* Additionally wrap WBL replay error
Although WBL replay is already wrapped with errLoadWbl,
there are other errors that can happen during a WBL replay.
We should not try to repair WAL in those cases.
This commit additionally wraps the final error in Head.Init again
with errLoadWbl so that WBL replay errors can be identified properly.
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
Signed-off-by: Jesus Vazquez <jesusvzpg@gmail.com>
Co-authored-by: Jesus Vazquez <jesusvzpg@gmail.com>
Reverts change from https://github.com/prometheus/prometheus/pull/12906
The benchmarks show that it's slower when intersecting, which is a
common usage for ListPostings (when intersecting matchers from Head)
(old is before #12906, new is #12906):
│ old │ new │
│ sec/op │ sec/op vs base │
Intersect/LongPostings1-16 20.54µ ± 1% 21.11µ ± 1% +2.76% (p=0.000 n=20)
Intersect/LongPostings2-16 51.03m ± 1% 52.40m ± 2% +2.69% (p=0.000 n=20)
Intersect/ManyPostings-16 194.2m ± 3% 332.1m ± 1% +71.00% (p=0.000 n=20)
geomean 5.882m 7.161m +21.74%
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
It's implicit, but should be explicit. It is invalid to call At() after
a failed call to Next() or Seek().
Following up on https://github.com/prometheus/prometheus/pull/12906
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
The Next() call of ListPostings() was updating two values, while we can
just update the position. This is up to 30% faster for high number of
Postings.
goos: linux
goarch: amd64
pkg: github.com/prometheus/prometheus/tsdb/index
cpu: 11th Gen Intel(R) Core(TM) i7-11700K @ 3.60GHz
│ old │ new │
│ sec/op │ sec/op vs base │
ListPostings/count=100-16 819.2n ± 0% 732.6n ± 0% -10.58% (p=0.000 n=20)
ListPostings/count=1000-16 2.685µ ± 1% 2.017µ ± 0% -24.88% (p=0.000 n=20)
ListPostings/count=10000-16 21.43µ ± 1% 14.81µ ± 0% -30.91% (p=0.000 n=20)
ListPostings/count=100000-16 209.4µ ± 1% 143.3µ ± 0% -31.55% (p=0.000 n=20)
ListPostings/count=1000000-16 2.086m ± 1% 1.436m ± 1% -31.18% (p=0.000 n=20)
geomean 29.02µ 21.41µ -26.22%
We're talking about microseconds here, but they just keep adding.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
This avoids situations where metrics are scraped before the data they
are trying to look at is initialized.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Currently, the two goroutines race against each other and it's possible that the main test goroutine finishes way earlier than appendSeries has had a chance to run at all.
I tested this change by breaking the code that X fixed and running the race test 100 times. Without the additional time.Sleep the test failed 11 times. With the sleep it failed 65 out of the 100 runs. Which is still not ideal, but it's a step forward.
Signed-off-by: Dimitar Dimitrov <dimitar.dimitrov@grafana.com>
The test was introduced in # but was changed during the code review and not reran with the faulty code since then.
Closes #
Signed-off-by: Dimitar Dimitrov <dimitar.dimitrov@grafana.com>
Before cutting a new XOR chunk in case the chunk goes over the size
limit, check that the timestamp is in order and not equal or older
than the latest sample in the old chunk.
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
TestHeadDetectsDuplcateSampleAtSizeLimit tests a regression where a
duplicate sample,is appended to the head, right when the head chunk is
at the size limit. The test adds all samples as duplicate, thus
expecting that the result has exactly half of the samples.
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
Return annotations (warnings and infos) from PromQL queries
This generalizes the warnings we have already used before (but only for problems with remote read) as "annotations".
Annotations can be warnings or infos (the latter could be false positives). We do not treat them different in the API for now and return them all as "warnings". It would be easy to distinguish them and return infos separately, should that appear useful in the future.
The new annotations are then used to create a lot of warnings or infos during PromQL evaluations. Partially these are things we have wanted for a long time (e.g. inform the user that they have applied `rate` to a metric that doesn't look like a counter), but the new native histograms have created even more needs for those annotations (e.g. if a query tries to aggregate float numbers with histograms).
