 / (v.count - 1)
fields[k+"_s2"] = variance
fields[k+"_stdev"] = math.Sqrt(variance)
if config.variance {
fields[k+"_s2"] = variance
}
if config.stdev {
fields[k+"_stdev"] = math.Sqrt(variance)
}
}
//if count == 1 StdDev = infinite => so I won't send data
}
acc.AddFields(aggregate.name, fields, aggregate.tags)
if len(fields) > 0 {
acc.AddFields(aggregate.name, fields, aggregate.tags)
}
}
}
func parseStats(names []string) *configuredStats {
parsed := &configuredStats{}
for _, name := range names {
switch name {
case "count":
parsed.count = true
case "min":
parsed.min = true
case "max":
parsed.max = true
case "mean":
parsed.mean = true
case "s2":
parsed.variance = true
case "stdev":
parsed.stdev = true
default:
log.Printf("W! Unrecognized basic stat '%s', ignoring", name)
}
}
return parsed
}
func defaultStats() *configuredStats {
defaults := &configuredStats{}
defaults.count = true
defaults.min = true
defaults.max = true
defaults.mean = true
defaults.variance = true
defaults.stdev = true
return defaults
}
func getConfiguredStats(m *BasicStats) *configuredStats {
if m.statsConfig == nil {
if m.Stats == nil {
m.statsConfig = defaultStats()
} else {
m.statsConfig = parseStats(m.Stats)
}
}
return m.statsConfig
}
func (m *BasicStats) Reset() {
m.cache = make(map[uint64]aggregate)
}

View File

@@ -149,3 +149,211 @@ func TestBasicStatsDifferentPeriods(t *testing.T) {
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test only aggregating count
func TestBasicStatsWithOnlyCount(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"count"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
expectedFields := map[string]interface{}{
"a_count": float64(2),
"b_count": float64(2),
"c_count": float64(2),
"d_count": float64(2),
"e_count": float64(1),
}
expectedTags := map[string]string{
"foo": "bar",
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test only aggregating minimum
func TestBasicStatsWithOnlyMin(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"min"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
expectedFields := map[string]interface{}{
"a_min": float64(1),
"b_min": float64(1),
"c_min": float64(2),
"d_min": float64(2),
"e_min": float64(200),
}
expectedTags := map[string]string{
"foo": "bar",
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test only aggregating maximum
func TestBasicStatsWithOnlyMax(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"max"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
expectedFields := map[string]interface{}{
"a_max": float64(1),
"b_max": float64(3),
"c_max": float64(4),
"d_max": float64(6),
"e_max": float64(200),
}
expectedTags := map[string]string{
"foo": "bar",
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test only aggregating mean
func TestBasicStatsWithOnlyMean(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"mean"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
expectedFields := map[string]interface{}{
"a_mean": float64(1),
"b_mean": float64(2),
"c_mean": float64(3),
"d_mean": float64(4),
"e_mean": float64(200),
}
expectedTags := map[string]string{
"foo": "bar",
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test only aggregating variance
func TestBasicStatsWithOnlyVariance(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"s2"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
expectedFields := map[string]interface{}{
"a_s2": float64(0),
"b_s2": float64(2),
"c_s2": float64(2),
"d_s2": float64(8),
}
expectedTags := map[string]string{
"foo": "bar",
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test only aggregating standard deviation
func TestBasicStatsWithOnlyStandardDeviation(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"stdev"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
expectedFields := map[string]interface{}{
"a_stdev": float64(0),
"b_stdev": math.Sqrt(2),
"c_stdev": math.Sqrt(2),
"d_stdev": math.Sqrt(8),
}
expectedTags := map[string]string{
"foo": "bar",
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test only aggregating minimum and maximum
func TestBasicStatsWithMinAndMax(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"min", "max"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
expectedFields := map[string]interface{}{
"a_max": float64(1), //a
"a_min": float64(1),
"b_max": float64(3), //b
"b_min": float64(1),
"c_max": float64(4), //c
"c_min": float64(2),
"d_max": float64(6), //d
"d_min": float64(2),
"e_max": float64(200), //e
"e_min": float64(200),
}
expectedTags := map[string]string{
"foo": "bar",
}
acc.AssertContainsTaggedFields(t, "m1", expectedFields, expectedTags)
}
// Test that if an empty array is passed, no points are pushed
func TestBasicStatsWithNoStats(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
acc.AssertDoesNotContainMeasurement(t, "m1")
}
// Test that if an unknown stat is configured, it doesn't explode
func TestBasicStatsWithUnknownStat(t *testing.T) {
aggregator := NewBasicStats()
aggregator.Stats = []string{"crazy"}
aggregator.Add(m1)
aggregator.Add(m2)
acc := testutil.Accumulator{}
aggregator.Push(&acc)
acc.AssertDoesNotContainMeasurement(t, "m1")
}

View File

@@ -36,6 +36,7 @@ import (
_ "github.com/influxdata/telegraf/plugins/inputs/internal"
_ "github.com/influxdata/telegraf/plugins/inputs/interrupts"
_ "github.com/influxdata/telegraf/plugins/inputs/ipmi_sensor"
_ "github.com/influxdata/telegraf/plugins/inputs/ipset"
_ "github.com/influxdata/telegraf/plugins/inputs/iptables"
_ "github.com/influxdata/telegraf/plugins/inputs/jolokia"
_ "github.com/influxdata/telegraf/plugins/inputs/jolokia2"
@@ -53,6 +54,7 @@ import (
_ "github.com/influxdata/telegraf/plugins/inputs/mongodb"
_ "github.com/influxdata/telegraf/plugins/inputs/mqtt_consumer"
_ "github.com/influxdata/telegraf/plugins/inputs/mysql"
_ "github.com/influxdata/telegraf/plugins/inputs/nats"
_ "github.com/influxdata/telegraf/plugins/inputs/nats_consumer"
_ "github.com/influxdata/telegraf/plugins/inputs/net_response"
_ "github.com/influxdata/telegraf/plugins/inputs/nginx"

View File

@@ -2,7 +2,7 @@
The Apache plugin collects server performance information using the [`mod_status`](https://httpd.apache.org/docs/2.4/mod/mod_status.html) module of the [Apache HTTP Server](https://httpd.apache.org/).
Typically, the `mod_status` module is configured to expose a page at the `/server-status?auto` location of the Apache server. The [ExtendedStatus](https://httpd.apache.org/docs/2.4/mod/core.html#extendedstatus) option must be enabled in order to collect all available fields. For information about how to configure your server reference the [module documenation](https://httpd.apache.org/docs/2.4/mod/mod_status.html#enable).
Typically, the `mod_status` module is configured to expose a page at the `/server-status?auto` location of the Apache server. The [ExtendedStatus](https://httpd.apache.org/docs/2.4/mod/core.html#extendedstatus) option must be enabled in order to collect all available fields. For information about how to configure your server reference the [module documentation](https://httpd.apache.org/docs/2.4/mod/mod_status.html#enable).
### Configuration:

View File

@@ -1,7 +1,7 @@
# Bond Input Plugin
The Bond Input plugin collects bond interface status, bond's slaves interfaces
status and failures count of bond's slaves interfaces.
The Bond input plugin collects network bond interface status for both the
network bond interface as well as slave interfaces.
The plugin collects these metrics from `/proc/net/bonding/*` files.
### Configuration:

View File

@@ -106,7 +106,7 @@ the cluster. For more information on this technique reference
### Metrics:
Please consult the [Metrics Reference](https://docs.mesosphere.com/1.10/metrics/reference/)
for details on interprete field interpretation.
for details about field interpretation.
- dcos_node
- tags:

View File

@@ -325,7 +325,7 @@ func (c *ClusterClient) createLoginToken(sa *ServiceAccount) (string, error) {
UID: sa.AccountID,
StandardClaims: jwt.StandardClaims{
// How long we have to login with this token
ExpiresAt: int64(5 * time.Minute / time.Second),
ExpiresAt: time.Now().Add(5 * time.Minute).Unix(),
},
})
return token.SignedString(sa.PrivateKey)

View File

@@ -199,6 +199,9 @@ based on the availability of per-cpu stats on your system.
- network
- docker_container_blkio specific:
- device
- docker_container_health specific:
- health_status
- failing_streak
- docker_swarm specific:
- service_id
- service_name
@@ -257,4 +260,4 @@ io_serviced_recursive_total=6599i,io_serviced_recursive_write=107i 1453409536840
>docker_swarm,
service_id=xaup2o9krw36j2dy1mjx1arjw,service_mode=replicated,service_name=test,\
tasks_desired=3,tasks_running=3 1508968160000000000
```
```

View File

@@ -391,12 +391,13 @@ func (d *Docker) gatherContainer(
}
}
info, err := d.client.ContainerInspect(ctx, container.ID)
if err != nil {
return fmt.Errorf("Error inspecting docker container: %s", err.Error())
}
// Add whitelisted environment variables to tags
if len(d.TagEnvironment) > 0 {
info, err := d.client.ContainerInspect(ctx, container.ID)
if err != nil {
return fmt.Errorf("Error inspecting docker container: %s", err.Error())
}
for _, envvar := range info.Config.Env {
for _, configvar := range d.TagEnvironment {
dock_env := strings.SplitN(envvar, "=", 2)
@@ -408,6 +409,14 @@ func (d *Docker) gatherContainer(
}
}
if info.State.Health != nil {
healthfields := map[string]interface{}{
"health_status": info.State.Health.Status,
"failing_streak": info.ContainerJSONBase.State.Health.FailingStreak,
}
acc.AddFields("docker_container_health", healthfields, tags, time.Now())
}
gatherContainerStats(v, acc, tags, container.ID, d.PerDevice, d.Total, daemonOSType)
return nil

View File

@@ -477,4 +477,12 @@ var containerInspect = types.ContainerJSON{
"PATH=/bin:/sbin",
},
},
ContainerJSONBase: &types.ContainerJSONBase{
State: &types.ContainerState{
Health: &types.Health{
FailingStreak: 1,
Status: "Unhealthy",
},
},
},
}

View File

@@ -46,6 +46,17 @@ or [cluster-stats](https://www.elastic.co/guide/en/elasticsearch/reference/curre
# insecure_skip_verify = false
```
### Status mappings
When reporting health (green/yellow/red), additional field `status_code`
is reported. Field contains mapping from status:string to status_code:int
with following rules:
* `green` - 1
* `yellow` - 2
* `red` - 3
* `unknown` - 0
### Measurements & Fields:
field data circuit breaker measurement names:

View File

@@ -143,6 +143,19 @@ func NewElasticsearch() *Elasticsearch {
}
}
// perform status mapping
func mapHealthStatusToCode(s string) int {
switch strings.ToLower(s) {
case "green":
return 1
case "yellow":
return 2
case "red":
return 3
}
return 0
}
// SampleConfig returns sample configuration for this plugin.
func (e *Elasticsearch) SampleConfig() string {
return sampleConfig
@@ -311,6 +324,7 @@ func (e *Elasticsearch) gatherClusterHealth(url string, acc telegraf.Accumulator
measurementTime := time.Now()
clusterFields := map[string]interface{}{
"status": healthStats.Status,
"status_code": mapHealthStatusToCode(healthStats.Status),
"timed_out": healthStats.TimedOut,
"number_of_nodes": healthStats.NumberOfNodes,
"number_of_data_nodes": healthStats.NumberOfDataNodes,
@@ -330,6 +344,7 @@ func (e *Elasticsearch) gatherClusterHealth(url string, acc telegraf.Accumulator
for name, health := range healthStats.Indices {
indexFields := map[string]interface{}{
"status": health.Status,
"status_code": mapHealthStatusToCode(health.Status),
"number_of_shards": health.NumberOfShards,
"number_of_replicas": health.NumberOfReplicas,
"active_primary_shards": health.ActivePrimaryShards,

View File

@@ -54,6 +54,7 @@ const clusterHealthResponseWithIndices = `
var clusterHealthExpected = map[string]interface{}{
"status": "green",
"status_code": 1,
"timed_out": false,
"number_of_nodes": 3,
"number_of_data_nodes": 3,
@@ -66,6 +67,7 @@ var clusterHealthExpected = map[string]interface{}{
var v1IndexExpected = map[string]interface{}{
"status": "green",
"status_code": 1,
"number_of_shards": 10,
"number_of_replicas": 1,
"active_primary_shards": 10,
@@ -77,6 +79,7 @@ var v1IndexExpected = map[string]interface{}{
var v2IndexExpected = map[string]interface{}{
"status": "red",
"status_code": 3,
"number_of_shards": 10,
"number_of_replicas": 1,
"active_primary_shards": 0,

View File

@@ -1,175 +1,57 @@
# Exec Input Plugin
Please also see: [Telegraf Input Data Formats](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md)
The `exec` plugin executes the `commands` on every interval and parses metrics from
their output in any one of the accepted [Input Data Formats](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md).
### Example 1 - JSON
This plugin can be used to poll for custom metrics from any source.
#### Configuration
In this example a script called ```/tmp/test.sh```, a script called ```/tmp/test2.sh```, and
all scripts matching glob pattern ```/tmp/collect_*.sh``` are configured for ```[[inputs.exec]]```
in JSON format. Glob patterns are matched on every run, so adding new scripts that match the pattern
will cause them to be picked up immediately.
### Configuration:
```toml
# Read flattened metrics from one or more commands that output JSON to stdout
[[inputs.exec]]
# Shell/commands array
# Full command line to executable with parameters, or a glob pattern to run all matching files.
commands = ["/tmp/test.sh", "/tmp/test2.sh", "/tmp/collect_*.sh"]
## Commands array
commands = [
"/tmp/test.sh",
"/usr/bin/mycollector --foo=bar",
"/tmp/collect_*.sh"
]
## Timeout for each command to complete.
timeout = "5s"
# Data format to consume.
# NOTE json only reads numerical measurements, strings and booleans are ignored.
data_format = "json"
# measurement name suffix (for separating different commands)
## measurement name suffix (for separating different commands)
name_suffix = "_mycollector"
```
Other options for modifying the measurement names are:
```
name_prefix = "prefix_"
```
Let's say that we have the above configuration, and mycollector outputs the
following JSON:
```json
{
"a": 0.5,
"b": {
"c": 0.1,
"d": 5
}
}
```
The collected metrics will be stored as fields under the measurement
"exec_mycollector":
```
exec_mycollector a=0.5,b_c=0.1,b_d=5 1452815002357578567
```
If using JSON, only numeric values are parsed and turned into floats. Booleans
and strings will be ignored.
### Example 2 - Influx Line-Protocol
In this example an application called ```/usr/bin/line_protocol_collector```
and a script called ```/tmp/test2.sh``` are configured for ```[[inputs.exec]]```
in influx line-protocol format.
#### Configuration
```toml
[[inputs.exec]]
# Shell/commands array
# compatible with old version
# we can still use the old command configuration
# command = "/usr/bin/line_protocol_collector"
commands = ["/usr/bin/line_protocol_collector","/tmp/test2.sh"]
## Timeout for each command to complete.
timeout = "5s"
# Data format to consume.
# NOTE json only reads numerical measurements, strings and booleans are ignored.
## Data format to consume.
## Each data format has its own unique set of configuration options, read
## more about them here:
## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
data_format = "influx"
```
The line_protocol_collector application outputs the following line protocol:
Glob patterns in the `command` option are matched on every run, so adding new
scripts that match the pattern will cause them to be picked up immediately.
```
cpu,cpu=cpu0,host=foo,datacenter=us-east usage_idle=99,usage_busy=1
cpu,cpu=cpu1,host=foo,datacenter=us-east usage_idle=99,usage_busy=1
cpu,cpu=cpu2,host=foo,datacenter=us-east usage_idle=99,usage_busy=1
cpu,cpu=cpu3,host=foo,datacenter=us-east usage_idle=99,usage_busy=1
cpu,cpu=cpu4,host=foo,datacenter=us-east usage_idle=99,usage_busy=1
cpu,cpu=cpu5,host=foo,datacenter=us-east usage_idle=99,usage_busy=1
cpu,cpu=cpu6,host=foo,datacenter=us-east usage_idle=99,usage_busy=1
### Example:
This script produces static values, since no timestamp is specified the values are at the current time.
```sh
#!/bin/sh
echo 'example,tag1=a,tag2=b i=42i,j=43i,k=44i'
```
You will get data in InfluxDB exactly as it is defined above,
tags are cpu=cpuN, host=foo, and datacenter=us-east with fields usage_idle
and usage_busy. They will receive a timestamp at collection time.
Each line must end in \n, just as the Influx line protocol does.
### Example 3 - Graphite
We can also change the data_format to "graphite" to use the metrics collecting scripts such as (compatible with graphite):
* Nagios [Metrics Plugins](https://exchange.nagios.org/directory/Plugins)
* Sensu [Metrics Plugins](https://github.com/sensu-plugins)
In this example a script called /tmp/test.sh and a script called /tmp/test2.sh are configured for [[inputs.exec]] in graphite format.
#### Configuration
It can be paired with the following configuration and will be ran at the `interval` of the agent.
```toml
# Read flattened metrics from one or more commands that output JSON to stdout
[[inputs.exec]]
# Shell/commands array
commands = ["/tmp/test.sh","/tmp/test2.sh"]
## Timeout for each command to complete.
commands = ["sh /tmp/test.sh"]
timeout = "5s"
# Data format to consume.
# NOTE json only reads numerical measurements, strings and booleans are ignored.
data_format = "graphite"
# measurement name suffix (for separating different commands)
name_suffix = "_mycollector"
## Below configuration will be used for data_format = "graphite", can be ignored for other data_format
## If matching multiple measurement files, this string will be used to join the matched values.
separator = "."
## Each template line requires a template pattern. It can have an optional
## filter before the template and separated by spaces. It can also have optional extra
## tags following the template. Multiple tags should be separated by commas and no spaces
## similar to the line protocol format. The can be only one default template.
## Templates support below format:
## 1. filter + template
## 2. filter + template + extra tag
## 3. filter + template with field key
## 4. default template
templates = [
"*.app env.service.resource.measurement",
"stats.* .host.measurement* region=us-west,agent=sensu",
"stats2.* .host.measurement.field",
"measurement*"
]
```
Graphite messages are in this format:
```
metric_path value timestamp\n
data_format = "influx"
```
__metric_path__ is the metric namespace that you want to populate.
### Common Issues:
__value__ is the value that you want to assign to the metric at this time.
#### Q: My script works when I run it by hand, but not when Telegraf is running as a service.
__timestamp__ is the unix epoch time.
And test.sh/test2.sh will output:
```
sensu.metric.net.server0.eth0.rx_packets 461295119435 1444234982
sensu.metric.net.server0.eth0.tx_bytes 1093086493388480 1444234982
sensu.metric.net.server0.eth0.rx_bytes 1015633926034834 1444234982
sensu.metric.net.server0.eth0.tx_errors 0 1444234982
sensu.metric.net.server0.eth0.rx_errors 0 1444234982
sensu.metric.net.server0.eth0.tx_dropped 0 1444234982
sensu.metric.net.server0.eth0.rx_dropped 0 1444234982
```
The templates configuration will be used to parse the graphite metrics to support influxdb/opentsdb tagging store engines.
More detail information about templates, please refer to [The graphite Input](https://github.com/influxdata/influxdb/blob/master/services/graphite/README.md)
This may be related to the Telegraf service running as a different user. The
official packages run Telegraf as the `telegraf` user and group on Linux
systems.

View File

@@ -1,11 +1,14 @@
# HAproxy Input Plugin
# HAProxy Input Plugin
[HAproxy](http://www.haproxy.org/) input plugin gathers metrics directly from any running HAproxy instance. It can do so by using CSV generated by HAproxy status page or from admin socket(s).
The [HAProxy](http://www.haproxy.org/) input plugin gathers
[statistics](https://cbonte.github.io/haproxy-dconv/1.9/intro.html#3.3.16)
using the [stats socket](https://cbonte.github.io/haproxy-dconv/1.9/management.html#9.3)
or [HTTP statistics page](https://cbonte.github.io/haproxy-dconv/1.9/management.html#9) of a HAProxy server.
### Configuration:
```toml
# SampleConfig
# Read metrics of HAProxy, via socket or HTTP stats page
[[inputs.haproxy]]
## An array of address to gather stats about. Specify an ip on hostname
## with optional port. ie localhost, 10.10.3.33:1936, etc.
@@ -23,7 +26,7 @@
## By default, some of the fields are renamed from what haproxy calls them.
## Setting this option to true results in the plugin keeping the original
## field names.
# keep_field_names = true
# keep_field_names = false
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"
@@ -33,34 +36,77 @@
# insecure_skip_verify = false
```
#### `servers`
Server addresses need to explicitly start with 'http' if you wish to use HAproxy status page. Otherwise, address will be assumed to be an UNIX socket and protocol (if present) will be discarded.
#### HAProxy Configuration
For basic authentication you need to add username and password in the URL: `http://user:password@1.2.3.4/haproxy?stats`.
The following information may be useful when getting started, but please
consult the HAProxy documentation for complete and up to date instructions.
Following examples will all resolve to the same socket:
The [`stats enable`](https://cbonte.github.io/haproxy-dconv/1.8/configuration.html#4-stats%20enable)
option can be used to add unauthenticated access over HTTP using the default
settings. To enable the unix socket begin by reading about the
[`stats socket`](https://cbonte.github.io/haproxy-dconv/1.8/configuration.html#3.1-stats%20socket)
option.
#### servers
Server addresses must explicitly start with 'http' if you wish to use HAProxy
status page. Otherwise, addresses will be assumed to be an UNIX socket and
any protocol (if present) will be discarded.
When using socket names, wildcard expansion is supported so plugin can gather
stats from multiple sockets at once.
To use HTTP Basic Auth add the username and password in the userinfo section
of the URL: `http://user:password@1.2.3.4/haproxy?stats`. The credentials are
sent via the `Authorization` header and not using the request URL.
#### keep_field_names
By default, some of the fields are renamed from what haproxy calls them.
Setting the `keep_field_names` parameter to `true` will result in the plugin
keeping the original field names.
The following renames are made:
- `pxname` -> `proxy`
- `svname` -> `sv`
- `act` -> `active_servers`
- `bck` -> `backup_servers`
- `cli_abrt` -> `cli_abort`
- `srv_abrt` -> `srv_abort`
- `hrsp_1xx` -> `http_response.1xx`
- `hrsp_2xx` -> `http_response.2xx`
- `hrsp_3xx` -> `http_response.3xx`
- `hrsp_4xx` -> `http_response.4xx`
- `hrsp_5xx` -> `http_response.5xx`
- `hrsp_other` -> `http_response.other`
### Metrics:
For more details about collected metrics reference the [HAProxy CSV format
documentation](https://cbonte.github.io/haproxy-dconv/1.8/management.html#9.1).
- haproxy
- tags:
- `server` - address of the server data was gathered from
- `proxy` - proxy name
- `sv` - service name
- `type` - proxy session type
- fields:
- `status` (string)
- `check_status` (string)
- `last_chk` (string)
- `mode` (string)
- `tracked` (string)
- `agent_status` (string)
- `last_agt` (string)
- `addr` (string)
- `cookie` (string)
- `lastsess` (int)
- **all other stats** (int)
### Example Output:
```
socket:/var/run/haproxy.sock
unix:/var/run/haproxy.sock
foo:/var/run/haproxy.sock
/var/run/haproxy.sock
haproxy,server=/run/haproxy/admin.sock,proxy=public,sv=FRONTEND,type=frontend http_response.other=0i,req_rate_max=1i,comp_byp=0i,status="OPEN",rate_lim=0i,dses=0i,req_rate=0i,comp_rsp=0i,bout=9287i,comp_in=0i,mode="http",smax=1i,slim=2000i,http_response.1xx=0i,conn_rate=0i,dreq=0i,ereq=0i,iid=2i,rate_max=1i,http_response.2xx=1i,comp_out=0i,intercepted=1i,stot=2i,pid=1i,http_response.5xx=1i,http_response.3xx=0i,http_response.4xx=0i,conn_rate_max=1i,conn_tot=2i,dcon=0i,bin=294i,rate=0i,sid=0i,req_tot=2i,scur=0i,dresp=0i 1513293519000000000
```
When using socket names, wildcard expansion is supported so plugin can gather stats from multiple sockets at once.
If no servers are specified, then the default address of `http://127.0.0.1:1936/haproxy?stats` will be used.
#### `keep_field_names`
By default, some of the fields are renamed from what haproxy calls them. Setting the `keep_field_names` parameter to `true` will result in the plugin keeping the original field names.
### Measurements & Fields:
Plugin will gather measurements outlined in [HAproxy CSV format documentation](https://cbonte.github.io/haproxy-dconv/1.7/management.html#9.1).
### Tags:
- All measurements have the following tags:
- server - address of server data is gathered from
- proxy - proxy name as reported in `pxname`
- sv - service name as reported in `svname`

View File

@@ -54,7 +54,7 @@ var sampleConfig = `
## By default, some of the fields are renamed from what haproxy calls them.
## Setting this option to true results in the plugin keeping the original
## field names.
# keep_field_names = true
# keep_field_names = false
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"

View File

@@ -114,7 +114,7 @@ var (
func newTestHTTPListener() *HTTPListener {
listener := &HTTPListener{
ServiceAddress: ":0",
ServiceAddress: "localhost:0",
}
return listener
}
@@ -155,7 +155,7 @@ func newTestHTTPSListener() *HTTPListener {
})
listener := &HTTPListener{
ServiceAddress: ":0",
ServiceAddress: "localhost:0",
TlsAllowedCacerts: allowedCAFiles,
TlsCert: serviceCertFile,
TlsKey: serviceKeyFile,
@@ -309,7 +309,7 @@ func TestWriteHTTPNoNewline(t *testing.T) {
func TestWriteHTTPMaxLineSizeIncrease(t *testing.T) {
listener := &HTTPListener{
ServiceAddress: ":0",
ServiceAddress: "localhost:0",
MaxLineSize: 128 * 1000,
}
@@ -326,7 +326,7 @@ func TestWriteHTTPMaxLineSizeIncrease(t *testing.T) {
func TestWriteHTTPVerySmallMaxBody(t *testing.T) {
listener := &HTTPListener{
ServiceAddress: ":0",
ServiceAddress: "localhost:0",
MaxBodySize: 4096,
}
@@ -342,7 +342,7 @@ func TestWriteHTTPVerySmallMaxBody(t *testing.T) {
func TestWriteHTTPVerySmallMaxLineSize(t *testing.T) {
listener := &HTTPListener{
ServiceAddress: ":0",
ServiceAddress: "localhost:0",
MaxLineSize: 70,
}
@@ -368,7 +368,7 @@ func TestWriteHTTPVerySmallMaxLineSize(t *testing.T) {
func TestWriteHTTPLargeLinesSkipped(t *testing.T) {
listener := &HTTPListener{
ServiceAddress: ":0",
ServiceAddress: "localhost:0",
MaxLineSize: 100,
}

View File

@@ -32,6 +32,13 @@ The httpjson plugin collects data from HTTP URLs which respond with JSON. It fl
# "my_tag_2"
# ]
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"
# ssl_cert = "/etc/telegraf/cert.pem"
# ssl_key = "/etc/telegraf/key.pem"
## Use SSL but skip chain & host verification
# insecure_skip_verify = false
## HTTP Request Parameters (all values must be strings). For "GET" requests, data
## will be included in the query. For "POST" requests, data will be included
## in the request body as "x-www-form-urlencoded".
@@ -43,13 +50,6 @@ The httpjson plugin collects data from HTTP URLs which respond with JSON. It fl
# [inputs.httpjson.headers]
# X-Auth-Token = "my-xauth-token"
# apiVersion = "v1"
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"
# ssl_cert = "/etc/telegraf/cert.pem"
# ssl_key = "/etc/telegraf/key.pem"
## Use SSL but skip chain & host verification
# insecure_skip_verify = false
```
### Measurements & Fields:

View File

@@ -100,6 +100,13 @@ var sampleConfig = `
# "my_tag_2"
# ]
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"
# ssl_cert = "/etc/telegraf/cert.pem"
# ssl_key = "/etc/telegraf/key.pem"
## Use SSL but skip chain & host verification
# insecure_skip_verify = false
## HTTP parameters (all values must be strings). For "GET" requests, data
## will be included in the query. For "POST" requests, data will be included
## in the request body as "x-www-form-urlencoded".
@@ -111,13 +118,6 @@ var sampleConfig = `
# [inputs.httpjson.headers]
# X-Auth-Token = "my-xauth-token"
# apiVersion = "v1"
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"
# ssl_cert = "/etc/telegraf/cert.pem"
# ssl_key = "/etc/telegraf/key.pem"
## Use SSL but skip chain & host verification
# insecure_skip_verify = false
`
func (h *HttpJson) SampleConfig() string {

View File

@@ -22,7 +22,10 @@ ipmitool -I lan -H SERVER -U USERID -P PASSW0RD sdr
[[inputs.ipmi_sensor]]
## optionally specify the path to the ipmitool executable
# path = "/usr/bin/ipmitool"
#
##
## optionally force session privilege level. Can be CALLBACK, USER, OPERATOR, ADMINISTRATOR
# privilege = "ADMINISTRATOR"
##
## optionally specify one or more servers via a url matching
## [username[:password]@][protocol[(address)]]
## e.g.

View File

@@ -14,10 +14,12 @@ type Connection struct {
Password string
Port int
Interface string
Privilege string
}
func NewConnection(server string) *Connection {
func NewConnection(server string, privilege string) *Connection {
conn := &Connection{}
conn.Privilege = privilege
inx1 := strings.LastIndex(server, "@")
inx2 := strings.Index(server, "(")
inx3 := strings.Index(server, ")")
@@ -59,7 +61,9 @@ func (t *Connection) options() []string {
if t.Port != 0 {
options = append(options, "-p", strconv.Itoa(t.Port))
}
if t.Privilege != "" {
options = append(options, "-L", t.Privilege)
}
return options
}

View File

@@ -23,6 +23,7 @@ func TestNewConnection(t *testing.T) {
Username: "USERID",
Password: "PASSW0RD",
Interface: "lan",
Privilege: "USER",
},
},
{
@@ -32,11 +33,12 @@ func TestNewConnection(t *testing.T) {
Username: "USERID",
Password: "PASS:!@#$%^&*(234)_+W0RD",
Interface: "lan",
Privilege: "USER",
},
},
}
for _, v := range testData {
assert.Equal(t, v.con, NewConnection(v.addr))
assert.Equal(t, v.con, NewConnection(v.addr, "USER"))
}
}

View File

@@ -17,15 +17,19 @@ var (
)
type Ipmi struct {
Path string
Servers []string
Timeout internal.Duration
Path string
Privilege string
Servers []string
Timeout internal.Duration
}
var sampleConfig = `
## optionally specify the path to the ipmitool executable
# path = "/usr/bin/ipmitool"
#
##
## optionally force session privilege level. Can be CALLBACK, USER, OPERATOR, ADMINISTRATOR
# privilege = "ADMINISTRATOR"
##
## optionally specify one or more servers via a url matching
## [username[:password]@][protocol[(address)]]
## e.g.
@@ -77,13 +81,11 @@ func (m *Ipmi) Gather(acc telegraf.Accumulator) error {
func (m *Ipmi) parse(acc telegraf.Accumulator, server string) error {
opts := make([]string, 0)
hostname := ""
if server != "" {
conn := NewConnection(server)
conn := NewConnection(server, m.Privilege)
hostname = conn.Hostname
opts = conn.options()
}
opts = append(opts, "sdr")
cmd := execCommand(m.Path, opts...)
out, err := internal.CombinedOutputTimeout(cmd, m.Timeout.Duration)

View File

@@ -15,9 +15,10 @@ import (
func TestGather(t *testing.T) {
i := &Ipmi{
Servers: []string{"USERID:PASSW0RD@lan(192.168.1.1)"},
Path: "ipmitool",
Timeout: internal.Duration{Duration: time.Second * 5},
Servers: []string{"USERID:PASSW0RD@lan(192.168.1.1)"},
Path: "ipmitool",
Privilege: "USER",
Timeout: internal.Duration{Duration: time.Second * 5},
}
// overwriting exec commands with mock commands
execCommand = fakeExecCommand
@@ -29,7 +30,7 @@ func TestGather(t *testing.T) {
assert.Equal(t, acc.NFields(), 266, "non-numeric measurements should be ignored")
conn := NewConnection(i.Servers[0])
conn := NewConnection(i.Servers[0], i.Privilege)
assert.Equal(t, "USERID", conn.Username)
assert.Equal(t, "lan", conn.Interface)

View File

@@ -0,0 +1,62 @@
# Ipset Plugin
The ipset plugin gathers packets and bytes counters from Linux ipset.
It uses the output of the command "ipset save".
Ipsets created without the "counters" option are ignored.
Results are tagged with:
- ipset name
- ipset entry
There are 3 ways to grant telegraf the right to run ipset:
* Run as root (strongly discouraged)
* Use sudo
* Configure systemd to run telegraf with CAP_NET_ADMIN and CAP_NET_RAW capabilities.
### Using systemd capabilities
You may run `systemctl edit telegraf.service` and add the following:
```
[Service]
CapabilityBoundingSet=CAP_NET_RAW CAP_NET_ADMIN
AmbientCapabilities=CAP_NET_RAW CAP_NET_ADMIN
```
### Using sudo
You may edit your sudo configuration with the following:
```sudo
telegraf ALL=(root) NOPASSWD: /sbin/ipset save
```
### Configuration
```toml
[[inputs.ipset]]
## By default, we only show sets which have already matched at least 1 packet.
## set include_unmatched_sets = true to gather them all.
include_unmatched_sets = false
## Adjust your sudo settings appropriately if using this option ("sudo ipset save")
## You can avoid using sudo or root, by setting appropriate privileges for
## the telegraf.service systemd service.
use_sudo = false
## The default timeout of 1s for ipset execution can be overridden here:
# timeout = "1s"
```
### Example Output
```
$ sudo ipset save
create myset hash:net family inet hashsize 1024 maxelem 65536 counters comment
add myset 10.69.152.1 packets 8 bytes 672 comment "machine A"
```
```
$ telegraf --config telegraf.conf --input-filter ipset --test --debug
* Plugin: inputs.ipset, Collection 1
> ipset,rule=10.69.152.1,host=trashme,set=myset bytes_total=8i,packets_total=672i 1507615028000000000
```

View File

@@ -0,0 +1,126 @@
package ipset
import (
"bufio"
"bytes"
"fmt"
"os/exec"
"strconv"
"strings"
"time"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/internal"
"github.com/influxdata/telegraf/plugins/inputs"
)
// Ipsets is a telegraf plugin to gather packets and bytes counters from ipset
type Ipset struct {
IncludeUnmatchedSets bool
UseSudo bool
Timeout internal.Duration
lister setLister
}
type setLister func(Timeout internal.Duration, UseSudo bool) (*bytes.Buffer, error)
const measurement = "ipset"
var defaultTimeout = internal.Duration{Duration: time.Second}
// Description returns a short description of the plugin
func (ipset *Ipset) Description() string {
return "Gather packets and bytes counters from Linux ipsets"
}
// SampleConfig returns sample configuration options.
func (ipset *Ipset) SampleConfig() string {
return `
## By default, we only show sets which have already matched at least 1 packet.
## set include_unmatched_sets = true to gather them all.
include_unmatched_sets = false
## Adjust your sudo settings appropriately if using this option ("sudo ipset save")
use_sudo = false
## The default timeout of 1s for ipset execution can be overridden here:
# timeout = "1s"
`
}
func (ips *Ipset) Gather(acc telegraf.Accumulator) error {
out, e := ips.lister(ips.Timeout, ips.UseSudo)
if e != nil {
acc.AddError(e)
}
scanner := bufio.NewScanner(out)
for scanner.Scan() {
line := scanner.Text()
// Ignore sets created without the "counters" option
nocomment := strings.Split(line, "\"")[0]
if !(strings.Contains(nocomment, "packets") &&
strings.Contains(nocomment, "bytes")) {
continue
}
data := strings.Fields(line)
if len(data) < 7 {
acc.AddError(fmt.Errorf("Error parsing line (expected at least 7 fields): %s", line))
continue
}
if data[0] == "add" && (data[4] != "0" || ips.IncludeUnmatchedSets) {
tags := map[string]string{
"set": data[1],
"rule": data[2],
}
packets_total, err := strconv.ParseUint(data[4], 10, 64)
if err != nil {
acc.AddError(err)
}
bytes_total, err := strconv.ParseUint(data[6], 10, 64)
if err != nil {
acc.AddError(err)
}
fields := map[string]interface{}{
"packets_total": packets_total,
"bytes_total": bytes_total,
}
acc.AddCounter(measurement, fields, tags)
}
}
return nil
}
func setList(Timeout internal.Duration, UseSudo bool) (*bytes.Buffer, error) {
// Is ipset installed ?
ipsetPath, err := exec.LookPath("ipset")
if err != nil {
return nil, err
}
var args []string
cmdName := ipsetPath
if UseSudo {
cmdName = "sudo"
args = append(args, ipsetPath)
}
args = append(args, "save")
cmd := exec.Command(cmdName, args...)
var out bytes.Buffer
cmd.Stdout = &out
err = internal.RunTimeout(cmd, Timeout.Duration)
if err != nil {
return &out, fmt.Errorf("error running ipset save: %s", err)
}
return &out, nil
}
func init() {
inputs.Add("ipset", func() telegraf.Input {
return &Ipset{
lister: setList,
Timeout: defaultTimeout,
}
})
}

View File

@@ -0,0 +1,135 @@
package ipset
import (
"bytes"
"errors"
"fmt"
"reflect"
"testing"
"github.com/influxdata/telegraf/internal"
"github.com/influxdata/telegraf/testutil"
)
func TestIpset(t *testing.T) {
tests := []struct {
name string
value string
tags []map[string]string
fields [][]map[string]interface{}
err error
}{
{
name: "0 sets, no results",
value: "",
},
{
name: "Empty sets, no values",
value: `create myset hash:net family inet hashsize 1024 maxelem 65536
create myset2 hash:net,port family inet hashsize 16384 maxelem 524288 counters comment
`,
},
{
name: "Non-empty sets, but no counters, no results",
value: `create myset hash:net family inet hashsize 1024 maxelem 65536
add myset 1.2.3.4
`,
},
{
name: "Line with data but not enough fields",
value: `create hash:net family inet hashsize 1024 maxelem 65536 counters
add myset 4.5.6.7 packets 123 bytes
`,
err: fmt.Errorf("Error parsing line (expected at least 7 fields): \t\t\t\tadd myset 4.5.6.7 packets 123 bytes"),
},
{
name: "Non-empty sets, counters, no comment",
value: `create myset hash:net family inet hashsize 1024 maxelem 65536 counters
add myset 1.2.3.4 packets 1328 bytes 79680
add myset 2.3.4.5 packets 0 bytes 0
add myset 3.4.5.6 packets 3 bytes 222
`,
tags: []map[string]string{
map[string]string{"set": "myset", "rule": "1.2.3.4"},
map[string]string{"set": "myset", "rule": "3.4.5.6"},
},
fields: [][]map[string]interface{}{
{map[string]interface{}{"packets_total": uint64(1328), "bytes_total": uint64(79680)}},
{map[string]interface{}{"packets_total": uint64(3), "bytes_total": uint64(222)}},
},
},
{
name: "Sets with counters and comment",
value: `create myset hash:net family inet hashsize 1024 maxelem 65536 counters comment
add myset 1.2.3.4 packets 1328 bytes 79680 comment "first IP"
add myset 2.3.4.5 packets 0 bytes 0 comment "2nd IP"
add myset 3.4.5.6 packets 3 bytes 222 "3rd IP"
`,
tags: []map[string]string{
map[string]string{"set": "myset", "rule": "1.2.3.4"},
map[string]string{"set": "myset", "rule": "3.4.5.6"},
},
fields: [][]map[string]interface{}{
{map[string]interface{}{"packets_total": uint64(1328), "bytes_total": uint64(79680)}},
{map[string]interface{}{"packets_total": uint64(3), "bytes_total": uint64(222)}},
},
},
}
for i, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
i++
ips := &Ipset{
lister: func(Timeout internal.Duration, UseSudo bool) (*bytes.Buffer, error) {
return bytes.NewBufferString(tt.value), nil
},
}
acc := new(testutil.Accumulator)
err := acc.GatherError(ips.Gather)
if !reflect.DeepEqual(tt.err, err) {
t.Errorf("%d: expected error '%#v' got '%#v'", i, tt.err, err)
}
if len(tt.tags) == 0 {
n := acc.NFields()
if n != 0 {
t.Errorf("%d: expected 0 values got %d", i, n)
}
return
}
n := 0
for j, tags := range tt.tags {
for k, fields := range tt.fields[j] {
if len(acc.Metrics) < n+1 {
t.Errorf("%d: expected at least %d values got %d", i, n+1, len(acc.Metrics))
break
}
m := acc.Metrics[n]
if !reflect.DeepEqual(m.Measurement, measurement) {
t.Errorf("%d %d %d: expected measurement '%#v' got '%#v'\n", i, j, k, measurement, m.Measurement)
}
if !reflect.DeepEqual(m.Tags, tags) {
t.Errorf("%d %d %d: expected tags\n%#v got\n%#v\n", i, j, k, tags, m.Tags)
}
if !reflect.DeepEqual(m.Fields, fields) {
t.Errorf("%d %d %d: expected fields\n%#v got\n%#v\n", i, j, k, fields, m.Fields)
}
n++
}
}
})
}
}
func TestIpset_Gather_listerError(t *testing.T) {
errFoo := errors.New("error foobar")
ips := &Ipset{
lister: func(Timeout internal.Duration, UseSudo bool) (*bytes.Buffer, error) {
return new(bytes.Buffer), errFoo
},
}
acc := new(testutil.Accumulator)
err := acc.GatherError(ips.Gather)
if !reflect.DeepEqual(err, errFoo) {
t.Errorf("Expected error %#v got\n%#v\n", errFoo, err)
}
}

View File

@@ -46,7 +46,7 @@ func (ja *JolokiaAgent) SampleConfig() string {
# insecure_skip_verify = false
## Add metrics to read
[[inputs.jolokia2.metric]]
[[inputs.jolokia2_agent.metric]]
name = "java_runtime"
mbean = "java.lang:type=Runtime"
paths = ["Uptime"]

View File

@@ -11,7 +11,7 @@ For more information, please check the [Mesos Observability Metrics](http://meso
## Timeout, in ms.
timeout = 100
## A list of Mesos masters.
masters = ["localhost:5050"]
masters = ["http://localhost:5050"]
## Master metrics groups to be collected, by default, all enabled.
master_collections = [
"resources",
@@ -35,6 +35,13 @@ For more information, please check the [Mesos Observability Metrics](http://meso
# "tasks",
# "messages",
# ]
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"
# ssl_cert = "/etc/telegraf/cert.pem"
# ssl_key = "/etc/telegraf/key.pem"
## Use SSL but skip chain & host verification
# insecure_skip_verify = false
```
By default this plugin is not configured to gather metrics from mesos. Since a mesos cluster can be deployed in numerous ways it does not provide any default
@@ -235,7 +242,8 @@ Mesos slave metric groups
### Tags:
- All master/slave measurements have the following tags:
- server
- server (network location of server: `host:port`)
- url (URL origin of server: `scheme://host:port`)
- role (master/slave)
- All master measurements have the extra tags:

View File

@@ -7,11 +7,14 @@ import (
"log"
"net"
"net/http"
"net/url"
"strconv"
"strings"
"sync"
"time"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/internal"
"github.com/influxdata/telegraf/plugins/inputs"
jsonparser "github.com/influxdata/telegraf/plugins/parsers/json"
)
@@ -30,6 +33,20 @@ type Mesos struct {
Slaves []string
SlaveCols []string `toml:"slave_collections"`
//SlaveTasks bool
// Path to CA file
SSLCA string `toml:"ssl_ca"`
// Path to host cert file
SSLCert string `toml:"ssl_cert"`
// Path to cert key file
SSLKey string `toml:"ssl_key"`
// Use SSL but skip chain & host verification
InsecureSkipVerify bool
initialized bool
client *http.Client
masterURLs []*url.URL
slaveURLs []*url.URL
}
var allMetrics = map[Role][]string{
@@ -41,7 +58,7 @@ var sampleConfig = `
## Timeout, in ms.
timeout = 100
## A list of Mesos masters.
masters = ["localhost:5050"]
masters = ["http://localhost:5050"]
## Master metrics groups to be collected, by default, all enabled.
master_collections = [
"resources",
@@ -65,6 +82,13 @@ var sampleConfig = `
# "tasks",
# "messages",
# ]
## Optional SSL Config
# ssl_ca = "/etc/telegraf/ca.pem"
# ssl_cert = "/etc/telegraf/cert.pem"
# ssl_key = "/etc/telegraf/key.pem"
## Use SSL but skip chain & host verification
# insecure_skip_verify = false
`
// SampleConfig returns a sample configuration block
@@ -77,7 +101,28 @@ func (m *Mesos) Description() string {
return "Telegraf plugin for gathering metrics from N Mesos masters"
}
func (m *Mesos) SetDefaults() {
func parseURL(s string, role Role) (*url.URL, error) {
if !strings.HasPrefix(s, "http://") && !strings.HasPrefix(s, "https://") {
host, port, err := net.SplitHostPort(s)
// no port specified
if err != nil {
host = s
switch role {
case MASTER:
port = "5050"
case SLAVE:
port = "5051"
}
}
s = "http://" + host + ":" + port
log.Printf("W! [inputs.mesos] Using %q as connection URL; please update your configuration to use an URL", s)
}
return url.Parse(s)
}
func (m *Mesos) initialize() error {
if len(m.MasterCols) == 0 {
m.MasterCols = allMetrics[MASTER]
}
@@ -87,33 +132,71 @@ func (m *Mesos) SetDefaults() {
}
if m.Timeout == 0 {
log.Println("I! [mesos] Missing timeout value, setting default value (100ms)")
log.Println("I! [inputs.mesos] Missing timeout value, setting default value (100ms)")
m.Timeout = 100
}
rawQuery := "timeout=" + strconv.Itoa(m.Timeout) + "ms"
m.masterURLs = make([]*url.URL, 0, len(m.Masters))
for _, master := range m.Masters {
u, err := parseURL(master, MASTER)
if err != nil {
return err
}
u.RawQuery = rawQuery
m.masterURLs = append(m.masterURLs, u)
}
m.slaveURLs = make([]*url.URL, 0, len(m.Slaves))
for _, slave := range m.Slaves {
u, err := parseURL(slave, SLAVE)
if err != nil {
return err
}
u.RawQuery = rawQuery
m.slaveURLs = append(m.slaveURLs, u)
}
client, err := m.createHttpClient()
if err != nil {
return err
}
m.client = client
return nil
}
// Gather() metrics from given list of Mesos Masters
func (m *Mesos) Gather(acc telegraf.Accumulator) error {
var wg sync.WaitGroup
m.SetDefaults()
for _, v := range m.Masters {
wg.Add(1)
go func(c string) {
acc.AddError(m.gatherMainMetrics(c, ":5050", MASTER, acc))
wg.Done()
return
}(v)
if !m.initialized {
err := m.initialize()
if err != nil {
return err
}
m.initialized = true
}
for _, v := range m.Slaves {
var wg sync.WaitGroup
for _, master := range m.masterURLs {
wg.Add(1)
go func(c string) {
acc.AddError(m.gatherMainMetrics(c, ":5051", SLAVE, acc))
go func(master *url.URL) {
acc.AddError(m.gatherMainMetrics(master, MASTER, acc))
wg.Done()
return
}(v)
}(master)
}
for _, slave := range m.slaveURLs {
wg.Add(1)
go func(slave *url.URL) {
acc.AddError(m.gatherMainMetrics(slave, SLAVE, acc))
wg.Done()
return
}(slave)
// if !m.SlaveTasks {
// continue
@@ -121,7 +204,7 @@ func (m *Mesos) Gather(acc telegraf.Accumulator) error {
// wg.Add(1)
// go func(c string) {
// acc.AddError(m.gatherSlaveTaskMetrics(c, ":5051", acc))
// acc.AddError(m.gatherSlaveTaskMetrics(slave, acc))
// wg.Done()
// return
// }(v)
@@ -132,6 +215,24 @@ func (m *Mesos) Gather(acc telegraf.Accumulator) error {
return nil
}
func (m *Mesos) createHttpClient() (*http.Client, error) {
tlsCfg, err := internal.GetTLSConfig(
m.SSLCert, m.SSLKey, m.SSLCA, m.InsecureSkipVerify)
if err != nil {
return nil, err
}
client := &http.Client{
Transport: &http.Transport{
Proxy: http.ProxyFromEnvironment,
TLSClientConfig: tlsCfg,
},
Timeout: 4 * time.Second,
}
return client, nil
}
// metricsDiff() returns set names for removal
func metricsDiff(role Role, w []string) []string {
b := []string{}
@@ -393,15 +494,6 @@ func (m *Mesos) filterMetrics(role Role, metrics *map[string]interface{}) {
}
}
var tr = &http.Transport{
ResponseHeaderTimeout: time.Duration(3 * time.Second),
}
var client = &http.Client{
Transport: tr,
Timeout: time.Duration(4 * time.Second),
}
// TaskStats struct for JSON API output /monitor/statistics
type TaskStats struct {
ExecutorID string `json:"executor_id"`
@@ -409,22 +501,15 @@ type TaskStats struct {
Statistics map[string]interface{} `json:"statistics"`
}
func (m *Mesos) gatherSlaveTaskMetrics(address string, defaultPort string, acc telegraf.Accumulator) error {
func (m *Mesos) gatherSlaveTaskMetrics(u *url.URL, acc telegraf.Accumulator) error {
var metrics []TaskStats
host, _, err := net.SplitHostPort(address)
if err != nil {
host = address
address = address + defaultPort
}
tags := map[string]string{
"server": host,
"server": u.Hostname(),
"url": urlTag(u),
}
ts := strconv.Itoa(m.Timeout) + "ms"
resp, err := client.Get("http://" + address + "/monitor/statistics?timeout=" + ts)
resp, err := m.client.Get(withPath(u, "/monitor/statistics").String())
if err != nil {
return err
@@ -459,24 +544,31 @@ func (m *Mesos) gatherSlaveTaskMetrics(address string, defaultPort string, acc t
return nil
}
func withPath(u *url.URL, path string) *url.URL {
c := *u
c.Path = path
return &c
}
func urlTag(u *url.URL) string {
c := *u
c.Path = ""
c.User = nil
c.RawQuery = ""
return c.String()
}
// This should not belong to the object
func (m *Mesos) gatherMainMetrics(a string, defaultPort string, role Role, acc telegraf.Accumulator) error {
func (m *Mesos) gatherMainMetrics(u *url.URL, role Role, acc telegraf.Accumulator) error {
var jsonOut map[string]interface{}
host, _, err := net.SplitHostPort(a)
if err != nil {
host = a
a = a + defaultPort
}
tags := map[string]string{
"server": host,
"server": u.Hostname(),
"url": urlTag(u),
"role": string(role),
}
ts := strconv.Itoa(m.Timeout) + "ms"
resp, err := client.Get("http://" + a + "/metrics/snapshot?timeout=" + ts)
resp, err := m.client.Get(withPath(u, "/metrics/snapshot").String())
if err != nil {
return err

View File

@@ -6,10 +6,12 @@ import (
"math/rand"
"net/http"
"net/http/httptest"
"net/url"
"os"
"testing"
"github.com/influxdata/telegraf/testutil"
"github.com/stretchr/testify/require"
)
var masterMetrics map[string]interface{}
@@ -378,3 +380,19 @@ func TestSlaveFilter(t *testing.T) {
}
}
}
func TestWithPathDoesNotModify(t *testing.T) {
u, err := url.Parse("http://localhost:5051")
require.NoError(t, err)
v := withPath(u, "/xyzzy")
require.Equal(t, u.String(), "http://localhost:5051")
require.Equal(t, v.String(), "http://localhost:5051/xyzzy")
}
func TestURLTagDoesNotModify(t *testing.T) {
u, err := url.Parse("http://a:b@localhost:5051?timeout=1ms")
require.NoError(t, err)
v := urlTag(u)
require.Equal(t, u.String(), "http://a:b@localhost:5051?timeout=1ms")
require.Equal(t, v, "http://localhost:5051")
}

View File

@@ -147,7 +147,7 @@ func (m *Mysql) Gather(acc telegraf.Accumulator) error {
tlsConfig, err := internal.GetTLSConfig(m.SSLCert, m.SSLKey, m.SSLCA, false)
if err != nil {
log.Printf("E! MySQL Error registering TLS config: %s", err)
return fmt.Errorf("registering TLS config: %s", err)
}
if tlsConfig != nil {
@@ -169,182 +169,6 @@ func (m *Mysql) Gather(acc telegraf.Accumulator) error {
return nil
}
type mapping struct {
onServer string
inExport string
}
var mappings = []*mapping{
{
onServer: "Aborted_",
inExport: "aborted_",
},
{
onServer: "Bytes_",
inExport: "bytes_",
},
{
onServer: "Com_",
inExport: "commands_",
},
{
onServer: "Created_",
inExport: "created_",
},
{
onServer: "Handler_",
inExport: "handler_",
},
{
onServer: "Innodb_",
inExport: "innodb_",
},
{
onServer: "Key_",
inExport: "key_",
},
{
onServer: "Open_",
inExport: "open_",
},
{
onServer: "Opened_",
inExport: "opened_",
},
{
onServer: "Qcache_",
inExport: "qcache_",
},
{
onServer: "Table_",
inExport: "table_",
},
{
onServer: "Tokudb_",
inExport: "tokudb_",
},
{
onServer: "Threads_",
inExport: "threads_",
},
{
onServer: "Access_",
inExport: "access_",
},
{
onServer: "Aria__",
inExport: "aria_",
},
{
onServer: "Binlog__",
inExport: "binlog_",
},
{
onServer: "Busy_",
inExport: "busy_",
},
{
onServer: "Connection_",
inExport: "connection_",
},
{
onServer: "Delayed_",
inExport: "delayed_",
},
{
onServer: "Empty_",
inExport: "empty_",
},
{
onServer: "Executed_",
inExport: "executed_",
},
{
onServer: "Executed_",
inExport: "executed_",
},
{
onServer: "Feature_",
inExport: "feature_",
},
{
onServer: "Flush_",
inExport: "flush_",
},
{
onServer: "Last_",
inExport: "last_",
},
{
onServer: "Master_",
inExport: "master_",
},
{
onServer: "Max_",
inExport: "max_",
},
{
onServer: "Memory_",
inExport: "memory_",
},
{
onServer: "Not_",
inExport: "not_",
},
{
onServer: "Performance_",
inExport: "performance_",
},
{
onServer: "Prepared_",
inExport: "prepared_",
},
{
onServer: "Rows_",
inExport: "rows_",
},
{
onServer: "Rpl_",
inExport: "rpl_",
},
{
onServer: "Select_",
inExport: "select_",
},
{
onServer: "Slave_",
inExport: "slave_",
},
{
onServer: "Slow_",
inExport: "slow_",
},
{
onServer: "Sort_",
inExport: "sort_",
},
{
onServer: "Subquery_",
inExport: "subquery_",
},
{
onServer: "Tc_",
inExport: "tc_",
},
{
onServer: "Threadpool_",
inExport: "threadpool_",
},
{
onServer: "wsrep_",
inExport: "wsrep_",
},
{
onServer: "Uptime_",
inExport: "uptime_",
},
}
var (
// status counter
generalThreadStates = map[string]uint32{
@@ -717,9 +541,8 @@ func (m *Mysql) gatherGlobalVariables(db *sql.DB, serv string, acc telegraf.Accu
fields[key] = string(val)
tags[key] = string(val)
}
// parse value, if it is numeric then save, otherwise ignore
if floatVal, ok := parseValue(val); ok {
fields[key] = floatVal
if value, ok := parseValue(val); ok {
fields[key] = value
}
// Send 20 fields at a time
if len(fields) >= 20 {
@@ -769,7 +592,7 @@ func (m *Mysql) gatherSlaveStatuses(db *sql.DB, serv string, acc telegraf.Accumu
}
// range over columns, and try to parse values
for i, col := range cols {
// skip unparsable values
col = strings.ToLower(col)
if value, ok := parseValue(*vals[i].(*sql.RawBytes)); ok {
fields["slave_"+col] = value
}
@@ -820,98 +643,36 @@ func (m *Mysql) gatherBinaryLogs(db *sql.DB, serv string, acc telegraf.Accumulat
// the mappings of actual names and names of each status to be exported
// to output is provided on mappings variable
func (m *Mysql) gatherGlobalStatuses(db *sql.DB, serv string, acc telegraf.Accumulator) error {
// If user forgot the '/', add it
if strings.HasSuffix(serv, ")") {
serv = serv + "/"
} else if serv == "localhost" {
serv = ""
}
// run query
rows, err := db.Query(globalStatusQuery)
if err != nil {
return err
}
defer rows.Close()
// parse the DSN and save host name as a tag
servtag := getDSNTag(serv)
tags := map[string]string{"server": servtag}
fields := make(map[string]interface{})
for rows.Next() {
var name string
var val interface{}
var key string
var val sql.RawBytes
err = rows.Scan(&name, &val)
if err != nil {
if err = rows.Scan(&key, &val); err != nil {
return err
}
var found bool
key = strings.ToLower(key)
// iterate over mappings and gather metrics that is provided on mapping
for _, mapped := range mappings {
if strings.HasPrefix(name, mapped.onServer) {
// convert numeric values to integer
i, _ := strconv.Atoi(string(val.([]byte)))
fields[mapped.inExport+name[len(mapped.onServer):]] = i
found = true
}
if value, ok := parseValue(val); ok {
fields[key] = value
}
// Send 20 fields at a time
if len(fields) >= 20 {
acc.AddFields("mysql", fields, tags)
fields = make(map[string]interface{})
}
if found {
continue
}
// search for specific values
switch name {
case "Queries":
i, err := strconv.ParseInt(string(val.([]byte)), 10, 64)
if err != nil {
acc.AddError(fmt.Errorf("E! Error mysql: parsing %s int value (%s)", name, err))
} else {
fields["queries"] = i
}
case "Questions":
i, err := strconv.ParseInt(string(val.([]byte)), 10, 64)
if err != nil {
acc.AddError(fmt.Errorf("E! Error mysql: parsing %s int value (%s)", name, err))
} else {
fields["questions"] = i
}
case "Slow_queries":
i, err := strconv.ParseInt(string(val.([]byte)), 10, 64)
if err != nil {
acc.AddError(fmt.Errorf("E! Error mysql: parsing %s int value (%s)", name, err))
} else {
fields["slow_queries"] = i
}
case "Connections":
i, err := strconv.ParseInt(string(val.([]byte)), 10, 64)
if err != nil {
acc.AddError(fmt.Errorf("E! Error mysql: parsing %s int value (%s)", name, err))
} else {
fields["connections"] = i
}
case "Syncs":
i, err := strconv.ParseInt(string(val.([]byte)), 10, 64)
if err != nil {
acc.AddError(fmt.Errorf("E! Error mysql: parsing %s int value (%s)", name, err))
} else {
fields["syncs"] = i
}
case "Uptime":
i, err := strconv.ParseInt(string(val.([]byte)), 10, 64)
if err != nil {
acc.AddError(fmt.Errorf("E! Error mysql: parsing %s int value (%s)", name, err))
} else {
fields["uptime"] = i
}
}
}
// Send any remaining fields
if len(fields) > 0 {
@@ -1059,7 +820,7 @@ func (m *Mysql) GatherProcessListStatuses(db *sql.DB, serv string, acc telegraf.
for s, c := range stateCounts {
fields[newNamespace("threads", s)] = c
}
acc.AddFields("mysql_info_schema", fields, tags)
acc.AddFields("mysql_process_list", fields, tags)
return nil
}
@@ -1272,7 +1033,7 @@ func (m *Mysql) gatherInfoSchemaAutoIncStatuses(db *sql.DB, serv string, acc tel
fields["auto_increment_column"] = incValue
fields["auto_increment_column_max"] = maxInt
acc.AddFields("mysql_info_schema", fields, tags)
acc.AddFields("mysql_table_schema", fields, tags)
}
return nil
}
@@ -1287,21 +1048,19 @@ func (m *Mysql) gatherInnoDBMetrics(db *sql.DB, serv string, acc telegraf.Accumu
}
defer rows.Close()
var key string
var val sql.RawBytes
// parse DSN and save server tag
servtag := getDSNTag(serv)
tags := map[string]string{"server": servtag}
fields := make(map[string]interface{})
for rows.Next() {
var key string
var val sql.RawBytes
if err := rows.Scan(&key, &val); err != nil {
return err
}
key = strings.ToLower(key)
// parse value, if it is numeric then save, otherwise ignore
if floatVal, ok := parseValue(val); ok {
fields[key] = floatVal
if value, ok := parseValue(val); ok {
fields[key] = value
}
// Send 20 fields at a time
if len(fields) >= 20 {
@@ -1671,23 +1430,17 @@ func (m *Mysql) gatherTableSchema(db *sql.DB, serv string, acc telegraf.Accumula
tags["schema"] = tableSchema
tags["table"] = tableName
acc.AddFields(newNamespace("info_schema", "table_rows"),
map[string]interface{}{"value": tableRows}, tags)
acc.AddFields("mysql_table_schema",
map[string]interface{}{"rows": tableRows}, tags)
dlTags := copyTags(tags)
dlTags["component"] = "data_length"
acc.AddFields(newNamespace("info_schema", "table_size", "data_length"),
map[string]interface{}{"value": dataLength}, dlTags)
acc.AddFields("mysql_table_schema",
map[string]interface{}{"data_length": dataLength}, tags)
ilTags := copyTags(tags)
ilTags["component"] = "index_length"
acc.AddFields(newNamespace("info_schema", "table_size", "index_length"),
map[string]interface{}{"value": indexLength}, ilTags)
acc.AddFields("mysql_table_schema",
map[string]interface{}{"index_length": indexLength}, tags)
dfTags := copyTags(tags)
dfTags["component"] = "data_free"
acc.AddFields(newNamespace("info_schema", "table_size", "data_free"),
map[string]interface{}{"value": dataFree}, dfTags)
acc.AddFields("mysql_table_schema",
map[string]interface{}{"data_free": dataFree}, tags)
versionTags := copyTags(tags)
versionTags["type"] = tableType
@@ -1695,24 +1448,34 @@ func (m *Mysql) gatherTableSchema(db *sql.DB, serv string, acc telegraf.Accumula
versionTags["row_format"] = rowFormat
versionTags["create_options"] = createOptions
acc.AddFields(newNamespace("info_schema", "table_version"),
map[string]interface{}{"value": version}, versionTags)
acc.AddFields("mysql_table_schema_version",
map[string]interface{}{"table_version": version}, versionTags)
}
}
return nil
}
// parseValue can be used to convert values such as "ON","OFF","Yes","No" to 0,1
func parseValue(value sql.RawBytes) (float64, bool) {
if bytes.Compare(value, []byte("Yes")) == 0 || bytes.Compare(value, []byte("ON")) == 0 {
func parseValue(value sql.RawBytes) (interface{}, bool) {
if bytes.EqualFold(value, []byte("YES")) || bytes.Compare(value, []byte("ON")) == 0 {
return 1, true
}
if bytes.Compare(value, []byte("No")) == 0 || bytes.Compare(value, []byte("OFF")) == 0 {
if bytes.EqualFold(value, []byte("NO")) || bytes.Compare(value, []byte("OFF")) == 0 {
return 0, true
}
n, err := strconv.ParseFloat(string(value), 64)
return n, err == nil
if val, err := strconv.ParseInt(string(value), 10, 64); err == nil {
return val, true
}
if val, err := strconv.ParseFloat(string(value), 64); err == nil {
return val, true
}
if len(string(value)) > 0 {
return string(value), true
}
return nil, false
}
// findThreadState can be used to find thread state by command and plain state

View File

@@ -127,26 +127,29 @@ func TestMysqlDNSAddTimeout(t *testing.T) {
}
}
}
func TestParseValue(t *testing.T) {
testCases := []struct {
rawByte sql.RawBytes
value float64
output interface{}
boolValue bool
}{
{sql.RawBytes("Yes"), 1, true},
{sql.RawBytes("No"), 0, false},
{sql.RawBytes("123"), int64(123), true},
{sql.RawBytes("abc"), "abc", true},
{sql.RawBytes("10.1"), 10.1, true},
{sql.RawBytes("ON"), 1, true},
{sql.RawBytes("OFF"), 0, false},
{sql.RawBytes("ABC"), 0, false},
{sql.RawBytes("OFF"), 0, true},
{sql.RawBytes("NO"), 0, true},
{sql.RawBytes("YES"), 1, true},
{sql.RawBytes("No"), 0, true},
{sql.RawBytes("Yes"), 1, true},
{sql.RawBytes(""), nil, false},
}
for _, cases := range testCases {
if value, ok := parseValue(cases.rawByte); value != cases.value && ok != cases.boolValue {
t.Errorf("want %d with %t, got %d with %t", int(cases.value), cases.boolValue, int(value), ok)
if got, ok := parseValue(cases.rawByte); got != cases.output && ok != cases.boolValue {
t.Errorf("for %s wanted %t, got %t", string(cases.rawByte), cases.output, got)
}
}
}
func TestNewNamespace(t *testing.T) {
testCases := []struct {
words []string

View File

@@ -0,0 +1,42 @@
# NATS Input Plugin
The [NATS](http://www.nats.io/about/) monitoring plugin gathers metrics from
the NATS [monitoring http server](https://www.nats.io/documentation/server/gnatsd-monitoring/).
### Configuration
```toml
[[inputs.nats]]
## The address of the monitoring endpoint of the NATS server
server = "http://localhost:8222"
## Maximum time to receive response
# response_timeout = "5s"
```
### Metrics:
- nats
- tags
- server
- fields:
- uptime (integer, nanoseconds)
- mem (integer, bytes)
- subscriptions (integer, count)
- out_bytes (integer, bytes)
- connections (integer, count)
- in_msgs (integer, bytes)
- total_connections (integer, count)
- cores (integer, count)
- cpu (integer, count)
- slow_consumers (integer, count)
- routes (integer, count)
- remotes (integer, count)
- out_msgs (integer, count)
- in_bytes (integer, bytes)
### Example Output:
```
nats,server=http://localhost:8222 uptime=117158348682i,mem=6647808i,subscriptions=0i,out_bytes=0i,connections=0i,in_msgs=0i,total_connections=0i,cores=2i,cpu=0,slow_consumers=0i,routes=0i,remotes=0i,out_msgs=0i,in_bytes=0i 1517015107000000000
```

