diff --git a/CHANGELOG.md b/CHANGELOG.md index 91e933102..1812c65fd 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,22 +1,5 @@ ## v1.0 [unreleased] -### Features - -- [#1413](https://github.com/influxdata/telegraf/issues/1413): Separate container_version from container_image tag. -- [#1525](https://github.com/influxdata/telegraf/pull/1525): Support setting per-device and total metrics for Docker network and blockio. -- [#1466](https://github.com/influxdata/telegraf/pull/1466): MongoDB input plugin: adding per DB stats from db.stats() - -### Bugfixes - -- [#1519](https://github.com/influxdata/telegraf/pull/1519): Fix error race conditions and partial failures. -- [#1477](https://github.com/influxdata/telegraf/issues/1477): nstat: fix inaccurate config panic. -- [#1481](https://github.com/influxdata/telegraf/issues/1481): jolokia: fix handling multiple multi-dimensional attributes. -- [#1430](https://github.com/influxdata/telegraf/issues/1430): Fix prometheus character sanitizing. Sanitize more win_perf_counters characters. -- [#1534](https://github.com/influxdata/telegraf/pull/1534): Add diskio io_time to FreeBSD & report timing metrics as ms (as linux does). -- [#1379](https://github.com/influxdata/telegraf/issues/1379): Fix covering Amazon Linux for post remove flow. - -## v1.0 beta 3 [2016-07-18] - ### Release Notes **Breaking Change**: Aerospike main server node measurements have been renamed @@ -49,8 +32,15 @@ should now look like: path = "/" ``` +- `flush_jitter` behavior has been changed. The random jitter will now be +evaluated at every flush interval, rather than once at startup. This makes it +consistent with the behavior of `collection_jitter`. + ### Features +- [#1413](https://github.com/influxdata/telegraf/issues/1413): Separate container_version from container_image tag. +- [#1525](https://github.com/influxdata/telegraf/pull/1525): Support setting per-device and total metrics for Docker network and blockio. +- [#1466](https://github.com/influxdata/telegraf/pull/1466): MongoDB input plugin: adding per DB stats from db.stats() - [#1503](https://github.com/influxdata/telegraf/pull/1503): Add tls support for certs to RabbitMQ input plugin - [#1289](https://github.com/influxdata/telegraf/pull/1289): webhooks input plugin. Thanks @francois2metz and @cduez! - [#1247](https://github.com/influxdata/telegraf/pull/1247): rollbar webhook plugin. @@ -65,73 +55,11 @@ should now look like: - [#1434](https://github.com/influxdata/telegraf/pull/1434): Add measurement name arg to logparser plugin. - [#1479](https://github.com/influxdata/telegraf/pull/1479): logparser: change resp_code from a field to a tag. - [#1411](https://github.com/influxdata/telegraf/pull/1411): Implement support for fetching hddtemp data - -### Bugfixes - -- [#1472](https://github.com/influxdata/telegraf/pull/1472): diskio input plugin: set 'skip_serial_number = true' by default to avoid high cardinality. -- [#1426](https://github.com/influxdata/telegraf/pull/1426): nil metrics panic fix. -- [#1384](https://github.com/influxdata/telegraf/pull/1384): Fix datarace in apache input plugin. -- [#1399](https://github.com/influxdata/telegraf/issues/1399): Add `read_repairs` statistics to riak plugin. -- [#1405](https://github.com/influxdata/telegraf/issues/1405): Fix memory/connection leak in prometheus input plugin. -- [#1378](https://github.com/influxdata/telegraf/issues/1378): Trim BOM from config file for Windows support. -- [#1339](https://github.com/influxdata/telegraf/issues/1339): Prometheus client output panic on service reload. -- [#1461](https://github.com/influxdata/telegraf/pull/1461): Prometheus parser, protobuf format header fix. -- [#1334](https://github.com/influxdata/telegraf/issues/1334): Prometheus output, metric refresh and caching fixes. -- [#1432](https://github.com/influxdata/telegraf/issues/1432): Panic fix for multiple graphite outputs under very high load. -- [#1412](https://github.com/influxdata/telegraf/pull/1412): Instrumental output has better reconnect behavior -- [#1460](https://github.com/influxdata/telegraf/issues/1460): Remove PID from procstat plugin to fix cardinality issues. -- [#1427](https://github.com/influxdata/telegraf/issues/1427): Cassandra input: version 2.x "column family" fix. -- [#1463](https://github.com/influxdata/telegraf/issues/1463): Shared WaitGroup in Exec plugin -- [#1436](https://github.com/influxdata/telegraf/issues/1436): logparser: honor modifiers in "pattern" config. -- [#1418](https://github.com/influxdata/telegraf/issues/1418): logparser: error and exit on file