Commit Graph

899 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
a8562d643b lib/promscrape: add -promscrape.dropOriginalLabels command-line flag for reducing memory usage when discovering big number of scrape targets
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/878
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/825
2020-11-10 00:20:49 +02:00
Aliaksandr Valialkin
b8083b7659 lib/promscrape: clean references to label name and label value strings after applying per-target relabeling
This should reduce memory usage when per-target relabeling creates big number of temporary labels
with long names and/or values.

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/825
2020-11-07 16:19:52 +02:00
Aliaksandr Valialkin
efebc3b6fb app/vmselect/promql: code cleanup after 43823addea 2020-11-06 01:31:33 +02:00
n4mine
3127aa92b5 app/vmselect/promql: fix when the parameter of maxValue(), minValue() leading by NaN. it will cause {top,bottom}k_{max,min} return inappropriate result (#883) 2020-11-06 01:31:31 +02:00
Aliaksandr Valialkin
767231f41f app/vmstorage/transport: properly handle request to labelValuesOnTimeRange 2020-11-05 02:08:04 +02:00
Aliaksandr Valialkin
72011bcc45 app/vmselect: properly handle errors in GetLabelsOnTimeRange and GetLabelValuesOnTimeRange 2020-11-05 01:36:34 +02:00
Aliaksandr Valialkin
c5e6c5f5a6 app/vmselect: optimize querying for /api/v1/labels and /api/v1/label/<name>/values when start and end args are set 2020-11-05 01:19:29 +02:00
Aliaksandr Valialkin
1336e47c86 docs/vmagent.md: update after 4c808d58bf 2020-11-04 20:33:49 +02:00
Nikolay
5b235b902b Adds ready probe (#874)
* adds leading forward slash check for scrapeURL path
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/835

* adds ready probe for scrape config initialization,
it should prevent metrics loss during vmagent rolling update,
/ready api will return 425 http code, if some scrape config still waits for initialization.

* updates docs

* Update app/vmagent/README.md

* renames var

* Update app/vmagent/README.md

Co-authored-by: Aliaksandr Valialkin <valyala@gmail.com>
2020-11-04 20:33:48 +02:00
Nikolay
d0a9b24c5a reduces memory usage for vmagent, (#880)
* reduces memory usage for vmagent,
limits count of droppedTarget, that can be stored for /api/v1/targets page up to 999 items,
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/878

* Update app/vmagent/README.md

* Update app/vmagent/README.md

Co-authored-by: Aliaksandr Valialkin <valyala@gmail.com>
2020-11-04 17:13:33 +02:00
Aliaksandr Valialkin
407a46c11e Revert "docs/vmagent.md: mention about -promscrape.dropOriginalLabels"
This reverts commit 1a80acc712.
2020-11-04 11:45:35 +02:00
Aliaksandr Valialkin
1a80acc712 docs/vmagent.md: mention about -promscrape.dropOriginalLabels 2020-11-04 11:16:16 +02:00
Aliaksandr Valialkin
887a3c317f app/vmagent/remotewrite: drop packets only on 409 status code, since there are other valid 4xx status codes, which shouldnt result in packet drop 2020-11-03 14:24:57 +02:00
Aliaksandr Valialkin
66de02fbb4 app/vmselect/promql: allow dropping trailing sample only for default_rollup function
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/850
2020-11-02 02:11:06 +02:00
Aliaksandr Valialkin
ca2e0f1e04 app/vmagent/remotewrite: drop packets if remote storage returns 4xx status code
This makes consistent the behaviour with Prometheus.
See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/873
2020-11-02 00:45:01 +02:00
Aliaksandr Valialkin
6b623eba02 app/vmselect/promql: go fmt 2020-11-02 00:18:24 +02:00
Aliaksandr Valialkin
7c0b658865 app/vmselect/promql: do not drop trailing datapoints for instant queries
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/845
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/748
2020-11-02 00:12:53 +02:00
Roman Khavronenko
333675875f vmalert: skip automatically added labels on alerts restore (#871)
Label `alertgroup` was introduced in #611 and automatically added to generated
time series. By mistake, this new label wasn't correctly purged on restore event
and affected alert's ID uniqueness. This commit removes `alertgroup` label
in restore function.

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/870
2020-11-01 23:26:00 +02:00
kreedom
40172c0721 vmbackup fix panic when no origin fs given (#859)
* use fsnil when no origin fs
2020-11-01 23:17:01 +02:00
Aliaksandr Valialkin
ed724d25ba lib/promscrape: add stream parse mode for efficient scraping of targets that expose millions of metrics 2020-11-01 23:12:26 +02:00
Aliaksandr Valialkin
abdf22e0bb app/vmagent: expose /api/v1/targets page according to https://prometheus.io/docs/prometheus/latest/querying/api/#targets
This page is exposed by vmagent and by a single-node VictoriaMetrics

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/643
2020-10-20 21:55:14 +03:00
Aliaksandr Valialkin
c4464594b7 app/vmselect/promql: allow passing optional third argument to topk_* and bottomk_* functions in order to obtain sum of time series outside top/bottom K 2020-10-20 20:09:55 +03:00
Aliaksandr Valialkin
9c5cd5a6c5 lib/storage: code cleanup after 5bfd4e6218 2020-10-20 16:10:53 +03:00
Aliaksandr Valialkin
0db7c2b500 app/vmstorage: support for -retentionPeriod smaller than one month
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/173
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/17
2020-10-20 14:42:46 +03:00
kreedom
4526cf92d3 vmalert - add dryRun (#842)
vmalert: add `dryRun` flag for rules validation without running the service
2020-10-20 10:49:22 +03:00
Seva Poliakov
e6bf9eaac7 Fix typo in vnrestore readme 2020-10-20 10:49:22 +03:00
Aliaksandr Valialkin
ee2902ddaf app/vmselect/promql: an attempt to improve heuristics for dropping trailing data points in time series
Now trailing data points are additionally dropped for time series with a single raw sample