114
plugins/inputs/nats/nats.go Normal file
View File

@@ -0,0 +1,114 @@
// +build !freebsd
package nats
import (
"io/ioutil"
"net/http"
"net/url"
"path"
"time"
"encoding/json"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/internal"
"github.com/influxdata/telegraf/plugins/inputs"
gnatsd "github.com/nats-io/gnatsd/server"
)
type Nats struct {
Server string
ResponseTimeout internal.Duration
client *http.Client
}
var sampleConfig = `
## The address of the monitoring endpoint of the NATS server
server = "http://localhost:8222"
## Maximum time to receive response
# response_timeout = "5s"
`
func (n *Nats) SampleConfig() string {
return sampleConfig
}
func (n *Nats) Description() string {
return "Provides metrics about the state of a NATS server"
}
func (n *Nats) Gather(acc telegraf.Accumulator) error {
url, err := url.Parse(n.Server)
if err != nil {
return err
}
url.Path = path.Join(url.Path, "varz")
if n.client == nil {
n.client = n.createHTTPClient()
}
resp, err := n.client.Get(url.String())
if err != nil {
return err
}
defer resp.Body.Close()
bytes, err := ioutil.ReadAll(resp.Body)
if err != nil {
return err
}
stats := new(gnatsd.Varz)
err = json.Unmarshal([]byte(bytes), &stats)
if err != nil {
return err
}
acc.AddFields("nats",
map[string]interface{}{
"in_msgs": stats.InMsgs,
"out_msgs": stats.OutMsgs,
"in_bytes": stats.InBytes,
"out_bytes": stats.OutBytes,
"uptime": stats.Now.Sub(stats.Start).Nanoseconds(),
"cores": stats.Cores,
"cpu": stats.CPU,
"mem": stats.Mem,
"connections": stats.Connections,
"total_connections": stats.TotalConnections,
"subscriptions": stats.Subscriptions,
"slow_consumers": stats.SlowConsumers,
"routes": stats.Routes,
"remotes": stats.Remotes,
},
map[string]string{"server": n.Server},
time.Now())
return nil
}
func (n *Nats) createHTTPClient() *http.Client {
transport := &http.Transport{
Proxy: http.ProxyFromEnvironment,
}
timeout := n.ResponseTimeout.Duration
if timeout == time.Duration(0) {
timeout = 5 * time.Second
}
return &http.Client{
Transport: transport,
Timeout: timeout,
}
}
func init() {
inputs.Add("nats", func() telegraf.Input {
return &Nats{
Server: "http://localhost:8222",
}
})
}

View File

@@ -0,0 +1,3 @@
// +build freebsd
package nats

View File

@@ -0,0 +1,114 @@
// +build !freebsd
package nats
import (
"fmt"
"net/http"
"net/http/httptest"
"testing"
"github.com/influxdata/telegraf/testutil"
"github.com/stretchr/testify/require"
)
var sampleVarz = `
{
"server_id": "n2afhLHLl64Gcaj7S7jaNa",
"version": "1.0.0",
"go": "go1.8",
"host": "0.0.0.0",
"auth_required": false,
"ssl_required": false,
"tls_required": false,
"tls_verify": false,
"addr": "0.0.0.0",
"max_connections": 65536,
"ping_interval": 120000000000,
"ping_max": 2,
"http_host": "0.0.0.0",
"http_port": 1337,
"https_port": 0,
"auth_timeout": 1,
"max_control_line": 1024,
"cluster": {
"addr": "0.0.0.0",
"cluster_port": 0,
"auth_timeout": 1
},
"tls_timeout": 0.5,
"port": 4222,
"max_payload": 1048576,
"start": "1861-04-12T10:15:26.841483489-05:00",
"now": "2011-10-05T15:24:23.722084098-07:00",
"uptime": "150y5md237h8m57s",
"mem": 15581184,
"cores": 48,
"cpu": 9,
"connections": 5,
"total_connections": 109,
"routes": 1,
"remotes": 2,
"in_msgs": 74148556,
"out_msgs": 68863261,
"in_bytes": 946267004717,
"out_bytes": 948110960598,
"slow_consumers": 2,
"subscriptions": 4,
"http_req_stats": {
"/": 1,
"/connz": 100847,
"/routez": 0,
"/subsz": 1,
"/varz": 205785
},
"config_load_time": "2017-07-24T10:15:26.841483489-05:00"
}
`
func TestMetricsCorrect(t *testing.T) {
var acc testutil.Accumulator
srv := newTestNatsServer()
defer srv.Close()
n := &Nats{Server: srv.URL}
err := n.Gather(&acc)
require.NoError(t, err)
fields := map[string]interface{}{
"in_msgs": int64(74148556),
"out_msgs": int64(68863261),
"in_bytes": int64(946267004717),
"out_bytes": int64(948110960598),
"uptime": int64(4748742536880600609),
"cores": 48,
"cpu": float64(9),
"mem": int64(15581184),
"connections": int(5),
"total_connections": uint64(109),
"subscriptions": uint32(4),
"slow_consumers": int64(2),
"routes": int(1),
"remotes": int(2),
}
tags := map[string]string{
"server": srv.URL,
}
acc.AssertContainsTaggedFields(t, "nats", fields, tags)
}
func newTestNatsServer() *httptest.Server {
return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
var rsp string
switch r.URL.Path {
case "/varz":
rsp = sampleVarz
default:
panic("Cannot handle request")
}
fmt.Fprintln(w, rsp)
}))
}

View File

@@ -4,6 +4,8 @@ This plugin gathers metrics from OpenLDAP's cn=Monitor backend.
### Configuration:
To use this plugin you must enable the [monitoring](https://www.openldap.org/devel/admin/monitoringslapd.html) backend.
```toml
[[inputs.openldap]]
host = "localhost"
@@ -23,50 +25,62 @@ This plugin gathers metrics from OpenLDAP's cn=Monitor backend.
# dn/password to bind with. If bind_dn is empty, an anonymous bind is performed.
bind_dn = ""
bind_password = ""
# reverse metric names so they sort more naturally
# Defaults to false if unset, but is set to true when generating a new config
reverse_metric_names = true
```
### Measurements & Fields:
All **monitorCounter**, **monitorOpInitiated**, and **monitorOpCompleted** attributes are gathered based on this LDAP query:
All **monitorCounter**, **monitoredInfo**, **monitorOpInitiated**, and **monitorOpCompleted** attributes are gathered based on this LDAP query:
```(|(objectClass=monitorCounterObject)(objectClass=monitorOperation))```
```(|(objectClass=monitorCounterObject)(objectClass=monitorOperation)(objectClass=monitoredObject))```
Metric names are based on their entry DN.
Metric names are based on their entry DN with the cn=Monitor base removed. If `reverse_metric_names` is not set, metrics are based on their DN. If `reverse_metric_names` is set to `true`, the names are reversed. This is recommended as it allows the names to sort more naturally.
Metrics for the **monitorOp*** attributes have **_initiated** and **_completed** added to the base name.
Metrics for the **monitorOp*** attributes have **_initiated** and **_completed** added to the base name as appropriate.
An OpenLDAP 2.4 server will provide these metrics:
- openldap
- max_file_descriptors_connections
- current_connections
- total_connections
- abandon_operations_completed
- abandon_operations_initiated
- add_operations_completed
- add_operations_initiated
- bind_operations_completed
- bind_operations_initiated
- compare_operations_completed
- compare_operations_initiated
- delete_operations_completed
- delete_operations_initiated
- extended_operations_completed
- extended_operations_initiated
- modify_operations_completed
- modify_operations_initiated
- modrdn_operations_completed
- modrdn_operations_initiated
- search_operations_completed
- search_operations_initiated
- unbind_operations_completed
- unbind_operations_initiated
- bytes_statistics
- entries_statistics
- pdu_statistics
- referrals_statistics
- read_waiters
- write_waiters
- connections_current
- connections_max_file_descriptors
- connections_total
- operations_abandon_completed
- operations_abandon_initiated
- operations_add_completed
- operations_add_initiated
- operations_bind_completed
- operations_bind_initiated
- operations_compare_completed
- operations_compare_initiated
- operations_delete_completed
- operations_delete_initiated
- operations_extended_completed
- operations_extended_initiated
- operations_modify_completed
- operations_modify_initiated
- operations_modrdn_completed
- operations_modrdn_initiated
- operations_search_completed
- operations_search_initiated
- operations_unbind_completed
- operations_unbind_initiated
- statistics_bytes
- statistics_entries
- statistics_pdu
- statistics_referrals
- threads_active
- threads_backload
- threads_max
- threads_max_pending
- threads_open
- threads_pending
- threads_starting
- time_uptime
- waiters_read
- waiters_write
### Tags:
@@ -78,5 +92,5 @@ An OpenLDAP 2.4 server will provide these metrics:
```
$ telegraf -config telegraf.conf -input-filter openldap -test --debug
* Plugin: inputs.openldap, Collection 1
> openldap,server=localhost,port=389,host=zirzla search_operations_completed=2i,delete_operations_completed=0i,read_waiters=1i,total_connections=1004i,bind_operations_completed=3i,unbind_operations_completed=3i,referrals_statistics=0i,current_connections=1i,bind_operations_initiated=3i,compare_operations_completed=0i,add_operations_completed=2i,delete_operations_initiated=0i,unbind_operations_initiated=3i,search_operations_initiated=3i,add_operations_initiated=2i,max_file_descriptors_connections=4096i,abandon_operations_initiated=0i,write_waiters=0i,modrdn_operations_completed=0i,abandon_operations_completed=0i,pdu_statistics=23i,modify_operations_initiated=0i,bytes_statistics=1660i,entries_statistics=17i,compare_operations_initiated=0i,modrdn_operations_initiated=0i,extended_operations_completed=0i,modify_operations_completed=0i,extended_operations_initiated=0i 1499990455000000000
> openldap,server=localhost,port=389,host=niska.ait.psu.edu operations_bind_initiated=10i,operations_unbind_initiated=6i,operations_modrdn_completed=0i,operations_delete_initiated=0i,operations_add_completed=2i,operations_delete_completed=0i,operations_abandon_completed=0i,statistics_entries=1516i,threads_open=2i,threads_active=1i,waiters_read=1i,operations_modify_completed=0i,operations_extended_initiated=4i,threads_pending=0i,operations_search_initiated=36i,operations_compare_initiated=0i,connections_max_file_descriptors=4096i,operations_modify_initiated=0i,operations_modrdn_initiated=0i,threads_max=16i,time_uptime=6017i,connections_total=1037i,connections_current=1i,operations_add_initiated=2i,statistics_bytes=162071i,operations_unbind_completed=6i,operations_abandon_initiated=0i,statistics_pdu=1566i,threads_max_pending=0i,threads_backload=1i,waiters_write=0i,operations_bind_completed=10i,operations_search_completed=35i,operations_compare_completed=0i,operations_extended_completed=4i,statistics_referrals=0i,threads_starting=0i 1516912070000000000
```

View File

@@ -20,6 +20,7 @@ type Openldap struct {
SslCa string
BindDn string
BindPassword string
ReverseMetricNames bool
}
const sampleConfig string = `
@@ -40,13 +41,18 @@ const sampleConfig string = `
# dn/password to bind with. If bind_dn is empty, an anonymous bind is performed.
bind_dn = ""
bind_password = ""
# Reverse metric names so they sort more naturally. Recommended.
# This defaults to false if unset, but is set to true when generating a new config
reverse_metric_names = true
`
var searchBase = "cn=Monitor"
var searchFilter = "(|(objectClass=monitorCounterObject)(objectClass=monitorOperation))"
var searchAttrs = []string{"monitorCounter", "monitorOpInitiated", "monitorOpCompleted"}
var searchFilter = "(|(objectClass=monitorCounterObject)(objectClass=monitorOperation)(objectClass=monitoredObject))"
var searchAttrs = []string{"monitorCounter", "monitorOpInitiated", "monitorOpCompleted", "monitoredInfo"}
var attrTranslate = map[string]string{
"monitorCounter": "",
"monitoredInfo": "",
"monitorOpInitiated": "_initiated",
"monitorOpCompleted": "_completed",
}
@@ -69,6 +75,7 @@ func NewOpenldap() *Openldap {
SslCa: "",
BindDn: "",
BindPassword: "",
ReverseMetricNames: false,
}
}
@@ -149,7 +156,7 @@ func gatherSearchResult(sr *ldap.SearchResult, o *Openldap, acc telegraf.Accumul
"port": strconv.Itoa(o.Port),
}
for _, entry := range sr.Entries {
metricName := dnToMetric(entry.DN, searchBase)
metricName := dnToMetric(entry.DN, o)
for _, attr := range entry.Attributes {
if len(attr.Values[0]) >= 1 {
if v, err := strconv.ParseInt(attr.Values[0], 10, 64); err == nil {
@@ -162,15 +169,30 @@ func gatherSearchResult(sr *ldap.SearchResult, o *Openldap, acc telegraf.Accumul
return
}
// Convert a DN to metric name, eg cn=Read,cn=Waiters,cn=Monitor to read_waiters
func dnToMetric(dn, searchBase string) string {
metricName := strings.Trim(dn, " ")
metricName = strings.Replace(metricName, " ", "_", -1)
metricName = strings.ToLower(metricName)
metricName = strings.TrimPrefix(metricName, "cn=")
metricName = strings.Replace(metricName, strings.ToLower(searchBase), "", -1)
metricName = strings.Replace(metricName, "cn=", "_", -1)
return strings.Replace(metricName, ",", "", -1)
// Convert a DN to metric name, eg cn=Read,cn=Waiters,cn=Monitor becomes waiters_read
// Assumes the last part of the DN is cn=Monitor and we want to drop it
func dnToMetric(dn string, o *Openldap) string {
if o.ReverseMetricNames {
var metricParts []string
dn = strings.Trim(dn, " ")
dn = strings.Replace(dn, " ", "_", -1)
dn = strings.Replace(dn, "cn=", "", -1)
dn = strings.ToLower(dn)
metricParts = strings.Split(dn, ",")
for i, j := 0, len(metricParts)-1; i < j; i, j = i+1, j-1 {
metricParts[i], metricParts[j] = metricParts[j], metricParts[i]
}
return strings.Join(metricParts[1:], "_")
} else {
metricName := strings.Trim(dn, " ")
metricName = strings.Replace(metricName, " ", "_", -1)
metricName = strings.ToLower(metricName)
metricName = strings.TrimPrefix(metricName, "cn=")
metricName = strings.Replace(metricName, strings.ToLower("cn=Monitor"), "", -1)
metricName = strings.Replace(metricName, "cn=", "_", -1)
return strings.Replace(metricName, ",", "", -1)
}
}
func init() {

View File

@@ -148,3 +148,24 @@ func commonTests(t *testing.T, o *Openldap, acc *testutil.Accumulator) {
assert.Equal(t, strconv.Itoa(o.Port), acc.TagValue("openldap", "port"), "Has a tag value of port=o.Port")
assert.True(t, acc.HasInt64Field("openldap", "total_connections"), "Has an integer field called total_connections")
}
func TestOpenldapReverseMetrics(t *testing.T) {
if testing.Short() {
t.Skip("Skipping integration test in short mode")
}
o := &Openldap{
Host: testutil.GetLocalHost(),
Port: 389,
Ssl: "",
InsecureSkipVerify: true,
BindDn: "cn=manager,cn=config",
BindPassword: "secret",
ReverseMetricNames: true,
}
var acc testutil.Accumulator
err := o.Gather(&acc)
require.NoError(t, err)
assert.True(t, acc.HasInt64Field("openldap", "connections_total"), "Has an integer field called connections_total")
}

View File

@@ -17,7 +17,8 @@ urls = ["www.google.com"] # required
# ping_interval = 1.0
## per-ping timeout, in s. 0 == no timeout (ping -W <TIMEOUT>)
# timeout = 1.0
## interface to send ping from (ping -I <INTERFACE>)
## interface or source address to send ping from (ping -I <INTERFACE/SRC_ADDR>)
## on Darwin and Freebsd only source address possible: (ping -S <SRC_ADDR>)
# interface = ""
```

View File

@@ -34,7 +34,7 @@ type Ping struct {
// Ping timeout, in seconds. 0 means no timeout (ping -W <TIMEOUT>)
Timeout float64
// Interface to send ping from (ping -I <INTERFACE>)
// Interface or source address to send ping from (ping -I/-S <INTERFACE/SRC_ADDR>)
Interface string
// URLs to ping
@@ -60,7 +60,8 @@ const sampleConfig = `
# ping_interval = 1.0
## per-ping timeout, in s. 0 == no timeout (ping -W <TIMEOUT>)
# timeout = 1.0
## interface to send ping from (ping -I <INTERFACE>)
## interface or source address to send ping from (ping -I <INTERFACE/SRC_ADDR>)
## on Darwin and Freebsd only source address possible: (ping -S <SRC_ADDR>)
# interface = ""
`
@@ -179,7 +180,15 @@ func (p *Ping) args(url string) []string {
}
}
if p.Interface != "" {
args = append(args, "-I", p.Interface)
switch runtime.GOOS {
case "linux":
args = append(args, "-I", p.Interface)
case "freebsd", "darwin":
args = append(args, "-S", p.Interface)
default:
// Not sure the best option here, just assume GNU ping?
args = append(args, "-I", p.Interface)
}
}
args = append(args, url)
return args

View File

@@ -13,6 +13,25 @@ For each of the active, hold, incoming, maildrop, and deferred queues (http://ww
# queue_directory = "/var/spool/postfix"
```
#### Permissions:
Telegraf will need read access to the files in the queue directory. You may
need to alter the permissions of these directories to provide access to the
telegraf user.
Unix permissions:
```sh
$ sudo chgrp -R telegraf /var/spool/postfix/{active,hold,incoming,deferred}
$ sudo chmod -R g+rXs /var/spool/postfix/{active,hold,incoming,deferred}
$ sudo usermod -a -G postdrop telegraf
$ sudo chmod g+r /var/spool/postfix/maildrop
```
Posix ACL:
```sh
$ sudo setfacl -Rdm u:telegraf:rX /var/spool/postfix/{active,hold,incoming,deferred,maildrop}
```
### Measurements & Fields:
- postfix_queue

View File

@@ -1,77 +0,0 @@
package postgresql
import (
"fmt"
"net"
"net/url"
"sort"
"strings"
)
// pulled from lib/pq
// ParseURL no longer needs to be used by clients of this library since supplying a URL as a
// connection string to sql.Open() is now supported:
//
// sql.Open("postgres", "postgres://bob:secret@1.2.3.4:5432/mydb?sslmode=verify-full")
//
// It remains exported here for backwards-compatibility.
//
// ParseURL converts a url to a connection string for driver.Open.
// Example:
//
// "postgres://bob:secret@1.2.3.4:5432/mydb?sslmode=verify-full"
//
// converts to:
//
// "user=bob password=secret host=1.2.3.4 port=5432 dbname=mydb sslmode=verify-full"
//
// A minimal example:
//
// "postgres://"
//
// This will be blank, causing driver.Open to use all of the defaults
func ParseURL(uri string) (string, error) {
u, err := url.Parse(uri)
if err != nil {
return "", err
}
if u.Scheme != "postgres" && u.Scheme != "postgresql" {
return "", fmt.Errorf("invalid connection protocol: %s", u.Scheme)
}
var kvs []string
escaper := strings.NewReplacer(` `, `\ `, `'`, `\'`, `\`, `\\`)
accrue := func(k, v string) {
if v != "" {
kvs = append(kvs, k+"="+escaper.Replace(v))
}
}
if u.User != nil {
v := u.User.Username()
accrue("user", v)
v, _ = u.User.Password()
accrue("password", v)
}
if host, port, err := net.SplitHostPort(u.Host); err != nil {
accrue("host", u.Host)
} else {
accrue("host", host)
accrue("port", port)
}
if u.Path != "" {
accrue("dbname", u.Path[1:])
}
q := u.Query()
for k := range q {
accrue(k, q.Get(k))
}
sort.Strings(kvs) // Makes testing easier (not a performance concern)
return strings.Join(kvs, " "), nil
}

