On a 32 bit architecture the size of int is 32 bits. Thus converting from
int64, uint64 can overflow it and flip the sign.
Try for yourself in playground:
package main
import "fmt"
func main() {
x := int64(0x1F0000001)
y := int64(1)
z := int32(x - y) // numerically this is 0x1F0000000
fmt.Printf("%v\n", z)
}
Prints -268435456 as if x was smaller.
Followup to #12650
Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.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>
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>
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>
In the head and in v1 postings on disk, it makes no difference whether
postings are sorted. Only for v2 does the code step through in order.
So, move the sorting to where it is required, and thus skip it entirely
in the head.
Label values in on-disk blocks are already sorted, but `slices.Sort` is
very fast on already-sorted data so we don't bother checking.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
This allocates memory for all the returned values, which skews the
result. We aren't trying to benchmark `ExpandPostings`, so just step
through all the values without storing them to consume them.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Previously all the postings constructed were consumed on the first
iteration, so subsequent iterations did no work.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Instead of passing in a `ScratchBuilder` and `Labels`, just pass the
builder and the caller can extract labels from it. In many cases the
caller didn't use the Labels value anyway.
Now in `Labels.ScratchBuilder` we need a slightly different API: one
to assign what will be the result, instead of overwriting some other
`Labels`. This is safer and easier to reason about.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
This necessitates a change to the `tsdb.IndexReader` interface:
`index.Reader` is used from multiple goroutines concurrently, so we
can't have state in it.
We do retain a `ScratchBuilder` in `blockBaseSeriesSet` which is
iterator-like.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
* Add BenchmarkOpenBlock
* Use specific types when reading offset table
Instead of reading a generic-ish []string, we can read a generic type
which would be specifically labels.Label.
This avoid allocating a slice that escapes to the heap, making it both
faster and more efficient in terms of memory management.
* Update error message for unexpected number of keys
* s/posting offset table/postings offset table/
* Remove useless lastKey assignment
* Use two []bytes vars, simplify
Applied PR feedback: removed generics, moved the label indices reading
to that specific test as we're not using it in production anyway, we're
just testing what we've just built.
Also using two []bytes variables for name and value that use the backing
buffer instead of using strings, this reduces allocations a lot as we
only copy them when we store them (this is optimized by the compiler).
* Fix the dumb bug
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Co-authored-by: Marco Pracucci <marco@pracucci.com>
Use new experimental package `golang.org/x/exp/slices`.
slices.Sort works on values that are directly comparable, like ints,
so avoids the overhad of an interface call to `.Less()`.
Left tests unchanged, because they don't need the speed and it may be
a cross-check that slices.Sort gives the same answer.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Use new experimental package `golang.org/x/exp/slices`.
Some of the speedup comes from comparing SeriesRef (which is an int64)
directly rather than through an interface `.Less()` call; some comes
from exp/slices using "pattern-defeating quicksort(pdqsort)".
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Signed-off-by: Bryan Boreham <bjboreham@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>
* refactor: move from io/ioutil to io and os packages
* use fs.DirEntry instead of os.FileInfo after os.ReadDir
Signed-off-by: MOREL Matthieu <matthieu.morel@cnp.fr>
* tsdb: avoid slice-to-interface allocation in EnsureOrder
This is pulling the `seriesRefSlice` out of the loop, so the compiler
doesn't allocate a new one on the heap every time.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
* tsdb: use pointer type in Pool for EnsureOrder
As noted by staticcheck, Pool prefers the objects in the pool to have
pointer type. This is a little more fiddly to code, but avoids
allocation of a wrapper object every time a slice is put into the pool.
Removed a comment that said fixing this has a performance penalty: not
borne out by benchmarks.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Unexported postingsWithIndexHeap's methods that don't need to be
exported, and added detailed comments.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
See this comment for detailed explanation:
https://github.com/prometheus/prometheus/pull/9907#issuecomment-1002189932
TL;DR: if we don't call Pop() on the heap implementation, we don't need
to return our param as an `interface{}` so we save an allocation.
This would be popped for every label value, so it can be thousands of
saved allocations here (see benchmarks).
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Added validation to expected postings length compared to the bytes slice
length. With 32bit postings, we expect to have 4 bytes per each posting.
If the number doesn't add up, we know that the input data is not
compatible with our code (maybe it's cut, or padded with trash, or even
written in a different coded).