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/748
2020-10-17 10:44:26 +03:00
Roman Khavronenko
d6155a3f33 vmalert: update docs to highlight the state restore requirements; (#833)
Address https://github.com/VictoriaMetrics/VictoriaMetrics/issues/830
2020-10-13 18:34:00 +03:00
Aliaksandr Valialkin
b9a4601c97 app/vmselect/promql: return a single time series at max from absent() function like Prometheus does 2020-10-13 15:56:10 +03:00
Aliaksandr Valialkin
217c192c88 app/vmselect/promql: improve time series staleness detection
This should prevent from double counting for time series at the time when it changes label.
The most common case is in K8S, which changes pod uid label with each new deployment.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/748
2020-10-13 12:20:08 +03:00
Aliaksandr Valialkin
f877e703c8 app/vmselect/promql: fix mode_over_time calculations
Previously `mode_over_time` could return garbage due to improper shuffling of input data points.
2020-10-13 11:58:30 +03:00
Aliaksandr Valialkin
d884ab13dc app/vmselect/prometheus: fix golangci-lint warning 2020-10-13 09:36:18 +03:00
Aliaksandr Valialkin
0867dea5fc app/vmselect: add ability to export data in CSV format via /api/v1/export/csv 2020-10-12 20:08:08 +03:00
Aliaksandr Valialkin
938b3b7ed1 lib/promscrape: code prettifying after 9bd9f67718 2020-10-12 16:13:59 +03:00
Nikolay Khramchikhin
7f96712b38 Adds dockerswarm sd (#818)
* adds dockerswarm service discovery

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/656

 Following roles supported: services, tasks and nodes.
 Basic, token and tls auth supported.
 Added tests for labels generation.

* added unix socket support to discovery utils

Co-authored-by: Aliaksandr Valialkin <valyala@gmail.com>
2020-10-12 16:13:58 +03:00
Aliaksandr Valialkin
2d03d0e2dd app/vmselect/promql: keep metric name after applying more functions, which dont change time series meaning
Functions are:

* keep_last_value
* keep_next_value
* interpolate
* running_min
* running_max
* running_avg
* range_min
* range_max
* range_avg
* range_first
* range_last
* range_quantile
* smooth_exponential

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/674
2020-10-12 11:48:38 +03:00
Aliaksandr Valialkin
3881c84afe Revert "app/vmselect/promql: remove metric name after applying ceil, floor and round functions in order to be more consistent with Prometheus"
This reverts commit ac45082216.

Reason for revert: the previous behavior for VictoriaMetrics is easier to understand and use by users -
functions, which don't change the meaning of the time series shouldn't drop metric name.

Now the following functions do not drop metric names:

* ceil
* floor
* round

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/674
2020-10-12 11:48:38 +03:00
Aliaksandr Valialkin
79d70480b7 Revert "app/vmselect/promql: remove metric name after applying clamp_min and clamp_max functions in order to be consistent with Prometheus"
This reverts commit bb61a4769b.

Reason for revert: the previous behavior for VictoriaMetrics is easier to understand and use by users -
functions, which don't change the meaning of the time series shouldn't drop metric name.

Now the following functions do not drop metric name:

* clamp_min
* clamp_max

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/674
2020-10-12 11:48:38 +03:00
Aliaksandr Valialkin
8c37b63ea9 Revert "app/vmselect/promql: remove metric name from results of certain rollup functions in order to be consistent with Prometheus"
This reverts commit e5202a4eae.

Reason for revert: the previous behavior for VictoriaMetrics is easier to understand and use by users -
functions, which don't change the meaning of the time series shouldn't drop metric name.

Now the following functions do not drop metric name:

* max_over_time
* min_over_time
* avg_over_time
* quantile_over_time
* geomean_over_time
* mode_over_time
* holt_winters
* predict_linear

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/674
2020-10-12 11:48:38 +03:00
Aliaksandr Valialkin
de1c07b937 lib/backup: add MustStop() method for all remote filesystems 2020-10-09 15:32:13 +03:00
Aliaksandr Valialkin
bf6d523bef lib/backup/fslocal: add FS.MustStop() method for stopping bandwidth limiter 2020-10-09 15:11:55 +03:00
Aliaksandr Valialkin
9b7ce5d004 app/{vminsert,vmagent}: take into account all the inserted rows before relabeling in vm_rows_inserted_total and vmagent_rows_inserted_total metrics 2020-10-09 13:38:49 +03:00
Aliaksandr Valialkin
d2e917d1cb app/vmstorage: add vm_rows_added_to_storage_total metric, which shows the total number of rows added to storage since app start 2020-10-09 13:36:17 +03:00
Aliaksandr Valialkin
4b1c401790 app/vmalert: accept days, weeks and years in for: part of config like Prometheus does
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/817
2020-10-08 20:13:20 +03:00
Aliaksandr Valialkin
35b8ffaa17 docs/vmagent.md: clarify -promscrape.suppressDuplicateScrapeTargetErrors command-line flag usage 2020-10-08 19:24:05 +03:00
Aliaksandr Valialkin
0d44e371f3 lib/promscrape: add -promscrape.suppressDuplicateScrapeTargetErrors command-line flag in order to suppress duplicate scrape target errors
Show also original labels for duplicate targets in error message in order to simplify debugging the issue.

Now `/targets` endpoint accepts optional `show_original_labels=1` query arg, which shows original labels for each target.
This may simplify debugging for target relabeling.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/651
2020-10-08 18:59:25 +03:00
Aliaksandr Valialkin
f9f8e4a39c app/vmalert: do not pring description for all the flags on config errors
The description is too big to consume by human and it just distracts humans.
2020-10-08 13:35:46 +03:00
Aliaksandr Valialkin
f6ee6efc34 app/vmselect/promql: add missing label filters to binary operands before query execution
This implements the optimization described at https://utcc.utoronto.ca/~cks/space/blog/sysadmin/PrometheusLabelNonOptimization

See also https://github.com/cortexproject/cortex/issues/3253
2020-10-07 21:17:11 +03:00
Dmitry Shihovtsev
aec863e70b Fix typos in the vmalert datasource (#814)
* Fix typos in the vmalert datasource

* Fix typo in the vmalert datasource test
2020-10-07 18:00:29 +03:00
Aliaksandr Valialkin
b51fa16177 app/vmstorage: add -finalMergeDelay command-line flag for configuring the delay before final merge for per-month partitions after no new data is ingested to it 2020-10-07 17:42:31 +03:00
Aliaksandr Valialkin
c4d309aa41 app/vmagent: add a link to https://victoriametrics.github.io/vmagent.html from main page 2020-10-06 15:30:07 +03:00
Aliaksandr Valialkin
abfd3a8fab app/{vminsert,vmselect,vmstorage}: add a link to https://victoriametrics.github.io/Cluster-VictoriaMetrics.html from main page of every cluster component 2020-10-06 15:30:07 +03:00
Nikolay Khramchikhin
b4c77fc6d2 Adds openstack sd (#811)
* adds openstack service discovery

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/728

 implemented hypervisors and instance discovery with openstack v3 api.
 Added tests for labeling and data parsing.
 Added token refresh.