View File

@@ -2,26 +2,21 @@ package postgresql
import (
"bytes"
"database/sql"
"fmt"
"regexp"
"sort"
"strings"
// register in driver.
_ "github.com/jackc/pgx/stdlib"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/internal"
"github.com/influxdata/telegraf/plugins/inputs"
)
type Postgresql struct {
Address string
Service
Databases []string
IgnoredDatabases []string
OrderedColumns []string
AllColumns []string
sanitizedAddress string
}
var ignoredColumns = map[string]bool{"stats_reset": true}
@@ -41,6 +36,15 @@ var sampleConfig = `
## to grab metrics for.
##
address = "host=localhost user=postgres sslmode=disable"
## A custom name for the database that will be used as the "server" tag in the
## measurement output. If not specified, a default one generated from
## the connection address is used.
# outputaddress = "db01"
## connection configuration.
## maxlifetime - specify the maximum lifetime of a connection.
## default is forever (0s)
max_lifetime = "0s"
## A list of databases to explicitly ignore. If not specified, metrics for all
## databases are gathered. Do NOT use with the 'databases' option.
@@ -63,24 +67,13 @@ func (p *Postgresql) IgnoredColumns() map[string]bool {
return ignoredColumns
}
var localhost = "host=localhost sslmode=disable"
func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
var (
err error
db *sql.DB
query string
err error
query string
columns []string
)
if p.Address == "" || p.Address == "localhost" {
p.Address = localhost
}
if db, err = sql.Open("pgx", p.Address); err != nil {
return err
}
defer db.Close()
if len(p.Databases) == 0 && len(p.IgnoredDatabases) == 0 {
query = `SELECT * FROM pg_stat_database`
} else if len(p.IgnoredDatabases) != 0 {
@@ -91,7 +84,7 @@ func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
strings.Join(p.Databases, "','"))
}
rows, err := db.Query(query)
rows, err := p.DB.Query(query)
if err != nil {
return err
}
@@ -99,16 +92,12 @@ func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
defer rows.Close()
// grab the column information from the result
p.OrderedColumns, err = rows.Columns()
if err != nil {
if columns, err = rows.Columns(); err != nil {
return err
} else {
p.AllColumns = make([]string, len(p.OrderedColumns))
copy(p.AllColumns, p.OrderedColumns)
}
for rows.Next() {
err = p.accRow(rows, acc)
err = p.accRow(rows, acc, columns)
if err != nil {
return err
}
@@ -116,7 +105,7 @@ func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
query = `SELECT * FROM pg_stat_bgwriter`
bg_writer_row, err := db.Query(query)
bg_writer_row, err := p.DB.Query(query)
if err != nil {
return err
}
@@ -124,22 +113,17 @@ func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
defer bg_writer_row.Close()
// grab the column information from the result
p.OrderedColumns, err = bg_writer_row.Columns()
if err != nil {
if columns, err = bg_writer_row.Columns(); err != nil {
return err
} else {
for _, v := range p.OrderedColumns {
p.AllColumns = append(p.AllColumns, v)
}
}
for bg_writer_row.Next() {
err = p.accRow(bg_writer_row, acc)
err = p.accRow(bg_writer_row, acc, columns)
if err != nil {
return err
}
}
sort.Strings(p.AllColumns)
return bg_writer_row.Err()
}
@@ -147,37 +131,20 @@ type scanner interface {
Scan(dest ...interface{}) error
}
var passwordKVMatcher, _ = regexp.Compile("password=\\S+ ?")
func (p *Postgresql) SanitizedAddress() (_ string, err error) {
var canonicalizedAddress string
if strings.HasPrefix(p.Address, "postgres://") || strings.HasPrefix(p.Address, "postgresql://") {
canonicalizedAddress, err = ParseURL(p.Address)
if err != nil {
return p.sanitizedAddress, err
}
} else {
canonicalizedAddress = p.Address
}
p.sanitizedAddress = passwordKVMatcher.ReplaceAllString(canonicalizedAddress, "")
return p.sanitizedAddress, err
}
func (p *Postgresql) accRow(row scanner, acc telegraf.Accumulator) error {
func (p *Postgresql) accRow(row scanner, acc telegraf.Accumulator, columns []string) error {
var columnVars []interface{}
var dbname bytes.Buffer
// this is where we'll store the column name with its *interface{}
columnMap := make(map[string]*interface{})
for _, column := range p.OrderedColumns {
for _, column := range columns {
columnMap[column] = new(interface{})
}
// populate the array of interface{} with the pointers in the right order
for i := 0; i < len(columnMap); i++ {
columnVars = append(columnVars, columnMap[p.OrderedColumns[i]])
columnVars = append(columnVars, columnMap[columns[i]])
}
// deconstruct array of variables and send to Scan
@@ -215,6 +182,14 @@ func (p *Postgresql) accRow(row scanner, acc telegraf.Accumulator) error {
func init() {
inputs.Add("postgresql", func() telegraf.Input {
return &Postgresql{}
return &Postgresql{
Service: Service{
MaxIdle: 1,
MaxOpen: 1,
MaxLifetime: internal.Duration{
Duration: 0,
},
},
}
})
}

View File

@@ -15,19 +15,18 @@ func TestPostgresqlGeneratesMetrics(t *testing.T) {
}
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
Databases: []string{"postgres"},
}
var acc testutil.Accumulator
err := p.Gather(&acc)
require.NoError(t, err)
availableColumns := make(map[string]bool)
for _, col := range p.AllColumns {
availableColumns[col] = true
}
require.NoError(t, p.Start(&acc))
require.NoError(t, p.Gather(&acc))
intMetrics := []string{
"xact_commit",
@@ -71,39 +70,27 @@ func TestPostgresqlGeneratesMetrics(t *testing.T) {
metricsCounted := 0
for _, metric := range intMetrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasInt64Field("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasInt64Field("postgresql", metric))
metricsCounted++
}
for _, metric := range int32Metrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasInt32Field("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasInt32Field("postgresql", metric))
metricsCounted++
}
for _, metric := range floatMetrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasFloatField("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasFloatField("postgresql", metric))
metricsCounted++
}
for _, metric := range stringMetrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasStringField("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasStringField("postgresql", metric))
metricsCounted++
}
assert.True(t, metricsCounted > 0)
assert.Equal(t, len(availableColumns)-len(p.IgnoredColumns()), metricsCounted)
assert.Equal(t, len(floatMetrics)+len(intMetrics)+len(int32Metrics)+len(stringMetrics), metricsCounted)
}
func TestPostgresqlTagsMetricsWithDatabaseName(t *testing.T) {
@@ -112,15 +99,19 @@ func TestPostgresqlTagsMetricsWithDatabaseName(t *testing.T) {
}
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
Databases: []string{"postgres"},
}
var acc testutil.Accumulator
err := p.Gather(&acc)
require.NoError(t, err)
require.NoError(t, p.Start(&acc))
require.NoError(t, p.Gather(&acc))
point, ok := acc.Get("postgresql")
require.True(t, ok)
@@ -134,14 +125,18 @@ func TestPostgresqlDefaultsToAllDatabases(t *testing.T) {
}
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
}
var acc testutil.Accumulator
err := p.Gather(&acc)
require.NoError(t, err)
require.NoError(t, p.Start(&acc))
require.NoError(t, p.Gather(&acc))
var found bool
@@ -163,14 +158,17 @@ func TestPostgresqlIgnoresUnwantedColumns(t *testing.T) {
}
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
}
var acc testutil.Accumulator
err := p.Gather(&acc)
require.NoError(t, err)
require.NoError(t, p.Start(&acc))
require.NoError(t, p.Gather(&acc))
for col := range p.IgnoredColumns() {
assert.False(t, acc.HasMeasurement(col))
@@ -183,15 +181,19 @@ func TestPostgresqlDatabaseWhitelistTest(t *testing.T) {
}
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
Databases: []string{"template0"},
}
var acc testutil.Accumulator
err := p.Gather(&acc)
require.NoError(t, err)
require.NoError(t, p.Start(&acc))
require.NoError(t, p.Gather(&acc))
var foundTemplate0 = false
var foundTemplate1 = false
@@ -219,15 +221,18 @@ func TestPostgresqlDatabaseBlacklistTest(t *testing.T) {
}
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
IgnoredDatabases: []string{"template0"},
}
var acc testutil.Accumulator
err := p.Gather(&acc)
require.NoError(t, err)
require.NoError(t, p.Start(&acc))
require.NoError(t, p.Gather(&acc))
var foundTemplate0 = false
var foundTemplate1 = false

View File

@@ -0,0 +1,142 @@
package postgresql
import (
"database/sql"
"fmt"
"net"
"net/url"
"regexp"
"sort"
"strings"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/internal"
)
// pulled from lib/pq
// ParseURL no longer needs to be used by clients of this library since supplying a URL as a
// connection string to sql.Open() is now supported:
//
// sql.Open("postgres", "postgres://bob:secret@1.2.3.4:5432/mydb?sslmode=verify-full")
//
// It remains exported here for backwards-compatibility.
//
// ParseURL converts a url to a connection string for driver.Open.
// Example:
//
// "postgres://bob:secret@1.2.3.4:5432/mydb?sslmode=verify-full"
//
// converts to:
//
// "user=bob password=secret host=1.2.3.4 port=5432 dbname=mydb sslmode=verify-full"
//
// A minimal example:
//
// "postgres://"
//
// This will be blank, causing driver.Open to use all of the defaults
func parseURL(uri string) (string, error) {
u, err := url.Parse(uri)
if err != nil {
return "", err
}
if u.Scheme != "postgres" && u.Scheme != "postgresql" {
return "", fmt.Errorf("invalid connection protocol: %s", u.Scheme)
}
var kvs []string
escaper := strings.NewReplacer(` `, `\ `, `'`, `\'`, `\`, `\\`)
accrue := func(k, v string) {
if v != "" {
kvs = append(kvs, k+"="+escaper.Replace(v))
}
}
if u.User != nil {
v := u.User.Username()
accrue("user", v)
v, _ = u.User.Password()
accrue("password", v)
}
if host, port, err := net.SplitHostPort(u.Host); err != nil {
accrue("host", u.Host)
} else {
accrue("host", host)
accrue("port", port)
}
if u.Path != "" {
accrue("dbname", u.Path[1:])
}
q := u.Query()
for k := range q {
accrue(k, q.Get(k))
}
sort.Strings(kvs) // Makes testing easier (not a performance concern)
return strings.Join(kvs, " "), nil
}
// Service common functionality shared between the postgresql and postgresql_extensible
// packages.
type Service struct {
Address string
Outputaddress string
MaxIdle int
MaxOpen int
MaxLifetime internal.Duration
DB *sql.DB
}
// Start starts the ServiceInput's service, whatever that may be
func (p *Service) Start(telegraf.Accumulator) (err error) {
const localhost = "host=localhost sslmode=disable"
if p.Address == "" || p.Address == "localhost" {
p.Address = localhost
}
if p.DB, err = sql.Open("pgx", p.Address); err != nil {
return err
}
p.DB.SetMaxOpenConns(p.MaxOpen)
p.DB.SetMaxIdleConns(p.MaxIdle)
p.DB.SetConnMaxLifetime(p.MaxLifetime.Duration)
return nil
}
// Stop stops the services and closes any necessary channels and connections
func (p *Service) Stop() {
p.DB.Close()
}
var kvMatcher, _ = regexp.Compile("(password|sslcert|sslkey|sslmode|sslrootcert)=\\S+ ?")
// SanitizedAddress utility function to strip sensitive information from the connection string.
func (p *Service) SanitizedAddress() (sanitizedAddress string, err error) {
var (
canonicalizedAddress string
)
if p.Outputaddress != "" {
return p.Outputaddress, nil
}
if strings.HasPrefix(p.Address, "postgres://") || strings.HasPrefix(p.Address, "postgresql://") {
if canonicalizedAddress, err = parseURL(p.Address); err != nil {
return sanitizedAddress, err
}
} else {
canonicalizedAddress = p.Address
}
sanitizedAddress = kvMatcher.ReplaceAllString(canonicalizedAddress, "")
return sanitizedAddress, err
}