This is needed in downstream projects to correctly identify cached
postings written with an unknown codec, but it's also a good idea to
validate it here.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Add more size checks when writing individual sections in the index.
Signed-off-by: Peter Štibraný <pstibrany@gmail.com>
* Use uint and add comment about it.
Signed-off-by: Peter Štibraný <pstibrany@gmail.com>
This creates a new `model` directory and moves all data-model related
packages over there:
exemplar labels relabel rulefmt textparse timestamp value
All the others are more or less utilities and have been moved to `util`:
gate logging modetimevfs pool runtime
Signed-off-by: beorn7 <beorn@grafana.com>
* TSDB: demistify seriesRefs and ChunkRefs
The TSDB package contains many types of series and chunk references,
all shrouded in uint types. Often the same uint value may
actually mean one of different types, in non-obvious ways.
This PR aims to clarify the code and help navigating to relevant docs,
usage, etc much quicker.
Concretely:
* Use appropriately named types and document their semantics and
relations.
* Make multiplexing and demuxing of types explicit
(on the boundaries between concrete implementations and generic
interfaces).
* Casting between different types should be free. None of the changes
should have any impact on how the code runs.
TODO: Implement BlockSeriesRef where appropriate (for a future PR)
Signed-off-by: Dieter Plaetinck <dieter@grafana.com>
* feedback
Signed-off-by: Dieter Plaetinck <dieter@grafana.com>
* agent: demistify seriesRefs and ChunkRefs
Signed-off-by: Dieter Plaetinck <dieter@grafana.com>
This saves memory, effort and locking.
Since every symbol is also added to postings, `Symbols()` can be
implemented there instead. This now has to build a map for
deduplication, but `Symbols()` is only called for compaction, and `gc()`
used to rebuild the symbols map after every compaction so not an
additional cost.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
The previous code re-used series IDs 1-1000 many times over, so a lot
of time was spent ensuring the lists of series were in ascending order.
The intended use of `MemPostings.Add()` is that all series IDs are
unique, and changing the benchmark to do this lets it finish ten times
faster.
(It doesn't affect the benchmark result, just the setup code)
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
* Push the matchers for LabelNames all the way into the index.
NB This doesn't actually implement it in the index, just plumbs it through for now...
Signed-off-by: Tom Wilkie <tom@grafana.com>
* Hack it up. Does not work.
Signed-off-by: Tom Wilkie <tom@grafana.com>
* Revert changes I don't understand
Can't see why do we need to hold a mutex on symbols, and the purpose of
the LabelNamesFor method.
Maybe I'll need to re-add this later.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Implement LabelNamesFor
This method provides the label names that appear in the postings
provided. We do that deeper than the label values because we know
beforehand that most of the label names we'll be the same across
different postings, and we don't want to go down an up looking up the
same symbols for all different series.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Mutex on symbols should be unlocked
However, I still don't understand why do we need a mutex here.
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Fix head.LabelNamesFor
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Implement mockIndex LabelNames with matchers
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Nitpick on slice initialisation
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Add tests for LabelNamesWithMatchers
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Fix the mutex mess on head.LabelValues/LabelNames
I still don't see why we need to grab that unrelated mutex, but at least
now we're grabbing it consistently
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Check error after iterating postings
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Use the error from posting when there was en error in postings
Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Update storage/interface.go comment
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>
* Update tsdb/index/index.go comment
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>
* Update tsdb/index/index.go wrapped error msg
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>
* Update tsdb/index/index.go wrapped error msg
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>
* Update tsdb/index/index.go warpped error msg
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>
* Remove unneeded comment
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Add testcases for LabelNames w/matchers in api.go
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
* Use t.Cleanup() instead of defer in tests
Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
Co-authored-by: Tom Wilkie <tom@grafana.com>
Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>
* Compaction fails when total symbol size exceeds 2^32 bytes.
Signed-off-by: tanghengjian <1040104807@qq.com>
* Compaction fails when total symbol size exceeds 2^32 bytes.
Signed-off-by: tanghengjian <1040104807@qq.com>
* Compaction fails when total symbol size exceeds 2^32 bytes.