* Apply suggestions from code review

* Apply suggestions from code review

Co-authored-by: Aliaksandr Valialkin <valyala@gmail.com>
2020-10-05 16:48:54 +03:00
Aliaksandr Valialkin
3e0c473cc9 app/vmselect/promql: fill gaps on graphs for range_* and running_* functions
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/806
2020-10-02 14:02:47 +03:00
Aliaksandr Valialkin
fd7dd5064a lib/storage: code cleanup after 10f2eedee0
Remove the code that uses metricIDs caches for the current and the previous hour during metricIDs search,
since this code became unused after implementing per-day inverted index almost a year ago.

While at it, fix a bug, which could prevent from finding time series with names containing dots (aka Graphite-like names
such as `foo.bar.baz`).
2020-10-01 19:12:04 +03:00
Roman Khavronenko
368b890e11 vmalert: make maxIdleConnections configurable for datasource HTTP client (#797)
Address https://github.com/VictoriaMetrics/VictoriaMetrics/issues/795
2020-09-30 09:51:14 +03:00
Aliaksandr Valialkin
536aa8779a app/vmstorage: rename vm_{big|small}_merge_need_free_disk_space to vm_merge_need_free_disk_space
This simplifies alerting.
2020-09-29 22:53:33 +03:00
Aliaksandr Valialkin
097a4c10dd app/vmstorage: add metrics for determining whether background merges need additional disk space to complete
These metrics are:

* vm_small_merge_need_free_disk_space
* vm_big_merge_need_free_disk_space

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/686
2020-09-29 21:47:47 +03:00
Aliaksandr Valialkin
5dca7bbe85 app/vmagent/remotewrite: do not show -remoteWrite.url in logs if -remoteWrite.showURL isn't set
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/773
2020-09-29 19:49:19 +03:00
Aliaksandr Valialkin
61f4801b93 app/vmselect/graphite: do not substitute path and path. with path.. in /metrics/find/?format=completer output 2020-09-29 18:03:45 +03:00
Aliaksandr Valialkin
f4d74ccfec docs/{vmbackup,vmrestore}: formatting fixes 2020-09-29 13:19:13 +03:00
Aliaksandr Valialkin
5179df7082 docs/vmbackup.md: make docs about minio config more prominent 2020-09-29 13:16:34 +03:00
Aliaksandr Valialkin
79b00f7b6b docs: improve readability a bit 2020-09-29 13:05:05 +03:00
Nikolay Khramchikhin
d77f56fd97 update vmbackup/vmrestore README usage (#794)
* update vmbackup/vmrestore README usage

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/381

with minio and configuration file examples.

* Apply suggestions from code review

Co-authored-by: Roman Khavronenko <hagen1778@gmail.com>

* added backup/restore docs changes

* added example for relabelConfig flag

* Apply suggestions from code review

Co-authored-by: Aliaksandr Valialkin <valyala@gmail.com>
Co-authored-by: Roman Khavronenko <hagen1778@gmail.com>
2020-09-29 13:05:04 +03:00
Aliaksandr Valialkin
0d082cdf53 app/vmselect/netstorage: remove unused code 2020-09-29 11:55:08 +03:00
Aliaksandr Valialkin
c47972d843 app/vmselect/prometheus: check for errors returned from bufferedwriter.Write
This makes `make errcheck` happy
2020-09-29 11:36:54 +03:00
Aliaksandr Valialkin
e66f7edfc9 app/vmselect/graphite: properly handle case when /metrics/find finds both leaf and node for the given query=prefix.*
In this case only node must be returned with stripped dot in the end of id as carbonapi does
2020-09-29 11:29:38 +03:00
Aliaksandr Valialkin
ffa6581c46 app/vminsert: refresh the list of healthy storage nodes only if the the row cannot be sent to destination storage node
Previously the list had been generated for each rerouted row. This could consume additional CPU time during rerouting,
which could lead to rerouting slowdown.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/791
2020-09-29 01:29:24 +03:00
Aliaksandr Valialkin
bc37f1cbec app/vminsert: do not pollute logs with repated cannot dial storageNode errors
Log only the first error per -storageNode
2020-09-29 00:20:32 +03:00
Aliaksandr Valialkin
2ee0dc27a6 app/vmstorage: parallelize data processing obtained from a single connection from vminsert
Previously vmstorage could use only a single CPU core for data processing from a single connection from vminsert.
Now all the CPU cores can be used for data processing from a single connection from vminsert.
This should improve the maximum data ingestion performance for a single vminsert->vmstorage connection.
2020-09-28 21:41:16 +03:00
Aliaksandr Valialkin
9d123eb22a app/vminsert: remove useless delays when sending data to vmstorage
This improves the maximum data ingestion performance for cluster VictoriaMetrics

