Commit graph

757 commits

Author SHA1 Message Date
SuperQ 25b0991c3d
Enable additional Go metrics
Enable some additioal Go runtime metrics in order to observe additional
performance data.

Enables a number of new metrics:
```
HELP go_gc_cycles_automatic_gc_cycles_total Count of completed GC cycles generated by the Go runtime.
HELP go_gc_cycles_forced_gc_cycles_total Count of completed GC cycles forced by the application.
HELP go_gc_cycles_total_gc_cycles_total Count of all completed GC cycles.
HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function.
HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function.
HELP go_gc_heap_allocs_by_size_bytes Distribution of heap allocations by approximate size. Bucket counts increase monotonically. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_allocs_bytes_total Cumulative sum of memory allocated to the heap by the application.
HELP go_gc_heap_allocs_objects_total Cumulative count of heap allocations triggered by the application. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_frees_by_size_bytes Distribution of freed heap allocations by approximate size. Bucket counts increase monotonically. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_frees_bytes_total Cumulative sum of heap memory freed by the garbage collector.
HELP go_gc_heap_frees_objects_total Cumulative count of heap allocations whose storage was freed by the garbage collector. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_goal_bytes Heap size target for the end of the GC cycle.
HELP go_gc_heap_live_bytes Heap memory occupied by live objects that were marked by the previous GC.
HELP go_gc_heap_objects_objects Number of objects, live or unswept, occupying heap memory.
HELP go_gc_heap_tiny_allocs_objects_total Count of small allocations that are packed together into blocks. These allocations are counted separately from other allocations because each individual allocation is not tracked by the runtime, only their block. Each block is already accounted for in allocs-by-size and frees-by-size.
HELP go_gc_limiter_last_enabled_gc_cycle GC cycle the last time the GC CPU limiter was enabled. This metric is useful for diagnosing the root cause of an out-of-memory error, because the limiter trades memory for CPU time when the GC's CPU time gets too high. This is most likely to occur with use of SetMemoryLimit. The first GC cycle is cycle 1, so a value of 0 indicates that it was never enabled.
HELP go_gc_pauses_seconds Deprecated. Prefer the identical /sched/pauses/total/gc:seconds.
HELP go_gc_scan_globals_bytes The total amount of global variable space that is scannable.
HELP go_gc_scan_heap_bytes The total amount of heap space that is scannable.
HELP go_gc_scan_stack_bytes The number of bytes of stack that were scanned last GC cycle.
HELP go_gc_scan_total_bytes The total amount space that is scannable. Sum of all metrics in /gc/scan.
HELP go_gc_stack_starting_size_bytes The stack size of new goroutines.
HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously.
HELP go_sched_goroutines_goroutines Count of live goroutines.
HELP go_sched_latencies_seconds Distribution of the time goroutines have spent in the scheduler in a runnable state before actually running. Bucket counts increase monotonically.
HELP go_sched_pauses_stopping_gc_seconds Distribution of individual GC-related stop-the-world stopping latencies. This is the time it takes from deciding to stop the world until all Ps are stopped. This is a subset of the total GC-related stop-the-world time (/sched/pauses/total/gc:seconds). During this time, some threads may be executing. Bucket counts increase monotonically.
HELP go_sched_pauses_stopping_other_seconds Distribution of individual non-GC-related stop-the-world stopping latencies. This is the time it takes from deciding to stop the world until all Ps are stopped. This is a subset of the total non-GC-related stop-the-world time (/sched/pauses/total/other:seconds). During this time, some threads may be executing. Bucket counts increase monotonically.
HELP go_sched_pauses_total_gc_seconds Distribution of individual GC-related stop-the-world pause latencies. This is the time from deciding to stop the world until the world is started again. Some of this time is spent getting all threads to stop (this is measured directly in /sched/pauses/stopping/gc:seconds), during which some threads may still be running. Bucket counts increase monotonically.
HELP go_sched_pauses_total_other_seconds Distribution of individual non-GC-related stop-the-world pause latencies. This is the time from deciding to stop the world until the world is started again. Some of this time is spent getting all threads to stop (measured directly in /sched/pauses/stopping/other:seconds). Bucket counts increase monotonically.
```