permissions/missing errors. -- [#1499](https://github.com/influxdata/telegraf/pull/1499): Make the user able to specify full path for HAproxy stats -- [#1521](https://github.com/influxdata/telegraf/pull/1521): Fix Redis url, an extra "tcp://" was added. - -## v1.0 beta 2 [2016-06-21] - -### Features - - [#1340](https://github.com/influxdata/telegraf/issues/1340): statsd: do not log every dropped metric. - [#1368](https://github.com/influxdata/telegraf/pull/1368): Add precision rounding to all metrics on collection. - [#1390](https://github.com/influxdata/telegraf/pull/1390): Add support for Tengine - [#1320](https://github.com/influxdata/telegraf/pull/1320): Logparser input plugin for parsing grok-style log patterns. - [#1397](https://github.com/influxdata/telegraf/issues/1397): ElasticSearch: now supports connecting to ElasticSearch via SSL - -### Bugfixes - -- [#1330](https://github.com/influxdata/telegraf/issues/1330): Fix exec plugin panic when using single binary. -- [#1336](https://github.com/influxdata/telegraf/issues/1336): Fixed incorrect prometheus metrics source selection. -- [#1112](https://github.com/influxdata/telegraf/issues/1112): Set default Zookeeper chroot to empty string. -- [#1335](https://github.com/influxdata/telegraf/issues/1335): Fix overall ping timeout to be calculated based on per-ping timeout. -- [#1374](https://github.com/influxdata/telegraf/pull/1374): Change "default" retention policy to "". -- [#1377](https://github.com/influxdata/telegraf/issues/1377): Graphite output mangling '%' character. -- [#1396](https://github.com/influxdata/telegraf/pull/1396): Prometheus input plugin now supports x509 certs authentication - -## v1.0 beta 1 [2016-06-07] - -### Release Notes - -- `flush_jitter` behavior has been changed. The random jitter will now be -evaluated at every flush interval, rather than once at startup. This makes it -consistent with the behavior of `collection_jitter`. - -- All AWS plugins now utilize a standard mechanism for evaluating credentials. -This allows all AWS plugins to support environment variables, shared credential -files & profiles, and role assumptions. See the specific plugin README for -details. - -- The AWS CloudWatch input plugin can now declare a wildcard value for a metric -dimension. This causes the plugin to read all metrics that contain the specified -dimension key regardless of value. This is used to export collections of metrics -without having to know the dimension values ahead of time. - -- The AWS CloudWatch input plugin can now be configured with the `cache_ttl` -attribute. This configures the TTL of the internal metric cache. This is useful -in conjunction with wildcard dimension values as it will control the amount of -time before a new metric is included by the plugin. - -### Features - - [#1262](https://github.com/influxdata/telegraf/pull/1261): Add graylog input pluging. - [#1294](https://github.com/influxdata/telegraf/pull/1294): consul input plugin. Thanks @harnash - [#1164](https://github.com/influxdata/telegraf/pull/1164): conntrack input plugin. Thanks @robinpercy! @@ -150,6 +78,38 @@ time before a new metric is included by the plugin. ### Bugfixes +- [#1519](https://github.com/influxdata/telegraf/pull/1519): Fix error race conditions and partial failures. +- [#1477](https://github.com/influxdata/telegraf/issues/1477): nstat: fix inaccurate config panic. +- [#1481](https://github.com/influxdata/telegraf/issues/1481): jolokia: fix handling multiple multi-dimensional attributes. +- [#1430](https://github.com/influxdata/telegraf/issues/1430): Fix prometheus character sanitizing. Sanitize more win_perf_counters characters. +- [#1534](https://github.com/influxdata/telegraf/pull/1534): Add diskio io_time to FreeBSD & report timing metrics as ms (as linux does). +- [#1379](https://github.com/influxdata/telegraf/issues/1379): Fix covering Amazon Linux for post remove flow. +- [#1584](https://github.com/influxdata/telegraf/issues/1584): procstat missing fields: read/write bytes & count +- [#1472](https://github.com/influxdata/telegraf/pull/1472): diskio input plugin: set 'skip_serial_number = true' by default to avoid high cardinality. +- [#1426](https://github.com/influxdata/telegraf/pull/1426): nil metrics panic fix. +- [#1384](https://github.com/influxdata/telegraf/pull/1384): Fix datarace in apache input plugin. +- [#1399](https://github.com/influxdata/telegraf/issues/1399): Add `read_repairs` statistics to riak plugin. +- [#1405](https://github.com/influxdata/telegraf/issues/1405): Fix memory/connection leak in prometheus