Commit Graph

6317 Commits

Author SHA1 Message Date
Zakhar Bessarab
f3a51e8b1d
app/vmagent: add -remoteWrite.removeDanglingQueues flag (#4017)
* app/vmagent: add `-remoteWrite.removeDanglingQueues` flag which allows to automatically remove dangling persistent queue contents

Related issue: #4014

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

* app/vmagent: address review feedback

- remove persistent queues files by default
- rename `remoteWrite.removeDanglingQueues` to `remoteWrite.keepDanglingQueues`
- update docs to reflect changed behaviour

Related issue: #4014

* Apply suggestions from code review

---------

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-03-27 18:15:28 -07:00
Nikolay
9b1e002287
app/vmselect: properly remove temp files at windows system (#4020)
With non-posix compliant systems it's not possible to remove unclosed files.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-27 18:10:15 -07:00
Aliaksandr Valialkin
02ee4ffd4d
app/vmselect/promql: follow-up for 79e1c6a6fc
- Document the fix at docs/CHANGELOG.md
- Add tests with multiple adjancent zero buckets
- Simplify the fix a bit

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/296
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4021
2023-03-27 18:03:36 -07:00
Ze'ev Klapow
79e1c6a6fc
fix le buckets when adjacent vmrange is empty (#4021)
There is a bug here where if you have a single bucket like:

foo{vmrange="4.084e+02...4.642e+02"} 2 123

The expected output is three le encoded buckets like:

foo{le="4.084e+02"} 0 123
foo{le="4.642e+02"} 2 123
foo{le="+Inf"} 2 123

This correctly encodes the start and end of the vmrange.
If however, the input contains the previous bucket, and that bucket is
empty then you only get the end le and +Inf out currently, i.e:

foo{vmrange="7.743e+05...8.799e+05"} 5 123
foo{vmrange="6.813e+05...7.743e+05"} 0 123

results in:

foo{le="8.799e+05"} 5 123
foo{le="+Inf"} 5 123

This causes issues when you go to compute a quantile because this means
that the assumed lower bound of the buckets is 0 and this we interpolate
between 0->end rather than the vmrange start->end as expected.
2023-03-27 17:54:19 -07:00
Aliaksandr Valialkin
9e02b3d48a
vendor: make vendor-update 2023-03-27 15:28:02 -07:00
Aliaksandr Valialkin
622000797a
app/vmselect: follow-up for 10ab086366
- Expose stats.seriesFetched at `/api/v1/query_range` responses too
  for the sake of consistency.

- Initialize QueryStats when it is needed and pass it to EvalConfig then.
  This guarantees that the QueryStats is properly collected when the query
  contains some subqueries.
2023-03-27 15:22:00 -07:00
Roman Khavronenko
4021aa11b5
app/vmselect: export seriesFetched stat for /query responses (#3925)
The change adds a new field `seriesFetched` to EvalConfig object.
Since EvalConfig object can be copied inside `Exec`,
`seriesFetched` is a pointer which can be updated by all copied
objects.

The reason for having stats is that other components, like vmalert,
could benefit from this information.

Signed-off-by: hagen1778 <roman@victoriametrics.com>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-03-27 15:18:25 -07:00
Yury Molodov
3214b1c315
vmui: heatmap (#3780)
* fix: add stroke and font for all axes

* feat: add util for generate gradient

* feat: add heatmap plugin

* feat: add heatmap legend

* feat: add heatmap graph (#3384)

* vmui: add heatmap graph (#3384)

