From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Mel Gorman <mgorman@techsingularity.net>
Cc: Chuck Lever <chuck.lever@oracle.com>,
Mel Gorman <mgorman@suse.de>,
Linux NFS Mailing List <linux-nfs@vger.kernel.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
brouer@redhat.com,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>
Subject: Re: alloc_pages_bulk()
Date: Mon, 22 Feb 2021 21:44:20 +0100 [thread overview]
Message-ID: <20210222214420.1341e50f@carbon> (raw)
In-Reply-To: <20210215120608.GE3697@techsingularity.net>
On Mon, 15 Feb 2021 12:06:09 +0000
Mel Gorman <mgorman@techsingularity.net> wrote:
> On Thu, Feb 11, 2021 at 04:20:31PM +0000, Chuck Lever wrote:
> > > On Feb 11, 2021, at 4:12 AM, Mel Gorman <mgorman@techsingularity.net> wrote:
> > >
> > > <SNIP>
> > >
> > > Parameters to __rmqueue_pcplist are garbage as the parameter order changed.
> > > I'm surprised it didn't blow up in a spectacular fashion. Again, this
> > > hasn't been near any testing and passing a list with high orders to
> > > free_pages_bulk() will corrupt lists too. Mostly it's a curiousity to see
> > > if there is justification for reworking the allocator to fundamentally
> > > deal in batches and then feed batches to pcp lists and the bulk allocator
> > > while leaving the normal GFP API as single page "batches". While that
> > > would be ideal, it's relatively high risk for regressions. There is still
> > > some scope for adding a basic bulk allocator before considering a major
> > > refactoring effort.
> > >
> > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > > index f8353ea7b977..8f3fe7de2cf7 100644
> > > --- a/mm/page_alloc.c
> > > +++ b/mm/page_alloc.c
> > > @@ -5892,7 +5892,7 @@ __alloc_pages_bulk_nodemask(gfp_t gfp_mask, unsigned int order,
> > > pcp_list = &pcp->lists[migratetype];
> > >
> > > while (nr_pages) {
> > > - page = __rmqueue_pcplist(zone, gfp_mask, migratetype,
> > > + page = __rmqueue_pcplist(zone, migratetype, alloc_flags,
> > > pcp, pcp_list);
> > > if (!page)
> > > break;
> >
> > The NFS server is considerably more stable now. Thank you!
> >
>
> Thanks for testing!
I've done some testing here:
https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org
Performance summary:
- Before: 3,677,958 pps
- After : 4,066,028 pps
I'll describe/show the page_pool changes tomorrow.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
next prev parent reply other threads:[~2021-02-22 20:44 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <2A0C36E7-8CB0-486F-A8DB-463CA28C5C5D@oracle.com>
2021-02-08 17:50 ` Fwd: alloc_pages_bulk() Chuck Lever
2021-02-09 10:31 ` alloc_pages_bulk() Jesper Dangaard Brouer
2021-02-09 13:37 ` alloc_pages_bulk() Chuck Lever
2021-02-09 17:27 ` alloc_pages_bulk() Vlastimil Babka
2021-02-10 9:51 ` alloc_pages_bulk() Christoph Hellwig
2021-02-10 8:41 ` alloc_pages_bulk() Mel Gorman
2021-02-10 11:41 ` alloc_pages_bulk() Jesper Dangaard Brouer
2021-02-10 13:07 ` alloc_pages_bulk() Mel Gorman
2021-02-10 22:58 ` alloc_pages_bulk() Chuck Lever
2021-02-11 9:12 ` alloc_pages_bulk() Mel Gorman
2021-02-11 12:26 ` alloc_pages_bulk() Jesper Dangaard Brouer
2021-02-15 12:00 ` alloc_pages_bulk() Mel Gorman
2021-02-15 16:10 ` alloc_pages_bulk() Jesper Dangaard Brouer
2021-02-22 9:42 ` alloc_pages_bulk() Mel Gorman
2021-02-22 11:42 ` alloc_pages_bulk() Jesper Dangaard Brouer
2021-02-22 14:08 ` alloc_pages_bulk() Mel Gorman
2021-02-11 16:20 ` alloc_pages_bulk() Chuck Lever
2021-02-15 12:06 ` alloc_pages_bulk() Mel Gorman
2021-02-15 16:00 ` alloc_pages_bulk() Chuck Lever
2021-02-22 20:44 ` Jesper Dangaard Brouer [this message]
2021-02-09 22:01 ` Fwd: alloc_pages_bulk() Matthew Wilcox
2021-02-09 22:55 ` alloc_pages_bulk() Chuck Lever
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=20210222214420.1341e50f@carbon \
--to=brouer@redhat.com \
--cc=chuck.lever@oracle.com \
--cc=linux-mm@kvack.org \
--cc=linux-nfs@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mgorman@techsingularity.net \
--cc=netdev@vger.kernel.org \
/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).