From: Vlastimil Babka <vbabka@suse.cz>
To: "Christoph Lameter (Ampere)" <cl@gentwo.org>
Cc: Hao Li <hao.li@linux.dev>, Harry Yoo <harry.yoo@oracle.com>,
Petr Tesarik <ptesarik@suse.com>,
David Rientjes <rientjes@google.com>,
Roman Gushchin <roman.gushchin@linux.dev>,
Andrew Morton <akpm@linux-foundation.org>,
Uladzislau Rezki <urezki@gmail.com>,
"Liam R. Howlett" <Liam.Howlett@oracle.com>,
Suren Baghdasaryan <surenb@google.com>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Alexei Starovoitov <ast@kernel.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
linux-rt-devel@lists.linux.dev, bpf@vger.kernel.org,
kasan-dev@googlegroups.com,
kernel test robot <oliver.sang@intel.com>,
stable@vger.kernel.org, "Paul E. McKenney" <paulmck@kernel.org>
Subject: Re: [PATCH v4 00/22] slab: replace cpu (partial) slabs with sheaves
Date: Fri, 6 Feb 2026 17:44:45 +0100 [thread overview]
Message-ID: <699982e5-6660-4e48-be57-3ee7326a20d5@suse.cz> (raw)
In-Reply-To: <2abde505-1e35-8d74-2806-7a3cd430e306@gentwo.org>
On 2/4/26 19:24, Christoph Lameter (Ampere) wrote:
> On Wed, 4 Feb 2026, Vlastimil Babka wrote:
>
>> > So I think the performance of the percpu partial list and the sheaves mechanism
>> > is roughly the same, which is consistent with our expectations.
>>
>> Thanks!
>
> There are other considerations that usually do not show up well in
> benchmark tests.
>
> The sheaves cannot do the spatial optimizations that cpu partial lists
> provide. Fragmentation in slab caches (and therefore the nubmer of
> partial slab pages) will increase since
>
> 1. The objects are not immediately returned to their slab pages but end up
> in some queuing structure.
>
> 2. Available objects from a single slab page are not allocated in sequence
> to empty partial pages and remove the page from the partial lists.
>
> Objects are put into some queue on free and are processed on a FIFO basis.
> Objects allocated may come from lots of different slab pages potentially
> increasing TLB pressure.
IIUC this is what you said before [1] and the cover letter has a link and a
summary of it.
[1] https://lore.kernel.org/all/f7c33974-e520-387e-9e2f-1e523bfe1545@gentwo.org/
prev parent reply other threads:[~2026-02-06 16:44 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-23 6:52 Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 01/22] mm/slab: add rcu_barrier() to kvfree_rcu_barrier_on_cache() Vlastimil Babka
2026-01-27 16:08 ` Liam R. Howlett
2026-01-23 6:52 ` [PATCH v4 02/22] mm/slab: fix false lockdep warning in __kfree_rcu_sheaf() Vlastimil Babka
2026-01-23 12:03 ` Sebastian Andrzej Siewior
2026-01-24 10:58 ` Harry Yoo
2026-01-23 6:52 ` [PATCH v4 03/22] slab: add SLAB_CONSISTENCY_CHECKS to SLAB_NEVER_MERGE Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 04/22] mm/slab: move and refactor __kmem_cache_alias() Vlastimil Babka
2026-01-27 16:17 ` Liam R. Howlett
2026-01-27 16:59 ` Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 05/22] mm/slab: make caches with sheaves mergeable Vlastimil Babka
2026-01-27 16:23 ` Liam R. Howlett
2026-01-23 6:52 ` [PATCH v4 06/22] slab: add sheaves to most caches Vlastimil Babka
2026-01-26 6:36 ` Hao Li
2026-01-26 8:39 ` Vlastimil Babka
2026-01-26 13:59 ` Breno Leitao
2026-01-27 16:34 ` Liam R. Howlett
2026-01-27 17:01 ` Vlastimil Babka
2026-01-29 7:24 ` Zhao Liu
2026-01-29 8:21 ` Vlastimil Babka
2026-01-30 7:15 ` Zhao Liu
2026-02-04 18:01 ` Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 07/22] slab: introduce percpu sheaves bootstrap Vlastimil Babka
2026-01-26 6:13 ` Hao Li
2026-01-26 8:42 ` Vlastimil Babka
2026-01-27 17:31 ` Liam R. Howlett
2026-01-23 6:52 ` [PATCH v4 08/22] slab: make percpu sheaves compatible with kmalloc_nolock()/kfree_nolock() Vlastimil Babka
2026-01-23 18:05 ` Alexei Starovoitov
2026-01-27 17:36 ` Liam R. Howlett
2026-01-29 8:25 ` Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 09/22] slab: handle kmalloc sheaves bootstrap Vlastimil Babka
2026-01-27 18:30 ` Liam R. Howlett
2026-01-23 6:52 ` [PATCH v4 10/22] slab: add optimized sheaf refill from partial list Vlastimil Babka
2026-01-26 7:12 ` Hao Li
2026-01-29 7:43 ` Harry Yoo
2026-01-29 8:29 ` Vlastimil Babka
2026-01-27 20:05 ` Liam R. Howlett
2026-01-29 8:01 ` Harry Yoo
2026-01-23 6:52 ` [PATCH v4 11/22] slab: remove cpu (partial) slabs usage from allocation paths Vlastimil Babka
2026-01-23 18:17 ` Alexei Starovoitov
2026-01-23 6:52 ` [PATCH v4 12/22] slab: remove SLUB_CPU_PARTIAL Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 13/22] slab: remove the do_slab_free() fastpath Vlastimil Babka
2026-01-23 18:15 ` Alexei Starovoitov
2026-01-23 6:52 ` [PATCH v4 14/22] slab: remove defer_deactivate_slab() Vlastimil Babka
2026-01-23 17:31 ` Alexei Starovoitov
2026-01-23 6:52 ` [PATCH v4 15/22] slab: simplify kmalloc_nolock() Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 16/22] slab: remove struct kmem_cache_cpu Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 17/22] slab: remove unused PREEMPT_RT specific macros Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 18/22] slab: refill sheaves from all nodes Vlastimil Babka
2026-01-27 14:28 ` Mateusz Guzik
2026-01-27 22:04 ` Vlastimil Babka
2026-01-29 9:16 ` Harry Yoo
2026-01-23 6:52 ` [PATCH v4 19/22] slab: update overview comments Vlastimil Babka
2026-01-23 6:52 ` [PATCH v4 20/22] slab: remove frozen slab checks from __slab_free() Vlastimil Babka
2026-01-29 7:16 ` Harry Yoo
2026-01-23 6:52 ` [PATCH v4 21/22] mm/slub: remove DEACTIVATE_TO_* stat items Vlastimil Babka
2026-01-29 7:21 ` Harry Yoo
2026-01-23 6:53 ` [PATCH v4 22/22] mm/slub: cleanup and repurpose some " Vlastimil Babka
2026-01-29 7:40 ` Harry Yoo
2026-01-29 15:18 ` [PATCH v4 00/22] slab: replace cpu (partial) slabs with sheaves Hao Li
2026-01-29 15:28 ` Vlastimil Babka
2026-01-29 16:06 ` Hao Li
2026-01-29 16:44 ` Liam R. Howlett
2026-01-30 4:38 ` Hao Li
2026-01-30 4:50 ` Hao Li
2026-01-30 6:17 ` Hao Li
2026-02-04 18:02 ` Vlastimil Babka
2026-02-04 18:24 ` Christoph Lameter (Ampere)
2026-02-06 16:44 ` Vlastimil Babka [this message]
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=699982e5-6660-4e48-be57-3ee7326a20d5@suse.cz \
--to=vbabka@suse.cz \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=ast@kernel.org \
--cc=bigeasy@linutronix.de \
--cc=bpf@vger.kernel.org \
--cc=cl@gentwo.org \
--cc=hao.li@linux.dev \
--cc=harry.yoo@oracle.com \
--cc=kasan-dev@googlegroups.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-rt-devel@lists.linux.dev \
--cc=oliver.sang@intel.com \
--cc=paulmck@kernel.org \
--cc=ptesarik@suse.com \
--cc=rientjes@google.com \
--cc=roman.gushchin@linux.dev \
--cc=stable@vger.kernel.org \
--cc=surenb@google.com \
--cc=urezki@gmail.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