* feat: add convert Prometheus to VictoriaMetrics histogram

* fix: prevent re-render graph

* feat: reset step for heatmap

* feat: normalize heatmap data

* fix: format heatmap legend

* wip

* app/vmselect/vmui: run `make vmui-update`

---------

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-03-26 00:30:02 -07:00
Aliaksandr Valialkin
92199c964c
docs/MetricsQL.md: quote min, max and avg args for rollup_*() functions in order to reduce the level of confusion when users try to pass the second argument to these functions 2023-03-26 00:01:51 -07:00
Aliaksandr Valialkin
72a0b49330
docs/CHANGELOG.md: document v1.87.4 LTS release 2023-03-25 22:43:59 -07:00
Aliaksandr Valialkin
5832242b44
app/vmselect/netstorage: reduce the contention at fs.ReaderAt stats collection on systems with big number of CPU cores
This optimization is based on the profile provided at https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3966#issuecomment-1483208419
2023-03-25 16:37:07 -07:00
Aliaksandr Valialkin
a1e496ced6
app/vmselect/netstorage: document why runtime.Gosched() is removed at 28f054bb00
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3966
2023-03-25 16:36:51 -07:00
Zakhar Bessarab
28f054bb00
vmselect/netstorage: remove direct calls to Gosched to reduce amount of locks for global scope
using `runtime.Gosched` requires acquiring global lock to check if there are any other goroutines to perform tasks. with the latest versions of runtime it can pause running goroutines automatically without requiring to call `Gosched` directly.

Updates #3966

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
2023-03-25 16:34:03 -07:00
Aliaksandr Valialkin
811f4a9380
app/{vmbackup,vmrestore}: publish vmbackup and vmrestore binaries for Windows
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 15:08:21 -07:00
Aliaksandr Valialkin
c8f2febaa1
lib/storage: consistently use OS-independent separator in file paths
This is needed for Windows support, which uses `\` instead of `/` as file separator

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 14:33:58 -07:00
Aliaksandr Valialkin
36bbdd7d4b
lib/mergeset: consistently use OS-independent separator in file paths
This is needed for Windows support, which uses `\` instead of `/` as file separator

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 13:39:41 -07:00
Aliaksandr Valialkin
b14d96618c
all: follow-up after 34634ec357
- Use windows.FlushFileBuffers() instead of windows.Fsync() at streamTracker.adviseDontNeed()
  for consistency with implementations for other architectures.
- Use filepath.Base() instead of filepath.Split(), since the dir part isn't used.
  This simplifies the code a bit.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 11:57:39 -07:00
Nikolay
34634ec357
lib/fs: adds memory map for windows (#3988)
This is a follow-up for 43b24164ef

* lib/fs: adds memory map for windows
it should improve performance for file reading

* lib/storage: replace '/' with os specific separator
it must fix an errors for windows

* lib/fs: mention windows fsync support

* lib/filestream: adds fdatasync for windows writes

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 11:43:19 -07:00
Aliaksandr Valialkin
2b851e69d2
app/vmselect/promql: typo fix after e7f46a0aab 2023-03-24 23:46:30 -07:00
Aliaksandr Valialkin
e7f46a0aab
app/vmselect/promql: follow-up for 7205c79c5a
- Allocate and initialize seriesByWorkerID slice in a single go instead
  of initializing every item in the list separately.
  This should reduce CPU usage a bit.
- Properly set anti-false sharing padding at timeseriesWithPadding structure
- Document the change at docs/CHANGELOG.md

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3966
2023-03-24 23:34:37 -07:00
Zakhar Bessarab
7205c79c5a
app/vmselect/promql: use lock-less approach to gather results of parallel processing for evalRollup* funcs (#4004)
* vmselect/promql: refactor `evalRollupNoIncrementalAggregate` to use lock-less approach for parallel workers computation

Locking there is causing issues when running on highly multi-core system as it introduces lock contention during results merge.

New implementation uses lock less approach to store results per workerID and merges final result in the end, this is expected to significantly reduce lock contention and CPU usage for systems with high number of cores.

Related: #3966
Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

* vmselect/promql: add pooling for `timeseriesWithPadding` to reduce allocations

Related: #3966
Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

* vmselect/promql: refactor `evalRollupFuncWithSubquery` to avoid using locks

Uses same approach as `evalRollupNoIncrementalAggregate` to remove locking between workers and reduce lock contention.