Signed-off-by: root <tanghengjian@oppo.com>
Co-authored-by: root <tanghengjian@oppo.com>
* tsdb: Expose total number of label pairs in head
Signed-off-by: Nguyen Le Vu Long <vulongvn98@gmail.com>
* fix: add comment for NumLabelPairs
Signed-off-by: Nguyen Le Vu Long <vulongvn98@gmail.com>
* fix: remove comment
Signed-off-by: Nguyen Le Vu Long <vulongvn98@gmail.com>
* Testify: move to require
Moving testify to require to fail tests early in case of errors.
Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>
* More moves
Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>
* MultiError: Refactored MultiError for more concise and safe usage.
* Less lines
* Goland IDE was marking every usage of old MultiError "potential nil" error
* It was easy to forgot using Err() when error was returned, now it's safely assured on compile time.
NOTE: Potentially I would rename package to merrors. (: In different PR.
Signed-off-by: Bartlomiej Plotka <bwplotka@gmail.com>
* Addressed review comments.
Signed-off-by: Bartlomiej Plotka <bwplotka@gmail.com>
* Addressed comments.
Signed-off-by: Bartlomiej Plotka <bwplotka@gmail.com>
* Fix after rebase.
Signed-off-by: Bartlomiej Plotka <bwplotka@gmail.com>
* Refactor test assertions
This pull request gets rid of assert.True where possible to use
fine-grained assertions.
Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>
Add back Windows CI, we lost it when tsdb was merged into the prometheus
repo. There's many tests failing outside tsdb, so only test tsdb for
now.
Fixes#6513
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
Rather than buffer up symbols in RAM, do it one by one
during compaction. Then use the reader's symbol handling
for symbol lookups during the rest of the index write.
There is some slowdown in compaction, due to having to look through a file
rather than a hash lookup. This is noise to the overall cost of compacting
series with thousands of samples though.
benchmark old ns/op new ns/op delta
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=101-4 539917175 675341565 +25.08%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=1001-4 2441815993 2477453524 +1.46%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=2001-4 3978543559 3922909687 -1.40%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=5001-4 8430219716 8586610007 +1.86%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=101-4 1786424591 1909552782 +6.89%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=1001-4 5328998202 6020839950 +12.98%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=2001-4 10085059958 11085278690 +9.92%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=5001-4 25497010155 27018079806 +5.97%
BenchmarkCompactionFromHead/labelnames=1,labelvalues=100000-4 2427391406 2817217987 +16.06%
BenchmarkCompactionFromHead/labelnames=10,labelvalues=10000-4 2592965497 2538805050 -2.09%
BenchmarkCompactionFromHead/labelnames=100,labelvalues=1000-4 2437388343 2668012858 +9.46%
BenchmarkCompactionFromHead/labelnames=1000,labelvalues=100-4 2317095324 2787423966 +20.30%
BenchmarkCompactionFromHead/labelnames=10000,labelvalues=10-4 2600239857 2096973860 -19.35%
benchmark old allocs new allocs delta
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=101-4 500851 470794 -6.00%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=1001-4 821527 791451 -3.66%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=2001-4 1141562 1111508 -2.63%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=5001-4 2141576 2111504 -1.40%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=101-4 871466 841424 -3.45%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=1001-4 1941428 1911415 -1.55%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=2001-4 3071573 3041510 -0.98%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=5001-4 6771648 6741509 -0.45%
BenchmarkCompactionFromHead/labelnames=1,labelvalues=100000-4 731493 824888 +12.77%
BenchmarkCompactionFromHead/labelnames=10,labelvalues=10000-4 793918 887311 +11.76%
BenchmarkCompactionFromHead/labelnames=100,labelvalues=1000-4 811842 905204 +11.50%
BenchmarkCompactionFromHead/labelnames=1000,labelvalues=100-4 832244 925081 +11.16%
BenchmarkCompactionFromHead/labelnames=10000,labelvalues=10-4 921553 1019162 +10.59%
benchmark old bytes new bytes delta
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=101-4 40532648 35698276 -11.93%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=1001-4 60340216 53409568 -11.49%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=2001-4 81087336 72065552 -11.13%
BenchmarkCompaction/type=normal,blocks=4,series=10000,samplesPerSeriesPerBlock=5001-4 142485576 120878544 -15.16%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=101-4 208661368 203831136 -2.31%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=1001-4 347345904 340484696 -1.98%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=2001-4 585185856 576244648 -1.53%
BenchmarkCompaction/type=vertical,blocks=4,series=10000,samplesPerSeriesPerBlock=5001-4 1357641792 1358966528 +0.10%
BenchmarkCompactionFromHead/labelnames=1,labelvalues=100000-4 126486664 119666744 -5.39%
BenchmarkCompactionFromHead/labelnames=10,labelvalues=10000-4 122323192 115117224 -5.89%
BenchmarkCompactionFromHead/labelnames=100,labelvalues=1000-4 126404504 119469864 -5.49%
BenchmarkCompactionFromHead/labelnames=1000,labelvalues=100-4 119047832 112230408 -5.73%
BenchmarkCompactionFromHead/labelnames=10000,labelvalues=10-4 136576016 116634800 -14.60%
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
Rather than keeping the entire symbol table in memory, keep every nth
offset and walk from there to the entry we need. This ends up slightly
slower, ~360ms per 1M series returned from PostingsForMatchers which is
not much considering the rest of the CPU such a query would go on to
use.
Make LabelValues use the postings tables, rather than having
to do symbol lookups. Use yoloString, as PostingsForMatchers
doesn't need the strings to stick around and adjust the API
call to keep the Querier open until it's all marshalled.
Remove allocatedSymbols memory optimisation, we no longer keep all the
symbol strings in heap memory. Remove LabelValuesFor and LabelIndices,
they're dead code. Ensure we've still tests for label indices,
and add missing test that we can work with old V1 Format index files.
PostingForMatchers performance is slightly better, with a big drop in
allocation counts due to using yoloString for LabelValues:
benchmark old ns/op new ns/op delta
BenchmarkPostingsForMatchers/Block/n="1"-4 36698 36681 -0.05%
BenchmarkPostingsForMatchers/Block/n="1",j="foo"-4 522786 560887 +7.29%
BenchmarkPostingsForMatchers/Block/j="foo",n="1"-4 511652 537680 +5.09%
BenchmarkPostingsForMatchers/Block/n="1",j!="foo"-4 522102 564239 +8.07%
BenchmarkPostingsForMatchers/Block/i=~".*"-4 113689911 111795919 -1.67%
BenchmarkPostingsForMatchers/Block/i=~".+"-4 135825572 132871085 -2.18%
BenchmarkPostingsForMatchers/Block/i=~""-4 40782628 38038181 -6.73%
BenchmarkPostingsForMatchers/Block/i!=""-4 31267869 29194327 -6.63%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",j="foo"-4 112733329 111568823 -1.03%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",i!="2",j="foo"-4 112868153 111232029 -1.45%
BenchmarkPostingsForMatchers/Block/n="1",i!=""-4 31338257 29349446 -6.35%
BenchmarkPostingsForMatchers/Block/n="1",i!="",j="foo"-4 32054482 29972436 -6.50%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",j="foo"-4 136504654 133968442 -1.86%
BenchmarkPostingsForMatchers/Block/n="1",i=~"1.+",j="foo"-4 27960350 27264997 -2.49%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!="2",j="foo"-4 136765564 133860724 -2.12%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!~"2.*",j="foo"-4 163714583 159453668 -2.60%
benchmark old allocs new allocs delta
BenchmarkPostingsForMatchers/Block/n="1"-4 6 6 +0.00%
BenchmarkPostingsForMatchers/Block/n="1",j="foo"-4 11 11 +0.00%
BenchmarkPostingsForMatchers/Block/j="foo",n="1"-4 11 11 +0.00%
BenchmarkPostingsForMatchers/Block/n="1",j!="foo"-4 17 15 -11.76%
BenchmarkPostingsForMatchers/Block/i=~".*"-4 100012 12 -99.99%
BenchmarkPostingsForMatchers/Block/i=~".+"-4 200040 100040 -49.99%
BenchmarkPostingsForMatchers/Block/i=~""-4 200045 100045 -49.99%
BenchmarkPostingsForMatchers/Block/i!=""-4 200041 100041 -49.99%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",j="foo"-4 100017 17 -99.98%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",i!="2",j="foo"-4 100023 23 -99.98%
BenchmarkPostingsForMatchers/Block/n="1",i!=""-4 200046 100046 -49.99%
BenchmarkPostingsForMatchers/Block/n="1",i!="",j="foo"-4 200050 100050 -49.99%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",j="foo"-4 200049 100049 -49.99%
BenchmarkPostingsForMatchers/Block/n="1",i=~"1.+",j="foo"-4 111150 11150 -89.97%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!="2",j="foo"-4 200055 100055 -49.99%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!~"2.*",j="foo"-4 311238 111238 -64.26%
benchmark old bytes new bytes delta
BenchmarkPostingsForMatchers/Block/n="1"-4 296 296 +0.00%
BenchmarkPostingsForMatchers/Block/n="1",j="foo"-4 424 424 +0.00%
BenchmarkPostingsForMatchers/Block/j="foo",n="1"-4 424 424 +0.00%
BenchmarkPostingsForMatchers/Block/n="1",j!="foo"-4 552 1544 +179.71%
BenchmarkPostingsForMatchers/Block/i=~".*"-4 1600482 1606125 +0.35%
BenchmarkPostingsForMatchers/Block/i=~".+"-4 17259065 17264709 +0.03%
BenchmarkPostingsForMatchers/Block/i=~""-4 17259150 17264780 +0.03%
BenchmarkPostingsForMatchers/Block/i!=""-4 17259048 17264680 +0.03%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",j="foo"-4 1600610 1606242 +0.35%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",i!="2",j="foo"-4 1600813 1606434 +0.35%
BenchmarkPostingsForMatchers/Block/n="1",i!=""-4 17259176 17264808 +0.03%
BenchmarkPostingsForMatchers/Block/n="1",i!="",j="foo"-4 17259304 17264936 +0.03%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",j="foo"-4 17259333 17264965 +0.03%
BenchmarkPostingsForMatchers/Block/n="1",i=~"1.+",j="foo"-4 3142628 3148262 +0.18%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!="2",j="foo"-4 17259509 17265141 +0.03%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!~"2.*",j="foo"-4 20405680 20416944 +0.06%
However overall Select performance is down and involves more allocs, due to
having to do more than a simple map lookup to resolve a symbol and that all the strings
returned are allocated:
benchmark old ns/op new ns/op delta
BenchmarkQuerierSelect/Block/1of1000000-4 506092636 862678244 +70.46%
BenchmarkQuerierSelect/Block/10of1000000-4 505638968 860917636 +70.26%
BenchmarkQuerierSelect/Block/100of1000000-4 505229450 882150048 +74.60%
BenchmarkQuerierSelect/Block/1000of1000000-4 515905414 862241115 +67.13%
BenchmarkQuerierSelect/Block/10000of1000000-4 516785354 874841110 +69.29%
BenchmarkQuerierSelect/Block/100000of1000000-4 540742808 907030187 +67.74%
BenchmarkQuerierSelect/Block/1000000of1000000-4 815224288 1181236903 +44.90%
benchmark old allocs new allocs delta
BenchmarkQuerierSelect/Block/1of1000000-4 4000020 6000020 +50.00%
BenchmarkQuerierSelect/Block/10of1000000-4 4000038 6000038 +50.00%
BenchmarkQuerierSelect/Block/100of1000000-4 4000218 6000218 +50.00%
BenchmarkQuerierSelect/Block/1000of1000000-4 4002018 6002018 +49.97%
BenchmarkQuerierSelect/Block/10000of1000000-4 4020018 6020018 +49.75%
BenchmarkQuerierSelect/Block/100000of1000000-4 4200018 6200018 +47.62%
BenchmarkQuerierSelect/Block/1000000of1000000-4 6000018 8000019 +33.33%
benchmark old bytes new bytes delta
BenchmarkQuerierSelect/Block/1of1000000-4 176001468 227201476 +29.09%
BenchmarkQuerierSelect/Block/10of1000000-4 176002620 227202628 +29.09%
BenchmarkQuerierSelect/Block/100of1000000-4 176014140 227214148 +29.09%
BenchmarkQuerierSelect/Block/1000of1000000-4 176129340 227329348 +29.07%
BenchmarkQuerierSelect/Block/10000of1000000-4 177281340 228481348 +28.88%
BenchmarkQuerierSelect/Block/100000of1000000-4 188801340 240001348 +27.12%
BenchmarkQuerierSelect/Block/1000000of1000000-4 304001340 355201616 +16.84%
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
With recent speed improvements to populate block,
the cancellation test now fails regularly on CI.
Use contexts to get the index writer to shut down
much faster, and that allows us to make the cancellation
test faster too.
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
Flushing buffers and doing a pwrite per posting is expensive
time wise, so go back to the old way for those. This doubles
our memory usage, but that's still small as it's only
~8 bytes per time series in the index. This is 30-40% faster.
benchmark old ns/op new ns/op delta
BenchmarkCompactionFromHead/labelnames=1,labelvalues=100000-4 1101429174 724362123 -34.23%
BenchmarkCompactionFromHead/labelnames=10,labelvalues=10000-4 1074466374 720977022 -32.90%
BenchmarkCompactionFromHead/labelnames=100,labelvalues=1000-4 1166510282 677702636 -41.90%
BenchmarkCompactionFromHead/labelnames=1000,labelvalues=100-4 1075013071 696855960 -35.18%
BenchmarkCompactionFromHead/labelnames=10000,labelvalues=10-4 1231673790 829328610 -32.67%
benchmark old allocs new allocs delta
BenchmarkCompactionFromHead/labelnames=1,labelvalues=100000-4 832571 731435 -12.15%
BenchmarkCompactionFromHead/labelnames=10,labelvalues=10000-4 894875 793823 -11.29%
BenchmarkCompactionFromHead/labelnames=100,labelvalues=1000-4 912931 811804 -11.08%
BenchmarkCompactionFromHead/labelnames=1000,labelvalues=100-4 933511 832366 -10.83%
BenchmarkCompactionFromHead/labelnames=10000,labelvalues=10-4 1022791 921554 -9.90%
benchmark old bytes new bytes delta
BenchmarkCompactionFromHead/labelnames=1,labelvalues=100000-4 129063496 126472364 -2.01%
BenchmarkCompactionFromHead/labelnames=10,labelvalues=10000-4 124154888 122300764 -1.49%
BenchmarkCompactionFromHead/labelnames=100,labelvalues=1000-4 128790648 126394856 -1.86%
BenchmarkCompactionFromHead/labelnames=1000,labelvalues=100-4 120570696 118946548 -1.35%
BenchmarkCompactionFromHead/labelnames=10000,labelvalues=10-4 138754288 136317432 -1.76%
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
Rather than building up a 2nd copy of all the posting
tables, construct it from the data we've already written
to disk. This takes more time, but saves memory.
Current benchmark numbers have this as slightly faster, but that's
likely due to the synthetic data not having many label names.
Memory usage is roughly halved for the relevant bits.
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
Rather than keeping the offset of each postings list, instead
keep the nth offset of the offset of the posting list. As postings
list offsets have always been sorted, we can then get to the closest
entry before the one we want an iterate forwards.
I haven't done much tuning on the 32 number, it was chosen to try
not to read through more than a 4k page of data.
Switch to a bulk interface for fetching postings. Use it to avoid having
to re-read parts of the posting offset table when querying lots of it.
For a index with what BenchmarkHeadPostingForMatchers uses RAM
for r.postings drops from 3.79MB to 80.19kB or about 48x.
Bytes allocated go down by 30%, and suprisingly CPU usage drops by
4-6% for typical queries too.
benchmark old ns/op new ns/op delta
BenchmarkPostingsForMatchers/Block/n="1"-4 35231 36673 +4.09%
BenchmarkPostingsForMatchers/Block/n="1",j="foo"-4 563380 540627 -4.04%
BenchmarkPostingsForMatchers/Block/j="foo",n="1"-4 536782 534186 -0.48%
BenchmarkPostingsForMatchers/Block/n="1",j!="foo"-4 533990 541550 +1.42%
BenchmarkPostingsForMatchers/Block/i=~".*"-4 113374598 117969608 +4.05%
BenchmarkPostingsForMatchers/Block/i=~".+"-4 146329884 139651442 -4.56%
BenchmarkPostingsForMatchers/Block/i=~""-4 50346510 44961127 -10.70%
BenchmarkPostingsForMatchers/Block/i!=""-4 41261550 35356165 -14.31%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",j="foo"-4 112544418 116904010 +3.87%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",i!="2",j="foo"-4 112487086 116864918 +3.89%
BenchmarkPostingsForMatchers/Block/n="1",i!=""-4 41094758 35457904 -13.72%
BenchmarkPostingsForMatchers/Block/n="1",i!="",j="foo"-4 41906372 36151473 -13.73%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",j="foo"-4 147262414 140424800 -4.64%
BenchmarkPostingsForMatchers/Block/n="1",i=~"1.+",j="foo"-4 28615629 27872072 -2.60%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!="2",j="foo"-4 147117177 140462403 -4.52%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!~"2.*",j="foo"-4 175096826 167902298 -4.11%
benchmark old allocs new allocs delta
BenchmarkPostingsForMatchers/Block/n="1"-4 4 6 +50.00%
BenchmarkPostingsForMatchers/Block/n="1",j="foo"-4 7 11 +57.14%
BenchmarkPostingsForMatchers/Block/j="foo",n="1"-4 7 11 +57.14%
BenchmarkPostingsForMatchers/Block/n="1",j!="foo"-4 15 17 +13.33%
BenchmarkPostingsForMatchers/Block/i=~".*"-4 100010 100012 +0.00%
BenchmarkPostingsForMatchers/Block/i=~".+"-4 200069 200040 -0.01%
BenchmarkPostingsForMatchers/Block/i=~""-4 200072 200045 -0.01%
BenchmarkPostingsForMatchers/Block/i!=""-4 200070 200041 -0.01%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",j="foo"-4 100013 100017 +0.00%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",i!="2",j="foo"-4 100017 100023 +0.01%
BenchmarkPostingsForMatchers/Block/n="1",i!=""-4 200073 200046 -0.01%
BenchmarkPostingsForMatchers/Block/n="1",i!="",j="foo"-4 200075 200050 -0.01%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",j="foo"-4 200074 200049 -0.01%
BenchmarkPostingsForMatchers/Block/n="1",i=~"1.+",j="foo"-4 111165 111150 -0.01%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!="2",j="foo"-4 200078 200055 -0.01%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!~"2.*",j="foo"-4 311282 311238 -0.01%
benchmark old bytes new bytes delta
BenchmarkPostingsForMatchers/Block/n="1"-4 264 296 +12.12%
BenchmarkPostingsForMatchers/Block/n="1",j="foo"-4 360 424 +17.78%
BenchmarkPostingsForMatchers/Block/j="foo",n="1"-4 360 424 +17.78%
BenchmarkPostingsForMatchers/Block/n="1",j!="foo"-4 520 552 +6.15%
BenchmarkPostingsForMatchers/Block/i=~".*"-4 1600461 1600482 +0.00%
BenchmarkPostingsForMatchers/Block/i=~".+"-4 24900801 17259077 -30.69%
BenchmarkPostingsForMatchers/Block/i=~""-4 24900836 17259151 -30.69%
BenchmarkPostingsForMatchers/Block/i!=""-4 24900760 17259048 -30.69%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",j="foo"-4 1600557 1600621 +0.00%
BenchmarkPostingsForMatchers/Block/n="1",i=~".*",i!="2",j="foo"-4 1600717 1600813 +0.01%
BenchmarkPostingsForMatchers/Block/n="1",i!=""-4 24900856 17259176 -30.69%
BenchmarkPostingsForMatchers/Block/n="1",i!="",j="foo"-4 24900952 17259304 -30.69%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",j="foo"-4 24900993 17259333 -30.69%
BenchmarkPostingsForMatchers/Block/n="1",i=~"1.+",j="foo"-4 3788311 3142630 -17.04%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!="2",j="foo"-4 24901137 17259509 -30.69%
BenchmarkPostingsForMatchers/Block/n="1",i=~".+",i!~"2.*",j="foo"-4 28693086 20405680 -28.88%
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
We can instead write it as we go, and then go back and write in the
length at the end.
Also fix the compaction benchmark, which indicates no changes.
For the benchmark, this brings maximum memory usage of the buffers
from ~200kB down to 128B.
Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
* Adding TSDB Head Stats like cardinality to Status Page
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Moving mutx to Head
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Renaming variabls
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Renaming variabls and html
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Removing unwanted whitespaces
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Adding Tests, Banchmarks and Max Heap for Postings Stats
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Adding more tests for postingstats and web handler
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Adding more tests for postingstats and web handler
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Remove generated asset file that is no longer used
Signed-off-by: Chris Marchbanks <csmarchbanks@gmail.com>
* Changing comment and variable name for more readability
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
* Using time.Duration in postings status function and removing refresh button from web page
Signed-off-by: Sharad Gaur <sgaur@splunk.com>
