From: Matthew Wilcox <willy@infradead.org>
To: Alexander Duyck <alexander.h.duyck@linux.intel.com>,
Mel Gorman <mgorman@techsingularity.net>,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Dan Williams <dan.j.williams@intel.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
David Hildenbrand <david@redhat.com>,
Jason Wang <jasowang@redhat.com>,
Dave Hansen <dave.hansen@intel.com>,
Michal Hocko <mhocko@suse.com>,
Liang Li <liliangleo@didiglobal.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
virtualization@lists.linux-foundation.org
Subject: Re: [RFC v2 PATCH 0/4] speed up page allocation for __GFP_ZERO
Date: Tue, 22 Dec 2020 12:23:12 +0000 [thread overview]
Message-ID: <20201222122312.GH874@casper.infradead.org> (raw)
In-Reply-To: <20201221162519.GA22504@open-light-1.localdomain>
On Mon, Dec 21, 2020 at 11:25:22AM -0500, Liang Li wrote:
> Creating a VM [64G RAM, 32 CPUs] with GPU passthrough
> =====================================================
> QEMU use 4K pages, THP is off
> round1 round2 round3
> w/o this patch: 23.5s 24.7s 24.6s
> w/ this patch: 10.2s 10.3s 11.2s
>
> QEMU use 4K pages, THP is on
> round1 round2 round3
> w/o this patch: 17.9s 14.8s 14.9s
> w/ this patch: 1.9s 1.8s 1.9s
> =====================================================
The cost of zeroing pages has to be paid somewhere. You've successfully
moved it out of this path that you can measure. So now you've put it
somewhere that you're not measuring. Why is this a win?
> Speed up kernel routine
> =======================
> This can’t be guaranteed because we don’t pre zero out all the free pages,
> but is true for most case. It can help to speed up some important system
> call just like fork, which will allocate zero pages for building page
> table. And speed up the process of page fault, especially for huge page
> fault. The POC of Hugetlb free page pre zero out has been done.
Try kernbench with and without your patch.
next prev parent reply other threads:[~2020-12-22 12:24 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-21 16:25 [RFC v2 PATCH 0/4] speed up page allocation for __GFP_ZERO Liang Li
2020-12-22 8:47 ` David Hildenbrand
2020-12-22 11:31 ` Liang Li
2020-12-22 11:57 ` David Hildenbrand
2020-12-22 14:00 ` Liang Li
2020-12-23 8:41 ` David Hildenbrand
2020-12-23 12:11 ` Liang Li
2021-01-04 20:18 ` David Hildenbrand
2021-01-05 2:14 ` Liang Li
2021-01-05 9:39 ` David Hildenbrand
2021-01-05 10:22 ` Liang Li
2021-01-05 10:27 ` David Hildenbrand
2020-12-22 12:23 ` Matthew Wilcox [this message]
2020-12-22 14:42 ` Liang Li
2021-01-04 12:51 ` Michal Hocko
2021-01-04 13:45 ` Liang Li
2020-12-22 17:11 ` Daniel Jordan
2020-12-22 19:13 ` Alexander Duyck
2021-01-04 12:55 ` Michal Hocko
2021-01-04 14:07 ` Liang Li
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=20201222122312.GH874@casper.infradead.org \
--to=willy@infradead.org \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.h.duyck@linux.intel.com \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=jasowang@redhat.com \
--cc=liliangleo@didiglobal.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@suse.com \
--cc=mst@redhat.com \
--cc=virtualization@lists.linux-foundation.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).