Commit Graph

8623 Commits (96419b78e06b027e58d59a7a436984a3e03bf484)

Author SHA1 Message Date
kodiakhq[bot] 96419b78e0
Merge pull request #5311 from influxdata/dom/instrument-kafka-produce
build: bump rskafka to latest
2022-08-04 15:20:45 +00:00
kodiakhq[bot] 0ba3ae1e0d
Merge branch 'main' into dom/instrument-kafka-produce 2022-08-04 15:13:49 +00:00
kodiakhq[bot] 600617ec08
Merge pull request #5307 from influxdata/dom/instrument-agg
feat: instrument kafka aggregated DML batch size
2022-08-04 14:57:40 +00:00
Dom Dwyer 36d36c507c ci: bump redpanda version 2022-08-04 16:57:28 +02:00
kodiakhq[bot] 76d3a12dab
Merge branch 'main' into dom/instrument-agg 2022-08-04 14:49:10 +00:00
Dom Dwyer 77fd967517 feat: instrument kafka aggregated DML batch size
The Kafka write buffer implementation (and only the Kafka impl) merges
together successive DML writes for the same namespace & partition within
a window of time.

This commit records the number of DML writes that have been merged
together to form a single batched op before it is dispatched to Kafka.
2022-08-04 16:48:56 +02:00
dependabot[bot] e8231b2986
chore(deps): Bump serde_json from 1.0.82 to 1.0.83 (#5297)
* chore(deps): Bump serde_json from 1.0.82 to 1.0.83

Bumps [serde_json](https://github.com/serde-rs/json) from 1.0.82 to 1.0.83.
- [Release notes](https://github.com/serde-rs/json/releases)
- [Commits](https://github.com/serde-rs/json/compare/v1.0.82...v1.0.83)

---
updated-dependencies:
- dependency-name: serde_json
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

* chore: Run cargo hakari tasks

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: CircleCI[bot] <circleci@influxdata.com>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-04 14:28:29 +00:00
Marco Neumann e24cecd926
fix: buffer allocation while reading parquet files (#5312)
Work around https://github.com/apache/arrow-rs/issues/2321 by limiting
reader batch size to number of rows (based on file-level metadata).

Fixes https://github.com/influxdata/conductor/issues/1103 .
2022-08-04 14:21:05 +00:00
Andrew Lamb 3989ac1386
refactor: remove `split_members` and use `split_conjunction` from upstream DataFusion (#5308)
* refactor: remove split_members and use split_conjunction from datafusion

* fix: clippy
2022-08-04 13:58:59 +00:00
Marco Neumann eea8270e83
fix: `compute_split_time` with small step sizes (#5309)
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-04 13:40:30 +00:00
Nga Tran 34ccc9c7f5 chore: Revert "chore: Revert "refactor: bump batch size (#5251)" (#5288)" (#5300)
This reverts commit 471b8be92f.

Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-04 13:19:46 +00:00
Dom Dwyer 1cad7e13ec build: bump rskafka to latest
Includes minor code changes needed to support the rskafka HEAD commit.

Breaking changes made in
    https://github.com/influxdata/rskafka/issues/160
2022-08-04 15:02:11 +02:00
Andrew Lamb 76171c5cea
refactor: simplify creating AND expressions (#5298)
* refactor: simplify creating AND expressions

* fix: fmt + clippy

Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-04 11:25:43 +00:00
Raphael Taylor-Davies 5f9ade103f
chore: tweak rustc flags (#5293)
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-04 09:12:21 +00:00
dependabot[bot] 251af3f844
chore(deps): Bump serde from 1.0.140 to 1.0.142 (#5296)
* chore(deps): Bump serde from 1.0.140 to 1.0.142

Bumps [serde](https://github.com/serde-rs/serde) from 1.0.140 to 1.0.142.
- [Release notes](https://github.com/serde-rs/serde/releases)
- [Commits](https://github.com/serde-rs/serde/compare/v1.0.140...v1.0.142)

---
updated-dependencies:
- dependency-name: serde
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

* chore: Run cargo hakari tasks

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: CircleCI[bot] <circleci@influxdata.com>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-04 08:49:12 +00:00
dependabot[bot] 07fe5c8af3
chore(deps): Bump libc from 0.2.126 to 0.2.127 (#5306)
Bumps [libc](https://github.com/rust-lang/libc) from 0.2.126 to 0.2.127.
- [Release notes](https://github.com/rust-lang/libc/releases)
- [Commits](https://github.com/rust-lang/libc/compare/0.2.126...0.2.127)