Related: #3966
Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

---------

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
2023-03-24 23:07:12 -07:00
Aliaksandr Valialkin
9436ae3b07
app/vmbackup: simplify code a bit after 5ba347bd2c
Unconditionally call deleteSnapshot() func just after making the snapshot, either successful or unsuccessful

Related issue: https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2055
2023-03-24 22:03:14 -07:00
Zakhar Bessarab
5ba347bd2c
app/vmbackup: delete created snapshot in case of error during backup (#4008)
Related issue: #2055

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-03-24 21:49:58 -07:00
Aliaksandr Valialkin
25446a7933
vendor: run make vendor-update 2023-03-24 18:08:06 -07:00
Aliaksandr Valialkin
ebc1caa5dc
app/vmselect/vmui: run make vmui-update after dc2c712a29 2023-03-24 18:01:39 -07:00
Aliaksandr Valialkin
27f9a1eda2
docs/CHANGELOG.md: cosmetic fixes: remove trailing whitespace and consistently use -flag instead of --flag 2023-03-24 15:44:33 -07:00
Alexander Marshalov
7c86dcc4fa
allowed using dashes and dots in environment variables names (#4009)
* allowed using dashes and dots in environment variables names for templating config files with envtemplate (#3999)

Signed-off-by: Alexander Marshalov <_@marshalov.org>

* Apply suggestions from code review

---------

Signed-off-by: Alexander Marshalov <_@marshalov.org>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-03-24 15:43:05 -07:00
Aliaksandr Valialkin
c1d871a45a
docs/vmauth.md: follow-up for 36edba9bfb
- Document `-configCheckInterval` command-line flag in `quick start` section
- Clarify the addition of `-configCheckInterval` at docs/CHANGELOG.md

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3990
2023-03-24 13:22:37 -07:00
Aliaksandr Valialkin
54796f69db
docs/vmagent.md: clarify that there is no need to specify multiple -remoteWrite.url options when writing data to a single VictoriaMetrics cluster when data replication is needed
Also add a link to https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#url-format from `getting started` section,
so users could quickly find how to write data to VictoriaMetrics cluster
2023-03-24 13:07:33 -07:00
Roman Khavronenko
365d2ff0bf
vmalert: add anchor char to Group's link (#4006)
This should help users to see that Group's name is clickable
and used for anchoring.

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2023-03-24 09:48:43 +01:00
Roman Khavronenko
8db6a71f83
vmalert: mention VMUI example for alert's source (#4005)
Signed-off-by: hagen1778 <roman@victoriametrics.com>
2023-03-24 09:40:55 +01:00
Roman Khavronenko
edeb56d208
docs: mention cluster URL for exporting series (#4002)
docs: mention cluster URL for exporting series

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2023-03-23 20:55:47 +01:00
Daria Karavaieva
24938872a6
Vmanomaly guide (#3834)
Setting up VMAnomaly on NodeExporter metrics with VictoriaMetrics and AlertManager.


* vmanomaly-guide-draft

* aletr graphs and description

* readme vmanomaly tutorial

* Added back fit_every param for performance

* vmanomaly guide fixes

* added spaces div

* spaces + resize image

* alert example grammar

* quotation marks

* docker link

* typo fixed

* more links

* reader section rephrased

* label change

* lower case for grafana service

* lower case for vm service

* yaml markdown

---------

Co-authored-by: Dima Lazerka <dima@victoriametrics.com>
2023-03-23 21:04:44 +02:00
Dmytro Kozlov
ba505dd357
docs: follow up after dc2c712a29 (#4001) 2023-03-23 18:27:55 +01:00
Dmytro Kozlov
dc2c712a29
app/vmui: update cardinality page (#3986)
vmui: update cardinality page

---------

Co-authored-by: Yury Moladau <yurymolodov@gmail.com>
2023-03-23 18:18:02 +01:00
Yury Molodov
023c65968f
vmui: display errors for each query individually (#3987) (#3994) 2023-03-23 13:10:59 +01:00
Alexander Marshalov
36edba9bfb
added configCheckInterval flag for vmauth (#3990) (#3991)
* added configCheckInterval flag for vmauth (#3990)
Signed-off-by: Alexander Marshalov <_@marshalov.org>
2023-03-23 09:34:12 +01:00
Nikolay
a2f716b6cc
lib/netutil: log only parsing errors for proxy-protocol (#3985)
* lib/netutil: log only parsing errors for proxy-protocol