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/791
2020-09-28 21:41:15 +03:00
Aliaksandr Valialkin
8df33bd5c1 app/{vminsert,vmagent}: improve data ingestion speed over a single connection
Process data obtianed from a single connection on all the available CPU cores.
2020-09-28 04:14:51 +03:00
Aliaksandr Valialkin
6d8c23fdbd app/{vminsert,vmselect}: skip accountID and projectID when marshaling/unmarshaling MetricName in /api/v1/export/native and /api/v1/import/native
This is needed in order to be able to migrate native data from/to single-node VictoriaMetrics
2020-09-28 00:58:58 +03:00
Aliaksandr Valialkin
db14f22fc0 app/vmselect: stop /api/v1/export/* execution if client disconnects 2020-09-27 23:52:42 +03:00
Aliaksandr Valialkin
aadbd014ff all: add native format for data export and import
The data can be exported via [/api/v1/export/native](https://victoriametrics.github.io/#how-to-export-data-in-native-format) handler
and imported via [/api/v1/import/native](https://victoriametrics.github.io/#how-to-import-data-in-native-format) handler.
2020-09-27 17:36:38 +03:00
Aliaksandr Valialkin
e83947a882 app/vminsert: code prettifying 2020-09-26 04:16:14 +03:00
Aliaksandr Valialkin
8fc9b77496 app/vmagent: reduce memory usage when importing data via /api/v1/import
Previously vmagent could use big amounts of RAM when each ingested JSON line
contained many samples.
2020-09-26 04:10:13 +03:00
Aliaksandr Valialkin
973df09686 app/vmselect/netstorage: do not spend CPU time on unpacking empty blocks during /api/v1/series calls 2020-09-24 20:44:15 +03:00
Aliaksandr Valialkin
b8bce348c5 app/vmselect/promql: properly limit implicitly set rollup window to -search.maxStalenessInterval
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/784
2020-09-23 23:24:09 +03:00
Aliaksandr Valialkin
543f3aea97 all: consistently use "%w" formatting in fmt.Errorf for wrapped errors 2020-09-23 22:48:21 +03:00
Aliaksandr Valialkin
8627365b48 app/vmselect/prometheus: code cleanup after 3ba507000c 2020-09-23 13:04:51 +03:00
Aliaksandr Valialkin
1fce79518a app/vmselect/prometheus: return timestamps from /api/v1/query, which match the time query arg
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/720
2020-09-23 12:59:23 +03:00
Aliaksandr Valialkin
0468cdf33e app/vmselect/netstorage: properly pre-allocate space for sbs 2020-09-22 23:51:01 +03:00
Aliaksandr Valialkin
69eb9783e6 app/vmselect: make sure the request doesnt wait in pending queue more than the configured timeout
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
2020-09-22 01:21:42 +03:00
Aliaksandr Valialkin
ed473c94ff docs/vmagent.md: typo fix 2020-09-21 21:49:08 +03:00
Aliaksandr Valialkin
e564725641 app/vmselect/searchutils: fixed tests after 2eb72e09ab 2020-09-21 21:31:28 +03:00
Aliaksandr Valialkin
07c6226334 app/vmselect: use time value rounded to seconds if it isnt passed to /api/v1/query
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/720
2020-09-21 21:24:46 +03:00
Nikolay Khramchikhin
0069353d5e Add improvements to ec2_sd_discovery (#775)
* Add improvements to ec2 discovery

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/771

 role_arn support with aws sts
 instance iam_role support
 refreshing temporary tokens

* Apply suggestions from code review

Co-authored-by: Roman Khavronenko <hagen1778@gmail.com>

* changed implementation, removed tests, clean up code

* moved endpoint builder into getEC2APIResponse

Co-authored-by: Roman Khavronenko <hagen1778@gmail.com>
2020-09-21 16:05:01 +03:00
Aliaksandr Valialkin
8cd89cb847 app/vmalert: remove unneeded UTC() call
UTC() doesn't change the underlying timestamp, so the call isn't needed here
2020-09-21 15:56:48 +03:00
Roman Khavronenko
d111969d39 vmalert: add support for datasource.lookback flag (#779)
New datasource flag `datasource.lookback` defines how far to look into
past when evaluating queries.

Address https://github.com/VictoriaMetrics/VictoriaMetrics/issues/668
2020-09-21 15:56:47 +03:00
Roman Khavronenko
0042b0f307 vmalert: fix the typo in error message (#782)
The error will be always nil so no sense in printing it.
2020-09-21 11:36:09 +03:00
Aliaksandr Valialkin
1c07d7bee7 app/vmagent: increase default value for -remoteWrite.queues from 1 to 4, since it has been appeared that many users hit this limit 2020-09-18 14:22:02 +03:00
Aliaksandr Valialkin
a1bebb660c app/vmselect/graphite: return proper results /metrics/find?query=foo.*.bar according to Graphite Metrics API 2020-09-18 11:53:28 +03:00
Aliaksandr Valialkin
9b15b11f74 app/vmstorage: added -forceMergeAuthKey command-line flag for protecting /internal/force_merge endpoint 2020-09-17 14:24:20 +03:00
Aliaksandr Valialkin
d96858b921 lib/storage: add /internal/force_merge handler for running forced compactions on historical per-month partitions
This may be useful for freeing up storage space after time series deletion.

See https://victoriametrics.github.io/#force-merge for more details.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/686
2020-09-17 12:20:56 +03:00
Aliaksandr Valialkin
406f4fe445 app/vmagent: substitute -remoteWrite.url with secret-url value in logs, since it may contain sensitive info such as passwords or auth tokens
Pass `-remoteWrite.showURL` command-line flag in order to see real `-remoteWrite.url` values in logs and at `/metrics` page.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/773
2020-09-16 22:36:18 +03:00
Aliaksandr Valialkin
9793008734 app/vmselect: add -search.storageTimeout command-line flag for limiting the maximum duration of query execution per each -storageNode
See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
2020-09-16 21:33:47 +03:00
Aliaksandr Valialkin
a9205fe308 app/vmselect: prevent from closing connection to vmstorage on query timeout by setting +2 secs deadline on connection comparing to query deadline
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
2020-09-16 21:14:00 +03:00
Aliaksandr Valialkin
1587f83fa0 app/vmselect/netstorage: typo fix after 03dfccfbed 2020-09-16 00:10:33 +03:00
Aliaksandr Valialkin
03dfccfbed app/vmselect/netstorage: reduce memory usage when the time range from query touches big number of samples per each time series 2020-09-15 21:08:09 +03:00
Aliaksandr Valialkin
27cd5555e6 app/vmselect/netstorage: mention that RunParallel or Cancel must be called on the returned results from ProcessSearchQuery 2020-09-15 20:39:43 +03:00
Aliaksandr Valialkin
1f0c0b0f6b app/vmselect: typo fix in -search.maxStalenessInterval description 2020-09-15 14:25:34 +03:00
Roman Khavronenko
e2b31590e6 vmalert: add Group name as label to generated alerts and timeseries (#761)
Solves #611
2020-09-11 23:41:12 +03:00
Roman Khavronenko
16e0bb496e vmalert: update groups on config reload only if changes detected (#759)
On config reload event `vmalert` reloads configuration for every group. While
it works for simple configurations, the more complex and heavy installations may
suffer from frequent config reloads.
The change introduces the `checksum` field for every group and is set to md5 hash
of yaml configuration. The checksum will change if on any change to group
definition like rules order or annotation change. Comparing the `checksum` field
on config reload event helps to detect if group should be updated.
The groups update is now done concurrently, so reload duration will be limited by
the slowest group now.

