Re: [PATCH v11 19/19] futex: Allow to make the private hash immutable.

[Shrikanth Hegde]

Hi Sebastian.

On 4/7/25 21:27, Sebastian Andrzej Siewior wrote:
> My initial testing showed that
> 	perf bench futex hash
>
> reported less operations/sec with private hash. After using the same
> amount of buckets in the private hash as used by the global hash then
> the operations/sec were about the same.
>
> This changed once the private hash became resizable. This feature added
> a RCU section and reference counting via atomic inc+dec operation into
> the hot path.
> The reference counting can be avoided if the private hash is made
> immutable.
> Extend PR_FUTEX_HASH_SET_SLOTS by a fourth argument which denotes if the
> private should be made immutable. Once set (to true) the a further
> resize is not allowed (same if set to global hash).
> Add PR_FUTEX_HASH_GET_IMMUTABLE which returns true if the hash can not
> be changed.
> Update "perf bench" suite.

It would be good option for the application to decide if it needs this.
Using this option makes the perf regression goes away using previous number of buckets.

Acked-by: Shrikanth Hegde <sshegde@xxxxxxxxxxxxx>

base:
./perf bench futex hash
Averaged 1556023 operations/sec (+- 0.08%), total secs = 10  <<-- 1.5M

with series:
./perf bench futex hash -b32768
Averaged 126499 operations/sec (+- 0.41%), total secs = 10   <<-- .12M

./perf bench futex hash -Ib32768
Averaged 1549339 operations/sec (+- 0.08%), total secs = 10  <<-- 1.5M


> For comparison, results of "perf bench futex hash -s":
> - Xeon CPU E5-2650, 2 NUMA nodes, total 32 CPUs:
>    - Before the introducing task local hash
>      shared  Averaged 1.487.148 operations/sec (+- 0,53%), total secs = 10
>      private Averaged 2.192.405 operations/sec (+- 0,07%), total secs = 10
>
>    - With the series
>      shared  Averaged 1.326.342 operations/sec (+- 0,41%), total secs = 10
>      -b128   Averaged   141.394 operations/sec (+- 1,15%), total secs = 10
>      -Ib128  Averaged   851.490 operations/sec (+- 0,67%), total secs = 10
>      -b8192  Averaged   131.321 operations/sec (+- 2,13%), total secs = 10
>      -Ib8192 Averaged 1.923.077 operations/sec (+- 0,61%), total secs = 10
>      128 is the default allocation of hash buckets.
>      8192 was the previous amount of allocated hash buckets.
>
> - Xeon(R) CPU E7-8890 v3, 4 NUMA nodes, total 144 CPUs:
>    - Before the introducing task local hash
>      shared   Averaged 1.810.936 operations/sec (+- 0,26%), total secs = 20
>      private  Averaged 2.505.801 operations/sec (+- 0,05%), total secs = 20
>
>    - With the series
>      shared   Averaged 1.589.002 operations/sec (+- 0,25%), total secs = 20
>      -b1024   Averaged    42.410 operations/sec (+- 0,20%), total secs = 20
>      -Ib1024  Averaged   740.638 operations/sec (+- 1,51%), total secs = 20
>      -b65536  Averaged    48.811 operations/sec (+- 1,35%), total secs = 20
>      -Ib65536 Averaged 1.963.165 operations/sec (+- 0,18%), total secs = 20
>      1024 is the default allocation of hash buckets.
>      65536 was the previous amount of allocated hash buckets.
>
> Cc: "Liang, Kan" <kan.liang@xxxxxxxxxxxxxxx>
> Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
> Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
> Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
> Cc: Ian Rogers <irogers@xxxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
> Cc: Mark Rutland <mark.rutland@xxxxxxx>
> Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
> Cc: linux-perf-users@xxxxxxxxxxxxxxx
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
> ---
>   include/linux/futex.h                  |  2 +-
>   include/uapi/linux/prctl.h             |  1 +
>   kernel/futex/core.c                    | 42 ++++++++++++++++++++++----
>   kernel/sys.c                           |  2 +-
>   tools/include/uapi/linux/prctl.h       |  1 +
>   tools/perf/bench/futex-hash.c          |  1 +
>   tools/perf/bench/futex-lock-pi.c       |  1 +
>   tools/perf/bench/futex-requeue.c       |  1 +
>   tools/perf/bench/futex-wake-parallel.c |  1 +
>   tools/perf/bench/futex-wake.c          |  1 +
>   tools/perf/bench/futex.c               |  8 +++--
>   tools/perf/bench/futex.h               |  1 +
>   12 files changed, 51 insertions(+), 11 deletions(-)

nit: Does it makes sense to split this patch into futex and perf?