From: Dave Chinner <david@fromorbit.com>
To: Jan Kara <jack@suse.cz>
Cc: Dave Hansen <dave.hansen@intel.com>,
Andi Kleen <ak@linux.intel.com>,
linux-mm@kvack.org, Mel Gorman <mgorman@suse.de>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH 0/7 v1] Speed up page cache truncation
Date: Thu, 12 Oct 2017 08:24:01 +1100 [thread overview]
Message-ID: <20171011212401.GM15067@dastard> (raw)
In-Reply-To: <20171011210613.GQ3667@quack2.suse.cz>
On Wed, Oct 11, 2017 at 11:06:13PM +0200, Jan Kara wrote:
> On Wed 11-10-17 10:34:47, Dave Hansen wrote:
> > On 10/11/2017 01:06 AM, Jan Kara wrote:
> > >>> when rebasing our enterprise distro to a newer kernel (from 4.4 to 4.12) we
> > >>> have noticed a regression in bonnie++ benchmark when deleting files.
> > >>> Eventually we have tracked this down to a fact that page cache truncation got
> > >>> slower by about 10%. There were both gains and losses in the above interval of
> > >>> kernels but we have been able to identify that commit 83929372f629 "filemap:
> > >>> prepare find and delete operations for huge pages" caused about 10% regression
> > >>> on its own.
> > >> It's odd that just checking if some pages are huge should be that
> > >> expensive, but ok ..
> > > Yeah, I was surprised as well but profiles were pretty clear on this - part
> > > of the slowdown was caused by loads of page->_compound_head (PageTail()
> > > and page_compound() use that) which we previously didn't have to load at
> > > all, part was in hpage_nr_pages() function and its use.
> >
> > Well, page->_compound_head is part of the same cacheline as the rest of
> > the page, and the page is surely getting touched during truncation at
> > _some_ point. The hpage_nr_pages() might cause the cacheline to get
> > loaded earlier than before, but I can't imagine that it's that expensive.
>
> Then my intuition matches yours ;) but profiles disagree.
Do you get the same benefit across different filesystems?
> That being said
> I'm not really expert in CPU microoptimizations and profiling so feel free
> to gather perf profiles yourself before and after commit 83929372f629 and
> get better explanation of where the cost is - I would be really curious
> what you come up with because the explanation I have disagrees with my
> intuition as well...
When I see this sort of stuff my immediate thought is "what is the
change in the icache footprint of the hot codepath"? There's a
few IO benchmarks (e.g. IOZone) that are l1/l2 cache footprint
sensitive on XFS, and can see up to 10% differences in performance
from kernel build to kernel build that have no code changes in the
IO paths or l1/l2 dcache footprint.
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2017-10-11 21:24 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-10 15:19 [PATCH 0/7 v1] Speed up page cache truncation Jan Kara
2017-10-10 15:19 ` [PATCH 1/7] mm: Speedup cancel_dirty_page() for clean pages Jan Kara
2017-10-10 15:19 ` [PATCH 2/7] mm: Refactor truncate_complete_page() Jan Kara
2017-10-10 15:19 ` [PATCH 3/7] mm: Factor out page cache page freeing into a separate function Jan Kara
2017-10-10 15:19 ` [PATCH 4/7] mm: Move accounting updates before page_cache_tree_delete() Jan Kara
2017-10-10 15:19 ` [PATCH 5/7] mm: Move clearing of page->mapping to page_cache_tree_delete() Jan Kara
2017-10-10 15:19 ` [PATCH 6/7] mm: Factor out checks and accounting from __delete_from_page_cache() Jan Kara
2017-10-10 15:19 ` [PATCH 7/7] mm: Batch radix tree operations when truncating pages Jan Kara
2017-10-11 7:39 ` Mel Gorman
2017-10-17 23:05 ` Andrew Morton
2017-10-18 10:44 ` Jan Kara
2017-10-10 17:25 ` [PATCH 0/7 v1] Speed up page cache truncation Andi Kleen
2017-10-11 8:06 ` Jan Kara
2017-10-11 16:51 ` Andi Kleen
2017-10-11 17:34 ` Dave Hansen
2017-10-11 17:59 ` Mel Gorman
2017-10-11 18:37 ` Andi Kleen
2017-10-11 21:06 ` Jan Kara
2017-10-11 21:24 ` Dave Chinner [this message]
2017-10-12 9:09 ` Mel Gorman
2017-10-12 14:07 ` Jan Kara
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=20171011212401.GM15067@dastard \
--to=david@fromorbit.com \
--cc=ak@linux.intel.com \
--cc=dave.hansen@intel.com \
--cc=jack@suse.cz \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.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).