View File

@@ -43,7 +43,11 @@ The example below has two queries are specified, with the following parameters:
# withdbname was true.
# Be careful that if the withdbname is set to false you don't have to define
# the where clause (aka with the dbname)
# the tagvalue field is used to define custom tags (separated by comas)
#
# the tagvalue field is used to define custom tags (separated by comas).
# the query is expected to return columns which match the names of the
# defined tags. The values in these columns must be of a string-type,
# a number-type or a blob-type.
#
# Structure :
# [[inputs.postgresql_extensible.query]]
@@ -109,6 +113,15 @@ using postgreql extensions ([pg_stat_statements](http://www.postgresql.org/docs/
version=901
withdbname=false
tagvalue="db"
[[inputs.postgresql_extensible.query]]
sqlquery="""
SELECT type, (enabled || '') AS enabled, COUNT(*)
FROM application_users
GROUP BY type, enabled
"""
version=901
withdbname=false
tagvalue="type,enabled"
```
# Postgresql Side

View File

@@ -2,29 +2,24 @@ package postgresql_extensible
import (
"bytes"
"database/sql"
"fmt"
"log"
"regexp"
"strings"
// register in driver.
_ "github.com/jackc/pgx/stdlib"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/internal"
"github.com/influxdata/telegraf/plugins/inputs"
"github.com/influxdata/telegraf/plugins/inputs/postgresql"
)
type Postgresql struct {
Address string
Outputaddress string
Databases []string
OrderedColumns []string
AllColumns []string
AdditionalTags []string
sanitizedAddress string
Query []struct {
postgresql.Service
Databases []string
AdditionalTags []string
Query []struct {
Sqlquery string
Version int
Withdbname bool
@@ -58,14 +53,20 @@ var sampleConfig = `
## to grab metrics for.
#
address = "host=localhost user=postgres sslmode=disable"
## connection configuration.
## maxlifetime - specify the maximum lifetime of a connection.
## default is forever (0s)
max_lifetime = "0s"
## A list of databases to pull metrics about. If not specified, metrics for all
## databases are gathered.
## databases = ["app_production", "testing"]
#
# outputaddress = "db01"
## A custom name for the database that will be used as the "server" tag in the
## measurement output. If not specified, a default one generated from
## the connection address is used.
# outputaddress = "db01"
#
## Define the toml config where the sql queries are stored
## New queries can be added, if the withdbname is set to true and there is no
@@ -113,36 +114,25 @@ func (p *Postgresql) IgnoredColumns() map[string]bool {
return ignoredColumns
}
var localhost = "host=localhost sslmode=disable"
func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
var (
err error
db *sql.DB
sql_query string
query_addon string
db_version int
query string
tag_value string
meas_name string
columns []string
)
if p.Address == "" || p.Address == "localhost" {
p.Address = localhost
}
if db, err = sql.Open("pgx", p.Address); err != nil {
return err
}
defer db.Close()
// Retreiving the database version
query = `select substring(setting from 1 for 3) as version from pg_settings where name='server_version_num'`
err = db.QueryRow(query).Scan(&db_version)
if err != nil {
if err = p.DB.QueryRow(query).Scan(&db_version); err != nil {
db_version = 0
}
// We loop in order to process each query
// Query is not run if Database version does not match the query version.
@@ -168,7 +158,7 @@ func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
sql_query += query_addon
if p.Query[i].Version <= db_version {
rows, err := db.Query(sql_query)
rows, err := p.DB.Query(sql_query)
if err != nil {
acc.AddError(err)
continue
@@ -177,15 +167,11 @@ func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
defer rows.Close()
// grab the column information from the result
p.OrderedColumns, err = rows.Columns()
if err != nil {
if columns, err = rows.Columns(); err != nil {
acc.AddError(err)
continue
} else {
for _, v := range p.OrderedColumns {
p.AllColumns = append(p.AllColumns, v)
}
}
p.AdditionalTags = nil
if tag_value != "" {
tag_list := strings.Split(tag_value, ",")
@@ -195,7 +181,7 @@ func (p *Postgresql) Gather(acc telegraf.Accumulator) error {
}
for rows.Next() {
err = p.accRow(meas_name, rows, acc)
err = p.accRow(meas_name, rows, acc, columns)
if err != nil {
acc.AddError(err)
break
@@ -210,27 +196,7 @@ type scanner interface {
Scan(dest ...interface{}) error
}
var KVMatcher, _ = regexp.Compile("(password|sslcert|sslkey|sslmode|sslrootcert)=\\S+ ?")
func (p *Postgresql) SanitizedAddress() (_ string, err error) {
if p.Outputaddress != "" {
return p.Outputaddress, nil
}
var canonicalizedAddress string
if strings.HasPrefix(p.Address, "postgres://") || strings.HasPrefix(p.Address, "postgresql://") {
canonicalizedAddress, err = postgresql.ParseURL(p.Address)
if err != nil {
return p.sanitizedAddress, err
}
} else {
canonicalizedAddress = p.Address
}
p.sanitizedAddress = KVMatcher.ReplaceAllString(canonicalizedAddress, "")
return p.sanitizedAddress, err
}
func (p *Postgresql) accRow(meas_name string, row scanner, acc telegraf.Accumulator) error {
func (p *Postgresql) accRow(meas_name string, row scanner, acc telegraf.Accumulator, columns []string) error {
var (
err error
columnVars []interface{}
@@ -241,13 +207,13 @@ func (p *Postgresql) accRow(meas_name string, row scanner, acc telegraf.Accumula
// this is where we'll store the column name with its *interface{}
columnMap := make(map[string]*interface{})
for _, column := range p.OrderedColumns {
for _, column := range columns {
columnMap[column] = new(interface{})
}
// populate the array of interface{} with the pointers in the right order
for i := 0; i < len(columnMap); i++ {
columnVars = append(columnVars, columnMap[p.OrderedColumns[i]])
columnVars = append(columnVars, columnMap[columns[i]])
}
// deconstruct array of variables and send to Scan
@@ -275,7 +241,7 @@ func (p *Postgresql) accRow(meas_name string, row scanner, acc telegraf.Accumula
fields := make(map[string]interface{})
COLUMN:
for col, val := range columnMap {
log.Printf("D! postgresql_extensible: column: %s = %T: %s\n", col, *val, *val)
log.Printf("D! postgresql_extensible: column: %s = %T: %v\n", col, *val, *val)
_, ignore := ignoredColumns[col]
if ignore || *val == nil {
continue
@@ -310,6 +276,14 @@ COLUMN:
func init() {
inputs.Add("postgresql_extensible", func() telegraf.Input {
return &Postgresql{}
return &Postgresql{
Service: postgresql.Service{
MaxIdle: 1,
MaxOpen: 1,
MaxLifetime: internal.Duration{
Duration: 0,
},
},
}
})
}

View File

@@ -4,22 +4,28 @@ import (
"fmt"
"testing"
"github.com/influxdata/telegraf/plugins/inputs/postgresql"
"github.com/influxdata/telegraf/testutil"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func queryRunner(t *testing.T, q query) (*Postgresql, *testutil.Accumulator) {
func queryRunner(t *testing.T, q query) *testutil.Accumulator {
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: postgresql.Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
Databases: []string{"postgres"},
Query: q,
}
var acc testutil.Accumulator
p.Start(&acc)
require.NoError(t, acc.GatherError(p.Gather))
return p, &acc
return &acc
}
func TestPostgresqlGeneratesMetrics(t *testing.T) {
@@ -27,18 +33,13 @@ func TestPostgresqlGeneratesMetrics(t *testing.T) {
t.Skip("Skipping integration test in short mode")
}
p, acc := queryRunner(t, query{{
acc := queryRunner(t, query{{
Sqlquery: "select * from pg_stat_database",
Version: 901,
Withdbname: false,
Tagvalue: "",
}})
availableColumns := make(map[string]bool)
for _, col := range p.AllColumns {
availableColumns[col] = true
}
intMetrics := []string{
"xact_commit",
"xact_rollback",
@@ -71,39 +72,27 @@ func TestPostgresqlGeneratesMetrics(t *testing.T) {
metricsCounted := 0
for _, metric := range intMetrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasInt64Field("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasInt64Field("postgresql", metric))
metricsCounted++
}
for _, metric := range int32Metrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasInt32Field("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasInt32Field("postgresql", metric))
metricsCounted++
}
for _, metric := range floatMetrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasFloatField("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasFloatField("postgresql", metric))
metricsCounted++
}
for _, metric := range stringMetrics {
_, ok := availableColumns[metric]
if ok {
assert.True(t, acc.HasStringField("postgresql", metric))
metricsCounted++
}
assert.True(t, acc.HasStringField("postgresql", metric))
metricsCounted++
}
assert.True(t, metricsCounted > 0)
assert.Equal(t, len(availableColumns)-len(p.IgnoredColumns()), metricsCounted)
assert.Equal(t, len(floatMetrics)+len(intMetrics)+len(int32Metrics)+len(stringMetrics), metricsCounted)
}
func TestPostgresqlQueryOutputTests(t *testing.T) {
@@ -137,7 +126,7 @@ func TestPostgresqlQueryOutputTests(t *testing.T) {
}
for q, assertions := range examples {
_, acc := queryRunner(t, query{{
acc := queryRunner(t, query{{
Sqlquery: q,
Version: 901,
Withdbname: false,
@@ -153,7 +142,7 @@ func TestPostgresqlFieldOutput(t *testing.T) {
t.Skip("Skipping integration test in short mode")
}
_, acc := queryRunner(t, query{{
acc := queryRunner(t, query{{
Sqlquery: "select * from pg_stat_database",
Version: 901,
Withdbname: false,
@@ -216,13 +205,18 @@ func TestPostgresqlIgnoresUnwantedColumns(t *testing.T) {
}
p := &Postgresql{
Address: fmt.Sprintf("host=%s user=postgres sslmode=disable",
testutil.GetLocalHost()),
Service: postgresql.Service{
Address: fmt.Sprintf(
"host=%s user=postgres sslmode=disable",
testutil.GetLocalHost(),
),
},
}
var acc testutil.Accumulator
require.NoError(t, acc.GatherError(p.Gather))
require.NoError(t, p.Start(&acc))
require.NoError(t, acc.GatherError(p.Gather))
assert.NotEmpty(t, p.IgnoredColumns())
for col := range p.IgnoredColumns() {
assert.False(t, acc.HasMeasurement(col))

View File

@@ -1,121 +1,138 @@
# Telegraf plugin: procstat
# Procstat Input Plugin
#### Description
The procstat plugin can be used to monitor the system resource usage of one or more processes.
The procstat plugin can be used to monitor system resource usage by an
individual process using their /proc data.
Processes can be selected for monitoring using one of several methods:
- pidfile
- exe
- pattern
- user
- systemd_unit
- cgroup
Processes can be specified either by pid file, by executable name, by command
line pattern matching, by username, by systemd unit name, or by cgroup name/path
(in this order or priority). Procstat plugin will use `pgrep` when executable
name is provided to obtain the pid. Procstat plugin will transmit IO, memory,
cpu, file descriptor related measurements for every process specified. A prefix
can be set to isolate individual process specific measurements.
### Configuration:
The plugin will tag processes according to how they are specified in the configuration. If a pid file is used, a "pidfile" tag will be generated.
On the other hand, if an executable is used an "exe" tag will be generated. Possible tag names:
* pidfile
* exe
* pattern
* user
* systemd_unit
* cgroup
Additionally the plugin will tag processes by their PID (pid_tag = true in the config) and their process name:
* pid
* process_name
Example:
```
```toml
# Monitor process cpu and memory usage
[[inputs.procstat]]
exe = "influxd"
prefix = "influxd"
## PID file to monitor process
pid_file = "/var/run/nginx.pid"
## executable name (ie, pgrep <exe>)
# exe = "nginx"
## pattern as argument for pgrep (ie, pgrep -f <pattern>)
# pattern = "nginx"
## user as argument for pgrep (ie, pgrep -u <user>)
# user = "nginx"
## Systemd unit name
# systemd_unit = "nginx.service"
## CGroup name or path
# cgroup = "systemd/system.slice/nginx.service"
## override for process_name
## This is optional; default is sourced from /proc/<pid>/status
# process_name = "bar"
## Field name prefix
# prefix = ""
## Add PID as a tag instead of a field; useful to differentiate between
## processes whose tags are otherwise the same. Can create a large number
## of series, use judiciously.
# pid_tag = false
## Method to use when finding process IDs. Can be one of 'pgrep', or
## 'native'. The pgrep finder calls the pgrep executable in the PATH while
## the native finder performs the search directly in a manor dependent on the
## platform. Default is 'pgrep'
# pid_finder = "pgrep"
```
#### Windows support
Preliminary support for Windows has been added, however you may prefer using
the `win_perf_counters` input plugin as a more mature alternative.
When using the `pid_finder = "native"` in Windows, the pattern lookup method is
implemented as a WMI query. The pattern allows fuzzy matching using only
[WMI query patterns](https://msdn.microsoft.com/en-us/library/aa392263(v=vs.85).aspx):
```toml
[[inputs.procstat]]
pid_file = "/var/run/lxc/dnsmasq.pid"
pattern = "%influx%"
pid_finder = "native"
```
The above configuration would result in output like:
### Metrics:
- procstat
- tags:
- pid (when `pid_tag` is true)
- process_name
- pidfile (when defined)
- exe (when defined)
- pattern (when defined)
- user (when selected)
- systemd_unit (when defined)
- cgroup (when defined)
- fields:
- cpu_time (int)
- cpu_time_guest (float)
- cpu_time_guest_nice (float)
- cpu_time_idle (float)
- cpu_time_iowait (float)
- cpu_time_irq (float)
- cpu_time_nice (float)
- cpu_time_soft_irq (float)
- cpu_time_steal (float)
- cpu_time_stolen (float)
- cpu_time_system (float)
- cpu_time_user (float)
- cpu_usage (float)
- involuntary_context_switches (int)
- memory_data (int)
- memory_locked (int)
- memory_rss (int)
- memory_stack (int)
- memory_swap (int)
- memory_vms (int)
- nice_priority (int)
- num_fds (int, *telegraf* may need to be ran as **root**)
- num_threads (int)
- pid (int)
- read_bytes (int, *telegraf* may need to be ran as **root**)
- read_count (int, *telegraf* may need to be ran as **root**)
- realtime_priority (int)
- rlimit_cpu_time_hard (int)
- rlimit_cpu_time_soft (int)
- rlimit_file_locks_hard (int)
- rlimit_file_locks_soft (int)
- rlimit_memory_data_hard (int)
- rlimit_memory_data_soft (int)
- rlimit_memory_locked_hard (int)
- rlimit_memory_locked_soft (int)
- rlimit_memory_rss_hard (int)
- rlimit_memory_rss_soft (int)
- rlimit_memory_stack_hard (int)
- rlimit_memory_stack_soft (int)
- rlimit_memory_vms_hard (int)
- rlimit_memory_vms_soft (int)
- rlimit_nice_priority_hard (int)
- rlimit_nice_priority_soft (int)
- rlimit_num_fds_hard (int)
- rlimit_num_fds_soft (int)
- rlimit_realtime_priority_hard (int)
- rlimit_realtime_priority_soft (int)
- rlimit_signals_pending_hard (int)
- rlimit_signals_pending_soft (int)
- signals_pending (int)
- voluntary_context_switches (int)
- write_bytes (int, *telegraf* may need to be ran as **root**)
- write_count (int, *telegraf* may need to be ran as **root**)
*NOTE: Resource limit > 2147483647 will be reported as 2147483647.*
### Example Output:
```
> procstat,pidfile=/var/run/lxc/dnsmasq.pid,process_name=dnsmasq rlimit_file_locks_soft=2147483647i,rlimit_signals_pending_hard=1758i,voluntary_context_switches=478i,read_bytes=307200i,cpu_time_user=0.01,cpu_time_guest=0,memory_swap=0i,memory_locked=0i,rlimit_num_fds_hard=4096i,rlimit_nice_priority_hard=0i,num_fds=11i,involuntary_context_switches=20i,read_count=23i,memory_rss=1388544i,rlimit_memory_rss_soft=2147483647i,rlimit_memory_rss_hard=2147483647i,nice_priority=20i,rlimit_cpu_time_hard=2147483647i,cpu_time=0i,write_bytes=0i,cpu_time_idle=0,cpu_time_nice=0,memory_data=229376i,memory_stack=135168i,rlimit_cpu_time_soft=2147483647i,rlimit_memory_data_hard=2147483647i,rlimit_memory_locked_hard=65536i,rlimit_signals_pending_soft=1758i,write_count=11i,cpu_time_iowait=0,cpu_time_steal=0,cpu_time_stolen=0,rlimit_memory_stack_soft=8388608i,cpu_time_system=0.02,cpu_time_guest_nice=0,rlimit_memory_locked_soft=65536i,rlimit_memory_vms_soft=2147483647i,rlimit_file_locks_hard=2147483647i,rlimit_realtime_priority_hard=0i,pid=828i,num_threads=1i,cpu_time_soft_irq=0,rlimit_memory_vms_hard=2147483647i,rlimit_realtime_priority_soft=0i,memory_vms=15884288i,rlimit_memory_stack_hard=2147483647i,cpu_time_irq=0,rlimit_memory_data_soft=2147483647i,rlimit_num_fds_soft=1024i,signals_pending=0i,rlimit_nice_priority_soft=0i,realtime_priority=0i
> procstat,exe=influxd,process_name=influxd rlimit_num_fds_hard=16384i,rlimit_signals_pending_hard=1758i,realtime_priority=0i,rlimit_memory_vms_hard=2147483647i,rlimit_signals_pending_soft=1758i,cpu_time_stolen=0,rlimit_memory_stack_hard=2147483647i,rlimit_realtime_priority_hard=0i,cpu_time=0i,pid=500i,voluntary_context_switches=975i,cpu_time_idle=0,memory_rss=3072000i,memory_locked=0i,rlimit_nice_priority_soft=0i,signals_pending=0i,nice_priority=20i,read_bytes=823296i,cpu_time_soft_irq=0,rlimit_memory_data_hard=2147483647i,rlimit_memory_locked_soft=65536i,write_count=8i,cpu_time_irq=0,memory_vms=33501184i,rlimit_memory_stack_soft=8388608i,cpu_time_iowait=0,rlimit_memory_vms_soft=2147483647i,rlimit_nice_priority_hard=0i,num_fds=29i,memory_data=229376i,rlimit_cpu_time_soft=2147483647i,rlimit_file_locks_soft=2147483647i,num_threads=1i,write_bytes=0i,cpu_time_steal=0,rlimit_memory_rss_hard=2147483647i,cpu_time_guest=0,cpu_time_guest_nice=0,cpu_usage=0,rlimit_memory_locked_hard=65536i,rlimit_file_locks_hard=2147483647i,involuntary_context_switches=38i,read_count=16851i,memory_swap=0i,rlimit_memory_data_soft=2147483647i,cpu_time_user=0.11,rlimit_cpu_time_hard=2147483647i,rlimit_num_fds_soft=16384i,rlimit_realtime_priority_soft=0i,cpu_time_system=0.27,cpu_time_nice=0,memory_stack=135168i,rlimit_memory_rss_soft=2147483647i
procstat,pidfile=/var/run/lxc/dnsmasq.pid,process_name=dnsmasq rlimit_file_locks_soft=2147483647i,rlimit_signals_pending_hard=1758i,voluntary_context_switches=478i,read_bytes=307200i,cpu_time_user=0.01,cpu_time_guest=0,memory_swap=0i,memory_locked=0i,rlimit_num_fds_hard=4096i,rlimit_nice_priority_hard=0i,num_fds=11i,involuntary_context_switches=20i,read_count=23i,memory_rss=1388544i,rlimit_memory_rss_soft=2147483647i,rlimit_memory_rss_hard=2147483647i,nice_priority=20i,rlimit_cpu_time_hard=2147483647i,cpu_time=0i,write_bytes=0i,cpu_time_idle=0,cpu_time_nice=0,memory_data=229376i,memory_stack=135168i,rlimit_cpu_time_soft=2147483647i,rlimit_memory_data_hard=2147483647i,rlimit_memory_locked_hard=65536i,rlimit_signals_pending_soft=1758i,write_count=11i,cpu_time_iowait=0,cpu_time_steal=0,cpu_time_stolen=0,rlimit_memory_stack_soft=8388608i,cpu_time_system=0.02,cpu_time_guest_nice=0,rlimit_memory_locked_soft=65536i,rlimit_memory_vms_soft=2147483647i,rlimit_file_locks_hard=2147483647i,rlimit_realtime_priority_hard=0i,pid=828i,num_threads=1i,cpu_time_soft_irq=0,rlimit_memory_vms_hard=2147483647i,rlimit_realtime_priority_soft=0i,memory_vms=15884288i,rlimit_memory_stack_hard=2147483647i,cpu_time_irq=0,rlimit_memory_data_soft=2147483647i,rlimit_num_fds_soft=1024i,signals_pending=0i,rlimit_nice_priority_soft=0i,realtime_priority=0i
procstat,exe=influxd,process_name=influxd rlimit_num_fds_hard=16384i,rlimit_signals_pending_hard=1758i,realtime_priority=0i,rlimit_memory_vms_hard=2147483647i,rlimit_signals_pending_soft=1758i,cpu_time_stolen=0,rlimit_memory_stack_hard=2147483647i,rlimit_realtime_priority_hard=0i,cpu_time=0i,pid=500i,voluntary_context_switches=975i,cpu_time_idle=0,memory_rss=3072000i,memory_locked=0i,rlimit_nice_priority_soft=0i,signals_pending=0i,nice_priority=20i,read_bytes=823296i,cpu_time_soft_irq=0,rlimit_memory_data_hard=2147483647i,rlimit_memory_locked_soft=65536i,write_count=8i,cpu_time_irq=0,memory_vms=33501184i,rlimit_memory_stack_soft=8388608i,cpu_time_iowait=0,rlimit_memory_vms_soft=2147483647i,rlimit_nice_priority_hard=0i,num_fds=29i,memory_data=229376i,rlimit_cpu_time_soft=2147483647i,rlimit_file_locks_soft=2147483647i,num_threads=1i,write_bytes=0i,cpu_time_steal=0,rlimit_memory_rss_hard=2147483647i,cpu_time_guest=0,cpu_time_guest_nice=0,cpu_usage=0,rlimit_memory_locked_hard=65536i,rlimit_file_locks_hard=2147483647i,involuntary_context_switches=38i,read_count=16851i,memory_swap=0i,rlimit_memory_data_soft=2147483647i,cpu_time_user=0.11,rlimit_cpu_time_hard=2147483647i,rlimit_num_fds_soft=16384i,rlimit_realtime_priority_soft=0i,cpu_time_system=0.27,cpu_time_nice=0,memory_stack=135168i,rlimit_memory_rss_soft=2147483647i
```
# Measurements
Note: prefix can be set by the user, per process.
Threads related measurement names:
- procstat_[prefix_]num_threads value=5
File descriptor related measurement names (*telegraf* needs to run as **root**):
- procstat_[prefix_]num_fds value=4
Priority related measurement names:
- procstat_[prefix_]realtime_priority value=0
- procstat_[prefix_]nice_priority value=20
Signals related measurement names:
- procstat_[prefix_]signals_pending value=0
Context switch related measurement names:
- procstat_[prefix_]voluntary_context_switches value=250
- procstat_[prefix_]involuntary_context_switches value=0
I/O related measurement names (*telegraf* needs to run as **root**):
- procstat_[prefix_]read_count value=396
- procstat_[prefix_]write_count value=1
- procstat_[prefix_]read_bytes value=1019904
- procstat_[prefix_]write_bytes value=1
CPU related measurement names:
- procstat_[prefix_]cpu_time value=0.01
- procstat_[prefix_]cpu_time_user value=0
- procstat_[prefix_]cpu_time_system value=0.01
- procstat_[prefix_]cpu_time_idle value=0
- procstat_[prefix_]cpu_time_nice value=0
- procstat_[prefix_]cpu_time_iowait value=0
- procstat_[prefix_]cpu_time_irq value=0
- procstat_[prefix_]cpu_time_soft_irq value=0
- procstat_[prefix_]cpu_time_steal value=0
- procstat_[prefix_]cpu_time_stolen value=0
- procstat_[prefix_]cpu_time_guest value=0
- procstat_[prefix_]cpu_time_guest_nice value=0
Memory related measurement names:
- procstat_[prefix_]memory_rss value=1777664
- procstat_[prefix_]memory_vms value=24227840
- procstat_[prefix_]memory_swap value=282624
- procstat_[prefix_]memory_data value=229376
- procstat_[prefix_]memory_stack value=135168
- procstat_[prefix_]memory_locked value=0
Resource limits:
- procstat_[prefix_]rlimit_cpu_time_hard value=2147483647
- procstat_[prefix_]rlimit_cpu_time_soft value=2147483647
- procstat_[prefix_]rlimit_file_locks_hard value=2147483647
- procstat_[prefix_]rlimit_file_locks_soft value=2147483647
- procstat_[prefix_]rlimit_memory_data_hard value=2147483647
- procstat_[prefix_]rlimit_memory_data_soft value=2147483647
- procstat_[prefix_]rlimit_memory_locked_hard value=65536
- procstat_[prefix_]rlimit_memory_locked_soft value=65536
- procstat_[prefix_]rlimit_memory_rss_hard value=2147483647
- procstat_[prefix_]rlimit_memory_rss_soft value=2147483647
- procstat_[prefix_]rlimit_memory_stack_hard value=2147483647
- procstat_[prefix_]rlimit_memory_stack_soft value=8388608
- procstat_[prefix_]rlimit_memory_vms_hard value=2147483647
- procstat_[prefix_]rlimit_memory_vms_soft value=2147483647
- procstat_[prefix_]rlimit_nice_priority_hard value=0
- procstat_[prefix_]rlimit_nice_priority_soft value=0
- procstat_[prefix_]rlimit_num_fds_hard value=16384
- procstat_[prefix_]rlimit_num_fds_soft value=16384
- procstat_[prefix_]rlimit_realtime_priority_hard value=0
- procstat_[prefix_]rlimit_realtime_priority_soft value=0
- procstat_[prefix_]rlimit_signals_pending_hard value=1758
- procstat_[prefix_]rlimit_signals_pending_soft value=1758
*NOTE: Due to a limitation in an underlying library Telegraf uses, any resource limit > 2147483647 will be misreported as 2147483647.*

View File

@@ -0,0 +1,57 @@
package procstat
import (
"fmt"
"io/ioutil"
"strconv"
"strings"
"github.com/shirou/gopsutil/process"
)
//NativeFinder uses gopsutil to find processes
type NativeFinder struct {
}
//NewNativeFinder ...
func NewNativeFinder() (PIDFinder, error) {
return &NativeFinder{}, nil
}
//Uid will return all pids for the given user
func (pg *NativeFinder) Uid(user string) ([]PID, error) {
var dst []PID
procs, err := process.Processes()
if err != nil {
return dst, err
}
for _, p := range procs {
username, err := p.Username()
if err != nil {
//skip, this can happen if we don't have permissions or
//the pid no longer exists
continue
}
if username == user {
dst = append(dst, PID(p.Pid))
}
}
return dst, nil
}
//PidFile returns the pid from the pid file given.
func (pg *NativeFinder) PidFile(path string) ([]PID, error) {
var pids []PID
pidString, err := ioutil.ReadFile(path)
if err != nil {
return pids, fmt.Errorf("Failed to read pidfile '%s'. Error: '%s'",
path, err)
}
pid, err := strconv.Atoi(strings.TrimSpace(string(pidString)))
if err != nil {
return pids, err
}
pids = append(pids, PID(pid))
return pids, nil
}

View File

@@ -0,0 +1,59 @@
// +build !windows
package procstat
import (
"regexp"
"github.com/shirou/gopsutil/process"
)
//Pattern matches on the process name
func (pg *NativeFinder) Pattern(pattern string) ([]PID, error) {
var pids []PID
regxPattern, err := regexp.Compile(pattern)
if err != nil {
return pids, err
}
procs, err := process.Processes()
if err != nil {
return pids, err
}
for _, p := range procs {
name, err := p.Exe()
if err != nil {
//skip, this can be caused by the pid no longer existing
//or you having no permissions to access it
continue
}
if regxPattern.MatchString(name) {
pids = append(pids, PID(p.Pid))
}
}
return pids, err
}
//FullPattern matches on the command line when the proccess was executed
func (pg *NativeFinder) FullPattern(pattern string) ([]PID, error) {
var pids []PID
regxPattern, err := regexp.Compile(pattern)
if err != nil {
return pids, err
}
procs, err := process.Processes()
if err != nil {
return pids, err
}
for _, p := range procs {
cmd, err := p.Cmdline()
if err != nil {
//skip, this can be caused by the pid no longer existing
//or you having no permissions to access it
continue
}
if regxPattern.MatchString(cmd) {
pids = append(pids, PID(p.Pid))
}
}
return pids, err
}

View File

@@ -0,0 +1,91 @@
package procstat
import (
"context"
"fmt"
"regexp"
"time"
"github.com/StackExchange/wmi"
"github.com/shirou/gopsutil/process"
)
//Timeout is the timeout used when making wmi calls
var Timeout = 5 * time.Second
type queryType string
const (
like = queryType("LIKE")
equals = queryType("=")
notEqual = queryType("!=")
)
//Pattern matches on the process name
func (pg *NativeFinder) Pattern(pattern string) ([]PID, error) {
var pids []PID
regxPattern, err := regexp.Compile(pattern)
if err != nil {
return pids, err
}
procs, err := process.Processes()
if err != nil {
return pids, err
}
for _, p := range procs {
name, err := p.Name()
if err != nil {
//skip, this can be caused by the pid no longer existing
//or you having no permissions to access it
continue
}
if regxPattern.MatchString(name) {
pids = append(pids, PID(p.Pid))
}
}
return pids, err
}
//FullPattern matches the cmdLine on windows and will find a pattern using a WMI like query
func (pg *NativeFinder) FullPattern(pattern string) ([]PID, error) {
var pids []PID
procs, err := getWin32ProcsByVariable("CommandLine", like, pattern, Timeout)
if err != nil {
return pids, err
}
for _, p := range procs {
pids = append(pids, PID(p.ProcessID))
}
return pids, nil
}
//GetWin32ProcsByVariable allows you to query any variable with a like query
func getWin32ProcsByVariable(variable string, qType queryType, value string, timeout time.Duration) ([]process.Win32_Process, error) {
var dst []process.Win32_Process
var query string
// should look like "WHERE CommandLine LIKE "procstat"
query = fmt.Sprintf("WHERE %s %s %q", variable, qType, value)
q := wmi.CreateQuery(&dst, query)
ctx, cancel := context.WithTimeout(context.Background(), timeout)
defer cancel()
err := WMIQueryWithContext(ctx, q, &dst)
if err != nil {
return []process.Win32_Process{}, fmt.Errorf("could not get win32Proc: %s", err)
}
return dst, nil
}
// WMIQueryWithContext - wraps wmi.Query with a timed-out context to avoid hanging
func WMIQueryWithContext(ctx context.Context, query string, dst interface{}, connectServerArgs ...interface{}) error {
errChan := make(chan error, 1)
go func() {
errChan <- wmi.Query(query, dst, connectServerArgs...)
}()
select {
case <-ctx.Done():
return ctx.Err()
case err := <-errChan:
return err
}
}

View File

@@ -0,0 +1,40 @@
package procstat
import (
"fmt"
"testing"
"os/user"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestGather_RealPattern(t *testing.T) {
pg, err := NewNativeFinder()
require.NoError(t, err)
pids, err := pg.Pattern(`procstat`)
require.NoError(t, err)
fmt.Println(pids)
assert.Equal(t, len(pids) > 0, true)
}
func TestGather_RealFullPattern(t *testing.T) {
pg, err := NewNativeFinder()
require.NoError(t, err)
pids, err := pg.FullPattern(`%procstat%`)
require.NoError(t, err)
fmt.Println(pids)
assert.Equal(t, len(pids) > 0, true)
}
func TestGather_RealUser(t *testing.T) {
user, err := user.Current()
require.NoError(t, err)
pg, err := NewNativeFinder()
require.NoError(t, err)
pids, err := pg.Uid(user.Username)
require.NoError(t, err)
fmt.Println(pids)
assert.Equal(t, len(pids) > 0, true)
}

View File

@@ -8,13 +8,6 @@ import (
"strings"
)
type PIDFinder interface {
PidFile(path string) ([]PID, error)
Pattern(pattern string) ([]PID, error)
Uid(user string) ([]PID, error)
FullPattern(path string) ([]PID, error)
}
// Implemention of PIDGatherer that execs pgrep to find processes
type Pgrep struct {
path string

View File

@@ -23,6 +23,13 @@ type Process interface {
RlimitUsage(bool) ([]process.RlimitStat, error)
}
type PIDFinder interface {
PidFile(path string) ([]PID, error)
Pattern(pattern string) ([]PID, error)
Uid(user string) ([]PID, error)
FullPattern(path string) ([]PID, error)
}
type Proc struct {
hasCPUTimes bool
tags map[string]string

View File

@@ -22,6 +22,7 @@ var (
type PID int32
type Procstat struct {
PidFinder string `toml:"pid_finder"`
PidFile string `toml:"pid_file"`
Exe string
Pattern string
@@ -32,14 +33,14 @@ type Procstat struct {
CGroup string `toml:"cgroup"`
PidTag bool
pidFinder PIDFinder
finder PIDFinder
createPIDFinder func() (PIDFinder, error)
procs map[PID]Process
createProcess func(PID) (Process, error)
}
var sampleConfig = `
## Must specify one of: pid_file, exe, or pattern
## PID file to monitor process
pid_file = "/var/run/nginx.pid"
## executable name (ie, pgrep <exe>)
@@ -56,12 +57,20 @@ var sampleConfig = `
## override for process_name
## This is optional; default is sourced from /proc/<pid>/status
# process_name = "bar"
## Field name prefix
prefix = ""
## comment this out if you want raw cpu_time stats
fielddrop = ["cpu_time_*"]
## This is optional; moves pid into a tag instead of a field
pid_tag = false
# prefix = ""
## Add PID as a tag instead of a field; useful to differentiate between
## processes whose tags are otherwise the same. Can create a large number
## of series, use judiciously.
# pid_tag = false
## Method to use when finding process IDs. Can be one of 'pgrep', or
## 'native'. The pgrep finder calls the pgrep executable in the PATH while
## the native finder performs the search directly in a manor dependent on the
## platform. Default is 'pgrep'
# pid_finder = "pgrep"
`
func (_ *Procstat) SampleConfig() string {
@@ -74,7 +83,15 @@ func (_ *Procstat) Description() string {
func (p *Procstat) Gather(acc telegraf.Accumulator) error {
if p.createPIDFinder == nil {
p.createPIDFinder = defaultPIDFinder
switch p.PidFinder {
case "native":
p.createPIDFinder = NewNativeFinder
case "pgrep":
p.createPIDFinder = NewPgrep
default:
p.createPIDFinder = defaultPIDFinder
}
}
if p.createProcess == nil {
p.createProcess = defaultProcess
@@ -252,14 +269,15 @@ func (p *Procstat) updateProcesses(prevInfo map[PID]Process) (map[PID]Process, e
// Create and return PIDGatherer lazily
func (p *Procstat) getPIDFinder() (PIDFinder, error) {
if p.pidFinder == nil {
if p.finder == nil {
f, err := p.createPIDFinder()
if err != nil {
return nil, err
}
p.pidFinder = f
p.finder = f
}
return p.pidFinder, nil
return p.finder, nil
}
// Get matching PIDs and their initial tags
@@ -292,7 +310,7 @@ func (p *Procstat) findPids() ([]PID, map[string]string, error) {
pids, err = p.cgroupPIDs()
tags = map[string]string{"cgroup": p.CGroup}
} else {
err = fmt.Errorf("Either exe, pid_file, user, or pattern has to be specified")
err = fmt.Errorf("Either exe, pid_file, user, pattern, systemd_unit, or cgroup must be specified")
}
return pids, tags, err