Signed-off-by: SuperQ <superq@gmail.com>
2024-05-28 10:53:04 +02:00
Arve Knudsen b2396c0c8f Upgrade to golangci-lint v1.59.0
Signed-off-by: Arve Knudsen <arve.knudsen@gmail.com>
2024-05-27 22:38:48 +02:00
Björn Rabenstein 1081e336a0
Merge pull request #14129 from prometheus/beorn7/doc
doc: Clarify the limits of dumping/backfilling via OpenMetrics
2024-05-23 13:37:42 +02:00
Björn Rabenstein 5c85a55e3f
Merge pull request #14120 from kushalShukla-web/remote
added some lines prometheus.md and main.go
2024-05-21 17:49:33 +02:00
beorn7 3127a4029e doc: Clarify the limits of dumping/backfilling via OpenMetrics
This is about native histograms (not yet supported) and staleness
markers (for which OpenMetrics support isn't even planned).

Signed-off-by: beorn7 <beorn@grafana.com>
2024-05-21 14:50:06 +02:00
Björn Rabenstein 3119b8a055
Merge pull request #13218 from machine424/ro-promtool
Make DBReadOnly more RO
2024-05-21 13:27:40 +02:00
kushagra Shukla 0fea1065fe added line When set, query.max-concurrency may need to be adjusted accordingly. Signed-off-by: kushagra Shukla <kushalshukla110@gmail.com>
Signed-off-by: kushagra Shukla <kushalshukla110@gmail.com>
2024-05-18 07:26:59 -04:00
Oleksandr Redko f10c3454e9 Enable perfsprint linter and fix up code
Signed-off-by: Oleksandr Redko <oleksandr.red+github@gmail.com>
2024-05-15 17:51:05 +03:00
Bryan Boreham 8fd96241ab test: add promqltest package references
To packages outside of promql.

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2024-05-08 16:08:04 +01:00
Arthur Silva Sens 0305490e4e
Merge pull request #13987 from prometheus/nativeHis-flag-ingestion
bugfix: Decouple native histogram ingestions and protobuf parsing
2024-04-25 10:56:40 -03:00
Arthur Silva Sens 7aacef9b42
bugfix: Decouple native histogram ingestions and protobuf parsing
Up until this point, if a scrape was done with the protobuf format Prometheus would always try to ingest native histograms even with the feature flag disabled. This causes problems with other feature-flags that depend on the protobuf format, like 'created-timestamp-zero-ingestion'. This commit decouples native histogram parsing from ingestion, making sure ingestion only happens when the 'native-histogram' feature-flag is enabled.

Signed-off-by: Arthur Silva Sens <arthur.sens@coralogix.com>
2024-04-24 17:02:52 -03:00
Will Hegedus bd1878700b
promtool: Fix panic on extended tsdb analyze (#13976)
Currently, running promtool tsdb analyze with the --extended flag
will cause an 'index out of range' error if running it
against a block that does not have any native histogram chunks.

This change ensures that promtool won't try to display data that doesn't exist.

Signed-off-by: Will Hegedus <whegedus@linode.com>
2024-04-24 11:35:34 +10:00
machine424 c5a1cc9148
chore(tsdb): add a sandboxDir to DBReadOnly, the directory can be used for transient file writes.
use it in loadDataAsQueryable to make sure the RO Head doesn't truncate or cut new chunks in data/chunks_head/.

add a -sandbox-dir-root flag to "promtool tsdb dump/dump-openmetrics" to control the root of that sandbox dirrectory.

Signed-off-by: machine424 <ayoubmrini424@gmail.com>
2024-04-15 17:00:25 +02:00
Matthieu MOREL 6f595c6762
golangci-lint: enable whitespace linter (#13905)
Signed-off-by: Matthieu MOREL <matthieu.morel35@gmail.com>
2024-04-11 09:27:54 +01:00
Matthieu MOREL d496687c8e golangci-lint: enable usestdlibvars linter
Signed-off-by: Matthieu MOREL <matthieu.morel35@gmail.com>
2024-04-08 19:26:23 +00:00
Bryan Boreham fc567a1df8
Merge pull request #13889 from komisan19/refactor/utilize_standard_functions_max/min
refactor: utilize standard functions max/min in promtool and tsdb
2024-04-06 10:23:18 +01:00
komisan19 0249e080b4 refactor: utilize standard functions max/min
Signed-off-by: komisan19 <18901496+komisan19@users.noreply.github.com>
2024-04-04 03:15:38 +09:00
Arthur Silva Sens db64d2dcdc
Update documentation about existing feature-flags
Signed-off-by: Arthur Silva Sens <arthur.sens@coralogix.com>
2024-04-02 19:18:57 -03:00
Artur Melanchyk 44dcf02c69
TSDB: make total lock-free by using atomic
Signed-off-by: Artur Melanchyk <artur.melanchyk@gmail.com>
2024-03-23 19:51:29 +01:00
Bryan Boreham 773170f372
Merge pull request #13822 from dgl/promtool-test-errors
promtool: Avoid using testify for user rule tests
2024-03-23 09:42:34 +01:00
David Leadbeater 7ec4a11472 promtool: Avoid using testify for user rule tests
Using testify outside of unit tests results in panics rather than a
useful error for the user.

Fixes #13703

Signed-off-by: David Leadbeater <dgl@dgl.cx>
2024-03-21 22:08:10 +11:00
heyitao c7ca85388f Fix yaml file format and clear ci errors
Signed-off-by: heyitao <heyitao@uniontech.com>
2024-03-21 11:32:02 +08:00
machine424 3eed6c760a
adjust signal termination warning log
Signed-off-by: machine424 <ayoubmrini424@gmail.com>
2024-03-14 18:45:45 +01:00
Arthur Silva Sens 07355c9199
Bump client_golang to 1.19
Signed-off-by: Arthur Silva Sens <arthur.sens@coralogix.com>
2024-03-06 09:11:13 -03:00
Bryan Boreham e79b9ed2ab
Merge pull request #13194 from machine424/open
promtool: add a "tsdb dump-openmetrics" to dump in OpemMetrics format.
2024-02-28 17:46:59 +00:00
machine424 4b71f6ffc2
promtool: add a "tsdb dump-openmetrics" to dump in OpemMetrics format.
This closes the loop, as the output can be fed into "tsdb create-blocks-from openmetrics"

Native histograms are not supported.

Signed-off-by: machine424 <ayoubmrini424@gmail.com>
2024-02-28 15:34:18 +01:00
machine424 f477e0539a
Move from golang.org/x/exp/slices into slices now that we only support Go >= 1.21
Prevent adding back golang.org/x/exp/slices.

Signed-off-by: machine424 <ayoubmrini424@gmail.com>
2024-02-28 14:54:53 +01:00
Bryan Boreham eff3a13e19 model/textparse: parsers take a labels SymbolTable
This allows strings to be interned to save memory.

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2024-02-26 11:45:25 +00:00
Łukasz Mierzwa 5597020a60 Use github.com/klauspost/compress for gzip and zlib
klauspost/compress is a high quality drop-in replacement for common Go
compression libraries. Since Prometheus sends out a lot of HTTP requests
that often return compressed output having improved compression
libraries helps to save cpu & memory resources.
On a test Prometheus server I was able to see cpu reduction from 31 to
30 cores.

Benchmark results:

name                                old time/op    new time/op    delta
TargetScraperGzip/metrics=1-8         69.4µs ± 4%    69.2µs ± 3%     ~     (p=0.122 n=50+50)
TargetScraperGzip/metrics=100-8       84.3µs ± 2%    80.9µs ± 2%   -4.02%  (p=0.000 n=48+46)
TargetScraperGzip/metrics=1000-8       296µs ± 1%     274µs ±14%   -7.35%  (p=0.000 n=47+45)
TargetScraperGzip/metrics=10000-8     2.06ms ± 1%    1.66ms ± 2%  -19.34%  (p=0.000 n=47+45)
TargetScraperGzip/metrics=100000-8    20.9ms ± 2%    17.5ms ± 3%  -16.50%  (p=0.000 n=49+50)

