From: Matthew Wilcox <firstname.lastname@example.org> To: Shijie Huang <email@example.com> Cc: firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com, Frank Wang <firstname.lastname@example.org> Subject: Re: Is it possible to implement the per-node page cache for programs/libraries? Date: Wed, 1 Sep 2021 04:25:01 +0100 [thread overview] Message-ID: <YS7yjcqA6txFHd99@casper.infradead.org> (raw) In-Reply-To: <email@example.com> On Wed, Sep 01, 2021 at 11:07:41AM +0800, Shijie Huang wrote: > In the NUMA, we only have one page cache for each file. For the > program/shared libraries, the > remote-access delays longer then the local-access. > > So, is it possible to implement the per-node page cache for > programs/libraries? At this point, we have no way to support text replication within a process. So what you're suggesting (if implemented) would work for processes which limit themselves to a single node. That is, if you have a system with CPUs 0-3 on node 0 and CPUs 4-7 on node 1, a process which only works on node 0 or only works on node 1 will get text on the appropriate node. If there's a process which runs on both nodes 0 and 1, there's no support for per-node PGDs. So it will get a mix of pages from nodes 0 and 1, and that doesn't necessarily seem like a big win. I haven't yet dived into how hard it would be to make mm->pgd a per-node allocation. I have been thinking about this a bit; one of our internal performance teams flagged the potential performance win to me a few months ago. I don't have a concrete design for text replication yet; there have been various attempts over the years, but none were particularly compelling. By the way, the degree of performance win varies between different CPUs, but it's measurable on all the systems we've tested on (from three different vendors).
next prev parent reply other threads:[~2021-09-01 3:26 UTC|newest] Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-09-01 3:07 Shijie Huang 2021-09-01 3:07 ` Shijie Huang 2021-09-01 2:09 ` Barry Song 2021-09-01 2:09 ` Barry Song 2021-09-01 3:25 ` Matthew Wilcox [this message] 2021-09-01 13:30 ` Huang Shijie 2021-09-01 14:25 ` Huang Shijie 2021-09-01 11:32 ` Matthew Wilcox 2021-09-01 23:58 ` Matthew Wilcox 2021-09-02 0:15 ` Barry Song 2021-09-02 0:15 ` Barry Song 2021-09-02 1:13 ` Linus Torvalds 2021-09-02 1:13 ` Linus Torvalds 2021-09-02 10:16 ` Huang Shijie 2021-09-02 3:25 ` Nicholas Piggin 2021-09-02 10:17 ` Matthew Wilcox 2021-09-03 7:10 ` Nicholas Piggin 2021-09-03 19:01 ` Matthew Wilcox 2021-09-03 19:08 ` Linus Torvalds 2021-09-03 19:08 ` Linus Torvalds 2021-09-06 9:56 ` Huang Shijie 2021-09-03 23:42 ` Nicholas Piggin 2021-09-01 4:55 ` Al Viro 2021-09-01 13:10 ` Huang Shijie 2021-09-01 17:24 ` Linus Torvalds 2021-09-01 17:24 ` Linus Torvalds 2021-09-01 17:29 ` Linus Torvalds 2021-09-01 17:29 ` Linus Torvalds 2021-09-01 22:56 ` Barry Song 2021-09-01 22:56 ` Barry Song 2021-09-02 10:12 ` Huang Shijie 2021-09-02 10:08 ` Huang Shijie
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=YS7yjcqA6txFHd99@casper.infradead.org \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --subject='Re: Is it possible to implement the per-node page cache for programs/libraries?' \ /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
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.