input plugin. +- [#1378](https://github.com/influxdata/telegraf/issues/1378): Trim BOM from config file for Windows support. +- [#1339](https://github.com/influxdata/telegraf/issues/1339): Prometheus client output panic on service reload. +- [#1461](https://github.com/influxdata/telegraf/pull/1461): Prometheus parser, protobuf format header fix. +- [#1334](https://github.com/influxdata/telegraf/issues/1334): Prometheus output, metric refresh and caching fixes. +- [#1432](https://github.com/influxdata/telegraf/issues/1432): Panic fix for multiple graphite outputs under very high load. +- [#1412](https://github.com/influxdata/telegraf/pull/1412): Instrumental output has better reconnect behavior +- [#1460](https://github.com/influxdata/telegraf/issues/1460): Remove PID from procstat plugin to fix cardinality issues. +- [#1427](https://github.com/influxdata/telegraf/issues/1427): Cassandra input: version 2.x "column family" fix. +- [#1463](https://github.com/influxdata/telegraf/issues/1463): Shared WaitGroup in Exec plugin +- [#1436](https://github.com/influxdata/telegraf/issues/1436): logparser: honor modifiers in "pattern" config. +- [#1418](https://github.com/influxdata/telegraf/issues/1418): logparser: error and exit on file permissions/missing errors. +- [#1499](https://github.com/influxdata/telegraf/pull/1499): Make the user able to specify full path for HAproxy stats +- [#1521](https://github.com/influxdata/telegraf/pull/1521): Fix Redis url, an extra "tcp://" was added. +- [#1330](https://github.com/influxdata/telegraf/issues/1330): Fix exec plugin panic when using single binary. +- [#1336](https://github.com/influxdata/telegraf/issues/1336): Fixed incorrect prometheus metrics source selection. +- [#1112](https://github.com/influxdata/telegraf/issues/1112): Set default Zookeeper chroot to empty string. +- [#1335](https://github.com/influxdata/telegraf/issues/1335): Fix overall ping timeout to be calculated based on per-ping timeout. +- [#1374](https://github.com/influxdata/telegraf/pull/1374): Change "default" retention policy to "". +- [#1377](https://github.com/influxdata/telegraf/issues/1377): Graphite output mangling '%' character. +- [#1396](https://github.com/influxdata/telegraf/pull/1396): Prometheus input plugin now supports x509 certs authentication - [#1252](https://github.com/influxdata/telegraf/pull/1252) & [#1279](https://github.com/influxdata/telegraf/pull/1279): Fix systemd service. Thanks @zbindenren & @PierreF! - [#1221](https://github.com/influxdata/telegraf/pull/1221): Fix influxdb n_shards counter. - [#1258](https://github.com/influxdata/telegraf/pull/1258): Fix potential kernel plugin integer parse error. @@ -159,6 +119,7 @@ time before a new metric is included by the plugin. - [#1316](https://github.com/influxdata/telegraf/pull/1316): Removed leaked "database" tag on redis metrics. Thanks @PierreF! - [#1323](https://github.com/influxdata/telegraf/issues/1323): Processes plugin: fix potential error with /proc/net/stat directory. - [#1322](https://github.com/influxdata/telegraf/issues/1322): Fix rare RHEL 5.2 panic in gopsutil diskio gathering function. +- [#1586](https://github.com/influxdata/telegraf/pull/1586): Remove IF NOT EXISTS from influxdb output database creation. ## v0.13.1 [2016-05-24] diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index f02f109fd..a639e91f9 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -11,6 +11,7 @@ Output plugins READMEs are less structured, but any information you can provide on how the data will look is appreciated. See the [OpenTSDB output](https://github.com/influxdata/telegraf/tree/master/plugins/outputs/opentsdb) for a good example. +1. **Optional:** Write a [tickscript](https://docs.influxdata.com/kapacitor/v1.0/tick/syntax/) for your plugin and add it to [Kapacitor](https://github.com/influxdata/kapacitor/tree/master/examples/telegraf). Or mention @jackzampolin in a PR comment with some common queries that you would want to alert on and he will write one for you. ## GoDoc diff --git a/Godeps b/Godeps index 3a5fd29db..e2ed84402 100644 --- a/Godeps +++ b/Godeps @@ -45,7 +45,7 @@ github.com/prometheus/client_model fa8ad6fec33561be4280a8f0514318c79d7f6cb6 github.com/prometheus/common e8eabff8812b05acf522b45fdcd725a785188e37 github.com/prometheus/procfs 406e5b7bfd8201a36e2bb5f7bdae0b03380c2ce8 github.com/samuel/go-zookeeper 218e9c81c0dd8b3b18172b2bbfad92cc7d6db55f -github.com/shirou/gopsutil ee66bc560c366dd33b9a4046ba0b644caba46bed +github.com/shirou/gopsutil 4d0c402af66c78735c5ccf820dc2ca7de5e4ff08 github.com/soniah/gosnmp