Commit Graph

1937 Commits

Author SHA1 Message Date
kssenii
7643d84095 Merge branch 'master' of https://github.com/ClickHouse/ClickHouse into pg-ch-replica 2021-04-30 22:02:51 +00:00
alexey-milovidov
7fa24d7b26
Merge pull request #23664 from azat/msan-dtor
Enable use-after-destruction detection in MSan
2021-04-30 21:51:28 +03:00
filimonov
66eaf210a0
Update Dockerfile 2021-04-30 15:29:40 +02:00
filimonov
87e5aa8c2b
autodetect arch of gosu in server dockerfile 2021-04-30 15:27:31 +02:00
alexey-milovidov
fab763f8fa
Revert "Fix CI build for gcc-10" 2021-04-29 20:43:08 +03:00
Maksim Kita
5b4d2006aa Fix CI build for gcc-10 2021-04-29 14:29:55 +03:00
Azat Khuzhin
d83ea5844f Enable use-after-destruction detection in MSan
Refs: https://clang.llvm.org/docs/MemorySanitizer.html#use-after-destruction-detection
2021-04-28 23:02:52 +03:00
Maksim Kita
9bf96a278d
Merge pull request #23711 from ClickHouse/remove-old-compilers
Remove obsolete compilers
2021-04-28 22:51:21 +03:00
Ilya Yatsishin
8e67cab2a3
Merge pull request #23138 from qoega/add-dockerproxy-to-runner
Add dockerhub-proxy to runner
2021-04-28 17:10:28 +03:00
Alexander Kuzmenkov
0c1e897e80
Merge pull request #23707 from ClickHouse/aku/perf-stable-query-index
stable query indexes in perf test
2021-04-28 13:06:53 +03:00
Alexey Milovidov
eda56e52d8 Remove obsolete compilers 2021-04-28 07:16:48 +03:00
Alexander Kuzmenkov
cc0dd732d9 stable query indexes in perf test 2021-04-28 00:58:37 +03:00
Alexander Kuzmenkov
1e7fc204d8
Merge pull request #23554 from ClickHouse/aku/perf-numa-attributes
add numactl info to perf test run attributes
2021-04-27 14:09:57 +03:00
Ilya Yatsishin
a0003e6d42
Touch to rebuild 2021-04-27 13:41:39 +03:00
Alexander Kuzmenkov
9bb4d8769f
Merge pull request #23550 from ClickHouse/aku/perf-more-info
add more info to perf test report
2021-04-27 01:15:54 +03:00
Alexander Kuzmenkov
bfa47f7c5f
Update compare.sh 2021-04-26 12:41:29 +03:00
Alexander Kuzmenkov
5d101336ff fix 2021-04-26 12:39:54 +03:00
mergify[bot]
68ee3ff70e
Merge branch 'master' into limit-gcc 2021-04-25 05:01:45 +00:00
Alexey Milovidov
1c2d16f608 Fix build 2021-04-25 06:11:54 +03:00
alexey-milovidov
bd70aabf5c
Merge pull request #23605 from ClickHouse/cleanup-release
Remove rotten parts of release script
2021-04-25 05:51:02 +03:00
alexey-milovidov
025d40ade6
Merge pull request #23553 from ClickHouse/aku/trace-fg
export trace log from stateless tests in flamegraph-friendly format
2021-04-25 02:30:35 +03:00
Alexey Milovidov
fe76b2242a Remove rotten parts of release script 2021-04-25 02:11:31 +03:00
alexey-milovidov
c489355357
Merge pull request #23561 from ClickHouse/stress-test-less-oom
Less chance of OOM in stress tests
2021-04-24 23:16:50 +03:00
alexey-milovidov
877d245d8f
Merge pull request #23462 from zhang2014/fix/ISSUE-23310
ISSUES-23310 Try fix MySQL 8.0 address already in use
2021-04-24 04:17:21 +03:00
Alexey Milovidov
e9e4ab3813 Less chance of OOM in stress tests 2021-04-24 03:27:23 +03:00
Alexander Kuzmenkov
c40a300d03 add numactl info to perf run attributes 2021-04-23 23:52:18 +03:00
Alexander Kuzmenkov
77f0be25b6
Update run.sh 2021-04-23 23:03:53 +03:00
Alexander Kuzmenkov
5f1c825e1d
Update compare.sh 2021-04-23 22:01:24 +03:00
Alexander Kuzmenkov
5f23acfb47
Update Dockerfile 2021-04-23 21:58:37 +03:00
Alexander Kuzmenkov
9f187b594c
Update run.sh 2021-04-23 21:51:26 +03:00
Alexander Kuzmenkov
294dd3c6cc export trace log from stateless tests in flamegraph-friendly format 2021-04-23 21:50:02 +03:00
Alexander Kuzmenkov
e052edc7df
Update compare.sh 2021-04-23 20:32:30 +03:00
Alexander Kuzmenkov
bcc0744adb fix 2021-04-23 18:54:48 +03:00
Alexander Kuzmenkov
e51c844e2c add more info to perf test report 2021-04-23 16:47:33 +03:00
Alexander Kuzmenkov
0b990c9519
Merge pull request #23514 from ClickHouse/aku/perf-test-cpu-model
upload cpu model to perf test db
2021-04-23 09:25:51 +03:00
Alexander Kuzmenkov
1463d5089c
Update Dockerfile 2021-04-22 21:31:34 +03:00
Alexander Kuzmenkov
3f855cb714 more 2021-04-22 20:18:21 +03:00
Alexander Kuzmenkov
6a1414663f upload cpu model to perf test db 2021-04-22 19:48:32 +03:00
zhang2014
81496b2e63 Try fix MySQL 8.0 address already in use 2021-04-22 11:04:30 +08:00
Alexey Milovidov
8cb0e5579a Remove gcc from docs 2021-04-22 04:20:03 +03:00
alexey-milovidov
9c649932bc
Merge pull request #23375 from ClickHouse/fix-read-in-order-with-collation
Fix read in order optimization of COLLATE is present #22379
2021-04-21 15:00:02 +03:00
Alexey Milovidov
f4926a525f Exclude from fasttest 2021-04-20 23:32:18 +03:00
alexey-milovidov
db51ef8012
Merge pull request #23264 from azat/tests-artifacts-trace_log
Add trace_log into stateless/stress test artifacts
2021-04-20 21:44:30 +03:00
alexey-milovidov
a311a5c0b5
Merge pull request #23322 from azat/disable-min_bytes_to_use_mmap_io
Disable min_bytes_to_use_mmap_io by default
2021-04-20 19:27:47 +03:00
Azat Khuzhin
2575d03a33 Add trace_log into stateless/stress test artifacts 2021-04-20 08:03:29 +03:00
alexey-milovidov
62899436db
Revert "add uniqThetaSketch" 2021-04-20 03:34:21 +03:00
robot-clickhouse
db82e9e3d5 Auto version update to [21.6.1.1] [54451] 2021-04-20 01:48:20 +03:00
Azat Khuzhin
6fba6f7ddd Disable min_bytes_to_use_mmap_io by default
Reading files using mmap() does not have any significant benefits over
plain read() [1].