name                                old alloc/op   new alloc/op   delta
TargetScraperGzip/metrics=1-8         6.06kB ± 0%    6.07kB ± 0%   +0.24%  (p=0.000 n=48+48)
TargetScraperGzip/metrics=100-8       7.04kB ± 0%    6.89kB ± 0%   -2.17%  (p=0.000 n=49+50)
TargetScraperGzip/metrics=1000-8      9.02kB ± 0%    8.35kB ± 1%   -7.49%  (p=0.000 n=50+50)
TargetScraperGzip/metrics=10000-8     18.1kB ± 1%    16.1kB ± 2%  -10.87%  (p=0.000 n=47+47)
TargetScraperGzip/metrics=100000-8    1.21MB ± 0%    1.01MB ± 2%  -16.69%  (p=0.000 n=36+50)

name                                old allocs/op  new allocs/op  delta
TargetScraperGzip/metrics=1-8           71.0 ± 0%      72.0 ± 0%   +1.41%  (p=0.000 n=50+50)
TargetScraperGzip/metrics=100-8         81.0 ± 0%      76.0 ± 0%   -6.17%  (p=0.000 n=50+50)
TargetScraperGzip/metrics=1000-8        92.0 ± 0%      83.0 ± 0%   -9.78%  (p=0.000 n=50+50)
TargetScraperGzip/metrics=10000-8       93.0 ± 0%      91.0 ± 0%   -2.15%  (p=0.000 n=50+50)
TargetScraperGzip/metrics=100000-8       111 ± 0%       135 ± 1%  +21.89%  (p=0.000 n=40+50)

Signed-off-by: Łukasz Mierzwa <l.mierzwa@gmail.com>
2024-02-22 17:08:15 +00:00
Bryan Boreham 5a6c8f9c15 promtool: use go-cmp instead of DeepEqual
go-cmp allows more control over unexported fields and implementation
details.

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2024-02-08 19:30:20 +00:00
Bryan Boreham 39af788dbd Tests: use replacement DeepEquals using go-cmp
Use DeepEqual replacement using go-cmp, which is more flexible.

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2024-02-08 19:30:20 +00:00
Bryan Boreham 16e68c01e4 tests: remove err from message when testify prints it already
For instance `require.NoError` will print the unexpected error; we don't
need to include it in the message.

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2024-02-01 14:18:01 +00:00
Paweł Szulik d5eb636a89 Refactor cmd tests to use testify.
Signed-off-by: Paweł Szulik <paul.szulik@gmail.com>
2024-02-01 13:51:31 +00:00
Marco Pracucci ac1c6eb3ef
Fix typo in CLI flag description
Signed-off-by: Marco Pracucci <marco@pracucci.com>
2024-01-29 10:11:50 +01:00
Danny Kopping 5bda33375a
Rename flag
Signed-off-by: Danny Kopping <danny.kopping@grafana.com>
2024-01-29 10:08:41 +01:00
Danny Kopping e7758d187e
Refactor concurrency control
Signed-off-by: Danny Kopping <danny.kopping@grafana.com>
2024-01-29 10:08:39 +01:00
Danny Kopping ed2933ca60
Add feature flag
Signed-off-by: Danny Kopping <danny.kopping@grafana.com>
2024-01-29 10:08:07 +01:00
Danny Kopping 940f83a540
Implementation
NOTE:
Rebased from main after refactor in #13014

Signed-off-by: Danny Kopping <danny.kopping@grafana.com>
2024-01-29 10:07:15 +01:00
Filip Petkovski 583f3e587c
Optimize histogram iterators (#13340)
Optimize histogram iterators

Histogram iterators allocate new objects in the AtHistogram and
AtFloatHistogram methods, which makes calculating rates over long
ranges expensive.

In #13215 we allowed an existing object to be reused
when converting an integer histogram to a float histogram. This commit follows
the same idea and allows injecting an existing object in the AtHistogram and
AtFloatHistogram methods. When the injected value is nil, iterators allocate
new histograms, otherwise they populate and return the injected object.

The commit also adds a CopyTo method to Histogram and FloatHistogram which
is used in the BufferedIterator to overwrite items in the ring instead of making
new copies.

Note that a specialized HPoint pool is needed for all of this to work 
(`matrixSelectorHPool`).