b1b4f885b12c5dcbd021c5cee1c904110de6db7d github.com/sparrc/aerospike-client-go d4bb42d2c2d39dae68e054116f4538af189e05d5 github.com/streadway/amqp b4f3ceab0337f013208d31348b578d83c0064744 diff --git a/cmd/telegraf/telegraf.go b/cmd/telegraf/telegraf.go index 6681ad073..e3398511a 100644 --- a/cmd/telegraf/telegraf.go +++ b/cmd/telegraf/telegraf.go @@ -39,12 +39,6 @@ var fOutputList = flag.Bool("output-list", false, "print available output plugins.") var fUsage = flag.String("usage", "", "print usage for a plugin, ie, 'telegraf -usage mysql'") -var fInputFiltersLegacy = flag.String("filter", "", - "filter the inputs to enable, separator is :") -var fOutputFiltersLegacy = flag.String("outputfilter", "", - "filter the outputs to enable, separator is :") -var fConfigDirectoryLegacy = flag.String("configdirectory", "", - "directory containing additional *.conf files") // Telegraf version, populated linker. // ie, -ldflags "-X main.version=`git describe --always --tags`" @@ -110,24 +104,11 @@ func main() { args := flag.Args() var inputFilters []string - if *fInputFiltersLegacy != "" { - fmt.Printf("WARNING '--filter' flag is deprecated, please use" + - " '--input-filter'") - inputFilter := strings.TrimSpace(*fInputFiltersLegacy) - inputFilters = strings.Split(":"+inputFilter+":", ":") - } if *fInputFilters != "" { inputFilter := strings.TrimSpace(*fInputFilters) inputFilters = strings.Split(":"+inputFilter+":", ":") } - var outputFilters []string - if *fOutputFiltersLegacy != "" { - fmt.Printf("WARNING '--outputfilter' flag is deprecated, please use" + - " '--output-filter'") - outputFilter := strings.TrimSpace(*fOutputFiltersLegacy) - outputFilters = strings.Split(":"+outputFilter+":", ":") - } if *fOutputFilters != "" { outputFilter := strings.TrimSpace(*fOutputFilters) outputFilters = strings.Split(":"+outputFilter+":", ":") @@ -145,34 +126,28 @@ func main() { } } - if *fOutputList { + // switch for flags which just do something and exit immediately + switch { + case *fOutputList: fmt.Println("Available Output Plugins:") for k, _ := range outputs.Outputs { fmt.Printf(" %s\n", k) } return - } - - if *fInputList { + case *fInputList: fmt.Println("Available Input Plugins:") for k, _ := range inputs.Inputs { fmt.Printf(" %s\n", k) } return - } - - if *fVersion { + case *fVersion: v := fmt.Sprintf("Telegraf - version %s", version) fmt.Println(v) return - } - - if *fSampleConfig { + case *fSampleConfig: config.PrintSampleConfig(inputFilters, outputFilters) return - } - - if *fUsage != "" { + case *fUsage != "": if err := config.PrintInputConfig(*fUsage); err != nil { if err2 := config.PrintOutputConfig(*fUsage); err2 != nil { log.Fatalf("%s and %s", err, err2) @@ -191,15 +166,6 @@ func main() { os.Exit(1) } - if *fConfigDirectoryLegacy != "" { - fmt.Printf("WARNING '--configdirectory' flag is deprecated, please use" + - " '--config-directory'") - err = c.LoadDirectory(*fConfigDirectoryLegacy) - if err != nil { - log.Fatal(err) - } - } - if *fConfigDirectory != "" { err = c.LoadDirectory(*fConfigDirectory) if err != nil { diff --git a/etc/telegraf.conf b/etc/telegraf.conf index 5189d2e3f..60877af20 100644 --- a/etc/telegraf.conf +++ b/etc/telegraf.conf @@ -55,7 +55,7 @@ ## By default, precision will be set to the same timestamp order as the ## collection interval, with the maximum being 1s. ## Precision will NOT be used for service inputs, such as logparser and statsd. - ## Valid values are "Nns", "Nus" (or "Nµs"), "Nms", "Ns". + ## Valid values are "ns", "us" (or "µs"), "ms", "s". precision = "" ## Run telegraf in debug mode debug = false @@ -1577,7 +1577,7 @@ # ## /var/log/**.log -> recursively find all .log files in /var/log # ## /var/log/*/*.log -> find all .log files with a parent dir in /var/log # ## /var/log/apache.log -> only tail the apache log file -# files = ["/var/log/influxdb/influxdb.log"] +# files = ["/var/log/apache/access.log"] # ## Read file from beginning. # from_beginning = false # @@ -1590,9 +1590,9 @@ # ## Other common built-in patterns are: # ## %{COMMON_LOG_FORMAT} (plain apache & nginx access logs) # ## %{COMBINED_LOG_FORMAT} (access logs + referrer & agent) -# patterns = ["%{INFLUXDB_HTTPD_LOG}"] +# patterns = ["%{COMBINED_LOG_FORMAT}"] # ## Name of the outputted measurement name. -# measurement = "influxdb_log" +# measurement = "apache_access_log" # ## Full path(s) to custom pattern files. # custom_pattern_files = [] # ## Custom patterns can also be defined here. Put one pattern per line. diff --git a/internal/config/config.go b/internal/config/config.go index 