Commit Graph

7 Commits

Author SHA1 Message Date
Azat Khuzhin
22611781b0 Fix jemalloc assertion due to non-monotonic CLOCK_MONOTONIC_COARSE
Recently one tricky assertion of jemalloc had been discovered [1]:

    Failed assertion: "nstime_compare(&decay->epoch, new_time) <= 0"

  [1]: https://github.com/ClickHouse/ClickHouse/issues/66193

And as it turns out it is really possible for CLOCK_MONOTONIC_COARSE to
go backwards, in a nutshell it can be done with ADJ_FREQUENCY, you can
find example here [2]. And I can't trigger this issue for non-coarse
clocks.

  [2]: https://gist.github.com/azat/7ea7f50ed75591b1af2d675a240ea94c?permalink_comment_id=5119222#gistcomment-5119222

But, jemalloc do not call clock_gettime() that frequently (I've verified
it), so it can use non-coarse version - CLOCK_MONOTONIC

I've also measured the latency of CLOCK_MONOTONIC and
CLOCK_MONOTONIC_COARSE, and it is 20ns vs 4ns per call [3], so make this
change affect performance you need really frequently calls of
clock_gettime.

  [3]: https://gist.github.com/azat/622fa1f9a5d8e7d546ee9d294501961d?permalink_comment_id=5119245#gistcomment-5119245

Interesting, that this bug started to appears only after jemalloc heap
profiler had been enabled by default [4], no clue why (I would believe
more in a more frequent calls to clock_adjtime(ADJ_FREQUENCY), but I
can't verify this)

  [4]: https://github.com/ClickHouse/ClickHouse/pull/65702

To be continued...

Fixes: https://github.com/ClickHouse/ClickHouse/issues/66193
Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2024-07-14 08:21:13 +02:00
袁焊忠
47d9b0e6a1
[hotfix] [docs] Fix typo 2023-11-02 15:56:45 +08:00
Azat Khuzhin
054e84c382 jemalloc: add a note about JEMALLOC_PREFIX
Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2022-02-17 21:25:58 +03:00
Azat Khuzhin
bc5aeb4dcf jemalloc: add a note about musl support
Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2022-02-17 21:25:58 +03:00
Azat Khuzhin
1a98c1aace jemalloc: move JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF out from per-arch
Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2022-02-17 21:25:58 +03:00
Azat Khuzhin
e962649899 jemalloc: correctly disable JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF
Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2022-02-17 21:25:58 +03:00
alexey-milovidov
9cd5228df2
Using jemalloc instead of tcmalloc. ()
* Added jemalloc as submodule [#CLICKHOUSE-2]

* Imported jemalloc-cmake [#CLICKHOUSE-2]

* Added README for jemalloc-cmake [#CLICKHOUSE-2]

* Trying to add jemalloc [#CLICKHOUSE-2]

* Trying to add jemalloc [#CLICKHOUSE-2]

* Trying to add jemalloc [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]

* Add support for jemalloc: development [#CLICKHOUSE-2]
2018-08-02 03:20:20 +03:00