Partially solves #691 by improving config reload speed.
2020-09-11 23:41:12 +03:00
Aliaksandr Valialkin
b776a93608 app/vmselect/promql: support composite durations like Prometheus 2.21 does
The following durations are supported now: `1h5m35s` or `1s543ms`

See https://github.com/prometheus/prometheus/releases/tag/v2.21.0
and https://github.com/prometheus/prometheus/pull/7713
2020-09-11 22:17:24 +03:00
Aliaksandr Valialkin
6382e8081a app/vmagent: allow setting multiple identical -remoteWrite.url values
This may be useful when each url is authenticated via different `-remoteWrite.basicAuth.username`.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/755
2020-09-11 15:17:29 +03:00
Aliaksandr Valialkin
d3ad0d365e app/vmselect: move Deadline from netstorage to searchutils
This removes dependency on netstorage from searchutils.
2020-09-11 13:39:13 +03:00
Aliaksandr Valialkin
58d3b82ae5 app/{vminsert,vmagent}: allow passing timestamp via timestamp query arg when ingesting data to /api/v1/import/prometheus
See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/750
2020-09-11 13:28:31 +03:00
Aliaksandr Valialkin
579c20756a app/vmselect: substitute inf values at smooth_exponential with the previous values
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/757
2020-09-11 12:23:56 +03:00
Aliaksandr Valialkin
d67e6d3d2e app/vmselect: skip infinite values when calculating smooth_exponential
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/757
2020-09-11 11:57:53 +03:00
Aliaksandr Valialkin
06427a184f app/vmselect/graphite: typo fix in label name for vm_request_duration_seconds metric 2020-09-11 01:59:52 +03:00
Aliaksandr Valialkin
f307e6f432 app/vmselect: initial implementation of Graphite Metrics API
See https://graphite-api.readthedocs.io/en/latest/api.html#the-metrics-api
2020-09-11 00:30:20 +03:00
Aliaksandr Valialkin
f5cb213ef9 lib/storage: reuse timestamp blocks for adjancent metric blocks with identical timestamps
This should reduce disk space usage when scraping targets containing metrics with identical names
such as `node_cpu_seconds_total`, histograms, quantiles, etc.

Expose `vm_timestamps_blocks_merged_total` and `vm_timestamps_bytes_saved_total` metrics for monitoring
the effectiveness of timestamp blocks merging.
2020-09-09 23:59:21 +03:00
Aliaksandr Valialkin
475698d2ad docs: sync docs for vmalert, vmauth, vmbackup and vmrestore 2020-09-09 21:10:48 +03:00
Aliaksandr Valialkin
5ab57f916b docs/vmagent.md: clarified the case when -remoteWrite.queues must be tuned
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/745
2020-09-08 20:15:49 +03:00
Aliaksandr Valialkin
f3a79abfb4 app/vmselect/promql: go fmt 2020-09-08 15:18:57 +03:00
Aliaksandr Valialkin
4f06eed1c1 app/vmselect/promql: adjust integrate() calculations to be more similar to calculations from InfluxDB: attempt #2
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/701
2020-09-08 14:36:23 +03:00
Aliaksandr Valialkin
0d0b606455 app/vmselect/promql: adjust integrate() calculations to be more similar to calculations from InfluxDB
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/701
2020-09-08 14:24:02 +03:00
Aliaksandr Valialkin
db91045348 app/vmselect/promql: increase floating point calculations accuracy by dividing by 1e3 instead of multiplying by 1e-3 2020-09-08 14:01:02 +03:00
Aliaksandr Valialkin
804304c365 app/vmselect: add missing deletion for temporary files on partial responses when -search.denyPartialResponse=true 2020-09-04 02:23:12 +03:00
Aliaksandr Valialkin
478d8f8393 app/vmselect/promql: add count_le_over_time(m[d], le) and count_gt_over_time(m[d], gt) functions
These functions returns the number of raw samples that don't exceed `le` or are bigger than `gt`.
These functions are complement to already existing `share_le_over_time(m[d], le)` and `share_gt_over_time(m[d], gt)`.
2020-09-03 15:28:58 +03:00
Aliaksandr Valialkin
3490160fd0 app/vmselect: unconditionally align time range boundaries to step for subqueries as Prometheus does 2020-09-03 13:22:06 +03:00
Aliaksandr Valialkin
a3cdef6b06 app/vmagent: properly flush big blocks of data
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/741

Thanks to @IceRain00 for the investigation and initial attempt to fix the issue
at https://github.com/VictoriaMetrics/VictoriaMetrics/pull/742
2020-09-03 12:12:12 +03:00
Aliaksandr Valialkin
de216bab41 app/vmagent: fix data race when accessing writeRequest.lastFlushTime 2020-09-03 12:12:09 +03:00
Nikolay Khramchikhin
80a9dc79fe changed vmalert behaviour (#738)
* VMAlert start with empty rules dir

There are some applications (operator for instance), that generates alerts configuration at runtime
and vmalert must start correctly without rules to support this behaviour.
Later application will add rules files and send SIGHUP to vmalert,
which will trigger reading rules files and start rules exectuion.

Removing rules files with SIGHUP signal must stop rules execution and
vmalert will wait for new rules.

* imports sorted

* added test cases for empty rules, removed blank line

* fixed imports conflict

* updated tests
2020-09-03 11:07:40 +03:00
Aliaksandr Valialkin
7ac10ee978 app/vmalert: imrovements over 3f932c2db1 2020-09-03 01:14:30 +03:00
DexterZhang
85f49ad439 feat: spread load of rule evaluation by group when starting new groups (#724)
* feat: spread load of rule evaluation by group when starting new groups

* review: reduce the resulting diff.