The annotations added here are not yet complete. A prominent example would be a warning about a range too short for a rate calculation. But such a warnings is more tricky to create with good fidelity and we will tackle it later.
Another TODO is to take annotations into account when evaluating recording rules.
---------
Signed-off-by: Jeanette Tan <jeanette.tan@grafana.com>
Case a) empty span is at the beginning of the spans.
Case b) two consequtive empty spans with positive offsets.
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
* Benchmark WBL
Extended WAL benchmark test with WBL parts too - added basic cases for
OOO handling - a percentage of series have a percentage of samples set
as OOO ones.
Signed-off-by: Fiona Liao <fiona.y.liao@gmail.com>
* Fix handling of explicit counter reset header in histograms.
Explicit counter reset were being ignored.
Also there was no unit test coverage.
Add test case for the first sample in a chunk.
Add test case for non first sample in chunk.
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
---------
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
Otherwise we have a highly unusual situation of over 100 chunks
in the headChunks list of each series, which heavily skews
performance.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
promql: Extend testing framework to support native histograms
This includes both the internal testing framework as well as the rules unit test feature of promtool.
This also adds a bunch of basic tests. Many of the code level tests can now be converted to tests within the framework, and more tests can be added easily.
---------
Signed-off-by: Harold Dost <h.dost@criteo.com>
Signed-off-by: Gregor Zeitlinger <gregor.zeitlinger@grafana.com>
Signed-off-by: Stephen Lang <stephen.lang@grafana.com>
Co-authored-by: Harold Dost <h.dost@criteo.com>
Co-authored-by: Stephen Lang <stephen.lang@grafana.com>
Co-authored-by: Gregor Zeitlinger <gregor.zeitlinger@grafana.com>
`rand.Read` has been deprecated since Go 1.20
`crypto/rand.Read` is more appropriate
Ref: https://tip.golang.org/doc/go1.20
Signed-off-by: Michal Biesek <michalbiesek@gmail.com>
Add a chunk size limit in bytes
This creates a hard cap for XOR chunks of 1024 bytes.
The limit for histogram chunk is also 1024 bytes, but it is a soft limit as a histogram has a dynamic size, and even a single one could be larger than 1024 bytes.
This also avoids cutting new histogram chunks if the existing chunk has fewer than 10 histograms yet. In that way, we are accepting "jumbo chunks" in order to have at least 10 histograms in a chunk, allowing compression to kick in.
Signed-off-by: Justin Lei <justin.lei@grafana.com>
So far, `ValidateHistogram` would not detect if the count did not
include the count in the zero bucket. This commit fixes the problem
and updates all the tests that have been undetected offenders so far.
Note that this problem would only ever create false negatives, so we
never falsely rejected to store a histogram because of it.
On the other hand, `ValidateFloatHistogram` has been to strict with
the count being at least as large as the sum of the counts in all the
buckets. Float precision issues could create false positives here, see
products of PromQL evaluations, it's actually quite hard to put an
upper limit no the floating point imprecision. Users could produce the
weirdest expressions, maxing out float precision problems. Therefore,
this commit simply removes that particular check from
`ValidateFloatHistogram`.
Signed-off-by: beorn7 <beorn@grafana.com>
Simlar to cleanup of WAL files on startup, cleanup temporary
chunk_snapshot dirs. This prevents storage space leaks due to terminated
snapshots on shutdown.
Signed-off-by: SuperQ <superq@gmail.com>
When a particular SeriesLifecycleCallback tries to optimize and run
closer to the Head, keeping track of the HeadSeriesRef instead of the
labelsets, it's impossible to handle the PostDeletion callback properly
as there's no way to know which series refs were deleted from the head.
This changes the callback to provide the series refs alongside the
labelsets, so the implementation can choose what to do.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
The most common case is to have a nil error when appending series, so
let's check that first instead of checking the 3 error types first.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Currently memSeries holds a single head chunk in-memory and a slice of mmapped chunks.
When append() is called on memSeries it might decide that a new headChunk is needed to use for given append() call.
