We're loading the time window once per each Append() call, plus once in
the Commit(). While not extremely expensive, atomic operations are also
not cheap.
Additionally, it makes sense to keep the window consistent for a single
append.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
OOOHeadIndexReader was using the headIndexReader PostingsForMatchers()
and LabelValues() implementation which lead to a very subtle bug that
led to wrong query results.
headIndexReader LabelValues() implementation checks if the query
timerange overlaps with the head maxt and mint and if it doesnt it
returns an empty list of values. Since this code was also used by the
ooo head it led to wrong results that we were not able to see in tests
because our queries where always from MinInt64 to MaxInt64. This commit
also adds a new test that performs multiple time range queries to make
sure this never happens again.
Signed-off-by: Jesus Vazquez <jesus.vazquez@grafana.com>
Relates to @bboreham optimization in https://github.com/prometheus/prometheus/pull/10859
Bryan did reduce the sleep time improving the deltas on the benchmark by
quite a lot. However I've been working on a similar implementation for
out of order and I noticed that we actually get into this method
thousands of times.
@ywwg had the brilliant idea of not always sleeping before the select
but actually make it a case in the select so we only sleep if we need
to.
The benchmark deltas are amazing
```
❯ benchstat old_implementation.txt new_implementation_using_time_after.txt
name old time/op new time/op delta
LoadWAL/batches=10,seriesPerBatch=100,samplesPerSeries=7200,exemplarsPerSeries=0,mmappedChunkT=0-8 521ms ±25% 253ms ± 6% -51.47% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=100,samplesPerSeries=7200,exemplarsPerSeries=36,mmappedChunkT=0-8 773ms ± 3% 369ms ±31% -52.23% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=100,samplesPerSeries=7200,exemplarsPerSeries=72,mmappedChunkT=0-8 592ms ±28% 297ms ±28% -49.80% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=100,samplesPerSeries=7200,exemplarsPerSeries=360,mmappedChunkT=0-8 547ms ± 2% 999ms ±187% ~ (p=0.690 n=5+5)
LoadWAL/batches=10,seriesPerBatch=10000,samplesPerSeries=50,exemplarsPerSeries=0,mmappedChunkT=0-8 11.3s ± 4% 1.3s ±44% -88.48% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=10000,samplesPerSeries=50,exemplarsPerSeries=2,mmappedChunkT=0-8 11.1s ± 1% 1.2s ±20% -89.08% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=0,mmappedChunkT=0-8 1.24s ± 3% 0.18s ± 7% -85.76% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=2,mmappedChunkT=0-8 1.24s ± 2% 0.18s ± 5% -85.24% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=5,mmappedChunkT=0-8 1.23s ± 5% 0.27s ±33% -77.73% (p=0.008 n=5+5)
LoadWAL/batches=10,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=24,mmappedChunkT=0-8 1.28s ± 1% 0.36s ± 7% -71.51% (p=0.008 n=5+5)
LoadWAL/batches=100,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=0,mmappedChunkT=3800-8 12.1s ± 1% 3.1s ± 6% -74.33% (p=0.008 n=5+5)
LoadWAL/batches=100,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=2,mmappedChunkT=3800-8 12.1s ± 1% 3.4s ± 4% -71.94% (p=0.008 n=5+5)
LoadWAL/batches=100,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=5,mmappedChunkT=3800-8 12.1s ± 1% 3.8s ±17% -68.35% (p=0.008 n=5+5)
LoadWAL/batches=100,seriesPerBatch=1000,samplesPerSeries=480,exemplarsPerSeries=24,mmappedChunkT=3800-8 12.4s ± 1% 4.0s ±18% -67.71% (p=0.008 n=5+5)
```
Benchmarked on Linux
```
goos: linux
goarch: amd64
pkg: github.com/prometheus/prometheus/tsdb
cpu: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
```
Signed-off-by: Jesus Vazquez <jesus.vazquez@grafana.com>
* Job queue
This PR reimplements chan chunkWriteJob with custom buffered queue that should use less memory, because it doesn't preallocate entire buffer for maximum queue size at once. Instead it allocates individual "segments" with smaller size.
As elements are added to the queue, they fill individual segments. When elements are removed from the queue (and segments), empty segments can be thrown away. This doesn't change memory usage of the queue when it's full, but should decrease its memory footprint when it's empty (queue will keep max 1 segment in such case).
Signed-off-by: Peter Štibraný <pstibrany@gmail.com>
* Modify test to work with low resolution timer.
Signed-off-by: Peter Štibraný <pstibrany@gmail.com>
* Improve comments.
Signed-off-by: Peter Štibraný <pstibrany@gmail.com>
* Avoid gaps in in-order data after restart with out-of-order enabled
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
* Fix tests, do the temporary patch only if OOO is enabled
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
* Avoid Peter's confusion
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
* Use latest OutOfOrderTimeWindow
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
This implementation is based on this design doc:
https://docs.google.com/document/d/1Kppm7qL9C-BJB1j6yb6-9ObG3AbdZnFUBYPNNWwDBYM/edit?usp=sharing
This commit adds support to accept out-of-order ("OOO") sample into the TSDB
up to a configurable time allowance. If OOO is enabled, overlapping querying
are automatically enabled.
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
Co-authored-by: Jesus Vazquez <jesus.vazquez@grafana.com>
Co-authored-by: Ganesh Vernekar <ganeshvern@gmail.com>
Co-authored-by: Dieter Plaetinck <dieter@grafana.com>
* dont waste space on the chunkRefMap
* add time factor
* add comments
* better readability
* add instrumentation and more comments
* formatting
* uppercase comments
* Address review feedback. Renamed "free" to "shrink" everywhere, updated comments and threshold to 1000.
* double space
Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com>
Co-authored-by: Peter Štibraný <pstibrany@gmail.com>
Co-authored-by: Mauro Stettler <mauro.stettler@gmail.com>
To avoid building up data in memory, commit and make a new appender
periodically.
The number `commitAfter = 10000` was chosen arbitrarily; testing with
10x more or less gives slightly worse results.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
When restarting Prometheus I sometimes see:
caller=db.go:832 level=error component=tsdb msg="compaction failed" err="compact head: persist head block: 2 errors: populate block: context canceled; context canceled"
And prometheus_tsdb_compactions_failed_total metric gets incremented.
This makes it more difficult to write alerts based on
prometheus_tsdb_compactions_failed_total metric since any restart can
trigger it.
Signed-off-by: Łukasz Mierzwa <l.mierzwa@gmail.com>
The code sleeps for a short time to allow goroutines to finish, however
it seems the duration can be reduced a lot, speeding up the reading
process.
I checked using some WAL data from production, and the queue is almost
always empty at the time we enter `waitForIdle()` so there is no danger
of spinning in the tight loop.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Instead of creating a new hashing object every time, call `crc32.Checksum`
which computes the answer without allocations.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
This PR reimplements chan chunkWriteJob with custom buffered queue that should use less memory, because it doesn't preallocate entire buffer for maximum queue size at once. Instead it allocates individual "segments" with smaller size.
As elements are added to the queue, they fill individual segments. When elements are removed from the queue (and segments), empty segments can be thrown away. This doesn't change memory usage of the queue when it's full, but should decrease its memory footprint when it's empty (queue will keep max 1 segment in such case).
* dont waste space on the chunkRefMap
* add time factor
* add comments
* better readability
* add instrumentation and more comments
* formatting
* uppercase comments
* Address review feedback. Renamed "free" to "shrink" everywhere, updated comments and threshold to 1000.
* double space
Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com>
Co-authored-by: Peter Štibraný <pstibrany@gmail.com>
* Rename walDir parameter to dir
Signed-off-by: Matej Gera <matejgera@gmail.com>
* Improve NewQueueManager comment
Signed-off-by: Matej Gera <matejgera@gmail.com>
This commit fixes a typo when reporting an error that the the symbols
table size has been exceeded.
Signed-off-by: Filip Petkovski <filip.petkovsky@gmail.com>
On macOS, the TestTombstoneCleanRetentionLimitsRace performs very
poorly. It takes more than a second to write out one block, and as it
writes 400 of them, we run into the 10-minute test timeout frequently.
While this doesn't fix the actual performance issue, breaking each
iteration into a subtest makes the test pass reliably (because each
iteration comfortably finishes in under a minute).
Related report: https://groups.google.com/g/prometheus-developers/c/jxQ6Ayg6VJ4/m/03H_DS9PDAAJ
Signed-off-by: Matthias Rampke <matthias@prometheus.io>
"Labels is a sorted set of labels. Order has to be guaranteed upon
instantiation." says the comment, so fix all the tests that break this
rule.
For `BenchmarkLabelValuesWithMatchers()` and
`BenchmarkHeadLabelValuesWithMatchers()` the amount of work done changes
significantly if you put the labels in order, because all series refs
get neatly partitioned by the `tens` label, so I renamed the labels
to maintain the previous behaviour.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