* Update app/vmalert/group.go

Co-authored-by: Roman Khavronenko <hagen1778@gmail.com>

Co-authored-by: Aliaksandr Valialkin <valyala@gmail.com>
Co-authored-by: Roman Khavronenko <hagen1778@gmail.com>
2020-09-03 01:14:26 +03:00
Aliaksandr Valialkin
4fa97430d7 app/{vminsert,vmagent}: allow adding extra labels when importing data via Prometheus, CSV and JSON line formats
Extra labels may be added to the imported data by passing `extra_label=name=value` query args.
Multiple query args may be passed in order to add multiple extra labels.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/719
2020-09-02 19:47:02 +03:00
Aliaksandr Valialkin
fe08b1eb26 app/vminsert: improve error message when the data cannot be sent to vmstorage - log reroutedBR buffer size
This should improve debuggability for improperly configured cluster
2020-08-31 17:51:44 +03:00
Aliaksandr Valialkin
6f9c1bc078 app/vmagent: log unsuccessful attempt number when sending data to -remoteWrite.url 2020-08-30 21:40:15 +03:00
Aliaksandr Valialkin
3b1ecac04b app/vmagent: apply sane limits to -remoteWrite.queues
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/707
2020-08-30 21:25:51 +03:00
Roman Khavronenko
08b76cb26f vmalert: update -rule flag description to enforce quotes using (#709)
Description for `-rule` flag uses as example specific chars like asterisks
which could be interpreted wrong by different shells. To avoid this, description
now contains quoted flag values.

See also #708
2020-08-28 09:46:35 +03:00
Roman Khavronenko
4b89da9463 lib/decimal: rename significant decimal digits to significant figures (#698)
The previous notion was inconsistent with what `decimal.Round` does.
According to [wiki](https://en.wikipedia.org/wiki/Significant_figures) rounding
applied to all significant figures, not just decimal ones.
2020-08-16 17:22:40 +03:00
Aliaksandr Valialkin
6aab2f4989 all: allow using KB, MB, GB, KiB, MiB and GiB suffixes in command-line flag values related to byte sizes or byte rates 2020-08-16 17:08:28 +03:00
Aliaksandr Valialkin
285665e93b app/vmselect/promql: allow passing multiple args to aggregate functions such as avg(q1, q2, q3) 2020-08-15 01:15:16 +03:00
Aliaksandr Valialkin
a2021d0dde docs/vmagent.md: mention that gaps in remote storage may appear if vmagent cannot keep up with data ingestion 2020-08-14 20:48:17 +03:00
Aliaksandr Valialkin
e7c0b2ca56 docs: update docs 2020-08-14 19:14:46 +03:00
Aliaksandr Valialkin
b996280c65 app/{vminsert,vmagent}: improve documentation for -influxListenAddr command-line flag 2020-08-14 18:03:08 +03:00
Aliaksandr Valialkin
60c7397be5 all: support %{ENV_VAR} placeholders in yaml configs in all the vm* components
Such placeholders are substituted by the corresponding environment variable values.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/583
2020-08-13 17:17:06 +03:00
Aliaksandr Valialkin
6721e47ae9 app: respect CPU limits set via cgroups
Update GOMAXPROCS to limits set via cgroups. This should reduce CPU trashing and reduce memory usage
for cases when VictoriaMetrics components run in containers with CPU limits.

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/685
2020-08-11 23:01:03 +03:00
Aliaksandr Valialkin
62b6e54622 app/vmselect: reduce memory usage when exporting time series with big number of samples via /api/v1/export if max_rows_per_line is set to non-zero value
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/685
2020-08-10 20:57:43 +03:00
Aliaksandr Valialkin
c9f5c5623f app/vmselect/netstorage: vary batch size for data unpacking depending on the available CPU cores
This should reduce contention on the channel with unpack work for systems with high number of CPU cores
2020-08-10 15:16:48 +03:00
Aliaksandr Valialkin
b3d4ff7ee2 app/vmstorage: improve error logging when the request times out 2020-08-10 13:17:24 +03:00
Roman Khavronenko
78afc61896 app/vmalert: extend metrics set exported by vmalert #573 (#654)
* app/vmalert: extend metrics set exported by `vmalert` #573

New metrics were added to improve observability:
+ vmalert_alerts_pending{alertname, group} - number of pending alerts per group
per alert;
+ vmalert_alerts_acitve{alertname, group} - number of active alerts per group
per alert;
+ vmalert_alerts_error{alertname, group} - is 1 if alertname ended up with error
during prev execution, is 0 if no errors happened;
+ vmalert_recording_rules_error{recording, group} - is 1 if recording rule
 ended up with error during prev execution, is 0 if no errors happened;
* vmalert_iteration_total{group, file} - now contains group and file name labels.
This should improve control over specific groups;
* vmalert_iteration_duration_seconds{group, file} - now contains group and file name labels. This should improve control over specific groups;

Some collisions for alerts and recording rules are possible, because neither
group name nor alert/recording rule name are unique for compatibility reasons.

Commit contains list of TODOs for Unregistering metrics since groups and rules
are ephemeral and could be removed without application restart. In order to
unlock Unregistering feature corresponding PR was filed - https://github.com/VictoriaMetrics/metrics/pull/13

* app/vmalert: extend metrics set exported by `vmalert` #573

The changes are following:
* add an ID label to rules metrics, since `name` collisions within one group is
a common case - see the k8s example alerts;
* supports metrics unregistering on rule updates. Consider the case when one rule
was added or removed from the group, or the whole group was added or removed.

The change depends on https://github.com/VictoriaMetrics/metrics/pull/16
where race condition for Unregister method was fixed.
2020-08-09 09:42:05 +03:00
ofen
3fea7c39be 401 Unauthorize HTTP error added (#681)
401 Unauthorize HTTP error added to trigger browser credentials pop-up promt [RFC 7235 https://developer.mozilla.org/en-US/docs/Web/HTTP/Authentication]
2020-08-09 09:39:37 +03:00
Aliaksandr Valialkin
67cacb22ac lib/httpserver: add -tls, -tlsCertFile and -tlsKeyFile command-line flags in every vm binary
This makes such binaries compatible with binaries from `master` branch (aka single-node version)

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/677
2020-08-07 10:57:32 +03:00
Aliaksandr Valialkin
95a8c492ef app/vmselect/promql: properly handle -n^m like Prometheus does
`-n^m` must be handled as `-(n^m)` instead of `(-n)^m`.