Previosly every error was logged. With configured TCP health checks at load-balancer or kubernetes, vmauth spams a lot of false positive error message into logs

* Update docs/CHANGELOG.md

Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>

* Update lib/netutil/tcplistener.go

Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>

---------

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>
2023-03-21 10:22:39 -07:00
Dmytro Kozlov
f0b09a1382
app/vmctl: follow up after aed59b9029 (#3983) 2023-03-21 15:53:53 +01:00
Aliaksandr Valialkin
6a78755b66
docs/vmagent.md: mention in docs that the target relabel debug page shows target url now 2023-03-20 22:20:03 -07:00
Dmytro Kozlov
e79cd24807
lib/promrelabel: make target url from labels on target relabel page (#3882)
* lib/promrelabel: make target url from labels on target relabel page

* wip

---------

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-03-20 22:07:52 -07:00
Aliaksandr Valialkin
e480b9881e
app/vmselect/promql: pass workerID to the callback inside doParallel()
This opens the possibility to remove tssLock from evalRollupFuncWithSubquery()
in the follow-up commit from @zekker6 in order to speed up the code
for systems with many CPU cores.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3966
2023-03-20 20:54:57 -07:00
Aliaksandr Valialkin
9e16329b2f
app/vmselect/promql: fix TestIncrementalAggr test on systems less than 3 CPU cores
This is a follow-up for 4856a4cf5a
2023-03-20 20:37:18 -07:00
Aliaksandr Valialkin
70959d5dab
app/vmselect/netstorage: reduce the number of calls to runtime.Gosched() at timeseriesWorker() and unpackWorker()
Call runtime.Gosched() only when there is a work to steal from other workers.
Simplify the timeseriesWorker() and unpackWroker() code a bit by inlining stealTimeseriesWork() and stealUnpackWork().

This should reduce CPU usage when processing queries on systems with big number of CPU cores.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3966
2023-03-20 20:31:02 -07:00
Aliaksandr Valialkin
4856a4cf5a
app/vmselect: optimize incremental aggregates a bit
Substitute sync.Map with an ordinary slice indexed by workerID.
This should reduce the overhead when updating the incremental aggregate state
2023-03-20 15:37:06 -07:00
Aliaksandr Valialkin
8622dee4b5
app/vmselect/vmui: make vmui-update after d4525bd2d0 2023-03-20 14:35:03 -07:00
Aliaksandr Valialkin
8d709f3483
docs/CHANGELOG.md: cosmetic fixes 2023-03-20 14:14:20 -07:00
Aliaksandr Valialkin
91533531f5
docs/Troubleshooting.md: document an additional case, which could result in slow inserts
If `-cacheExpireDuration` is lower than the interval between ingested samples for the same time series,
then vm_slow_row_inserts_total` metric is increased.

See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3976#issuecomment-1476883183
2023-03-20 13:28:36 -07:00
Roman Khavronenko
3283f0dae4
vmalert: support logs suppressing during config reloads (#3973)
* vmalert: support logs suppressing during config reloads

The change is mostly required for ENT version of vmalert,
since it supports object-storage for config files.
Reading data from object storage could be time-consuming,
so vmalert emits logs to track the progress.

However, these logs are mostly needed on start or on
manual config reload. Printing these logs each time
`rule.configCheckInterval` is triggered would too verbose.
So the change allows to control logs emitting during
config reloads.

Now, logs are emitted during start up or when SIGHUP is receieved.
For periodicall config checks logs emitted by config pkg are suppressed.

Signed-off-by: hagen1778 <roman@victoriametrics.com>

* vmalert: review fixes

Signed-off-by: hagen1778 <roman@victoriametrics.com>

---------

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2023-03-20 16:08:30 +01:00
Dmytro Kozlov
8da9502df6
app/vmctl: automatically check tty (#3938)
app/vmctl: automatically detect if TTY is available
2023-03-20 11:16:08 +01:00