View File

@@ -6,6 +6,7 @@ import (
"os"
"os/exec"
"path/filepath"
"runtime"
"strings"
"testing"
"time"
@@ -349,6 +350,10 @@ func TestGather_systemdUnitPIDs(t *testing.T) {
}
func TestGather_cgroupPIDs(t *testing.T) {
//no cgroups in windows
if runtime.GOOS == "windows" {
t.Skip("no cgroups in windows")
}
td, err := ioutil.TempDir("", "")
require.NoError(t, err)
defer os.RemoveAll(td)

View File

@@ -67,7 +67,7 @@ Measurement names are based on the Metric Family and tags are created for each
label. The value is added to a field named based on the metric type.
All metrics receive the `url` tag indicating the related URL specified in the
Telegraf configuration. If using Kubernetes service discovery the `address`
Telegraf configuration. If using Kubernetes service discovery the `address`
tag is also added indicating the discovered ip address.
### Example Output:

View File

@@ -20,7 +20,7 @@ const acceptHeader = `application/vnd.google.protobuf;proto=io.prometheus.client
type Prometheus struct {
// An array of urls to scrape metrics from.
Urls []string
URLs []string `toml:"urls"`
// An array of Kubernetes services to scrape metrics from.
KubernetesServices []string
@@ -73,12 +73,12 @@ func (p *Prometheus) Description() string {
var ErrProtocolError = errors.New("prometheus protocol error")
func (p *Prometheus) AddressToURL(u *url.URL, address string) string {
func (p *Prometheus) AddressToURL(u *url.URL, address string) *url.URL {
host := address
if u.Port() != "" {
host = address + ":" + u.Port()
}
reconstructedUrl := url.URL{
reconstructedURL := &url.URL{
Scheme: u.Scheme,
Opaque: u.Opaque,
User: u.User,
@@ -89,36 +89,42 @@ func (p *Prometheus) AddressToURL(u *url.URL, address string) string {
Fragment: u.Fragment,
Host: host,
}
return reconstructedUrl.String()
return reconstructedURL
}
type UrlAndAddress struct {
OriginalUrl string
Url string
type URLAndAddress struct {
OriginalURL *url.URL
URL *url.URL
Address string
}
func (p *Prometheus) GetAllURLs() ([]UrlAndAddress, error) {
allUrls := make([]UrlAndAddress, 0)
for _, url := range p.Urls {
allUrls = append(allUrls, UrlAndAddress{Url: url, OriginalUrl: url})
func (p *Prometheus) GetAllURLs() ([]URLAndAddress, error) {
allURLs := make([]URLAndAddress, 0)
for _, u := range p.URLs {
URL, err := url.Parse(u)
if err != nil {
log.Printf("prometheus: Could not parse %s, skipping it. Error: %s", u, err)
continue
}
allURLs = append(allURLs, URLAndAddress{URL: URL, OriginalURL: URL})
}
for _, service := range p.KubernetesServices {
u, err := url.Parse(service)
URL, err := url.Parse(service)
if err != nil {
return nil, err
}
resolvedAddresses, err := net.LookupHost(u.Hostname())
resolvedAddresses, err := net.LookupHost(URL.Hostname())
if err != nil {
log.Printf("prometheus: Could not resolve %s, skipping it. Error: %s", u.Host, err)
log.Printf("prometheus: Could not resolve %s, skipping it. Error: %s", URL.Host, err)
continue
}
for _, resolved := range resolvedAddresses {
serviceUrl := p.AddressToURL(u, resolved)
allUrls = append(allUrls, UrlAndAddress{Url: serviceUrl, Address: resolved, OriginalUrl: service})
serviceURL := p.AddressToURL(URL, resolved)
allURLs = append(allURLs, URLAndAddress{URL: serviceURL, Address: resolved, OriginalURL: URL})
}
}
return allUrls, nil
return allURLs, nil
}
// Reads stats from all configured servers accumulates stats.
@@ -134,16 +140,16 @@ func (p *Prometheus) Gather(acc telegraf.Accumulator) error {
var wg sync.WaitGroup
allUrls, err := p.GetAllURLs()
allURLs, err := p.GetAllURLs()
if err != nil {
return err
}
for _, url := range allUrls {
for _, URL := range allURLs {
wg.Add(1)
go func(serviceUrl UrlAndAddress) {
go func(serviceURL URLAndAddress) {
defer wg.Done()
acc.AddError(p.gatherURL(serviceUrl, acc))
}(url)
acc.AddError(p.gatherURL(serviceURL, acc))
}(URL)
}
wg.Wait()
@@ -178,8 +184,8 @@ func (p *Prometheus) createHttpClient() (*http.Client, error) {
return client, nil
}
func (p *Prometheus) gatherURL(url UrlAndAddress, acc telegraf.Accumulator) error {
var req, err = http.NewRequest("GET", url.Url, nil)
func (p *Prometheus) gatherURL(u URLAndAddress, acc telegraf.Accumulator) error {
var req, err = http.NewRequest("GET", u.URL.String(), nil)
req.Header.Add("Accept", acceptHeader)
var token []byte
var resp *http.Response
@@ -194,11 +200,11 @@ func (p *Prometheus) gatherURL(url UrlAndAddress, acc telegraf.Accumulator) erro
resp, err = p.client.Do(req)
if err != nil {
return fmt.Errorf("error making HTTP request to %s: %s", url.Url, err)
return fmt.Errorf("error making HTTP request to %s: %s", u.URL, err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
return fmt.Errorf("%s returned HTTP status %s", url.Url, resp.Status)
return fmt.Errorf("%s returned HTTP status %s", u.URL, resp.Status)
}
body, err := ioutil.ReadAll(resp.Body)
@@ -209,14 +215,16 @@ func (p *Prometheus) gatherURL(url UrlAndAddress, acc telegraf.Accumulator) erro
metrics, err := Parse(body, resp.Header)
if err != nil {
return fmt.Errorf("error reading metrics for %s: %s",
url.Url, err)
u.URL, err)
}
// Add (or not) collected metrics
for _, metric := range metrics {
tags := metric.Tags()
tags["url"] = url.OriginalUrl
if url.Address != "" {
tags["address"] = url.Address
// strip user and password from URL
u.OriginalURL.User = nil
tags["url"] = u.OriginalURL.String()
if u.Address != "" {
tags["address"] = u.Address
}
switch metric.Type() {

View File

@@ -37,7 +37,7 @@ func TestPrometheusGeneratesMetrics(t *testing.T) {
defer ts.Close()
p := &Prometheus{
Urls: []string{ts.URL},
URLs: []string{ts.URL},
}
var acc testutil.Accumulator
@@ -89,7 +89,7 @@ func TestPrometheusGeneratesMetricsAlthoughFirstDNSFails(t *testing.T) {
defer ts.Close()
p := &Prometheus{
Urls: []string{ts.URL},
URLs: []string{ts.URL},
KubernetesServices: []string{"http://random.telegraf.local:88/metrics"},
}