---
updated-dependencies:
- dependency-name: libc
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2022-08-04 08:40:23 +00:00
kodiakhq[bot] 2ecf02e7b2
Merge pull request #5299 from influxdata/crepererum/issue5272
fix: compactor-related freeze and shutdown  fixes
2022-08-03 21:13:09 +00:00
kodiakhq[bot] b3958321d3
Merge branch 'main' into crepererum/issue5272 2022-08-03 21:06:15 +00:00
dependabot[bot] 55e1e2ec2b
chore(deps): Bump thiserror from 1.0.31 to 1.0.32 (#5294)
* chore(deps): Bump thiserror from 1.0.31 to 1.0.32

Bumps [thiserror](https://github.com/dtolnay/thiserror) from 1.0.31 to 1.0.32.
- [Release notes](https://github.com/dtolnay/thiserror/releases)
- [Commits](https://github.com/dtolnay/thiserror/compare/1.0.31...1.0.32)

---
updated-dependencies:
- dependency-name: thiserror
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

* chore: Run cargo hakari tasks

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: CircleCI[bot] <circleci@influxdata.com>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 16:20:36 +00:00
Marco Neumann 039950b4fd feat: ensure clean compactor executor shutdown 2022-08-03 18:07:00 +02:00
Marco Neumann fd74f2639b fix: do not attempt to poll future lists in compactor
It seems that the buffering / parallelization code cannot deal with
empty lists and just freezes forever (which blocks shutdown but will
also freeze the compactor forever).
2022-08-03 18:04:05 +02:00
Marco Neumann 4bd8977d55 refactor: add some main function debug logs 2022-08-03 18:00:28 +02:00
Andrew Lamb 6011c4cd1f
chore: update datafusion pin (#5290)
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 15:43:18 +00:00
Marco Neumann 840e4801b8
feat: make querier RAM pool split a proper feature (#5283)
* feat: make querier RAM pool split a proper feature

- use propre pool names
- expose sizing via CLI/env

Closes https://github.com/influxdata/conductor/issues/1102.

* refactor: improve naming and docs

Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>

Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 15:27:23 +00:00
Andrew Lamb d0f88c664c
docs: improve some docstrings in `iox_query` (#5291)
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 15:20:12 +00:00
Nga Tran ee151c8b41
fix: make batch size back to 1024 to see if the OOM in the compactor go away (#5289)
* fix: make batch size back to 1024 to see if the OOM in the compactor go away

* fix: address review comments

* chore: Apply suggestions from code review

Co-authored-by: Marco Neumann <marco@crepererum.net>

* fix: import needed constant

Co-authored-by: Marco Neumann <marco@crepererum.net>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 15:13:04 +00:00
Marco Neumann 663a20d743
refactor: remove `--ingster-address` (#5255)
Closes #5002.
2022-08-03 15:05:01 +00:00
Nga Tran 471b8be92f
chore: Revert "refactor: bump batch size (#5251)" (#5288)
This reverts commit bb172f8fa8.
2022-08-03 14:23:45 +00:00
Marco Neumann 9fbc95c3ad
feat: add sequencer reset count metric and log to ingester (#5286)
Split out from #5253.

Helps with #5128.

Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 13:00:36 +00:00
dependabot[bot] 5fd59fcc43
chore(deps): Bump syn from 1.0.98 to 1.0.99 (#5284)
Bumps [syn](https://github.com/dtolnay/syn) from 1.0.98 to 1.0.99.
- [Release notes](https://github.com/dtolnay/syn/releases)
- [Commits](https://github.com/dtolnay/syn/compare/1.0.98...1.0.99)

---
updated-dependencies:
- dependency-name: syn
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2022-08-03 12:50:56 +00:00
Marco Neumann 273b3cc165
chore: replace `dotenv` with `dotenvy` (#5285)
The latter one is a maintained fork. This avoids having both crates
after #5282.
2022-08-03 12:41:38 +00:00
dependabot[bot] 7c67b93015
chore(deps): Bump sqlx from 0.6.0 to 0.6.1 (#5282)
Bumps [sqlx](https://github.com/launchbadge/sqlx) from 0.6.0 to 0.6.1.
- [Release notes](https://github.com/launchbadge/sqlx/releases)
- [Changelog](https://github.com/launchbadge/sqlx/blob/main/CHANGELOG.md)
- [Commits](https://github.com/launchbadge/sqlx/commits)

---
updated-dependencies:
- dependency-name: sqlx
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 12:19:16 +00:00
Marco Neumann 772dd858a8
feat: support for regex comparisons in storage CLI (#5281)
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 10:08:44 +00:00
dependabot[bot] 94fe5b4c10
chore(deps): Bump paste from 1.0.7 to 1.0.8 (#5280)
Bumps [paste](https://github.com/dtolnay/paste) from 1.0.7 to 1.0.8.
- [Release notes](https://github.com/dtolnay/paste/releases)
- [Commits](https://github.com/dtolnay/paste/compare/1.0.7...1.0.8)

