From: "Christoph Lameter (Ampere)" <cl@gentwo.org>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: Suren Baghdasaryan <surenb@google.com>,
"Liam R. Howlett" <Liam.Howlett@oracle.com>,
David Rientjes <rientjes@google.com>,
Roman Gushchin <roman.gushchin@linux.dev>,
Hyeonggon Yoo <42.hyeyoo@gmail.com>,
Uladzislau Rezki <urezki@gmail.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
rcu@vger.kernel.org, maple-tree@lists.infradead.org,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Alexei Starovoitov <ast@kernel.org>
Subject: Re: [PATCH RFC v2 00/10] SLUB percpu sheaves
Date: Fri, 14 Feb 2025 10:28:11 -0800 (PST) [thread overview]
Message-ID: <d731cf1b-a594-983e-90e1-9380410e38fc@gentwo.org> (raw)
In-Reply-To: <20250214-slub-percpu-caches-v2-0-88592ee0966a@suse.cz>
On Fri, 14 Feb 2025, Vlastimil Babka wrote:
> - Cheaper fast paths. For allocations, instead of local double cmpxchg,
> after Patch 5 it's preempt_disable() and no atomic operations. Same for
> freeing, which is normally a local double cmpxchg only for a short
> term allocations (so the same slab is still active on the same cpu when
> freeing the object) and a more costly locked double cmpxchg otherwise.
> The downside is the lack of NUMA locality guarantees for the allocated
> objects.
The local double cmpxchg is not an atomic instruction. For that it would
need a lock prefix.
The local cmpxchg is atomic vs an interrupt because the interrupt can only
occur between instructions. That is true for any processor instruction.
We use the fact that the cmpxchg does a RMV in one unbreakable
instruction to ensure that interrupts cannot do evil things to the fast path.
next prev parent reply other threads:[~2025-02-14 18:28 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-14 16:27 Vlastimil Babka
2025-02-14 16:27 ` [PATCH RFC v2 01/10] slab: add opt-in caching layer of " Vlastimil Babka
2025-02-22 22:46 ` Suren Baghdasaryan
2025-02-22 22:56 ` Suren Baghdasaryan
2025-03-12 14:57 ` Vlastimil Babka
2025-03-12 15:14 ` Suren Baghdasaryan
2025-03-17 10:09 ` Vlastimil Babka
2025-02-24 8:04 ` Harry Yoo
2025-03-12 14:59 ` Vlastimil Babka
2025-02-14 16:27 ` [PATCH RFC v2 02/10] slab: add sheaf support for batching kfree_rcu() operations Vlastimil Babka
2025-02-22 23:08 ` Suren Baghdasaryan
2025-03-12 16:19 ` Vlastimil Babka
2025-02-24 8:40 ` Harry Yoo
2025-03-12 16:16 ` Vlastimil Babka
2025-02-14 16:27 ` [PATCH RFC v2 03/10] locking/local_lock: Introduce localtry_lock_t Vlastimil Babka
2025-02-17 14:19 ` Sebastian Andrzej Siewior
2025-02-17 14:35 ` Vlastimil Babka
2025-02-17 15:07 ` Sebastian Andrzej Siewior
2025-02-18 18:41 ` Alexei Starovoitov
2025-02-26 17:00 ` Davidlohr Bueso
2025-02-26 17:15 ` Alexei Starovoitov
2025-02-26 19:28 ` Davidlohr Bueso
2025-02-14 16:27 ` [PATCH RFC v2 04/10] locking/local_lock: add localtry_trylock() Vlastimil Babka
2025-02-14 16:27 ` [PATCH RFC v2 05/10] slab: switch percpu sheaves locking to localtry_lock Vlastimil Babka
2025-02-23 2:33 ` Suren Baghdasaryan
2025-02-24 13:08 ` Harry Yoo
2025-02-14 16:27 ` [PATCH RFC v2 06/10] slab: sheaf prefilling for guaranteed allocations Vlastimil Babka
2025-02-23 3:54 ` Suren Baghdasaryan
2025-02-25 7:30 ` Harry Yoo
2025-03-12 17:09 ` Vlastimil Babka
2025-02-25 8:00 ` Harry Yoo
2025-03-12 18:16 ` Vlastimil Babka
2025-02-14 16:27 ` [PATCH RFC v2 07/10] slab: determine barn status racily outside of lock Vlastimil Babka
2025-02-23 4:00 ` Suren Baghdasaryan
2025-02-25 8:54 ` Harry Yoo
2025-03-12 18:23 ` Vlastimil Babka
2025-02-14 16:27 ` [PATCH RFC v2 08/10] tools: Add testing support for changes to rcu and slab for sheaves Vlastimil Babka
2025-02-23 4:24 ` Suren Baghdasaryan
2025-02-14 16:27 ` [PATCH RFC v2 09/10] tools: Add sheafs support to testing infrastructure Vlastimil Babka
2025-02-14 16:27 ` [PATCH RFC v2 10/10] maple_tree: use percpu sheaves for maple_node_cache Vlastimil Babka
2025-02-23 4:27 ` Suren Baghdasaryan
2025-02-14 18:28 ` Christoph Lameter (Ampere) [this message]
2025-02-23 0:19 ` [PATCH RFC v2 00/10] SLUB percpu sheaves Kent Overstreet
2025-02-23 4:44 ` Suren Baghdasaryan
2025-02-24 1:36 ` Suren Baghdasaryan
2025-02-24 1:43 ` Suren Baghdasaryan
2025-02-24 20:53 ` Vlastimil Babka
2025-02-24 21:12 ` Suren Baghdasaryan
2025-02-25 20:26 ` Suren Baghdasaryan
2025-03-04 10:54 ` Vlastimil Babka
2025-03-04 18:35 ` Suren Baghdasaryan
2025-03-04 19:08 ` Liam R. Howlett
2025-03-14 17:10 ` Suren Baghdasaryan
2025-03-17 11:08 ` Vlastimil Babka
2025-03-17 18:56 ` Suren Baghdasaryan
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=d731cf1b-a594-983e-90e1-9380410e38fc@gentwo.org \
--to=cl@gentwo.org \
--cc=42.hyeyoo@gmail.com \
--cc=Liam.Howlett@oracle.com \
--cc=ast@kernel.org \
--cc=bigeasy@linutronix.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=maple-tree@lists.infradead.org \
--cc=rcu@vger.kernel.org \
--cc=rientjes@google.com \
--cc=roman.gushchin@linux.dev \
--cc=surenb@google.com \
--cc=urezki@gmail.com \
--cc=vbabka@suse.cz \
/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