prometheus

Commit Graph

Author	SHA1	Message	Date
Mauro Stettler	b025390cb4	Disable chunk write queue by default, allow user to configure the exact size (#10425 ) * Disable chunk write queue by default Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * update flag description Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com>	3 years ago
Ganesh Vernekar	24827782cb	Fix panics when m-mapping head chunks (#10316 ) * Fix panics when m-mapping head chunks Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com> * Fix review comments Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com> * Fix reviews Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>	3 years ago
Mauro Stettler	bf959b36cb	Nits after PR 10051 merge (#10159 ) Signed-off-by: Marco Pracucci <marco@pracucci.com> Co-authored-by: Marco Pracucci <marco@pracucci.com>	3 years ago
Ganesh Vernekar	129ed4ec8b	Fix Example() function in TSDB (#10153 ) * Fix Example() function in TSDB Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com> * Fix tests Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>	3 years ago
Mauro Stettler	0df3489275	Write chunks via queue, predicting the refs (#10051 ) * Write chunks via queue, predicting the refs Our load tests have shown that there is a latency spike in the remote write handler whenever the head chunks need to be written, because chunkDiskMapper.WriteChunk() blocks until the chunks are written to disk. This adds a queue to the chunk disk mapper which makes the WriteChunk() method non-blocking unless the queue is full. Reads can still be served from the queue. Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * address PR feeddback Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * initialize metrics without .Add(0) Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * change isRunningMtx to normal lock Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * do not re-initialize chunkrefmap Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * update metric outside of lock scope Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * add benchmark for adding job to chunk write queue Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * remove unnecessary "success" var Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * gofumpt -extra Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * avoid WithLabelValues call in addJob Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * format comments Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * addressing PR feedback Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * rename cutExpectRef to cutAndExpectRef Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * use head.Init() instead of .initTime() Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * address PR feedback Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * PR feedback Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com> Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * update test according to PR feedback Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * replace callbackWg -> awaitCb Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * better test of truncation with empty files Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> * replace callbackWg -> awaitCb Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com> Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com>	3 years ago
Dieter Plaetinck	0fac9bb859	Add basic initial developer docs for TSDB (#9451 ) * Add basic initial developer docs for TSDB There's a decent amount of content already out there (blog posts, conference talks, etc), but: * when they get stale, they don't tend to get updated * they still leave me with questions that I'ld like to answer for developers (like me) who want to use, or work with, TSDB What I propose is developer docs inside the prometheus repository. Easy to find and harness the power of the community to expand it and keep it up to date. * perfect is the enemy of good. Let's have a base and incrementally improve * Markdown docs should be broad but not too deep. Source code comments can complement them, and are the ideal place for implementation details. Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * use example code that works out of the box Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * Apply suggestions from code review Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com> Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * PR feedback Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * more docs Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * PR feedback Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * Apply suggestions from code review Signed-off-by: Dieter Plaetinck <dieter@grafana.com> Co-authored-by: Bartlomiej Plotka <bwplotka@gmail.com> * Apply suggestions from code review Signed-off-by: Dieter Plaetinck <dieter@grafana.com> Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com> * feedback Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * Update tsdb/docs/usage.md Signed-off-by: Dieter Plaetinck <dieter@grafana.com> Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com> * final tweaks Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * workaround docs versioning issue Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * Move example code to real executable, testable example. Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * cleanup example test and make sure it always reproduces Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * obtain temp dir in a way that works with older Go versions Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * Fix Ganesh's comments Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com> Co-authored-by: Ganesh Vernekar <15064823+codesome@users.noreply.github.com> Co-authored-by: Bartlomiej Plotka <bwplotka@gmail.com> Co-authored-by: Ganesh Vernekar <ganeshvern@gmail.com>	3 years ago
Mauro Stettler	8a4f659126	fix error message Signed-off-by: Mauro Stettler <mauro.stettler@gmail.com>	3 years ago
Dieter Plaetinck	cda025b5b5	TSDB: demistify SeriesRefs and ChunkRefs (#9536 ) * 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>	3 years ago
Mateusz Gozdek	1a6c2283a3	Format Go source files using 'gofumpt -w -s -extra' Part of #9557 Signed-off-by: Mateusz Gozdek <mgozdekof@gmail.com>	3 years ago
Dieter Plaetinck	d5afe0a577	TSDB: Use a dedicated head chunk reference type (#9501 ) * Use dedicated Ref type Throughout the code base, there are reference types masked as regular integers. Let's use dedicated types. They are equivalent, but clearer semantically. This also makes it trivial to find where they are used, and from uses, find the centralized docs. Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * postpone some work until after possible return Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * clarify Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * rename feedback Signed-off-by: Dieter Plaetinck <dieter@grafana.com> * skip header is up to caller Signed-off-by: Dieter Plaetinck <dieter@grafana.com>	3 years ago
jinglina	1a430e5f89	remove redundant parentheses (#9134 ) Signed-off-by: jinglina <jinglinax@163.com>	3 years ago
Marco Pracucci	4b49ffbad5	Stop the bleed on chunk mapper panic (#8723 ) * Added test to reproduce panic on TSDB head chunks truncated while querying Signed-off-by: Marco Pracucci <marco@pracucci.com> * Added test for Querier too Signed-off-by: Marco Pracucci <marco@pracucci.com> * Stop the bleed on mmap-ed head chunks panic Signed-off-by: Marco Pracucci <marco@pracucci.com> * Lower memory pressure in tests to ensure it doesn't OOM Signed-off-by: Marco Pracucci <marco@pracucci.com> * Skip TestQuerier_ShouldNotPanicIfHeadChunkIsTruncatedWhileReadingQueriedChunks Signed-off-by: Marco Pracucci <marco@pracucci.com> * Experiment to not trigger runtime.GC() continuously Signed-off-by: Marco Pracucci <marco@pracucci.com> * Try to fix test in CI Signed-off-by: Marco Pracucci <marco@pracucci.com> * Do not call runtime.GC() at all Signed-off-by: Marco Pracucci <marco@pracucci.com> * I have no idea why it's failing in CI, skipping tests Signed-off-by: Marco Pracucci <marco@pracucci.com>	4 years ago
Bartlomiej Plotka	8bf7bc68f1	Fixed TestChunkDiskMapper_WriteChunk_Chunk_IterateChunks for go1.16 (#8538 ) Fixes https://github.com/prometheus/prometheus/issues/8403 Signed-off-by: Bartlomiej Plotka <bwplotka@gmail.com>	4 years ago
Guangwen Feng	e2cd6c5f57	Fix golint issue caused by typo Signed-off-by: Guangwen Feng <fenggw-fnst@cn.fujitsu.com>	4 years ago
Marco Pracucci	db19e05d93	Add option to customise head chunks write buffer size (#8201 ) * Add option to customise head chunks write buffer size Signed-off-by: Marco Pracucci <marco@pracucci.com> * Fixed tests Signed-off-by: Marco Pracucci <marco@pracucci.com>	4 years ago
Julien Pivotto	8bc369bf9b	Calculate head chunk size based on actual disk usage (#8139 ) Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>	4 years ago
Bartlomiej Plotka	3d8826a3d4	MultiError: Refactored MultiError for more concise and safe usage. (#8066 ) * 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>	4 years ago
Julien Pivotto	4e5b1722b3	Move away from testutil, refactor imports (#8087 ) Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>	4 years ago
Ganesh Vernekar	2624d827fa	Read repair empty last file in chunks_head (#8061 ) * Read repair empty file in chunks_head Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Refactor and introduce repairLastChunkFile Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Attempt windows test fix Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	4 years ago
Ganesh Vernekar	c806262206	Fix 'chunks.HeadReadWriter: maxt of the files are not set' error (#7856 ) * Fix chunks.HeadReadWriter: maxt of the files are not set Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	4 years ago
Yukun Sun	cfd4e05c9e	fix: return a corruption error when iterator function find a chunk that is out of sequence (#7855 ) Signed-off-by: sunyukun <sunyukun@didiglobal.com> Co-authored-by: sunyukun <sunyukun@didiglobal.com>	4 years ago
Max Neverov	bb5c6b38e2	Fix Possible Race Condition in TSDB (#7815 ) * Replace tsdb chunk mapper size with atomic; protect mmappedChunkFiles with read path mutex on DeleteCorrupted Signed-off-by: Max Neverov <neverov.max@gmail.com> * PR fixes Signed-off-by: Max Neverov <neverov.max@gmail.com>	4 years ago
Javier Palomo Almena	348ff4285f	tsdb: Replace sync/atomic with uber-go/atomic in tsdb (#7659 ) * tsdb/chunks: Replace sync/atomic with uber-go/atomic Signed-off-by: Javier Palomo <javier.palomo.almena@gmail.com> * tsdb/heaad: Replace sync/atomic with uber-go/atomic Signed-off-by: Javier Palomo <javier.palomo.almena@gmail.com> * vendor: Make go.uber.org/atomic a direct dependency There is no modifications to go.sum and vendor/ because it was already vendored. Signed-off-by: Javier Palomo <javier.palomo.almena@gmail.com> * tsdb: Remove comments referring to the sync/atomic alignment bug Related: https://golang.org/pkg/sync/atomic/#pkg-note-BUG Signed-off-by: Javier Palomo <javier.palomo.almena@gmail.com>	4 years ago
johncming	9801f52b0a	tsdb/chunks: fix bug of data race(#7643 ). (#7646 ) Signed-off-by: johncming <johncming@yahoo.com>	4 years ago
Ganesh Vernekar	b7c46a8c79	Merge remote-tracking branch 'upstream/master' into merge-release-2.19 Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	5 years ago
Ganesh Vernekar	48fae12b89	Fix unsequential m-map files (#7414 ) * Fix unsequential m-map files Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	5 years ago
Simon Pasquier	2f12049371	tsdb: improve logs when encountering corruption (#7308 ) * tsdb: improve logs when encountering corruption Signed-off-by: Simon Pasquier <spasquie@redhat.com> * Wrap corrupted block errors Signed-off-by: Simon Pasquier <spasquie@redhat.com> * Add file path to head chunks Signed-off-by: Simon Pasquier <spasquie@redhat.com>	5 years ago
Ganesh Vernekar	1627d234da	Moves the atomically accessed member to the top of the struct (#7365 ) * Moves the 64bit atomically accessed field to the top of the struct. Signed-off-by: Bryan Varner <1652015+bvarner@users.noreply.github.com> * Moves the 64bit atomically accessed field to the top of the struct. Signed-off-by: Bryan Varner <1652015+bvarner@users.noreply.github.com> * Fixing up go fmt formatting issues. Signed-off-by: Bryan Varner <1652015+bvarner@users.noreply.github.com> Co-authored-by: Bryan Varner <1652015+bvarner@users.noreply.github.com>	5 years ago
Ganesh Vernekar	a1355eb7c7	Remove time based m-map file creation (#7314 ) * Remove time based m-map file creation Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	5 years ago
Ganesh Vernekar	83619aa9ac	Preallocate m-map file only for Windows (#7306 ) Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	5 years ago
Krasimir Georgiev	09df8d94e0	More explicit chunks and head error handling. (#7277 )	5 years ago
Ganesh Vernekar	d4b9fe801f	M-map full chunks of Head from disk (#6679 ) When appending to the head and a chunk is full it is flushed to the disk and m-mapped (memory mapped) to free up memory Prom startup now happens in these stages - Iterate the m-maped chunks from disk and keep a map of series reference to its slice of mmapped chunks. - Iterate the WAL as usual. Whenever we create a new series, look for it's mmapped chunks in the map created before and add it to that series. If a head chunk is corrupted the currpted one and all chunks after that are deleted and the data after the corruption is recovered from the existing WAL which means that a corruption in m-mapped files results in NO data loss. [Mmaped chunks format](https://github.com/prometheus/prometheus/blob/master/tsdb/docs/format/head_chunks.md) - main difference is that the chunk for mmaping now also includes series reference because there is no index for mapping series to chunks. [The block chunks](https://github.com/prometheus/prometheus/blob/master/tsdb/docs/format/chunks.md) are accessed from the index which includes the offsets for the chunks in the chunks file - example - chunks of series ID have offsets 200, 500 etc in the chunk files. In case of mmaped chunks, the offsets are stored in memory and accessed from that. During WAL replay, these offsets are restored by iterating all m-mapped chunks as stated above by matching the series id present in the chunk header and offset of that chunk in that file. Prombench results _WAL Replay_ 1h Wal reply time 30% less wal reply time - 4m31 vs 3m36 2h Wal reply time 20% less wal reply time - 8m16 vs 7m _Memory During WAL Replay_ High Churn: 10-15% less RAM - 32gb vs 28gb 20% less RAM after compaction 34gb vs 27gb No Churn: 20-30% less RAM - 23gb vs 18gb 40% less RAM after compaction 32.5gb vs 20gb Screenshots are in [this comment](https://github.com/prometheus/prometheus/pull/6679#issuecomment-621678932) Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	5 years ago
Ganesh Vernekar	e50fdbc70c	Live m-mapping of chunks on disk (#6830 ) * Live m-mapping of chunks on disk Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Part 2 Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Part 3 Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Fix review comments Part 4 Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in> * Attempt to fix windows bug Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>	5 years ago

33 Commits (8b5eb562b12f4ea0e0f9126e7b25f5a450687970)