---
updated-dependencies:
- dependency-name: paste
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-03 09:03:25 +00:00
Stuart Carnie 964062b40c
feat: Add information about profiling using Instruments on macOS (#5275) 2022-08-03 08:45:33 +00:00
Marko Mikulicic a4e2f880be
feat: Expose a C API for the IOx LP parser (#5267)
Can be useful to call the IOx LP parser from other processes, for example from Go.
I used it to run an online comparison of IOx and influxdb Go LP parser in order to identify compatibility
issues.
2022-08-02 15:44:41 +00:00
Marco Neumann 8e2443d879
feat: use two RAM pools in querier (#5271)
Quick&Dirty implementation of a RAM-pool split to see if this has any
effect. I expect the querier performance to improve due to this because
large read buffers can no longer evict precious metadata.

Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-02 15:14:26 +00:00
Nga Tran 4812db9887
feat: fewer buckets but larger ranges for compaction duration histogram (#5259)
* chore: reduce log info

* feat: fewer buckets but larger ranges for compaction duration histogram

* chore: Apply suggestions from code review

Co-authored-by: Marko Mikulicic <mkm@influxdata.com>

* chore: run fmt after appying reviewer's suggestions

Co-authored-by: Marko Mikulicic <mkm@influxdata.com>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-02 14:19:30 +00:00
Andrew Lamb 9c9658ca38
test(influxdb_line_protocol): add value verification test (#5270) 2022-08-02 11:18:09 +00:00
Marco Neumann ee491cbbfc
fix: re-enable querier read buffer cache (#5268)
This reverts commit 82913743f1 / #5252.

I misjudged the cache hit ratio for the RB, see
https://github.com/influxdata/k8s-infra/pull/4548

So let's bring back the RB cache until we have some form of parquet
cache in place.
2022-08-02 08:37:30 +00:00
dependabot[bot] e57ae07db7
chore(deps): Bump serde from 1.0.140 to 1.0.141 (#5260)
Bumps [serde](https://github.com/serde-rs/serde) from 1.0.140 to 1.0.141.
- [Release notes](https://github.com/serde-rs/serde/releases)
- [Commits](https://github.com/serde-rs/serde/compare/v1.0.140...v1.0.141)

---
updated-dependencies:
- dependency-name: serde
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-02 07:52:06 +00:00
Marco Neumann a8f6d579c8
feat: add metric for predicate-based cache entry removal (#5257) 2022-08-02 07:44:53 +00:00
Marco Neumann fec6b18d80
feat: add metric for TTL cache expiration (#5256)
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-02 07:00:30 +00:00
Marko Mikulicic 7d15bd6029
Merge pull request #5265 from influxdata/lp_fp
fix: Fix bug and incompatibility in floating point parsing of scientific notation
2022-08-02 06:23:16 +02:00
Marko Mikulicic 84a856069b fix: Scientific notation without + or -
Closes #5264
2022-08-02 05:46:28 +02:00
Marko Mikulicic a926996485 fix: Negative scientific notation without decimal parts
Closes #5263
2022-08-02 05:40:55 +02:00
Nga Tran 8f1b6f2465
chore: reduce log info (#5254)
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-01 16:00:34 +00:00
Marco Neumann 82913743f1
refactor: disable querier read buffer cache (#5252)
Let's try and see how this performs in prod.

Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-01 15:43:22 +00:00
Marco Neumann bb172f8fa8
refactor: bump batch size (#5251)
This is what DataFusion uses by default and I don't see a reason why we
should use such small batch sizes.

The affect is probably only visible in certain filter-aggregate queries
that don't focus on a single series (because there we likely end up with
1 or 2 batches only, esp. after #5250) for coarse-grained filters, esp.
  when the filter key is not the first sort key.

Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-01 13:49:58 +00:00
Marco Neumann b12ebe1109
fix: do not panic on invalid timestamp ranges (#5249)
Timestamp ranges come from "untrusted" inputs (via gRPC) and must not
lead to panics. The only case where this could happen is at `start >
end`. Let's just set `start = end` in this case. Reaonsing:

- Semantically this is a sound range, since this is only a somewhat
  degenerated case of "empty".
- We already allow `start = end` to represent "empty" ranges.
- We already clamp (and therefore modify) `start` to the valid range.

Fixes https://github.com/influxdata/conductor/issues/1080.

Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
2022-08-01 13:35:34 +00:00