From: Andy Isaacson <adi@hexapodia.org>
To: Chris Frost <chris@frostnet.net>
Cc: Andi Kleen <andi@firstfloor.org>,
Wu Fengguang <fengguang.wu@intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Benny Halevy <bhalevy@panasas.com>,
Andrew@firstfloor.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org,
Steve VanDeBogart <vandebo-lkml@nerdbox.net>,
linux-fsdevel@vger.kernel.org, Matt Mackall <mpm@selenic.com>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH] fs: add fincore(2) (mincore(2) for file descriptors)
Date: Sat, 20 Feb 2010 19:02:38 -0800 [thread overview]
Message-ID: <20100221030238.GA26511@hexapodia.org> (raw)
In-Reply-To: <20100216181312.GA9700@frostnet.net>
On Tue, Feb 16, 2010 at 10:13:12AM -0800, Chris Frost wrote:
> Add the fincore() system call. fincore() is mincore() for file descriptors.
>
> The functionality of fincore() can be emulated with an mmap(), mincore(),
> and munmap(), but this emulation requires more system calls and requires
> page table modifications. fincore() can provide a significant performance
> improvement for non-sequential in-core queries.
In addition to being expensive, mmap/mincore/munmap perturb the VM's
eviction algorithm -- a page is less likely to be evicted if it's
mmapped when being considered for eviction.
I frequently see this happen when using mincore(1) from
http://bitbucket.org/radii/mincore/ -- "watch mincore -v *.big" while
*.big are being sequentially read results in a significant number of
pages remaining in-core, whereas if I only run mincore after the
sequential read is complete, the large files will be nearly-completely
out of core (except for the tail of the last file, of course).
It's very interesting to watch
% watch --interval=.5 mincore -v *
while an IO-intensive process is happening, such as mke2fs on a
filesystem image.
So, I support the addition of fincore(2) and would use it if it were
merged.
-andy
next prev parent reply other threads:[~2010-02-21 3:02 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20100120215712.GO27212@frostnet.net>
2010-01-22 1:17 ` [PATCH] fs: add fincore(2) (mincore(2) for file descriptors) Wu Fengguang
[not found] ` <87k4vc2rds.fsf@basil.nowhere.org>
2010-02-16 18:13 ` Chris Frost
2010-02-21 3:02 ` Andy Isaacson [this message]
2010-02-21 3:25 ` Wu Fengguang
2010-02-23 16:39 ` Andy Isaacson
2010-05-07 22:46 ` Cédric Villemain
2010-01-22 1:29 ` Paul E. McKenney
2010-01-26 22:12 ` Andrew Morton
2010-01-28 7:42 ` Steve VanDeBogart
2010-01-28 8:23 ` Andrew Morton
2010-01-28 8:32 ` Steve VanDeBogart
2010-01-28 23:54 ` Andres Freund
2010-01-27 18:14 ` Jamie Lokier
2010-01-28 8:23 ` Steve VanDeBogart
2010-01-20 21:57 Chris Frost
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=20100221030238.GA26511@hexapodia.org \
--to=adi@hexapodia.org \
--cc=Andrew@firstfloor.org \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=bhalevy@panasas.com \
--cc=chris@frostnet.net \
--cc=fengguang.wu@intel.com \
--cc=heiko.carstens@de.ibm.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mpm@selenic.com \
--cc=peterz@infradead.org \
--cc=vandebo-lkml@nerdbox.net \
--cc=viro@zeniv.linux.org.uk \
/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).