Context lock contention fix

[kitaisreal]

Changelog category (leave one):

• Performance Improvement

Changelog entry (a user-readable short description of the changes that goes to CHANGELOG.md):

Fix contention on Context lock, this significantly improves performance for a lot of short-running concurrent queries.

[robot-ch-test-poll4]

This is an automated comment for commit 71cb645 with description of existing statuses. It's updated for the latest CI running

❌ Click here to open a full report in a separate page

Successful checks

Check name	Description	Status
AST fuzzer	Runs randomly generated queries to catch program errors. The build type is optionally given in parenthesis. If it fails, ask a maintainer for help	✅ success
CI running	A meta-check that indicates the running CI. Normally, it's in success or pending state. The failed status indicates some problems with the PR	✅ success
ClickHouse build check	Builds ClickHouse in various configurations for use in further steps. You have to fix the builds that fail. Build logs often has enough information to fix the error, but you might have to reproduce the failure locally. The cmake options can be found in the build log, grepping for cmake. Use these options and follow the general build process	✅ success
Compatibility check	Checks that clickhouse binary runs on distributions with old libc versions. If it fails, ask a maintainer for help	✅ success
Docker image for servers	The check to build and optionally push the mentioned image to docker hub	✅ success
Fast test	Normally this is the first check that is ran for a PR. It builds ClickHouse and runs most of stateless functional tests, omitting some. If it fails, further checks are not started until it is fixed. Look at the report to see which tests fail, then reproduce the failure locally as described here	✅ success
Flaky tests	Checks if new added or modified tests are flaky by running them repeatedly, in parallel, with more randomization. Functional tests are run 100 times with address sanitizer, and additional randomization of thread scheduling. Integrational tests are run up to 10 times. If at least once a new test has failed, or was too long, this check will be red. We don't allow flaky tests, read the doc	✅ success
Install packages	Checks that the built packages are installable in a clear environment	✅ success
Integration tests	The integration tests report. In parenthesis the package type is given, and in square brackets are the optional part/total tests	✅ success
Mergeable Check	Checks if all other necessary checks are successful	✅ success
Performance Comparison	Measure changes in query performance. The performance test report is described in detail here. In square brackets are the optional part/total tests	✅ success
Push to Dockerhub	The check for building and pushing the CI related docker images to docker hub	✅ success
SQLTest	There's no description for the check yet, please add it to tests/ci/ci_config.py:CHECK_DESCRIPTIONS	✅ success
SQLancer	Fuzzing tests that detect logical bugs with SQLancer tool	✅ success
Sqllogic	Run clickhouse on the sqllogic test set against sqlite and checks that all statements are passed	✅ success
Stateful tests	Runs stateful functional tests for ClickHouse binaries built in various configurations -- release, debug, with sanitizers, etc	✅ success
Stateless tests	Runs stateless functional tests for ClickHouse binaries built in various configurations -- release, debug, with sanitizers, etc	✅ success
Style Check	Runs a set of checks to keep the code style clean. If some of tests failed, see the related log from the report	✅ success
Unit tests	Runs the unit tests for different release types	✅ success

Check name	Description	Status
Stress test	Runs stateless functional tests concurrently from several clients to detect concurrency-related errors	❌ failure
Upgrade check	Runs stress tests on server version from last release and then tries to upgrade it to the version from the PR. It checks if the new server can successfully startup without any errors, crashes or sanitizer asserts	❌ failure

[kitaisreal]

Benchmark to simulate complex short-running query, this is not worst case scenario.

./clickhouse-benchmark --query="SELECT * FROM (SELECT * FROM (SELECT * FROM (SELECT * FROM (SELECT * FROM (SELECT * FROM (SELECT * FROM (SELECT * FROM (SELECT * FROM (SELECT UserID, count(*) FROM (SELECT * FROM datasets.hits_v1 LIMIT 10) GROUP BY UserID))))))))) FORMAT Null" --concurrency=1000

Before:

localhost:9000, queries: 8698, QPS: 90.463, RPS: 904.634, MiB/s: 0.007, result RPS: 0.000, result MiB/s: 0.000.

0.000%		2.849 sec.
10.000%		9.661 sec.
20.000%		10.214 sec.
30.000%		10.499 sec.
40.000%		10.691 sec.
50.000%		10.851 sec.
60.000%		10.990 sec.
70.000%		11.145 sec.
80.000%		11.306 sec.
90.000%		11.529 sec.
95.000%		11.695 sec.
99.000%		12.049 sec.
99.900%		12.437 sec.
99.990%		12.986 sec.

SELECT
    quantileExact(0.5)(lock_wait_milliseconds),
    max(lock_wait_milliseconds)
FROM
(
    SELECT (ProfileEvents['ContextLockWaitMicroseconds']) / 1000. AS lock_wait_milliseconds
    FROM system.query_log
    WHERE lock_wait_milliseconds > 0
)

┌─quantileExact(0.5)(lock_wait_milliseconds)─┬─max(lock_wait_milliseconds)─┐
│                                  10428.938 │                   12771.711 │
└────────────────────────────────────────────┴─────────────────────────────┘

After:

Queries executed: 10177.

localhost:9000, queries: 10177, QPS: 175.670, RPS: 1756.703, MiB/s: 0.013, result RPS: 0.000, result MiB/s: 0.000.

0.000%		0.200 sec.
10.000%		3.185 sec.
20.000%		3.551 sec.
30.000%		4.096 sec.
40.000%		6.402 sec.
50.000%		6.559 sec.
60.000%		6.629 sec.
70.000%		6.697 sec.
80.000%		6.782 sec.
90.000%		6.947 sec.
95.000%		7.848 sec.
99.000%		9.959 sec.
99.900%		12.300 sec.
99.990%		13.092 sec.

SELECT quantileExact(0.5)(lock_wait_milliseconds), max(lock_wait_milliseconds) FROM (SELECT (ProfileEvents['ContextLockWaitMicroseconds'] / 1000.0) AS lock_wait_milliseconds FROM system.query_log WHERE lock_wait_milliseconds > 0)

┌─quantileExact(0.5)(lock_wait_milliseconds)─┬─max(lock_wait_milliseconds)─┐
│                                      0.001 │                       7.515 │
└────────────────────────────────────────────┴─────────────────────────────┘

[KochetovNicolai]

Looks ok. Maybe we can think about replacing it with std::call_once

[alexey-milovidov]

Why not something like

void initialize()
{
    static Initializer ...
}

[KochetovNicolai]

I did not check all the lock calls, but overall, it looks good. Let\s merge.

[kitaisreal]

@rschu1ze it is impossible to check all invariants in Context and we had a lot of bugs even before this refactoring, I started pull request that will use TSA for all Context and Shared context members to find bugs. It is not finished yet, but you can take a look #55278.