View File

@@ -40,6 +40,15 @@ For additional details reference the [RabbitMQ Management HTTP Stats](https://cd
## A list of queues to gather as the rabbitmq_queue measurement. If not
## specified, metrics for all queues are gathered.
# queues = ["telegraf"]
## A list of exchanges to gather as the rabbitmq_exchange measurement. If not
## specified, metrics for all exchanges are gathered.
# exchanges = ["telegraf"]
## Queues to include and exclude. Globs accepted.
## Note that an empty array for both will include all queues
# queue_name_include = []
# queue_name_exclude = []
```
### Measurements & Fields:
@@ -52,10 +61,13 @@ For additional details reference the [RabbitMQ Management HTTP Stats](https://cd
- messages (int, messages)
- messages_acked (int, messages)
- messages_delivered (int, messages)
- messages_delivered_get (int, messages)
- messages_published (int, messages)
- messages_ready (int, messages)
- messages_unacked (int, messages)
- queues (int, queues)
- clustering_listeners (int, cluster nodes)
- amqp_listeners (int, amqp nodes up)
- rabbitmq_node
- disk_free (int, bytes)
@@ -69,6 +81,7 @@ For additional details reference the [RabbitMQ Management HTTP Stats](https://cd
- run_queue (int, erlang processes)
- sockets_total (int, sockets)
- sockets_used (int, sockets)
- running (int, node up)
- rabbitmq_queue
- consumer_utilisation (float, percent)
@@ -94,6 +107,10 @@ For additional details reference the [RabbitMQ Management HTTP Stats](https://cd
- messages_redeliver_rate (float, messages per second)
- messages_unack (integer, count)
- rabbitmq_exchange
- messages_publish_in (int, count)
- messages_publish_out (int, count)
### Tags:
- All measurements have the following tags:
@@ -113,13 +130,29 @@ For additional details reference the [RabbitMQ Management HTTP Stats](https://cd
- durable
- auto_delete
- rabbitmq_exchange
- url
- exchange
- type
- vhost
- internal
- durable
- auto_delete
### Sample Queries:
Message rates for the entire node can be calculated from total message counts. For instance, to get the rate of messages published per minute, use this query:
```
SELECT NON_NEGATIVE_DERIVATIVE(LAST("messages_published"), 1m) AS messages_published_rate
FROM rabbitmq_overview WHERE time > now() - 10m GROUP BY time(1m)
```
### Example Output:
```
rabbitmq_queue,url=http://amqp.example.org:15672,queue=telegraf,vhost=influxdb,node=rabbit@amqp.example.org,durable=true,auto_delete=false,host=amqp.example.org messages_deliver_get=0i,messages_publish=329i,messages_publish_rate=0.2,messages_redeliver_rate=0,message_bytes_ready=0i,message_bytes_unacked=0i,messages_deliver=329i,messages_unack=0i,consumers=1i,idle_since="",messages=0i,messages_deliver_rate=0.2,messages_deliver_get_rate=0.2,messages_redeliver=0i,memory=43032i,message_bytes_ram=0i,messages_ack=329i,messages_ready=0i,messages_ack_rate=0.2,consumer_utilisation=1,message_bytes=0i,message_bytes_persist=0i 1493684035000000000
rabbitmq_overview,url=http://amqp.example.org:15672,host=amqp.example.org channels=2i,consumers=1i,exchanges=17i,messages_acked=329i,messages=0i,messages_ready=0i,messages_unacked=0i,connections=2i,queues=1i,messages_delivered=329i,messages_published=329i 1493684035000000000
rabbitmq_node,url=http://amqp.example.org:15672,node=rabbit@amqp.example.org,host=amqp.example.org fd_total=1024i,fd_used=32i,mem_limit=8363329126i,sockets_total=829i,disk_free=8175935488i,disk_free_limit=50000000i,mem_used=58771080i,proc_total=1048576i,proc_used=267i,run_queue=0i,sockets_used=2i 149368403500000000
rabbitmq_overview,url=http://amqp.example.org:15672,host=amqp.example.org channels=2i,consumers=1i,exchanges=17i,messages_acked=329i,messages=0i,messages_ready=0i,messages_unacked=0i,connections=2i,queues=1i,messages_delivered=329i,messages_published=329i,clustering_listeners=2i,amqp_listeners=1i 1493684035000000000
rabbitmq_node,url=http://amqp.example.org:15672,node=rabbit@amqp.example.org,host=amqp.example.org fd_total=1024i,fd_used=32i,mem_limit=8363329126i,sockets_total=829i,disk_free=8175935488i,disk_free_limit=50000000i,mem_used=58771080i,proc_total=1048576i,proc_used=267i,run_queue=0i,sockets_used=2i,running=1i 149368403500000000
rabbitmq_exchange,url=http://amqp.example.org:15672,exchange=telegraf,type=fanout,vhost=influxdb,internal=false,durable=true,auto_delete=false,host=amqp.example.org messages_publish_in=2i,messages_publish_out=1i 149368403500000000
```

View File

@@ -9,6 +9,7 @@ import (
"time"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/filter"
"github.com/influxdata/telegraf/internal"
"github.com/influxdata/telegraf/plugins/inputs"
)
@@ -48,10 +49,18 @@ type RabbitMQ struct {
ResponseHeaderTimeout internal.Duration `toml:"header_timeout"`
ClientTimeout internal.Duration `toml:"client_timeout"`
Nodes []string
Queues []string
Nodes []string
Queues []string
Exchanges []string
QueueInclude []string `toml:"queue_name_include"`
QueueExclude []string `toml:"queue_name_exclude"`
Client *http.Client
filterCreated bool
excludeEveryQueue bool
queueFilter filter.Filter
}
// OverviewResponse ...
@@ -59,6 +68,12 @@ type OverviewResponse struct {
MessageStats *MessageStats `json:"message_stats"`
ObjectTotals *ObjectTotals `json:"object_totals"`
QueueTotals *QueueTotals `json:"queue_totals"`
Listeners []Listeners `json:"listeners"`
}
// Listeners ...
type Listeners struct {
Protocol string `json:"protocol"`
}
// Details ...
@@ -72,12 +87,14 @@ type MessageStats struct {
AckDetails Details `json:"ack_details"`
Deliver int64
DeliverDetails Details `json:"deliver_details"`
DeliverGet int64
DeliverGet int64 `json:"deliver_get"`
DeliverGetDetails Details `json:"deliver_get_details"`
Publish int64
PublishDetails Details `json:"publish_details"`
Redeliver int64
RedeliverDetails Details `json:"redeliver_details"`
PublishIn int64 `json:"publish_in"`
PublishOut int64 `json:"publish_out"`
}
// ObjectTotals ...
@@ -131,12 +148,23 @@ type Node struct {
RunQueue int64 `json:"run_queue"`
SocketsTotal int64 `json:"sockets_total"`
SocketsUsed int64 `json:"sockets_used"`
Running bool `json:"running"`
}
type Exchange struct {
Name string
MessageStats `json:"message_stats"`
Type string
Internal bool
Vhost string
Durable bool
AutoDelete bool `json:"auto_delete"`
}
// gatherFunc ...
type gatherFunc func(r *RabbitMQ, acc telegraf.Accumulator)
var gatherFunctions = []gatherFunc{gatherOverview, gatherNodes, gatherQueues}
var gatherFunctions = []gatherFunc{gatherOverview, gatherNodes, gatherQueues, gatherExchanges}
var sampleConfig = `
## Management Plugin url. (default: http://localhost:15672)
@@ -171,6 +199,15 @@ var sampleConfig = `
## A list of queues to gather as the rabbitmq_queue measurement. If not
## specified, metrics for all queues are gathered.
# queues = ["telegraf"]
## A list of exchanges to gather as the rabbitmq_exchange measurement. If not
## specified, metrics for all exchanges are gathered.
# exchanges = ["telegraf"]
## Queues to include and exclude. Globs accepted.
## Note that an empty array for both will include all queues
queue_name_include = []
queue_name_exclude = []
`
// SampleConfig ...
@@ -201,6 +238,15 @@ func (r *RabbitMQ) Gather(acc telegraf.Accumulator) error {
}
}
// Create queue filter if not already created
if !r.filterCreated {
err := r.createQueueFilter()
if err != nil {
return err
}
r.filterCreated = true
}
var wg sync.WaitGroup
wg.Add(len(gatherFunctions))
for _, f := range gatherFunctions {
@@ -258,27 +304,39 @@ func gatherOverview(r *RabbitMQ, acc telegraf.Accumulator) {
return
}
if overview.QueueTotals == nil || overview.ObjectTotals == nil || overview.MessageStats == nil {
if overview.QueueTotals == nil || overview.ObjectTotals == nil || overview.MessageStats == nil || overview.Listeners == nil {
acc.AddError(fmt.Errorf("Wrong answer from rabbitmq. Probably auth issue"))
return
}
var clustering_listeners, amqp_listeners int64 = 0, 0
for _, listener := range overview.Listeners {
if listener.Protocol == "clustering" {
clustering_listeners++
} else if listener.Protocol == "amqp" {
amqp_listeners++
}
}
tags := map[string]string{"url": r.URL}
if r.Name != "" {
tags["name"] = r.Name
}
fields := map[string]interface{}{
"messages": overview.QueueTotals.Messages,
"messages_ready": overview.QueueTotals.MessagesReady,
"messages_unacked": overview.QueueTotals.MessagesUnacknowledged,
"channels": overview.ObjectTotals.Channels,
"connections": overview.ObjectTotals.Connections,
"consumers": overview.ObjectTotals.Consumers,
"exchanges": overview.ObjectTotals.Exchanges,
"queues": overview.ObjectTotals.Queues,
"messages_acked": overview.MessageStats.Ack,
"messages_delivered": overview.MessageStats.Deliver,
"messages_published": overview.MessageStats.Publish,
"messages": overview.QueueTotals.Messages,
"messages_ready": overview.QueueTotals.MessagesReady,
"messages_unacked": overview.QueueTotals.MessagesUnacknowledged,
"channels": overview.ObjectTotals.Channels,
"connections": overview.ObjectTotals.Connections,
"consumers": overview.ObjectTotals.Consumers,
"exchanges": overview.ObjectTotals.Exchanges,
"queues": overview.ObjectTotals.Queues,
"messages_acked": overview.MessageStats.Ack,
"messages_delivered": overview.MessageStats.Deliver,
"messages_delivered_get": overview.MessageStats.DeliverGet,
"messages_published": overview.MessageStats.Publish,
"clustering_listeners": clustering_listeners,
"amqp_listeners": amqp_listeners,
}
acc.AddFields("rabbitmq_overview", fields, tags)
}
@@ -301,6 +359,11 @@ func gatherNodes(r *RabbitMQ, acc telegraf.Accumulator) {
tags := map[string]string{"url": r.URL}
tags["node"] = node.Name
var running int64 = 0
if node.Running {
running = 1
}
fields := map[string]interface{}{
"disk_free": node.DiskFree,
"disk_free_limit": node.DiskFreeLimit,
@@ -313,12 +376,16 @@ func gatherNodes(r *RabbitMQ, acc telegraf.Accumulator) {
"run_queue": node.RunQueue,
"sockets_total": node.SocketsTotal,
"sockets_used": node.SocketsUsed,
"running": running,
}
acc.AddFields("rabbitmq_node", fields, tags, now)
}
}
func gatherQueues(r *RabbitMQ, acc telegraf.Accumulator) {
if r.excludeEveryQueue {
return
}
// Gather information about queues
queues := make([]Queue, 0)
err := r.requestJSON("/api/queues", &queues)
@@ -328,7 +395,7 @@ func gatherQueues(r *RabbitMQ, acc telegraf.Accumulator) {
}
for _, queue := range queues {
if !r.shouldGatherQueue(queue) {
if !r.queueFilter.Match(queue.Name) {
continue
}
tags := map[string]string{
@@ -373,6 +440,40 @@ func gatherQueues(r *RabbitMQ, acc telegraf.Accumulator) {
}
}
func gatherExchanges(r *RabbitMQ, acc telegraf.Accumulator) {
// Gather information about exchanges
exchanges := make([]Exchange, 0)
err := r.requestJSON("/api/exchanges", &exchanges)
if err != nil {
acc.AddError(err)
return
}
for _, exchange := range exchanges {
if !r.shouldGatherExchange(exchange) {
continue
}
tags := map[string]string{
"url": r.URL,
"exchange": exchange.Name,
"type": exchange.Type,
"vhost": exchange.Vhost,
"internal": strconv.FormatBool(exchange.Internal),
"durable": strconv.FormatBool(exchange.Durable),
"auto_delete": strconv.FormatBool(exchange.AutoDelete),
}
acc.AddFields(
"rabbitmq_exchange",
map[string]interface{}{
"messages_publish_in": exchange.MessageStats.PublishIn,
"messages_publish_out": exchange.MessageStats.PublishOut,
},
tags,
)
}
}
func (r *RabbitMQ) shouldGatherNode(node Node) bool {
if len(r.Nodes) == 0 {
return true
@@ -387,13 +488,34 @@ func (r *RabbitMQ) shouldGatherNode(node Node) bool {
return false
}
func (r *RabbitMQ) shouldGatherQueue(queue Queue) bool {
if len(r.Queues) == 0 {
func (r *RabbitMQ) createQueueFilter() error {
// Backwards compatibility for deprecated `queues` parameter.
if len(r.Queues) > 0 {
r.QueueInclude = append(r.QueueInclude, r.Queues...)
}
filter, err := filter.NewIncludeExcludeFilter(r.QueueInclude, r.QueueExclude)
if err != nil {
return err
}
r.queueFilter = filter
for _, q := range r.QueueExclude {
if q == "*" {
r.excludeEveryQueue = true
}
}
return nil
}
func (r *RabbitMQ) shouldGatherExchange(exchange Exchange) bool {
if len(r.Exchanges) == 0 {
return true
}
for _, name := range r.Queues {
if name == queue.Name {
for _, name := range r.Exchanges {
if name == exchange.Name {
return true
}
}

View File

@@ -51,7 +51,25 @@ const sampleOverviewResponse = `
"messages_unacknowledged_details": {
"rate": 0.0
}
}
},
"listeners": [
{
"name": "rabbit@node-a",
"protocol": "amqp"
},
{
"name": "rabbit@node-b",
"protocol": "amqp"
},
{
"name": "rabbit@node-a",
"protocol": "clustering"
},
{
"name": "rabbit@node-b",
"protocol": "clustering"
}
]
}
`
@@ -374,6 +392,102 @@ const sampleQueuesResponse = `
]
`
const sampleExchangesResponse = `
[
{
"arguments": { },
"internal": false,
"auto_delete": false,
"durable": true,
"type": "direct",
"vhost": "\/",
"name": ""
},
{
"message_stats": {
"publish_in_details": {
"rate": 0
},
"publish_in": 2,
"publish_out_details": {
"rate": 0
},
"publish_out": 1
},
"arguments": { },
"internal": false,
"auto_delete": false,
"durable": true,
"type": "fanout",
"vhost": "\/",
"name": "telegraf"
},
{
"arguments": { },
"internal": false,
"auto_delete": false,
"durable": true,
"type": "direct",
"vhost": "\/",
"name": "amq.direct"
},
{
"arguments": { },
"internal": false,
"auto_delete": false,
"durable": true,
"type": "fanout",
"vhost": "\/",
"name": "amq.fanout"
},
{
"arguments": { },
"internal": false,
"auto_delete": false,
"durable": true,
"type": "headers",
"vhost": "\/",
"name": "amq.headers"
},
{
"arguments": { },
"internal": false,
"auto_delete": false,
"durable": true,
"type": "headers",
"vhost": "\/",
"name": "amq.match"
},
{
"arguments": { },
"internal": true,
"auto_delete": false,
"durable": true,
"type": "topic",
"vhost": "\/",
"name": "amq.rabbitmq.log"
},
{
"arguments": { },
"internal": true,
"auto_delete": false,
"durable": true,
"type": "topic",
"vhost": "\/",
"name": "amq.rabbitmq.trace"
},
{
"arguments": { },
"internal": false,
"auto_delete": false,
"durable": true,
"type": "topic",
"vhost": "\/",
"name": "amq.topic"
}
]
`
func TestRabbitMQGeneratesMetrics(t *testing.T) {
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
var rsp string
@@ -385,6 +499,8 @@ func TestRabbitMQGeneratesMetrics(t *testing.T) {
rsp = sampleNodesResponse
case "/api/queues":
rsp = sampleQueuesResponse
case "/api/exchanges":
rsp = sampleExchangesResponse
default:
panic("Cannot handle request")
}
@@ -416,6 +532,8 @@ func TestRabbitMQGeneratesMetrics(t *testing.T) {
"consumers",
"exchanges",
"queues",
"clustering_listeners",
"amqp_listeners",
}
for _, metric := range intMetrics {
@@ -434,6 +552,7 @@ func TestRabbitMQGeneratesMetrics(t *testing.T) {
"run_queue",
"sockets_total",
"sockets_used",
"running",
}
for _, metric := range nodeIntMetrics {
@@ -441,4 +560,13 @@ func TestRabbitMQGeneratesMetrics(t *testing.T) {
}
assert.True(t, acc.HasMeasurement("rabbitmq_queue"))
exchangeIntMetrics := []string{
"messages_publish_in",
"messages_publish_out",
}
for _, metric := range exchangeIntMetrics {
assert.True(t, acc.HasInt64Field("rabbitmq_exchange", metric))
}
}

View File

@@ -87,7 +87,10 @@ Additionally the plugin also calculates the hit/miss ratio (keyspace\_hitrate) a
**Replication**
- connected_slaves(int, number)
- master_link_down_since_seconds(int, number)
- master_link_status(string)
- master_repl_offset(int, number)
- second_repl_offset(int, number)
- repl_backlog_active(int, number)
- repl_backlog_size(int, bytes)
- repl_backlog_first_byte_offset(int, number)

View File

@@ -2,21 +2,47 @@ package redis
import (
"bufio"
"errors"
"fmt"
"net"
"io"
"log"
"net/url"
"strconv"
"strings"
"sync"
"time"
"github.com/go-redis/redis"
"github.com/influxdata/telegraf"
"github.com/influxdata/telegraf/plugins/inputs"
)
type Redis struct {
Servers []string
clients []Client
initialized bool
}
type Client interface {
Info() *redis.StringCmd
BaseTags() map[string]string
}
type RedisClient struct {
client *redis.Client
tags map[string]string
}
func (r *RedisClient) Info() *redis.StringCmd {
return r.client.Info()
}
func (r *RedisClient) BaseTags() map[string]string {
tags := make(map[string]string)
for k, v := range r.tags {
tags[k] = v
}
return tags
}
var sampleConfig = `
@@ -32,8 +58,6 @@ var sampleConfig = `
servers = ["tcp://localhost:6379"]
`
var defaultTimeout = 5 * time.Second
func (r *Redis) SampleConfig() string {
return sampleConfig
}
@@ -48,111 +72,107 @@ var Tracking = map[string]string{
"role": "replication_role",
}
var ErrProtocolError = errors.New("redis protocol error")
const defaultPort = "6379"
// Reads stats from all configured servers accumulates stats.
// Returns one of the errors encountered while gather stats (if any).
func (r *Redis) Gather(acc telegraf.Accumulator) error {
if len(r.Servers) == 0 {
url := &url.URL{
Scheme: "tcp",
Host: ":6379",
}
r.gatherServer(url, acc)
func (r *Redis) init(acc telegraf.Accumulator) error {
if r.initialized {
return nil
}
var wg sync.WaitGroup
for _, serv := range r.Servers {
if len(r.Servers) == 0 {
r.Servers = []string{"tcp://localhost:6379"}
}
r.clients = make([]Client, len(r.Servers))
for i, serv := range r.Servers {
if !strings.HasPrefix(serv, "tcp://") && !strings.HasPrefix(serv, "unix://") {
log.Printf("W! [inputs.redis]: server URL found without scheme; please update your configuration file")
serv = "tcp://" + serv
}
u, err := url.Parse(serv)
if err != nil {
acc.AddError(fmt.Errorf("Unable to parse to address '%s': %s", serv, err))
continue
} else if u.Scheme == "" {
// fallback to simple string based address (i.e. "10.0.0.1:10000")
u.Scheme = "tcp"
u.Host = serv
u.Path = ""
return fmt.Errorf("Unable to parse to address %q: %v", serv, err)
}
if u.Scheme == "tcp" {
_, _, err := net.SplitHostPort(u.Host)
if err != nil {
u.Host = u.Host + ":" + defaultPort
password := ""
if u.User != nil {
pw, ok := u.User.Password()
if ok {
password = pw
}
}
var address string
if u.Scheme == "unix" {
address = u.Path
} else {
address = u.Host
}
client := redis.NewClient(
&redis.Options{
Addr: address,
Password: password,
Network: u.Scheme,
PoolSize: 1,
},
)
tags := map[string]string{}
if u.Scheme == "unix" {
tags["socket"] = u.Path
} else {
tags["server"] = u.Hostname()
tags["port"] = u.Port()
}
r.clients[i] = &RedisClient{
client: client,
tags: tags,
}
}
r.initialized = true
return nil
}
// Reads stats from all configured servers accumulates stats.
// Returns one of the errors encountered while gather stats (if any).
func (r *Redis) Gather(acc telegraf.Accumulator) error {
if !r.initialized {
err := r.init(acc)
if err != nil {
return err
}
}
var wg sync.WaitGroup
for _, client := range r.clients {
wg.Add(1)
go func(serv string) {
go func(client Client) {
defer wg.Done()
acc.AddError(r.gatherServer(u, acc))
}(serv)
acc.AddError(r.gatherServer(client, acc))
}(client)
}
wg.Wait()
return nil
}
func (r *Redis) gatherServer(addr *url.URL, acc telegraf.Accumulator) error {
var address string
if addr.Scheme == "unix" {
address = addr.Path
} else {
address = addr.Host
}
c, err := net.DialTimeout(addr.Scheme, address, defaultTimeout)
func (r *Redis) gatherServer(client Client, acc telegraf.Accumulator) error {
info, err := client.Info().Result()
if err != nil {
return fmt.Errorf("Unable to connect to redis server '%s': %s", address, err)
}
defer c.Close()
// Extend connection
c.SetDeadline(time.Now().Add(defaultTimeout))
if addr.User != nil {
pwd, set := addr.User.Password()
if set && pwd != "" {
c.Write([]byte(fmt.Sprintf("AUTH %s\r\n", pwd)))
rdr := bufio.NewReader(c)
line, err := rdr.ReadString('\n')
if err != nil {
return err
}
if line[0] != '+' {
return fmt.Errorf("%s", strings.TrimSpace(line)[1:])
}
}
return err
}
c.Write([]byte("INFO\r\n"))
c.Write([]byte("EOF\r\n"))
rdr := bufio.NewReader(c)
var tags map[string]string
if addr.Scheme == "unix" {
tags = map[string]string{"socket": addr.Path}
} else {
// Setup tags for all redis metrics
host, port := "unknown", "unknown"
// If there's an error, ignore and use 'unknown' tags
host, port, _ = net.SplitHostPort(addr.Host)
tags = map[string]string{"server": host, "port": port}
}
return gatherInfoOutput(rdr, acc, tags)
rdr := strings.NewReader(info)
return gatherInfoOutput(rdr, acc, client.BaseTags())
}
// gatherInfoOutput gathers
func gatherInfoOutput(
rdr *bufio.Reader,
rdr io.Reader,
acc telegraf.Accumulator,
tags map[string]string,
) error {
@@ -163,13 +183,11 @@ func gatherInfoOutput(
fields := make(map[string]interface{})
for scanner.Scan() {
line := scanner.Text()
if strings.Contains(line, "ERR") {
break
}
if len(line) == 0 {
continue
}
if line[0] == '#' {
if len(line) > 2 {
section = line[2:]
@@ -189,6 +207,10 @@ func gatherInfoOutput(
}
}
if strings.HasPrefix(name, "master_replid") {
continue
}
if name == "mem_allocator" {
continue
}

View File

@@ -86,6 +86,7 @@ func TestRedis_ParseMetrics(t *testing.T) {
"repl_backlog_size": int64(1048576),
"repl_backlog_first_byte_offset": int64(0),
"repl_backlog_histlen": int64(0),
"second_repl_offset": int64(-1),
"used_cpu_sys": float64(0.14),
"used_cpu_user": float64(0.05),
"used_cpu_sys_children": float64(0.00),
@@ -189,7 +190,10 @@ latest_fork_usec:0
# Replication
role:master
connected_slaves:0
master_replid:8c4d7b768b26826825ceb20ff4a2c7c54616350b
master_replid2:0000000000000000000000000000000000000000
master_repl_offset:0
second_repl_offset:-1
repl_backlog_active:0
repl_backlog_size:1048576
repl_backlog_first_byte_offset:0

View File

@@ -1,4 +1,4 @@
# Telegraf S.M.A.R.T. plugin
# S.M.A.R.T. Input Plugin
Get metrics using the command line utility `smartctl` for S.M.A.R.T. (Self-Monitoring, Analysis and Reporting Technology) storage devices. SMART is a monitoring system included in computer hard disk drives (HDDs) and solid-state drives (SSDs)[1] that detects and reports on various indicators of drive reliability, with the intent of enabling the anticipation of hardware failures.
See smartmontools (https://www.smartmontools.org/).
@@ -24,68 +24,7 @@ To enable SMART on a storage device run:
smartctl -s on <device>
```
## Measurements
- smart_device:
* Tags:
- `capacity`
- `device`
- `device_model`
- `enabled`
- `health`
- `serial_no`
- `wwn`
* Fields:
- `exit_status`
- `health_ok`
- `read_error_rate`
- `seek_error`
- `temp_c`
- `udma_crc_errors`
- smart_attribute:
* Tags:
- `device`
- `fail`
- `flags`
- `id`
- `name`
- `serial_no`
- `wwn`
* Fields:
- `exit_status`
- `raw_value`
- `threshold`
- `value`
- `worst`
### Flags
The interpretation of the tag `flags` is:
- *K* auto-keep
- *C* event count
- *R* error rate
- *S* speed/performance
- *O* updated online
- *P* prefailure warning
### Exit Status
The `exit_status` field captures the exit status of the smartctl command which
is defined by a bitmask. For the interpretation of the bitmask see the man page for
smartctl.
### Device Names
Device names, e.g., `/dev/sda`, are *not persistent*, and may be
subject to change across reboots or system changes. Instead, you can the
*World Wide Name* (WWN) or serial number to identify devices. On Linux block
devices can be referenced by the WWN in the following location:
`/dev/disk/by-id/`.
## Configuration
### Configuration:
```toml
# Read metrics from storage devices supporting S.M.A.R.T.
@@ -122,14 +61,72 @@ devices can be referenced by the WWN in the following location:
# devices = [ "/dev/ada0 -d atacam" ]
```
### Metrics:
- smart_device:
- tags:
- capacity
- device
- device_model
- enabled
- health
- serial_no
- wwn
- fields:
- exit_status
- health_ok
- read_error_rate
- seek_error
- temp_c
- udma_crc_errors
- smart_attribute:
- tags:
- device
- fail
- flags
- id
- name
- serial_no
- wwn
- fields:
- exit_status
- raw_value
- threshold
- value
- worst
#### Flags
The interpretation of the tag `flags` is:
- `K` auto-keep
- `C` event count
- `R` error rate
- `S` speed/performance
- `O` updated online
- `P` prefailure warning
#### Exit Status
The `exit_status` field captures the exit status of the smartctl command which
is defined by a bitmask. For the interpretation of the bitmask see the man page for
smartctl.
#### Device Names
Device names, e.g., `/dev/sda`, are *not persistent*, and may be
subject to change across reboots or system changes. Instead, you can the
*World Wide Name* (WWN) or serial number to identify devices. On Linux block
devices can be referenced by the WWN in the following location:
`/dev/disk/by-id/`.
To run `smartctl` with `sudo` create a wrapper script and use `path` in
the configuration to execute that.
## Output
### Output
Example output from an _Apple SSD_:
```
> smart_attribute,serial_no=S1K5NYCD964433,wwn=5002538655584d30,id=199,name=UDMA_CRC_Error_Count,flags=-O-RC-,fail=-,host=mbpro.local,device=/dev/rdisk0 threshold=0i,raw_value=0i,exit_status=0i,value=200i,worst=200i 1502536854000000000
> smart_attribute,device=/dev/rdisk0,serial_no=S1K5NYCD964433,wwn=5002538655584d30,id=240,name=Unknown_SSD_Attribute,flags=-O---K,fail=-,host=mbpro.local exit_status=0i,value=100i,worst=100i,threshold=0i,raw_value=0i 1502536854000000000
> smart_device,enabled=Enabled,host=mbpro.local,device=/dev/rdisk0,model=APPLE\ SSD\ SM0512F,serial_no=S1K5NYCD964433,wwn=5002538655584d30,capacity=500277790720 udma_crc_errors=0i,exit_status=0i,health_ok=true,read_error_rate=0i,temp_c=40i 1502536854000000000
smart_device,enabled=Enabled,host=mbpro.local,device=rdisk0,model=APPLE\ SSD\ SM0512F,serial_no=S1K5NYCD964433,wwn=5002538655584d30,capacity=500277790720 udma_crc_errors=0i,exit_status=0i,health_ok=true,read_error_rate=0i,temp_c=40i 1502536854000000000
smart_attribute,serial_no=S1K5NYCD964433,wwn=5002538655584d30,id=199,name=UDMA_CRC_Error_Count,flags=-O-RC-,fail=-,host=mbpro.local,device=rdisk0 threshold=0i,raw_value=0i,exit_status=0i,value=200i,worst=200i 1502536854000000000
smart_attribute,device=rdisk0,serial_no=S1K5NYCD964433,wwn=5002538655584d30,id=240,name=Unknown_SSD_Attribute,flags=-O---K,fail=-,host=mbpro.local exit_status=0i,value=100i,worst=100i,threshold=0i,raw_value=0i 1502536854000000000
```

View File

@@ -3,6 +3,7 @@ package smart
import (
"fmt"
"os/exec"
"path"
"regexp"
"strconv"
"strings"
@@ -134,7 +135,7 @@ func (m *Smart) scan() ([]string, error) {
devices := []string{}
for _, line := range strings.Split(string(out), "\n") {
dev := strings.Split(line, "#")
dev := strings.Split(line, " ")
if len(dev) > 1 && !excludedDev(m.Excludes, strings.TrimSpace(dev[0])) {
devices = append(devices, strings.TrimSpace(dev[0]))
}
@@ -178,13 +179,13 @@ func exitStatus(err error) (int, error) {
return 0, err
}
func gatherDisk(acc telegraf.Accumulator, usesudo, attributes bool, path, nockeck, device string, wg *sync.WaitGroup) {
func gatherDisk(acc telegraf.Accumulator, usesudo, attributes bool, smartctl, nockeck, device string, wg *sync.WaitGroup) {
defer wg.Done()
// smartctl 5.41 & 5.42 have are broken regarding handling of --nocheck/-n
args := []string{"--info", "--health", "--attributes", "--tolerance=verypermissive", "-n", nockeck, "--format=brief"}
args = append(args, strings.Split(device, " ")...)
cmd := sudo(usesudo, path, args...)
cmd := sudo(usesudo, smartctl, args...)
out, e := internal.CombinedOutputTimeout(cmd, time.Second*5)
outStr := string(out)
@@ -196,7 +197,8 @@ func gatherDisk(acc telegraf.Accumulator, usesudo, attributes bool, path, nockec
}
device_tags := map[string]string{}
device_tags["device"] = strings.Split(device, " ")[0]
device_node := strings.Split(device, " ")[0]
device_tags["device"] = path.Base(device_node)
device_fields := make(map[string]interface{})
device_fields["exit_status"] = exitStatus
@@ -240,7 +242,8 @@ func gatherDisk(acc telegraf.Accumulator, usesudo, attributes bool, path, nockec
tags := map[string]string{}
fields := make(map[string]interface{})
tags["device"] = strings.Split(device, " ")[0]
device_node := strings.Split(device, " ")[0]
tags["device"] = path.Base(device_node)
if serial, ok := device_tags["serial_no"]; ok {
tags["serial_no"] = serial

View File

@@ -89,7 +89,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "1",
@@ -107,7 +107,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "5",
@@ -125,7 +125,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "9",
@@ -143,7 +143,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "12",
@@ -161,7 +161,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "169",
@@ -179,7 +179,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "173",
@@ -197,7 +197,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "190",
@@ -215,7 +215,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "192",
@@ -233,7 +233,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "194",
@@ -251,7 +251,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "197",
@@ -269,7 +269,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "199",
@@ -287,7 +287,7 @@ func TestGatherAttributes(t *testing.T) {
"exit_status": int(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
"id": "240",
@@ -317,7 +317,7 @@ func TestGatherAttributes(t *testing.T) {
"udma_crc_errors": int64(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"model": "APPLE SSD SM256E",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",
@@ -363,7 +363,7 @@ func TestGatherNoAttributes(t *testing.T) {
"udma_crc_errors": int64(0),
},
map[string]string{
"device": "/dev/ada0",
"device": "ada0",
"model": "APPLE SSD SM256E",
"serial_no": "S0X5NZBC422720",
"wwn": "5002538043584d30",

View File

@@ -333,6 +333,9 @@ func TestGetSNMPConnection_caching(t *testing.T) {
}
func TestGosnmpWrapper_walk_retry(t *testing.T) {
if testing.Short() {
t.Skip("Skipping test due to random failures.")
}
srvr, err := net.ListenUDP("udp4", &net.UDPAddr{})
defer srvr.Close()
require.NoError(t, err)
@@ -379,6 +382,8 @@ func TestGosnmpWrapper_walk_retry(t *testing.T) {
}
func TestGosnmpWrapper_get_retry(t *testing.T) {
// TODO: Fix this test
t.Skip("Test failing too often, skip for now and revisit later.")
srvr, err := net.ListenUDP("udp4", &net.UDPAddr{})
defer srvr.Close()
require.NoError(t, err)

View File

@@ -246,6 +246,9 @@ func addAdminCoresStatusToAcc(acc telegraf.Accumulator, adminCoreStatus *AdminCo
// Add core metrics section to accumulator
func addCoreMetricsToAcc(acc telegraf.Accumulator, core string, mBeansData *MBeansData, time time.Time) error {
var coreMetrics map[string]Core
if len(mBeansData.SolrMbeans) < 2 {
return fmt.Errorf("no core metric data to unmarshall")
}
if err := json.Unmarshal(mBeansData.SolrMbeans[1], &coreMetrics); err != nil {
return err
}
@@ -274,9 +277,14 @@ func addCoreMetricsToAcc(acc telegraf.Accumulator, core string, mBeansData *MBea
func addQueryHandlerMetricsToAcc(acc telegraf.Accumulator, core string, mBeansData *MBeansData, time time.Time) error {
var queryMetrics map[string]QueryHandler
if len(mBeansData.SolrMbeans) < 4 {
return fmt.Errorf("no query handler metric data to unmarshall")
}
if err := json.Unmarshal(mBeansData.SolrMbeans[3], &queryMetrics); err != nil {
return err
}
for name, metrics := range queryMetrics {
coreFields := map[string]interface{}{
"15min_rate_reqs_per_second": metrics.Stats.One5minRateReqsPerSecond,
@@ -310,6 +318,9 @@ func addQueryHandlerMetricsToAcc(acc telegraf.Accumulator, core string, mBeansDa
func addUpdateHandlerMetricsToAcc(acc telegraf.Accumulator, core string, mBeansData *MBeansData, time time.Time) error {
var updateMetrics map[string]UpdateHandler
if len(mBeansData.SolrMbeans) < 6 {
return fmt.Errorf("no update handler metric data to unmarshall")
}
if err := json.Unmarshal(mBeansData.SolrMbeans[5], &updateMetrics); err != nil {
return err
}
@@ -364,6 +375,9 @@ func getFloat(unk interface{}) float64 {
// Add cache metrics section to accumulator
func addCacheMetricsToAcc(acc telegraf.Accumulator, core string, mBeansData *MBeansData, time time.Time) error {
if len(mBeansData.SolrMbeans) < 8 {
return fmt.Errorf("no cache metric data to unmarshall")
}
var cacheMetrics map[string]Cache
if err := json.Unmarshal(mBeansData.SolrMbeans[7], &cacheMetrics); err != nil {
return err

Some files were not shown because too many files have changed in this diff Show More