From: Peter Zijlstra <peterz@infradead.org>
To: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: "Sebastian Andrzej Siewior" <bigeasy@linutronix.de>,
"André Almeida" <andrealmeid@igalia.com>,
"Darren Hart" <dvhart@infradead.org>,
"Davidlohr Bueso" <dave@stgolabs.net>,
"Ingo Molnar" <mingo@redhat.com>,
"Juri Lelli" <juri.lelli@redhat.com>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Valentin Schneider" <vschneid@redhat.com>,
"Waiman Long" <longman@redhat.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v10 20/21] futex: Implement FUTEX2_NUMA
Date: Tue, 25 Mar 2025 23:56:00 +0100 [thread overview]
Message-ID: <20250325225600.GP36322@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <fc3a6902-a845-4b11-ace8-514f10194288@linux.ibm.com>
On Wed, Mar 26, 2025 at 01:22:19AM +0530, Shrikanth Hegde wrote:
> > + return &futex_queues[node][hash & futex_hashmask];
^^^^^^^
> > + hashsize = 256 * num_possible_cpus();
> > + hashsize /= num_possible_nodes();
>
> Wouldn't it be better to use num_online_nodes? each node may get a bigger
> hash bucket which means less collision no?
No. There are two problems with num_online_nodes, and both are evident
above.
Consider the case of a sparse set.
next prev parent reply other threads:[~2025-03-25 22:56 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-12 15:16 [PATCH v10 00/21] futex: Add support task local hash maps, FUTEX2_NUMA and FUTEX2_MPOL Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 01/21] rcuref: Provide rcuref_is_dead() Sebastian Andrzej Siewior
2025-03-13 4:23 ` Joel Fernandes
2025-03-13 7:55 ` Sebastian Andrzej Siewior
2025-03-14 10:36 ` Peter Zijlstra
2025-03-12 15:16 ` [PATCH v10 02/21] futex: Move futex_queue() into futex_wait_setup() Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 03/21] futex: Pull futex_hash() out of futex_q_lock() Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 04/21] futex: Create hb scopes Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 05/21] futex: Create futex_hash() get/put class Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 06/21] futex: Create helper function to initialize a hash slot Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 07/21] futex: Add basic infrastructure for local task local hash Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 08/21] futex: Hash only the address for private futexes Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 09/21] futex: Allow automatic allocation of process wide futex hash Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 10/21] futex: Decrease the waiter count before the unlock operation Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 11/21] futex: Introduce futex_q_lockptr_lock() Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 12/21] futex: Acquire a hash reference in futex_wait_multiple_setup() Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 13/21] futex: Allow to re-allocate the private local hash Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 14/21] futex: Resize local futex hash table based on number of threads Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 15/21] futex: s/hb_p/fph/ Sebastian Andrzej Siewior
2025-03-14 12:36 ` Peter Zijlstra
2025-03-14 13:10 ` Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 16/21] futex: Remove superfluous state Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 17/21] futex: Untangle and naming Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 18/21] futex: Rework SET_SLOTS Sebastian Andrzej Siewior
2025-03-26 15:37 ` Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 19/21] mm: Add vmalloc_huge_node() Sebastian Andrzej Siewior
2025-03-12 22:02 ` Andrew Morton
2025-03-13 7:59 ` Sebastian Andrzej Siewior
2025-03-13 22:08 ` Andrew Morton
2025-03-14 9:59 ` Sebastian Andrzej Siewior
2025-03-14 10:34 ` Andrew Morton
2025-03-12 15:16 ` [PATCH v10 20/21] futex: Implement FUTEX2_NUMA Sebastian Andrzej Siewior
2025-03-25 19:52 ` Shrikanth Hegde
2025-03-25 22:52 ` Peter Zijlstra
2025-03-25 22:56 ` Peter Zijlstra [this message]
2025-03-26 12:57 ` Shrikanth Hegde
2025-03-26 13:37 ` Peter Zijlstra
2025-03-26 15:06 ` Shrikanth Hegde
2025-03-26 8:03 ` Sebastian Andrzej Siewior
2025-03-12 15:16 ` [PATCH v10 21/21] futex: Implement FUTEX2_MPOL Sebastian Andrzej Siewior
2025-03-12 15:18 ` [PATCH v10 00/21] futex: Add support task local hash maps, FUTEX2_NUMA and FUTEX2_MPOL Sebastian Andrzej Siewior
2025-03-14 10:42 ` Peter Zijlstra
2025-03-14 10:58 ` Peter Zijlstra
2025-03-14 11:28 ` Sebastian Andrzej Siewior
2025-03-14 11:41 ` Peter Zijlstra
2025-03-14 12:00 ` Sebastian Andrzej Siewior
2025-03-14 12:30 ` Peter Zijlstra
2025-03-14 13:30 ` Sebastian Andrzej Siewior
2025-03-14 14:18 ` Peter Zijlstra
2025-03-14 14:40 ` Paul E. McKenney
2025-03-18 13:24 ` Shrikanth Hegde
2025-03-18 16:12 ` Davidlohr Bueso
2025-03-25 19:04 ` Shrikanth Hegde
2025-03-26 9:31 ` Sebastian Andrzej Siewior
2025-03-26 12:54 ` Shrikanth Hegde
2025-03-26 14:01 ` Sebastian Andrzej Siewior
2025-03-26 8:49 ` Sebastian Andrzej Siewior
2025-04-07 16:15 ` Sebastian Andrzej Siewior
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250325225600.GP36322@noisy.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=andrealmeid@igalia.com \
--cc=bigeasy@linutronix.de \
--cc=dave@stgolabs.net \
--cc=dvhart@infradead.org \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=mingo@redhat.com \
--cc=sshegde@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=vschneid@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox