* 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>
* 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>
* 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>
* 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>
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>
