dom
/
telegraf
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Add support for additional metrics on Linux in zfs input (#3565)

This commit is contained in:
Richard Elling 2018-01-03 17:45:48 -08:00 committed by Daniel Nelson
parent 5397c02570
commit 92acef1664
4 changed files with 261 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

77
plugins/inputs/zfs/README.md
View File

@ -13,8 +13,12 @@ from `sysctl` and `zpool` on FreeBSD.
# kstatPath = "/proc/spl/kstat/zfs"
## By default, telegraf gather all zfs stats
## If not specified, then default is:
## Override the stats list using the kstatMetrics array:
## For FreeBSD, the default is:
# kstatMetrics = ["arcstats", "zfetchstats", "vdev_cache_stats"]
## For Linux, the default is:
# kstatMetrics = ["abdstats", "arcstats", "dnodestats", "dbufcachestats",
# "dmu_tx", "fm", "vdev_mirror_stats", "zfetchstats", "zil"]
## By default, don't gather zpool stats
# poolMetrics = false
@ -22,8 +26,8 @@ from `sysctl` and `zpool` on FreeBSD.
### Measurements & Fields:
By default this plugin collects metrics about **Arc**, **Zfetch**, and
**Vdev cache**. All these metrics are either counters or measure sizes
By default this plugin collects metrics about ZFS internals and pool.
These metrics are either counters or measure sizes
in bytes. These metrics will be in the `zfs` measurement with the field
names listed bellow.
@ -33,7 +37,7 @@ each pool.
- zfs
With fields listed bellow.
#### Arc Stats
#### ARC Stats (FreeBSD and Linux)
- arcstats_allocated (FreeBSD only)
- arcstats_anon_evict_data (Linux only)
@ -153,7 +157,7 @@ each pool.
- arcstats_size
- arcstats_sync_wait_for_async (FreeBSD only)
#### Zfetch Stats
#### Zfetch Stats (FreeBSD and Linux)
- zfetchstats_bogus_streams (Linux only)
- zfetchstats_colinear_hits (Linux only)
@ -168,7 +172,7 @@ each pool.
- zfetchstats_stride_hits (Linux only)
- zfetchstats_stride_misses (Linux only)
#### Vdev Cache Stats
#### Vdev Cache Stats (FreeBSD)
- vdev_cache_stats_delegations
- vdev_cache_stats_hits
@ -176,21 +180,21 @@ each pool.
#### Pool Metrics (optional)
On Linux:
On Linux (reference: kstat accumulated time and queue length statistics):
- zfs_pool
- nread (integer, )
- nwritten (integer, )
- reads (integer, )
- writes (integer, )
- wtime (integer, )
- wlentime (integer, )
- wupdate (integer, )
- rtime (integer, )
- rlentime (integer, )
- rupdate (integer, )
- wcnt (integer, )
- rcnt (integer, )
- nread (integer, bytes)
- nwritten (integer, bytes)
- reads (integer, count)
- writes (integer, count)
- wtime (integer, nanoseconds)
- wlentime (integer, queuelength * nanoseconds)
- wupdate (integer, timestamp)
- rtime (integer, nanoseconds)
- rlentime (integer, queuelength * nanoseconds)
- rupdate (integer, timestamp)
- wcnt (integer, count)
- rcnt (integer, count)
On FreeBSD:
@ -224,7 +228,7 @@ $ ./telegraf --config telegraf.conf --input-filter zfs --test
A short description for some of the metrics.
#### Arc Stats
#### ARC Stats
`arcstats_hits` Total amount of cache hits in the arc.
@ -283,12 +287,43 @@ A short description for some of the metrics.
`zfetchstats_hits` Counts the number of cache hits, to items which are in the cache because of the prefetcher.
`zfetchstats_misses` Counts the number of prefetch cache misses.
`zfetchstats_colinear_hits` Counts the number of cache hits, to items which are in the cache because of the prefetcher (prefetched linear reads)
`zfetchstats_stride_hits` Counts the number of cache hits, to items which are in the cache because of the prefetcher (prefetched stride reads)
#### Vdev Cache Stats
#### Vdev Cache Stats (FreeBSD only)
note: the vdev cache is deprecated in some ZFS implementations
`vdev_cache_stats_hits` Hits to the vdev (device level) cache.
`vdev_cache_stats_misses` Misses to the vdev (device level) cache.
#### ABD Stats (Linux Only)
ABD is a linear/scatter dual typed buffer for ARC
`abdstats_linear_cnt` number of linear ABDs which are currently allocated
`abdstats_linear_data_size` amount of data stored in all linear ABDs
`abdstats_scatter_cnt` number of scatter ABDs which are currently allocated
`abdstats_scatter_data_size` amount of data stored in all scatter ABDs
#### DMU Stats (Linux Only)
`dmu_tx_dirty_throttle` counts when writes are throttled due to the amount of dirty data growing too large
`dmu_tx_memory_reclaim` counts when memory is low and throttling activity
`dmu_tx_memory_reserve` counts when memory footprint of the txg exceeds the ARC size
#### Fault Management Ereport errors (Linux Only)
`fm_erpt-dropped` counts when an error report cannot be created (eg available memory is too low)
#### ZIL (Linux Only)
note: ZIL measurements are system-wide, neither per-pool nor per-dataset
`zil_commit_count` counts when ZFS transactions are committed to a ZIL

4
plugins/inputs/zfs/zfs.go
View File

@ -19,7 +19,9 @@ var sampleConfig = `
## By default, telegraf gather all zfs stats
## If not specified, then default is:
# kstatMetrics = ["arcstats", "zfetchstats", "vdev_cache_stats"]
## For Linux, the default is:
# kstatMetrics = ["abdstats", "arcstats", "dnodestats", "dbufcachestats",
# "dmu_tx", "fm", "vdev_mirror_stats", "zfetchstats", "zil"]
## By default, don't gather zpool stats
# poolMetrics = false
`

11
plugins/inputs/zfs/zfs_linux.go
View File

@ -80,7 +80,11 @@ func gatherPoolStats(pool poolInfo, acc telegraf.Accumulator) error {
func (z *Zfs) Gather(acc telegraf.Accumulator) error {
kstatMetrics := z.KstatMetrics
if len(kstatMetrics) == 0 {
kstatMetrics = []string{"arcstats", "zfetchstats", "vdev_cache_stats"}
// vdev_cache_stats is deprecated
// xuio_stats are ignored because as of Sep-2016, no known
// consumers of xuio exist on Linux
kstatMetrics = []string{"abdstats", "arcstats", "dnodestats", "dbufcachestats",
"dmu_tx", "fm", "vdev_mirror_stats", "zfetchstats", "zil"}
}
kstatPath := z.KstatPath
@ -104,7 +108,7 @@ func (z *Zfs) Gather(acc telegraf.Accumulator) error {
for _, metric := range kstatMetrics {
lines, err := internal.ReadLines(kstatPath + "/" + metric)
if err != nil {
return err
continue
}
for i, line := range lines {
if i == 0 || i == 1 {
@ -115,6 +119,9 @@ func (z *Zfs) Gather(acc telegraf.Accumulator) error {
}
rawData := strings.Split(line, " ")
key := metric + "_" + rawData[0]
if metric == "zil" || metric == "dmu_tx" || metric == "dnodestats" {
key = rawData[0]
}
rawValue := rawData[len(rawData)-1]
value, _ := strconv.ParseInt(rawValue, 10, 64)
fields[key] = value

192
plugins/inputs/zfs/zfs_linux_test.go
View File

@ -115,16 +115,133 @@ streams_resets 4 20989756
streams_noresets 4 503182328
bogus_streams 4 0
`
const vdev_cache_statsContents = `7 1 0x01 3 144 23617323692 12081684236238879
name type data
delegations 4 0
hits 4 0
misses 4 0
`
const pool_ioContents = `11 3 0x00 1 80 2225326830828 32953476980628
nread nwritten reads writes wtime wlentime wupdate rtime rlentime rupdate wcnt rcnt
1884160 6450688 22 978 272187126 2850519036 2263669418655 424226814 2850519036 2263669871823 0 0
`
const zilContents = `7 1 0x01 14 672 34118481334 437444452158445
name type data
zil_commit_count 4 77
zil_commit_writer_count 4 77
zil_itx_count 4 1
zil_itx_indirect_count 4 2
zil_itx_indirect_bytes 4 3
zil_itx_copied_count 4 4
zil_itx_copied_bytes 4 5
zil_itx_needcopy_count 4 6
zil_itx_needcopy_bytes 4 7
zil_itx_metaslab_normal_count 4 8
zil_itx_metaslab_normal_bytes 4 9
zil_itx_metaslab_slog_count 4 10
zil_itx_metaslab_slog_bytes 4 11
`
const fmContents = `0 1 0x01 4 192 34087340971 437562103532892
name type data
erpt-dropped 4 101
erpt-set-failed 4 202
fmri-set-failed 4 303
payload-set-failed 4 404
`
const dmu_txContents = `5 1 0x01 11 528 34103260832 437683925071438
name type data
dmu_tx_assigned 4 39321636
dmu_tx_delay 4 111
dmu_tx_error 4 222
dmu_tx_suspended 4 333
dmu_tx_group 4 444
dmu_tx_memory_reserve 4 555
dmu_tx_memory_reclaim 4 666
dmu_tx_dirty_throttle 4 777
dmu_tx_dirty_delay 4 888
dmu_tx_dirty_over_max 4 999
dmu_tx_quota 4 101010
`
const abdstatsContents = `7 1 0x01 21 1008 25476602923533 29223577332204
name type data
struct_size 4 33840
linear_cnt 4 834
linear_data_size 4 989696
scatter_cnt 4 12
scatter_data_size 4 187904
scatter_chunk_waste 4 4608
scatter_order_0 4 1
scatter_order_1 4 21
scatter_order_2 4 11
scatter_order_3 4 33
scatter_order_4 4 44
scatter_order_5 4 76
scatter_order_6 4 489
scatter_order_7 4 237483
scatter_order_8 4 233
scatter_order_9 4 4411
scatter_order_10 4 1023
scatter_page_multi_chunk 4 32122
scatter_page_multi_zone 4 9930
scatter_page_alloc_retry 4 99311
scatter_sg_table_retry 4 99221
`
const dbufcachestatsContents = `
15 1 0x01 11 2992 6257505590736 8516276189184
name type data
size 4 242688
size_max 4 338944
max_bytes 4 62834368
lowater_bytes 4 56550932
hiwater_bytes 4 69117804
total_evicts 4 0
hash_collisions 4 0
hash_elements 4 31
hash_elements_max 4 32
hash_chains 4 0
hash_chain_max 4 0
`
const dnodestatsContents = `
10 1 0x01 28 7616 6257498525011 8671911551753
name type data
dnode_hold_dbuf_hold 4 0
dnode_hold_dbuf_read 4 0
dnode_hold_alloc_hits 4 1460
dnode_hold_alloc_misses 4 0
dnode_hold_alloc_interior 4 0
dnode_hold_alloc_lock_retry 4 0
dnode_hold_alloc_lock_misses 4 0
dnode_hold_alloc_type_none 4 0
dnode_hold_free_hits 4 2
dnode_hold_free_misses 4 0
dnode_hold_free_lock_misses 4 0
dnode_hold_free_lock_retry 4 0
dnode_hold_free_overflow 4 0
dnode_hold_free_refcount 4 0
dnode_hold_free_txg 4 0
dnode_allocate 4 2
dnode_reallocate 4 0
dnode_buf_evict 4 6
dnode_alloc_next_chunk 4 1
dnode_alloc_race 4 0
dnode_alloc_next_block 4 0
dnode_move_invalid 4 0
dnode_move_recheck1 4 0
dnode_move_recheck2 4 0
dnode_move_special 4 0
dnode_move_handle 4 0
dnode_move_rwlock 4 0
dnode_move_active 4 0
`
const vdevmirrorcachestatsContents = `
18 1 0x01 7 1904 6257505684227 9638257816287
name type data
rotating_linear 4 0
rotating_offset 4 0
rotating_seek 4 0
non_rotating_linear 4 0
non_rotating_seek 4 0
preferred_found 4 0
preferred_not_found 4 43
`
var testKstatPath = os.TempDir() + "/telegraf/proc/spl/kstat/zfs"
@ -183,7 +300,16 @@ func TestZfsGeneratesMetrics(t *testing.T) {
err = ioutil.WriteFile(testKstatPath+"/zfetchstats", []byte(zfetchstatsContents), 0644)
require.NoError(t, err)
err = ioutil.WriteFile(testKstatPath+"/vdev_cache_stats", []byte(vdev_cache_statsContents), 0644)
err = ioutil.WriteFile(testKstatPath+"/zil", []byte(zilContents), 0644)
require.NoError(t, err)
err = ioutil.WriteFile(testKstatPath+"/fm", []byte(fmContents), 0644)
require.NoError(t, err)
err = ioutil.WriteFile(testKstatPath+"/dmu_tx", []byte(dmu_txContents), 0644)
require.NoError(t, err)
err = ioutil.WriteFile(testKstatPath+"/abdstats", []byte(abdstatsContents), 0644)
require.NoError(t, err)
intMetrics := getKstatMetricsAll()
@ -339,9 +465,55 @@ func getKstatMetricsAll() map[string]interface{} {
"zfetchstats_streams_resets": int64(20989756),
"zfetchstats_streams_noresets": int64(503182328),
"zfetchstats_bogus_streams": int64(0),
"vdev_cache_stats_delegations": int64(0),
"vdev_cache_stats_hits": int64(0),
"vdev_cache_stats_misses": int64(0),
"zil_commit_count": int64(77),
"zil_commit_writer_count": int64(77),
"zil_itx_count": int64(1),
"zil_itx_indirect_count": int64(2),
"zil_itx_indirect_bytes": int64(3),
"zil_itx_copied_count": int64(4),
"zil_itx_copied_bytes": int64(5),
"zil_itx_needcopy_count": int64(6),
"zil_itx_needcopy_bytes": int64(7),
"zil_itx_metaslab_normal_count": int64(8),
"zil_itx_metaslab_normal_bytes": int64(9),
"zil_itx_metaslab_slog_count": int64(10),
"zil_itx_metaslab_slog_bytes": int64(11),
"fm_erpt-dropped": int64(101),
"fm_erpt-set-failed": int64(202),
"fm_fmri-set-failed": int64(303),
"fm_payload-set-failed": int64(404),
"dmu_tx_assigned": int64(39321636),
"dmu_tx_delay": int64(111),
"dmu_tx_error": int64(222),
"dmu_tx_suspended": int64(333),
"dmu_tx_group": int64(444),
"dmu_tx_memory_reserve": int64(555),
"dmu_tx_memory_reclaim": int64(666),
"dmu_tx_dirty_throttle": int64(777),
"dmu_tx_dirty_delay": int64(888),
"dmu_tx_dirty_over_max": int64(999),
"dmu_tx_quota": int64(101010),
"abdstats_struct_size": int64(33840),
"abdstats_linear_cnt": int64(834),
"abdstats_linear_data_size": int64(989696),
"abdstats_scatter_cnt": int64(12),
"abdstats_scatter_data_size": int64(187904),
"abdstats_scatter_chunk_waste": int64(4608),
"abdstats_scatter_order_0": int64(1),
"abdstats_scatter_order_1": int64(21),
"abdstats_scatter_order_2": int64(11),
"abdstats_scatter_order_3": int64(33),
"abdstats_scatter_order_4": int64(44),
"abdstats_scatter_order_5": int64(76),
"abdstats_scatter_order_6": int64(489),
"abdstats_scatter_order_7": int64(237483),
"abdstats_scatter_order_8": int64(233),
"abdstats_scatter_order_9": int64(4411),
"abdstats_scatter_order_10": int64(1023),
"abdstats_scatter_page_multi_chunk": int64(32122),
"abdstats_scatter_page_multi_zone": int64(9930),
"abdstats_scatter_page_alloc_retry": int64(99311),
"abdstats_scatter_sg_table_retry": int64(99221),
}
arcMetrics := getKstatMetricsArcOnly()
for k, v := range otherMetrics {