---------

Signed-off-by: Filip Petkovski <filip.petkovsky@gmail.com>
Co-authored-by: George Krajcsovits <krajorama@users.noreply.github.com>
2024-01-23 17:02:14 +01:00
Paulin Todev 78411d5e8b
SD Managers taking over responsibility for registration of debug metrics (#13375)
SD Managers take over responsibility for SD metrics registration

---------

Signed-off-by: Paulin Todev <paulin.todev@gmail.com>
Signed-off-by: Björn Rabenstein <github@rabenste.in>
Co-authored-by: Björn Rabenstein <github@rabenste.in>
2024-01-23 16:53:55 +01:00
SuperQ 2c0f9d1eee
Add automatic memory limit handling
Enable automatic detection of memory limits and configure GOMEMLIMIT to
match.
* Also includes a flag to allow controlling the reserved ratio.

Signed-off-by: SuperQ <superq@gmail.com>
2024-01-23 14:53:57 +01:00
Rewanth Tammana 102fd8cc88
Enhanced visibility for promtool test rules with JSON colored formatting (#13342)
* Added diff flag for unit test to improvise readability & debugging

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Removed blank spaces

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Fixed linting error

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Added cli flags to documentation

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Revert unrrelated linting fixes

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Fixed review suggestions

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Cleanup

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Updated flag description

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

* Updated flag description

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>

---------

Signed-off-by: Rewanth Tammana <22347290+rewanthtammana@users.noreply.github.com>
2024-01-18 09:49:16 -05:00
tyltr f97fa2736c remove obsolete build tag
Signed-off-by: tyltr <tylitianrui@126.com>
2024-01-17 22:26:32 +08:00
Giedrius Statkevičius b695e069b8
tsdb/main: wire "EnableOverlappingCompaction" to tsdb.Options (#13398)
This added the https://github.com/prometheus/prometheus/pull/13393
"EnableOverlappingCompaction" parameter to the compactor code but not to
the tsdb.Options. I forgot about that. Add it to `tsdb.Options` too and
set it to `true` in Prometheus.

Copy/paste the description from
https://github.com/prometheus/prometheus/pull/13393#issuecomment-1891787986

Signed-off-by: Giedrius Statkevičius <giedrius.statkevicius@vinted.com>
2024-01-15 16:42:40 +01:00
Ayoub Mrini ace9c8a3da
promtool: allow setting multiple matchers to "promtool tsdb dump" command. (#13296)
Conditions are ANDed inside the same matcher but matchers are ORed

Including unit tests for "promtool tsdb dump".

Refactor some matchers scraping utils.

Signed-off-by: machine424 <ayoubmrini424@gmail.com>
2024-01-15 10:29:53 +00:00
zenador 6150e1ca0e
Add analyze histograms command to promtool (#12331)
Add `query analyze` command to promtool

This command analyzes the buckets of classic and native histograms,
based on data queried from the Prometheus query API, i.e. it
doesn't require direct access to the TSDB files.

Signed-off-by: Jeanette Tan <jeanette.tan@grafana.com>

---------

Signed-off-by: Jeanette Tan <jeanette.tan@grafana.com>
2024-01-10 17:32:36 +01:00
Björn Rabenstein 9825a80498
Merge pull request #13023 from ptodev/prefer-to-not-register-metrics-globally-sd
Allow non-default registry to be used for metrics of SD components
2023-12-12 17:58:36 +01:00
Giedrius Statkevičius f36b56a62c
tsdb: remove unused option (#13282)
Digging around the TSDB code and I've found that this flag is unused so
let's remove it.

Signed-off-by: Giedrius Statkevičius <giedrius.statkevicius@vinted.com>
2023-12-12 09:58:54 +00:00
Paulin Todev 6279497124
Remove unnecessary else.
This was flagged by the linter.

Signed-off-by: Paulin Todev <paulin.todev@gmail.com>
2023-12-11 11:14:27 +00:00
Paulin Todev 6a5306a53c
Use const labels for Discovery Manager metrics.
Signed-off-by: Paulin Todev <paulin.todev@gmail.com>
2023-12-11 11:14:27 +00:00