  [1]: https://gist.github.com/azat/3d6c8d82bdd91e7a38d997fd6bcfd574

And not only it does not have significant benefits, it also has some
issues, due to max_server_memory_usage (default to 90% of available
RAM), since when you read files with mmap() eventually process RSS may
exceed max_server_memory_usage, and in this case any allocation will
fail (with "Memory limit exceeded (total)") error (yes kernel will
unload pages, but likely it will happens after queries will starting to
fail), like in this test [2].

  [2]: https://gist.github.com/azat/4813489828162e6c2ce131963c6a1acb

TL;DR;

Note that there was also an idea to take those mmap()'ed regions in
memory tracking (#23211), but there are some drawbacks (since accounting
mmap() is tricky, first of all you need to account only once per inode
for file and plus kernel can unload some pages and those memory will not
be used by the server anymore).

And as an adddition to #23211 there was #23212, that adds
max_bytes_to_use_mmap_io, but since mmap is not a subject for memory
accounting there is no need in it.
2021-04-20 00:25:16 +03:00
Alexander Kuzmenkov
2a4bcb6e3f
Merge pull request #23159 from ClickHouse/aku/merge-fusecount
merging sumCount fusion PR #21337
2021-04-19 16:47:13 +03:00
Kruglov Pavel
995973bf1f
Merge pull request #22609 from pingyu/datasketches-uniq
add uniqThetaSketch
2021-04-19 10:32:29 +03:00