9408d9efd..6823181e1 100644 --- a/internal/config/config.go +++ b/internal/config/config.go @@ -219,7 +219,7 @@ var header = `# Telegraf Configuration ## By default, precision will be set to the same timestamp order as the ## collection interval, with the maximum being 1s. ## Precision will NOT be used for service inputs, such as logparser and statsd. - ## Valid values are "Nns", "Nus" (or "Nµs"), "Nms", "Ns". + ## Valid values are "ns", "us" (or "µs"), "ms", "s". precision = "" ## Run telegraf in debug mode debug = false diff --git a/plugins/inputs/logparser/README.md b/plugins/inputs/logparser/README.md index 64e8909f5..1affcd811 100644 --- a/plugins/inputs/logparser/README.md +++ b/plugins/inputs/logparser/README.md @@ -14,17 +14,22 @@ regex patterns. ## /var/log/**.log -> recursively find all .log files in /var/log ## /var/log/*/*.log -> find all .log files with a parent dir in /var/log ## /var/log/apache.log -> only tail the apache log file - files = ["/var/log/influxdb/influxdb.log"] + files = ["/var/log/apache/access.log"] ## Read file from beginning. from_beginning = false ## Parse logstash-style "grok" patterns: - ## Telegraf builtin parsing patterns: https://goo.gl/dkay10 + ## Telegraf built-in parsing patterns: https://goo.gl/dkay10 [inputs.logparser.grok] ## This is a list of patterns to check the given log file(s) for. ## Note that adding patterns here increases processing time. The most - ## efficient configuration is to have one file & pattern per logparser. - patterns = ["%{INFLUXDB_HTTPD_LOG}"] + ## efficient configuration is to have one pattern per logparser. + ## Other common built-in patterns are: + ## %{COMMON_LOG_FORMAT} (plain apache & nginx access logs) + ## %{COMBINED_LOG_FORMAT} (access logs + referrer & agent) + patterns = ["%{COMBINED_LOG_FORMAT}"] + ## Name of the outputted measurement name. + measurement = "apache_access_log" ## Full path(s) to custom pattern files. custom_pattern_files = [] ## Custom patterns can also be defined here. Put one pattern per line. @@ -32,8 +37,6 @@ regex patterns. ''' ``` -> **Note:** The InfluxDB log pattern in the default configuration only works for Influx versions 1.0.0-beta1 or higher. - ## Grok Parser The grok parser uses a slightly modified version of logstash "grok" patterns, @@ -69,6 +72,7 @@ Timestamp modifiers can be used to convert captures to the timestamp of the - tag (converts the field into a tag) - drop (drops the field completely) - Timestamp modifiers: + - ts (This will auto-learn the timestamp format) - ts-ansic ("Mon Jan _2 15:04:05 2006") - ts-unix ("Mon Jan _2 15:04:05 MST 2006") - ts-ruby ("Mon Jan 02 15:04:05 -0700 2006") diff --git a/plugins/inputs/logparser/grok/grok.go b/plugins/inputs/logparser/grok/grok.go index d8691d7b9..70b759826 100644 --- a/plugins/inputs/logparser/grok/grok.go +++ b/plugins/inputs/logparser/grok/grok.go @@ -15,7 +15,7 @@ import ( "github.com/influxdata/telegraf" ) -var timeFormats = map[string]string{ +var timeLayouts = map[string]string{ "ts-ansic": "Mon Jan _2 15:04:05 2006", "ts-unix": "Mon Jan _2 15:04:05 MST 2006", "ts-ruby": "Mon Jan 02 15:04:05 -0700 2006", @@ -27,27 +27,33 @@ var timeFormats = map[string]string{ "ts-rfc3339": "2006-01-02T15:04:05Z07:00", "ts-rfc3339nano": "2006-01-02T15:04:05.999999999Z07:00", "ts-httpd": "02/Jan/2006:15:04:05 -0700", - "ts-epoch": "EPOCH", - "ts-epochnano": "EPOCH_NANO", + // These three are not exactly "layouts", but they are special cases that + // will get handled in the ParseLine function. + "ts-epoch": "EPOCH", + "ts-epochnano": "EPOCH_NANO", + "ts": "GENERIC_TIMESTAMP", // try parsing all known timestamp layouts. } const ( - INT = "int" - TAG = "tag" - FLOAT = "float" - STRING = "string" - DURATION = "duration" - DROP = "drop" + INT = "int" + TAG = "tag" + FLOAT = "float" + STRING = "string" + DURATION = "duration" + DROP = "drop" + EPOCH = "EPOCH" + EPOCH_NANO = "EPOCH_NANO" + GENERIC_TIMESTAMP = "GENERIC_TIMESTAMP" ) var ( - // matches named captures that contain a type. + // matches named captures that contain a modifier. // ie, // %{NUMBER:bytes:int} // %{IPORHOST:clientip:tag} // %{HTTPDATE:ts1:ts-http} // %{HTTPDATE:ts2:ts-"02 Jan 06 15:04"} - typedRe = regexp.MustCompile(`%{\w+:(\w+):(ts-".+"|t?s?-?\w+)}`) + modifierRe = regexp.MustCompile(`%{\w+:(\w+):(ts-".+"|t?s?-?