From: Matthew Wilcox <willy@infradead.org>
To: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-mm@kvack.org, tglx@linutronix.de, frederic@kernel.org,
Christoph Lameter <cl@linux.com>,
anna-maria@linutronix.de
Subject: Re: [PATCH 0/4 v2] mm/swap: Add locking for pagevec
Date: Wed, 24 Apr 2019 05:15:52 -0700 [thread overview]
Message-ID: <20190424121552.GD19031@bombadil.infradead.org> (raw)
In-Reply-To: <20190424111208.24459-1-bigeasy@linutronix.de>
On Wed, Apr 24, 2019 at 01:12:04PM +0200, Sebastian Andrzej Siewior wrote:
> The swap code synchronizes its access to the (four) pagevec struct
> (which is allocated per-CPU) by disabling preemption. This works and the
> one struct needs to be accessed from interrupt context is protected by
> disabling interrupts. This was manually audited and there is no lockdep
> coverage for this.
> There is one case where the per-CPU of a remote CPU needs to be accessed
> and this is solved by started a worker on the remote CPU and waiting for
> it to finish.
>
> In v1 [0] it was attempted to add per-CPU spinlocks for the access to
> struct. This would add lockdep coverage and access from a remote CPU so
> the worker wouldn't be required.
From my point of view, what is missing from this description is why we
want to be able to access these structs from a remote CPU. It's explained
a little better in the 4/4 changelog, but I don't see any numbers that
suggest what kinds of gains we might see (eg "reduces power consumption
by x% on a particular setup", or even "average length of time in idle
extended from x ms to y ms").
next prev parent reply other threads:[~2019-04-24 12:15 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-24 11:12 [PATCH 0/4 v2] mm/swap: Add locking for pagevec Sebastian Andrzej Siewior
2019-04-24 11:12 ` [PATCH 1/4] mm/page_alloc: Split drain_local_pages() Sebastian Andrzej Siewior
2019-04-24 11:12 ` [PATCH 2/4] mm/swap: Add static key dependent pagevec locking Sebastian Andrzej Siewior
2019-04-24 11:12 ` [PATCH 3/4] mm/swap: Access struct pagevec remotely Sebastian Andrzej Siewior
2019-04-24 11:12 ` [PATCH 4/4] mm/swap: Enable "use_pvec_lock" nohz_full dependent Sebastian Andrzej Siewior
2019-04-24 12:15 ` Matthew Wilcox [this message]
2019-04-26 8:00 ` [PATCH 0/4 v2] mm/swap: Add locking for pagevec Sebastian Andrzej Siewior
2020-06-16 16:55 ` Marcelo Tosatti
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=20190424121552.GD19031@bombadil.infradead.org \
--to=willy@infradead.org \
--cc=anna-maria@linutronix.de \
--cc=bigeasy@linutronix.de \
--cc=cl@linux.com \
--cc=frederic@kernel.org \
--cc=linux-mm@kvack.org \
--cc=tglx@linutronix.de \
/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;
as well as URLs for NNTP newsgroup(s).