If that happens it will first mmap existing head chunk and only after that happens it will create a new empty headChunk and continue appending
our sample to it.
Since appending samples uses write lock on memSeries no other read or write can happen until any append is completed.
When we have an append() that must create a new head chunk the whole memSeries is blocked until mmapping of existing head chunk finishes.
Mmapping itself uses a lock as it needs to be serialised, which means that the more chunks to mmap we have the longer each chunk might wait
for it to be mmapped.
If there's enough chunks that require mmapping some memSeries will be locked for long enough that it will start affecting
queries and scrapes.
Queries might timeout, since by default they have a 2 minute timeout set.
Scrapes will be blocked inside append() call, which means there will be a gap between samples. This will first affect range queries
or calls using rate() and such, since the time range requested in the query might have too few samples to calculate anything.
To avoid this we need to remove mmapping from append path, since mmapping is blocking.
But this means that when we cut a new head chunk we need to keep the old one around, so we can mmap it later.
This change makes memSeries.headChunk a linked list, memSeries.headChunk still points to the 'open' head chunk that receives new samples,
while older, yet to be mmapped, chunks are linked to it.
Mmapping is done on a schedule by iterating all memSeries one by one. Thanks to this we control when mmapping is done, since we trigger
it manually, which reduces the risk that it will have to compete for mmap locks with other chunks.
Signed-off-by: Łukasz Mierzwa <l.mierzwa@gmail.com>
If a new series is introduced in a storage.Appender instance, that
series should be written to the WAL once the storage.Appender is closed,
even on Rollback.
Previously, new series would only be written to the WAL when calling
Commit. However, because the series is stored in memory regardless,
subsequent calls to Commit may write samples to the WAL which reference
a series ID which that was never written.
Related to #11589. It's likely that this fix also resolves this issue,
but we need more testing from users to see if the problem persists after
this fix; there may be more cases where samples get written to the WAL
in Prometheus Agent mode without the corresponding series record.
Signed-off-by: Robert Fratto <robertfratto@gmail.com>
This has become a requirement for native histograms, as a single
histogram sample commonly has many buckets, so that providing many
exemplars makes sense.
Since OM text doesn't support native histograms yet, the test had to
be expanded to also support protobuf test cases.
Signed-off-by: beorn7 <beorn@grafana.com>
Snappy remains as the default compression but there is now a flag to switch
the compression algorithm.
Signed-off-by: Justin Lei <justin.lei@grafana.com>
* Apply matchers when fetching label values
Signed-off-by: Patrick Oyarzun <patrick.oyarzun@grafana.com>
* Avoid extra copying of label values
Signed-off-by: Patrick Oyarzun <patrick.oyarzun@grafana.com>
---------
Signed-off-by: Patrick Oyarzun <patrick.oyarzun@grafana.com>
Use AppendableGauge to detect corrupt chunk with gauge histograms.
Detect if first sample is a gauge but the chunk is not set up to contain
gauge histograms.
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
Signed-off-by: George Krajcsovits <krajorama@users.noreply.github.com>
Problem:
LabelValueStats - This will provide a list of the label names and memory used in bytes.
It is calculated by adding the length of all values for a given label name.
But internally Prometheus stores the name and the value independently for each series.
Solution:
MemPostings struct maintains the values to seriesRef map which is used
to get the number of series which contains the label values.
Using that LabelValueStats is calculated as: seriesCnt * len(value
name)
Signed-off-by: Baskar Shanmugam <baskar.shanmugam.career@gmail.com>
* WIP implement WAL watcher reading via notifications over a channel from
the TSDB code
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* Notify via head appenders Commit (finished all WAL logging) rather than
on each WAL Log call
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* Fix misspelled Notify plus add a metric for dropped Write notifications
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* Update tests to handle new notification pattern
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* this test maybe needs more time on windows?
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* does this test need more time on windows as well?
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* read timeout is already a time.Duration
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* remove mistakenly commited benchmark data files
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* address some review feedback
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* fix missed changes from previous commit
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* Fix issues from wrapper function
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* try fixing race condition in test by allowing tests to overwrite the
read ticker timeout instead of calling the Notify function
Signed-off-by: Callum Styan <callumstyan@gmail.com>
* fix linting
Signed-off-by: Callum Styan <callumstyan@gmail.com>
---------
Signed-off-by: Callum Styan <callumstyan@gmail.com>
The code did not handle spans with 0 length properly.
Spans with length zero are now skipped in the comparison.
Span index check not done against length-1, since length is a unit32,
thus subtracting 1 leads to 2^32, not -1.
Fixes and unit tests for both integer and float histograms added.
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
This changes usage of path to be replaced with path/filepath, allowing
for filepath.Base to properly return the base directory on systems where
`/` is not the standard path separator.
This resolves an issue on Windows where intermediate folders containing
a `.` were incorrectly considered to be a part of the checkpoint name.
Related to grafana/agent#3826.
Signed-off-by: Robert Fratto <robertfratto@gmail.com>
`head.deleted` holds the WAL segment in use at the time each series was
removed from the head. At the end of `truncateWAL()` we will delete
all segments up to `last`, so we can drop any series that were last seen
in a segment at or before that point.
(same change in Prometheus Agent too)
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Wiser coders than myself have come to the conclusion that a `switch`
statement is almost always superior to a statement that includes any
`else if`.
The exceptions that I have found in our codebase are just these two:
* The `if else` is followed by an additional statement before the next
condition (separated by a `;`).
* The whole thing is within a `for` loop and `break` statements are
used. In this case, using `switch` would require tagging the `for`
loop, which probably tips the balance.
Why are `switch` statements more readable?
For one, fewer curly braces. But more importantly, the conditions all
have the same alignment, so the whole thing follows the natural flow
of going down a list of conditions. With `else if`, in contrast, all
conditions but the first are "hidden" behind `} else if `, harder to
spot and (for no good reason) presented differently from the first
condition.
I'm sure the aforemention wise coders can list even more reasons.
In any case, I like it so much that I have found myself recommending
it in code reviews. I would like to make it a habit in our code base,
without making it a hard requirement that we would test on the CI. But
for that, there has to be a role model, so this commit eliminates all
`if else` occurrences, unless it is autogenerated code or fits one of
the exceptions above.
Signed-off-by: beorn7 <beorn@grafana.com>
We haven't updated golint-ci in our CI yet, but this commit prepares
for that.
There are a lot of new warnings, and it is mostly because the "revive"
linter got updated. I agree with most of the new warnings, mostly
around not naming unused function parameters (although it is justified
in some cases for documentation purposes – while things like mocks are
a good example where not naming the parameter is clearer).
I'm pretty upset about the "empty block" warning to include `for`
loops. It's such a common pattern to do something in the head of the
`for` loop and then have an empty block. There is still an open issue
about this: https://github.com/mgechev/revive/issues/810 I have
disabled "revive" altogether in files where empty blocks are used
excessively, and I have made the effort to add individual
`// nolint:revive` where empty blocks are used just once or twice.
It's borderline noisy, though, but let's go with it for now.
I should mention that none of the "empty block" warnings for `for`
loop bodies were legitimate.
Signed-off-by: beorn7 <beorn@grafana.com>
In the past, every sample value was a float, so it was fine to call a
variable holding such a float "value" or "sample". With native
histograms, a sample might have a histogram value. And a histogram
value is still a value. Calling a float value just "value" or "sample"
or "V" is therefore misleading. Over the last few commits, I already
renamed many variables, but this cleans up a few more places where the
changes are more invasive.
Note that we do not to attempt naming in the JSON APIs or in the
protobufs. That would be quite a disruption. However, internally, we
can call variables as we want, and we should go with the option of
avoiding misunderstandings.
Signed-off-by: beorn7 <beorn@grafana.com>
Previously, we had one “polymorphous” `sample` type in the `storage`
package. This commit breaks it up into `fSample`, `hSample`, and
`fhSample`, each still implementing the `tsdbutil.Sample` interface.
This reduces allocations in `sampleRing.Add` but inflicts the penalty
of the interface wrapper, which makes things worse in total.
This commit therefore just demonstrates the step taken. The next
commit will tackle the interface overhead problem.
Signed-off-by: beorn7 <beorn@grafana.com>
It seems that readOnlyDB was still opened which blocked the temp dir
cleanup.
Also changed the copy dir to be another TempDir instead of manually
creating one.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Use zeropool.Pool to workaround SA6002
I built a tiny library called https://github.com/colega/zeropool to
workaround the SA6002 staticheck issue.
While searching for the references of that SA6002 staticheck issues on
Github first results was Prometheus itself, with quite a lot of ignores
of it.
This changes the usages of `sync.Pool` to `zeropool.Pool[T]` where a
pointer is not available.
Also added a benchmark for HeadAppender Append/Commit when series
already exist, which is one of the most usual cases IMO, as I didn't find
any.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Improve BenchmarkHeadAppender with more cases
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* A little copying is better than a little dependency
https://www.youtube.com/watch?v=PAAkCSZUG1c&t=9m28s
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Fix imports order
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Add license header
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Copyright should be on one of the first 3 lines
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Use require.Equal for testing
I don't depend on testify in my lib, but here we have it available.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Avoid flaky test
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Also use zeropool for pointsPool in engine.go
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
---------
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
We need to make sure that `tsdb_errors.NewMulti` handles the errors.Is()
calls properly, like it's done in grafana/dskit.
Also we need to check that `errors.Is(err, context.Canceled)`, not that
`err == context.Canceled`.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Test that blocks are not marked as "compaction failed" during shutdown.
This shouldn't happen but this test currently fails.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
It took a `Labels` where the memory could be re-used, but in practice
this hardly ever benefitted. Especially after converting `relabel.Process`
to `relabel.ProcessBuilder`.
Comparing the parameter to `nil` was a bug; `EmptyLabels` is not `nil`
so the slice was reallocated multiple times by `append`.
Lastly `Builder.Labels()` now estimates that the final size will depend
on labels added and deleted.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
* Adds an affirmative log message for successful WAL repair
Signed-off-by: Vernon Miller <vernon.miller@grafana.com>
Signed-off-by: Vernon Miller <96601789+aldernero@users.noreply.github.com>
Co-authored-by: Ganesh Vernekar <ganeshvern@gmail.com>
Without this fix, if snapshots were enabled, and wbl goes missing
between restarts, then TSDB does not recognize that there are ooo
mmap chunks on disk and we cannot query them until those chunks
are compacted into blocks.
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
If the snapshot was enabled with some ooo mmap chunks on disk,
and wbl was removed between restarts, then we should still be able
to query the ooo mmap chunks after a restart. This test shows that
we are not able to query those ooo mmap chunks after a restart
under this situation.
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
M-map chunks replayed on startup are discarded if there
was no WAL and no snapshot loaded, because there is no
series created in the Head that it can map to. So only
load m-map chunks from disk if there is either a snapshot
loaded or there is WAL on disk.
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
Adds `WALReplayConcurrency` as an option on tsdb `Options` and `HeadOptions`.
If it is not set or set <=0, then `GOMAXPROCS` is used, which matches the previous behaviour.
Signed-off-by: Yuri Nikolic <durica.nikolic@grafana.com>
These benchmarks are all testing things related to what Prometheus does,
so perhaps have some historical interest, but we should not retain them
in the main repo.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
`safeChunk` is only obtained from the `headChunkReader.Chunk` call where
the chunk is already fetched and stored with the `safeChunk`. So, when
getting the iterator for the `safeChunk`, we don't need to get the chunk again.
Also removed a couple of unnecessary fields from `safeChunk` as a part of this.
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
* Export single ith test histogram generation functions
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
* Do not set counter reset hint for non-gauge histograms individually
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
* Apply suggestions from code review
Co-authored-by: Ganesh Vernekar <ganeshvern@gmail.com>
Signed-off-by: George Krajcsovits <krajorama@users.noreply.github.com>
---------
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
Signed-off-by: George Krajcsovits <krajorama@users.noreply.github.com>
Co-authored-by: Ganesh Vernekar <ganeshvern@gmail.com>
Paschalis Tsilias