\w+)}`) // matches a plain pattern name. ie, %{NUMBER} patternOnlyRe = regexp.MustCompile(`%{(\w+)}`) ) @@ -87,6 +93,12 @@ type Parser struct { // "RESPONSE_CODE": "%{NUMBER:rc:tag}" // } patterns map[string]string + // foundTsLayouts is a slice of timestamp patterns that have been found + // in the log lines. This slice gets updated if the user uses the generic + // 'ts' modifier for timestamps. This slice is checked first for matches, + // so that previously-matched layouts get priority over all other timestamp + // layouts. + foundTsLayouts []string g *grok.Grok tsModder *tsModder @@ -140,6 +152,7 @@ func (p *Parser) Compile() error { func (p *Parser) ParseLine(line string) (telegraf.Metric, error) { var err error + // values are the parsed fields from the log line var values map[string]string // the matching pattern string var patternName string @@ -165,6 +178,7 @@ func (p *Parser) ParseLine(line string) (telegraf.Metric, error) { continue } + // t is the modifier of the field var t string // check if pattern has some modifiers if types, ok := p.typeMap[patternName]; ok { @@ -210,20 +224,50 @@ func (p *Parser) ParseLine(line string) (telegraf.Metric, error) { tags[k] = v case STRING: fields[k] = strings.Trim(v, `"`) - case "EPOCH": + case EPOCH: iv, err := strconv.ParseInt(v, 10, 64) if err != nil { log.Printf("ERROR parsing %s to int: %s", v, err) } else { timestamp = time.Unix(iv, 0) } - case "EPOCH_NANO": + case EPOCH_NANO: iv, err := strconv.ParseInt(v, 10, 64) if err != nil { log.Printf("ERROR parsing %s to int: %s", v, err) } else { timestamp = time.Unix(0, iv) } + case GENERIC_TIMESTAMP: + var foundTs bool + // first try timestamp layouts that we've already found + for _, layout := range p.foundTsLayouts { + ts, err := time.Parse(layout, v) + if err == nil { + timestamp = ts + foundTs = true + break + } + } + // if we haven't found a timestamp layout yet, try all timestamp + // layouts. + if !foundTs { + for _, layout := range timeLayouts { + ts, err := time.Parse(layout, v) + if err == nil { + timestamp = ts + foundTs = true + p.foundTsLayouts = append(p.foundTsLayouts, layout) + break + } + } + } + // if we still haven't found a timestamp layout, log it and we will + // just use time.Now() + if !foundTs { + log.Printf("ERROR parsing timestamp [%s], could not find any "+ + "suitable time layouts.", v) + } case DROP: // goodbye! default: @@ -267,7 +311,7 @@ func (p *Parser) compileCustomPatterns() error { // check if pattern contains modifiers. Parse them out if it does. for name, pattern := range p.patterns { - if typedRe.MatchString(pattern) { + if modifierRe.MatchString(pattern) { // this pattern has modifiers, so parse out the modifiers pattern, err = p.parseTypedCaptures(name, pattern) if err != nil { @@ -280,13 +324,13 @@ func (p *Parser) compileCustomPatterns() error { return p.g.AddPatternsFromMap(p.patterns) } -// parseTypedCaptures parses the capture types, and then deletes the type from -// the line so that it is a valid "grok" pattern again. +// parseTypedCaptures parses the capture modifiers, and then deletes the +// modifier from the line so that it is a valid "grok" pattern again. // ie, // %{NUMBER:bytes:int} => %{NUMBER:bytes} (stores %{NUMBER}->bytes->int) // %{IPORHOST:clientip:tag} => %{IPORHOST:clientip} (stores %{IPORHOST}->clientip->tag) func (p *Parser) parseTypedCaptures(name, pattern string) (string, error) { - matches := typedRe.FindAllStringSubmatch(pattern, -1) + matches := modifierRe.FindAllStringSubmatch(pattern, -1) // grab the name of the capture pattern patternName := "%{" + name + "}" @@ -298,16 +342,18 @@ func (p *Parser) parseTypedCaptures(name, pattern string) (string, error) { hasTimestamp := false for _, match := range matches { // regex capture 1 is the name of the capture - // regex capture 2 is the type of the capture - if strings.HasPrefix(match[2], "ts-") { + // regex capture 2 is the modifier of the capture + if strings.HasPrefix(match[2], "ts") { if hasTimestamp { return pattern, fmt.Errorf("logparser pattern compile error: "+ "Each pattern is allowed only one named "+ "timestamp data type. pattern: %s", pattern) } - if f, ok := timeFormats[match[2]]; ok { - p.tsMap[patternName][match[1]] = f + if layout, ok := timeLayouts[match[2]]; ok { + // built-in time format + p.tsMap[patternName][match[1]] = layout } else { + // custom time format p.tsMap[patternName][match[1]] = strings.TrimSuffix(strings.TrimPrefix(match[2], `ts-"`), `"`) } hasTimestamp = true diff --git a/plugins/inputs/logparser/grok/grok_test.go b/plugins/inputs/logparser/grok/grok_test.go index 295f32609..bc8d980f2 100644 --- a/plugins/inputs/logparser/grok/grok_test.go +++ b/plugins/inputs/logparser/grok/grok_test.go @@ -38,32 +38,6 @@ func Benchmark_ParseLine_CombinedLogFormat(b *testing.B) { benchM = m } -func Benchmark_ParseLine_InfluxLog(b *testing.B) { - p := &Parser{ - Patterns: []string{"%{INFLUXDB_HTTPD_LOG}"}, - } - p.Compile() - - var m telegraf.Metric - for n := 0; n < b.N; n++ { - m, _ = p.ParseLine(`[httpd] 192.168.1.1 - - [14/Jun/2016:11:33:29 +0100] "POST /write?consistency=any&db=telegraf&precision=ns&rp= HTTP/1.1" 204 0 "-" "InfluxDBClient" 6f61bc44-321b-11e6-8050-000000000000 2513`) - } - benchM = m -} - -func Benchmark_ParseLine_InfluxLog_NoMatch(b *testing.B) { - p := &Parser{ - Patterns: []string{"%{INFLUXDB_HTTPD_LOG}"}, - } - p.Compile() - - var m telegraf.Metric - for n := 0; n < b.N; n++ { - m, _ = p.ParseLine(`[retention] 2016/06/14 14:38:24 retention policy shard deletion check commencing`) - } - benchM = m -} - func Benchmark_ParseLine_CustomPattern(b *testing.B) { p := &Parser{ Patterns: []string{"%{TEST_LOG_A}", "%{TEST_LOG_B}"}, @@ -108,9 +82,9 @@ func TestMeasurementName(t *testing.T) { assert.Equal(t, "my_web_log", m.Name()) } -func TestBuiltinInfluxdbHttpd(t *testing.T) { +func TestCustomInfluxdbHttpd(t *testing.T) { p := &Parser{ - Patterns: []string{"%{INFLUXDB_HTTPD_LOG}"}, + Patterns: []string{`\[httpd\] %{COMBINED_LOG_FORMAT} %{UUID:uuid:drop} %{NUMBER:response_time_us:int}`}, } assert.NoError(t, p.Compile()) @@ -333,6 +307,55 @@ func TestParseEpochErrors(t *testing.T) { assert.NoError(t, err) } +func TestParseGenericTimestamp(t *testing.T) { + p := &Parser{ + Patterns: []string{`\[%{HTTPDATE:ts:ts}\] response_time=%{POSINT:response_time:int} mymetric=%{NUMBER:metric:float}`}, + } + assert.NoError(t, p.Compile()) + + metricA, err := p.ParseLine(`[09/Jun/2016:03:37:03 +0000] response_time=20821 mymetric=10890.645`) + require.NotNil(t, metricA) + assert.NoError(t, err) + assert.Equal(t, + map[string]interface{}{ + "response_time": int64(20821), + "metric": float64(10890.645), + }, + metricA.Fields()) + assert.Equal(t, map[string]string{}, metricA.Tags()) + assert.Equal(t, time.Unix(1465443423, 0).UTC(), metricA.Time().UTC()) + + metricB, err := p.ParseLine(`[09/Jun/2016:03:37:04 +0000] response_time=20821 mymetric=10890.645`) + require.NotNil(t, metricB) + assert.NoError(t, err) + assert.Equal(t, + map[string]interface{}{ + "response_time": int64(20821), + "metric": float64(10890.645), + }, + metricB.Fields()) + assert.Equal(t, map[string]string{}, metricB.Tags()) + assert.Equal(t, time.Unix(1465443424, 0).UTC(), metricB.Time().UTC()) +} + +func TestParseGenericTimestampNotFound(t *testing.T) { + p := &Parser{ + Patterns: []string{`\[%{NOTSPACE:ts:ts}\] response_time=%{POSINT:response_time:int} mymetric=%{NUMBER:metric:float}`}, + } + assert.NoError(t, p.Compile()) + + metricA, err := p.ParseLine(`[foobar] response_time=20821 mymetric=10890.645`) + require.NotNil(t, metricA) + assert.NoError(t, err) + assert.Equal(t, + map[string]interface{}{ + "response_time": int64(20821), + "metric": float64(10890.645), + }, + metricA.Fields()) + assert.Equal(t, map[string]string{}, metricA.Tags()) +} + func TestCompileFileAndParse(t *testing.T) { p := &Parser{ Patterns: []string{"%{TEST_LOG_A}", "%{TEST_LOG_B}"}, diff --git a/plugins/inputs/logparser/grok/influx_patterns.go b/plugins/inputs/logparser/grok/influx_patterns.go index 53be0e20d..ff9d60ebf 100644 --- a/plugins/inputs/logparser/grok/influx_patterns.go +++ b/plugins/inputs/logparser/grok/influx_patterns.go @@ -55,15 +55,13 @@ EXAMPLE_LOG \[%{HTTPDATE:ts:ts-httpd}\] %{NUMBER:myfloat:float} %{RESPONSE_CODE} # Wider-ranging username matching vs. logstash built-in %{USER} NGUSERNAME [a-zA-Z\.\@\-\+_%]+ NGUSER %{NGUSERNAME} +# Wider-ranging client IP matching +CLIENT (?:%{IPORHOST}|%{HOSTPORT}|::1) ## ## COMMON LOG PATTERNS ## -# InfluxDB log patterns -CLIENT (?:%{IPORHOST}|%{HOSTPORT}|::1) -INFLUXDB_HTTPD_LOG \[httpd\] %{COMBINED_LOG_FORMAT} %{UUID:uuid:drop} %{NUMBER:response_time_us:int} - # apache & nginx logs, this is also known as the "common log format" # see https://en.wikipedia.org/wiki/Common_Log_Format COMMON_LOG_FORMAT %{CLIENT:client_ip} %{NGUSER:ident} %{NGUSER:auth} \[%{HTTPDATE:ts:ts-httpd}\] "(?:%{WORD:verb:tag} %{NOTSPACE:request}(?: HTTP/%{NUMBER:http_version:float})?|%{DATA})" %{NUMBER:resp_code:tag} (?:%{NUMBER:resp_bytes:int}|-) diff --git a/plugins/inputs/logparser/grok/patterns/influx-patterns b/plugins/inputs/logparser/grok/patterns/influx-patterns index 1db74a17a..6f4d81f89 100644 --- a/plugins/inputs/logparser/grok/patterns/influx-patterns +++ b/plugins/inputs/logparser/grok/patterns/influx-patterns @@ -51,15 +51,13 @@ EXAMPLE_LOG \[%{HTTPDATE:ts:ts-httpd}\] %{NUMBER:myfloat:float} %{RESPONSE_CODE} # Wider-ranging username matching vs. logstash built-in %{USER} NGUSERNAME [a-zA-Z\.