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/675
2020-08-07 07:42:42 +03:00
Aliaksandr Valialkin
7f93d61a56 app/vmselect/promql: remove metric name after applying clamp_min and clamp_max functions in order to be consistent with Prometheus
This improves VictoriaMetrics score at https://promlabs.com/promql-compliance-test-results-victoriametrics/
2020-08-06 23:42:55 +03:00
Aliaksandr Valialkin
01000505a0 app/vmselect/promql: remove metric name after applying ceil, floor and round functions in order to be more consistent with Prometheus
This improves VictoriaMetrics score at https://promlabs.com/promql-compliance-test-results-victoriametrics/
2020-08-06 23:34:03 +03:00
Aliaksandr Valialkin
75bff1a567 app/vmselect/promql: remove metric name from results of certain rollup functions in order to be consistent with Prometheus
Rollup functions:

  - avg_over_time
  - min_over_time
  - max_over_time
  - quantile_over_time

This improves VictoriaMetrics results at https://promlabs.com/promql-compliance-test-results-victoriametrics/
2020-08-06 23:29:18 +03:00
Aliaksandr Valialkin
8835004a4c app/vmselect: properly handle PromQL queries like scalar1 < metric < scalar2 like Prometheus does
This fixes some cases from https://promlabs.com/promql-compliance-test-results-victoriametrics/
2020-08-06 23:21:14 +03:00
Aliaksandr Valialkin
14ddb8a34e app/vmselect/netstorage: reduce CPU contention when upacking time series blocks by unpacking batches of such blocks instead of a single block
This should improve query performance on systems with big number of CPU cores (16 and more)
2020-08-06 17:50:13 +03:00
Aliaksandr Valialkin
46c98cd97a app/vmselect/netstorage: reduce contention on unpackworkCh and timeseriesWorkCh for multi-CPU system by providing more capacity for these chans 2020-08-06 17:22:39 +03:00
Aliaksandr Valialkin
a455930ab4 app/vmstorage: rename vm_cache_size_entries{type="storage/prefetchedMetricIDs"} to vm_cache_entries{type="storage/prefetchedMetricIDs"} to be consistent with other vm_cache_entries metrics 2020-08-06 16:34:18 +03:00
Aliaksandr Valialkin
a3e91c593b lib/storage: limit the number of concurrent calls to storage.searchTSIDs to GOMAXPROCS*2
This should limit the maximum memory usage and reduce CPU trashing on vmstorage
when multiple heavy queries are executed.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/648
2020-08-05 18:27:21 +03:00
Aliaksandr Valialkin
a930460236 app/vmagent: tune http client for sending data to remote storage in order to disable closing keep-alive connections
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/663
2020-08-04 21:01:40 +03:00
Aliaksandr Valialkin
a04f4a3d9a app/vmselect: use warning level instead of info level for logging slow queries that take longer than -search.logSlowQueryDuration 2020-08-04 20:24:38 +03:00
Aliaksandr Valialkin
bdb881c43b app/vmselect/promql: add zscore-related functions: zscore_over_time(m[d]) and zscore(q) by (...) 2020-08-03 21:52:15 +03:00
Aliaksandr Valialkin
94471a1273 app: remove duplicate *-pure makefile rules 2020-07-31 20:01:30 +03:00
Aliaksandr Valialkin
a2aa3a60eb app/vmselect: show X-Forwarded-For contents on /api/v1/status/active_queries page
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/659
2020-07-31 20:01:09 +03:00
Aliaksandr Valialkin
106e302d7a all: add mssing APP_NAME to vm*-GOARCH builds 2020-07-31 13:45:32 +03:00
Aliaksandr Valialkin
945645f38f docs/{vmagent,vmalert}: add instruction on how to build for ARM 2020-07-31 09:25:41 +03:00
Aliaksandr Valialkin
0c00fe70cf app/vmselect: do not adjust start and end query args passed to /api/v1/query_range when -search.disableCache command-line flag is set
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/563
2020-07-30 23:14:56 +03:00
Aliaksandr Valialkin
29bbab0ec9 lib/storage: remove prioritizing of merging small parts over merging big parts, since it doesn't work as expected
The prioritizing could lead to big merge starvation, which could end up in too big number of parts that must be merged into big parts.

Multiple big merges may be initiated after the migration from v1.39.0 or v1.39.1. It is OK - these merges should be finished soon,
which should return CPU and disk IO usage to normal levels.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/648
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/618
2020-07-30 20:02:22 +03:00
Aliaksandr Valialkin
338ee47d60 app/vmselect/promql: return non-empty value from rate_over_sum(m[d]) even if a single data point is located in the given [d] window
Just divide the data point value by the window duration in this case.
2020-07-29 12:37:34 +03:00
Aliaksandr Valialkin
717c554fb0 app/vmselect/promql: remove rollupFuncArg.realPrevValue handling, since the corner case in increase() is handled in another way now
See e00cfc854d for the approach used now.
2020-07-29 12:37:34 +03:00
Aliaksandr Valialkin
d9037b3970 app/vmselect/promql: fill gaps with 0 in rate_over_sum response when the last value before the selected time window isnt empty 2020-07-29 12:37:34 +03:00
Aliaksandr Valialkin
f6d4275087 app/{vmagent,vminsert}: properly preserve db tag from query string passed to Influx line protocol query
Previously `db` tag from the query string wasn't added to metrics after encountering `db` tag in the Influx line

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/653
2020-07-28 21:25:49 +03:00
Aliaksandr Valialkin
baebe86844 app/vmagent/remotewrite: add missing resp.Body.Close() after pushing data to remote storage
Missing body close could disable HTTP keep-alive connections.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/653
2020-07-28 21:00:25 +03:00
Aliaksandr Valialkin
0f6f0d30d3 app/vmselect: show query origin (aka remote_addr or client address) on the /api/v1/status/active_queries page for every query 2020-07-28 15:14:40 +03:00
Roman Khavronenko
ec6ed467c6 app/vmalert: support external.label to specify global labelset for all rules #622 (#652)
`external.label` flag supposed to help to distinguish alert or recording rules
source in situations when more than one `vmalert` runs for the same datasource
or AlertManager.
2020-07-28 14:23:04 +03:00
Aliaksandr Valialkin
9dccedc599 app/vmselect/promql: return empty values from group() if all the time series have no values at the given timestamp
This aligns `group()` behaviour to Prometheus
2020-07-28 13:41:04 +03:00
Aliaksandr Valialkin
d5057f6d04 app/vmagent/remotewrite: create new request on failure to send a block of data to remote storage
Previously the request body was already consumed before the retry, so this led to the following error:

    http: ContentLength=... with Body length 0
2020-07-27 17:33:05 +03:00
Aliaksandr Valialkin
b191e425b3 app/vmselect/promql: improve further the accuracy of buckets_limit() function
The accuracy is increased by mergin the smallest bucket with the smallest adjacent bucket.
2020-07-26 12:10:56 +03:00
Aliaksandr Valialkin
43871e79c6 app/vmselect/promql: avoid dropping inf bucket in buckets_limit
The `le="inf"` bucket must be preserved in order to maintain the maximum level of accuracy.
2020-07-25 17:00:25 +03:00
Aliaksandr Valialkin
978c1e930e app/vmselect/promql: optimize buckets_limit(k, buckets) for big number of buckets 2020-07-25 13:24:33 +03:00
Aliaksandr Valialkin
51cbf27077 app/vmselect/promql: improve the accuracy of buckets_limit(k, buckets) function
Now it properly merges the bucket with the previous bucket after deletion.
2020-07-24 17:07:30 +03:00
Aliaksandr Valialkin
cf69b1ea6f app/vmselect/promql: add buckets_limit(k, buckets) function, which limits the number of buckets per time series to k
This function works with both Prometheus-style and VictoriaMetrics-style buckets.
The function removes buckets with the lowest values in order to reserve the highest precision.
The function is useful for building heatmaps in Grafana from too big number of buckets.
2020-07-24 16:14:12 +03:00
Aliaksandr Valialkin
45334f61de app/vmselect: fix tests for rate_over_sum 2020-07-24 02:35:09 +03:00
Aliaksandr Valialkin
3526e8768a app/vmselect/promql: typo fix after 3e557c9861 2020-07-24 02:15:23 +03:00
Aliaksandr Valialkin
8d1721d128 app/vmselect/promql: add rate_over_sum(m[d]) function to MetricsQL, which returns rate over sum of m values over d duration
Something like `sum_over_time(m[d]) / d`, but more accurate.
2020-07-24 01:17:15 +03:00
Aliaksandr Valialkin
88e8bed0c9 app/vmselect/promql: allow setting [d] window smaller than the interval between raw points for avg_over_time
This makes `avg_over_time` behavior consistent with `sum_over_time` and `count_over_time` behaviors.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/636
2020-07-23 22:25:33 +03:00
Aliaksandr Valialkin
fb3d1380ac lib/storage: respect -search.maxQueryDuration when searching for time series in inverted index
Previously the time spent on inverted index search could exceed the configured `-search.maxQueryDuration`.
This commit stops searching in inverted index on query timeout.
2020-07-23 21:22:05 +03:00
Aliaksandr Valialkin
dbf3038637 lib/storage: add more fine-grained pace limiting for search 2020-07-23 19:21:49 +03:00
Aliaksandr Valialkin
16a4b1b20c app/vmselect/netstorage: protect from too smart compiler, which may break memory usage optimization in tmpBlocksFileWrapper.WriteBlocks 2020-07-23 17:57:24 +03:00
Aliaksandr Valialkin
0750d2cec1 app/vminsert: export vm_relabel_metrics_dropped_total metric that shows the number of metrics dropped due to relabeling 2020-07-23 14:58:02 +03:00
Aliaksandr Valialkin
55ed07add1 app/vmselect: typo fix after 0168e21fe32776e2f7f003f88e0e6e490eb2dcb0g 2020-07-23 14:11:15 +03:00
Aliaksandr Valialkin
7aa5b48508 app/vmselect: reduce memory usage when querying big number of time series with long labels
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/646
2020-07-23 13:48:58 +03:00
Aliaksandr Valialkin
49a0011837 app/vminsert: do not call ApplyRelabeling function if relabeling is disabled
This should reduce CPU usage a bit when `-relabelConfig` isn't set
2020-07-23 13:35:36 +03:00
Aliaksandr Valialkin
c91ccce50c app/vminsert: fix relabeling for metrics ingested via Influx line protocol
Previously the enabled relabeling with `-relabelConfig` command-line flag could result in missing labels
if a single Influx line protocol message contains multiple field values.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/638
2020-07-23 13:25:37 +03:00
Aliaksandr Valialkin
b8303afcd8 lib/storage: improve prioritizing of data ingestion over querying
Prioritize also small merges over big merges.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/291
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/648
2020-07-23 01:40:38 +03:00
Aliaksandr Valialkin
20d0c41ac5 app/vmselect/prometheus: support d, w and y suffixes for durations passed to step in /api/v1/query_range like Prometheus does
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/641
2020-07-22 16:27:27 +03:00
Aliaksandr Valialkin
bd4299fafe app/vmselect/netstorage: reduce memory allocations when unpacking time series data by using a pool for unpackWork entries
This should slightly reduce load on GC when processing queries that touch big number of time series.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/646 according to the provided memory profile
2020-07-22 15:04:42 +03:00
Aliaksandr Valialkin
a3f48e395e app/vmagent: add -remoteWrite.decimalPlaces command-line flag, which may be used for reducing disk space usage on the remote storage 2020-07-21 21:55:42 +03:00
Aliaksandr Valialkin
5bb4fe1ba4 app/vmselect: take into account the time spent in wait queue before query execution as time spent on the query 2020-07-21 19:00:00 +03:00
Aliaksandr Valialkin
0755cb3b50 app/vmselect/promql: skip the first value in time series passed to increase() if it exceeds by more than 10x the delta between the next value and the first value
This should prvent from inflated `increase()` results for time series that start from big initial values.
Such cases may occur when a label value changes in a metric without counter reset.
2020-07-21 17:24:28 +03:00
Aliaksandr Valialkin
71eba8dcf5 app/vmselect: log the total available memory for concurrent requests on not enough memory errors
This should simplify root cause analysis
2020-07-20 19:51:58 +03:00
Aliaksandr Valialkin
3b246aa569 app/vmagent: add -remoteWrite.proxyURL command-line option
This option allows writing data to `-remoteWrite.url` via http, https or socks5 proxy.
This is similar to `proxy_url` option in `remote_write` section of Prometheus.
See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write
2020-07-20 19:31:08 +03:00
Aliaksandr Valialkin
8bee3ef91b docs/vmagent.md: sync with app/vmagent/README.md 2020-07-20 17:09:30 +03:00
Roman Khavronenko
8949ec961d app/vmagent: mention grafana dashboard in README (#639) 2020-07-20 17:09:27 +03:00