\@\-\+_%]+ NGUSER %{NGUSERNAME} +# Wider-ranging client IP matching +CLIENT (?:%{IPORHOST}|%{HOSTPORT}|::1) ## ## COMMON LOG PATTERNS ## -# InfluxDB log patterns -CLIENT (?:%{IPORHOST}|%{HOSTPORT}|::1) -INFLUXDB_HTTPD_LOG \[httpd\] %{COMBINED_LOG_FORMAT} %{UUID:uuid:drop} %{NUMBER:response_time_us:int} - # apache & nginx logs, this is also known as the "common log format" # see https://en.wikipedia.org/wiki/Common_Log_Format COMMON_LOG_FORMAT %{CLIENT:client_ip} %{NGUSER:ident} %{NGUSER:auth} \[%{HTTPDATE:ts:ts-httpd}\] "(?:%{WORD:verb:tag} %{NOTSPACE:request}(?: HTTP/%{NUMBER:http_version:float})?|%{DATA})" %{NUMBER:resp_code:tag} (?:%{NUMBER:resp_bytes:int}|-) diff --git a/plugins/inputs/logparser/logparser.go b/plugins/inputs/logparser/logparser.go index 6b29ea031..8ded03edc 100644 --- a/plugins/inputs/logparser/logparser.go +++ b/plugins/inputs/logparser/logparser.go @@ -45,7 +45,7 @@ const sampleConfig = ` ## /var/log/**.log -> recursively find all .log files in /var/log ## /var/log/*/*.log -> find all .log files with a parent dir in /var/log ## /var/log/apache.log -> only tail the apache log file - files = ["/var/log/influxdb/influxdb.log"] + files = ["/var/log/apache/access.log"] ## Read file from beginning. from_beginning = false @@ -58,9 +58,9 @@ const sampleConfig = ` ## Other common built-in patterns are: ## %{COMMON_LOG_FORMAT} (plain apache & nginx access logs) ## %{COMBINED_LOG_FORMAT} (access logs + referrer & agent) - patterns = ["%{INFLUXDB_HTTPD_LOG}"] + patterns = ["%{COMBINED_LOG_FORMAT}"] ## Name of the outputted measurement name. - measurement = "influxdb_log" + measurement = "apache_access_log" ## Full path(s) to custom pattern files. custom_pattern_files = [] ## Custom patterns can also be defined here. Put one pattern per line. diff --git a/plugins/inputs/procstat/spec_processor.go b/plugins/inputs/procstat/spec_processor.go index 3789e99d0..5143d8bcc 100644 --- a/plugins/inputs/procstat/spec_processor.go +++ b/plugins/inputs/procstat/spec_processor.go @@ -71,7 +71,7 @@ func (p *SpecProcessor) pushMetrics() { fields[prefix+"read_count"] = io.ReadCount fields[prefix+"write_count"] = io.WriteCount fields[prefix+"read_bytes"] = io.ReadBytes - fields[prefix+"write_bytes"] = io.WriteCount + fields[prefix+"write_bytes"] = io.WriteBytes } cpu_time, err := p.proc.Times() diff --git a/plugins/inputs/tail/tail_test.go b/plugins/inputs/tail/tail_test.go index f9f6bff28..31ecfbf30 100644 --- a/plugins/inputs/tail/tail_test.go +++ b/plugins/inputs/tail/tail_test.go @@ -17,6 +17,8 @@ func TestTailFromBeginning(t *testing.T) { tmpfile, err := ioutil.TempFile("", "") require.NoError(t, err) defer os.Remove(tmpfile.Name()) + _, err = tmpfile.WriteString("cpu,mytag=foo usage_idle=100\n") + require.NoError(t, err) tt := NewTail() tt.FromBeginning = true @@ -28,12 +30,10 @@ func TestTailFromBeginning(t *testing.T) { acc := testutil.Accumulator{} require.NoError(t, tt.Start(&acc)) - - _, err = tmpfile.WriteString("cpu,mytag=foo usage_idle=100\n") - require.NoError(t, err) + time.Sleep(time.Millisecond * 100) require.NoError(t, tt.Gather(&acc)) // arbitrary sleep to wait for message to show up - time.Sleep(time.Millisecond * 250) + time.Sleep(time.Millisecond * 150) acc.AssertContainsTaggedFields(t, "cpu", map[string]interface{}{ diff --git a/plugins/outputs/influxdb/influxdb.go b/plugins/outputs/influxdb/influxdb.go index 2b9fd101c..24065d114 100644 --- a/plugins/outputs/influxdb/influxdb.go +++ b/plugins/outputs/influxdb/influxdb.go @@ -146,7 +146,7 @@ func (i *InfluxDB) Connect() error { func createDatabase(c client.Client, database string) error { // Create Database if it doesn't exist _, err := c.Query(client.Query{ - Command: fmt.Sprintf("CREATE DATABASE IF NOT EXISTS \"%s\"", database), + Command: fmt.Sprintf("CREATE DATABASE \"%s\"", database), }) return err } diff --git a/scripts/build.py b/scripts/build.py index 426aa87bb..77befd599 100755 --- a/scripts/build.py +++ b/scripts/build.py @@ -83,29 +83,17 @@ targets = { } supported_builds = { - "darwin": [ "amd64" ], "windows": [ "amd64" ], "linux": [ "amd64", "i386", "armhf", "armel", "arm64", "static_amd64" ], "freebsd": [ "amd64" ] } supported_packages = { - "darwin": [ "tar" ], "linux": [ "deb", "rpm", "tar" ], "windows": [ "zip" ], "freebsd": [ "tar" ] } -supported_tags = { - # "linux": { - # "amd64": ["sensors"] - # } -} - -prereq_cmds = { - # "linux": "sudo apt-get install lm-sensors libsensors4-dev" -} - ################ #### Telegraf Functions ################