I am writing tests for the write back section of the kernel. This is
the stuff found in fs/fs-writeback.c.
Currently I have tests to fsync millions of inodes concurrently, tests
involving mounting and unmounting file systems, and other tests to
tickle some starvation of big file situations. Has an
On Dec 22, 2007 2:06 AM, Andrew Morton <[EMAIL PROTECTED]> wrote:
> Oh boy. Do we really want to add all this stuff to JBD just for
> drop_caches which is a silly root-only broken-in-22-other-ways thing?
>
> Michael, might your convert-inode-lists-to-tree patches eliminate the need
> for taking in
On Dec 22, 2007 2:06 AM, Andrew Morton <[EMAIL PROTECTED]> wrote:
> On Mon, 17 Dec 2007 12:13:22 + richard <[EMAIL PROTECTED]> wrote:
> Michael, might your convert-inode-lists-to-tree patches eliminate the need
> for taking inode_lock in drop_pagecache_sb()? Probably not, as it uses an
> rbtre
From: Michael Rubin <[EMAIL PROTECTED]>
Fixing a bug where writing to large files while concurrently writing to
smaller ones creates a situation where writeback cannot keep up with the
traffic and memory baloons until the we hit the threshold watermark. This
can result in surprising l
On Dec 12, 2007 12:55 PM, Peter Zijlstra <[EMAIL PROTECTED]> wrote:
>
> On Mon, 2007-12-10 at 18:02 -0800, Michael Rubin wrote:
> > From: Michael Rubin <[EMAIL PROTECTED]>
> The part I miss here is the rationale on _how_ you solve the problem.
>
> The patch itsel
From: Michael Rubin <[EMAIL PROTECTED]>
This is an attempt to unify the writeback data structures. By adding an
rb tree we are able to have one consistent time ordering mechanism for
writeback. This should aid debugging and allow for future work with more
sophisticated time ordering methods
>From [EMAIL PROTECTED] Wed Nov 28 11:10:06 2007
Message-Id: <[EMAIL PROTECTED]>
Date: Wed, 28 Nov 2007 11:01:21 -0800
From: [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Subject: [patch 1/1] Writeback fix for concurrent large and small file writes.
From: Michael Rubin <[EMAIL PROTECTED]>
Thank you. Integrated the fixes in my patch.
On Nov 28, 2007 6:13 PM, Frans Pop <[EMAIL PROTECTED]> wrote:
> Two typos in comments.
>
> Cheers,
> FJP
>
> Michael Rubin wrote:
> > + * The flush tree organizes the dirtied_when keys with the rb_tree. Any
> > + *
at happens.
mrubin
On Nov 28, 2007 4:34 PM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
> On Wed, Nov 28, 2007 at 11:29:57AM -0800, Michael Rubin wrote:
> > >From [EMAIL PROTECTED] Wed Nov 28 11:10:06 2007
> > Message-Id: <[EMAIL PROTECTED]>
> > Date: Wed, 28 Nov
Due to my faux pas of top posting (see
http://www.zip.com.au/~akpm/linux/patches/stuff/top-posting.txt) I am
resending this email.
On Nov 28, 2007 4:34 PM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
> Could you demonstrate the situation? Or if I guess it right, could it
> be fixed by the following pa
On Nov 29, 2007 5:32 PM, Fengguang Wu <[EMAIL PROTECTED]:
> > On Nov 28, 2007 4:34 PM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
> > > Could you demonstrate the situation? Or if I guess it right, could it
> > > be fixed by the following patch?
Feng I am sorry to have been mistaken but I reran my tes
From: Michael Rubin <[EMAIL PROTECTED]>
For those of you who have waited so long. This is the third submission
of the first attempt at this patch. It is a trilogy.
Two changes are in this patch. They are dependant on each other.
In addition we get an unintended performance improvement. S
On Jan 15, 2008 12:46 AM, Peter Zijlstra <[EMAIL PROTECTED]> wrote:
> Just a quick question, how does this interact/depend-uppon etc.. with
> Fengguangs patches I still have in my mailbox? (Those from Dec 28th)
They don't. They apply to a 2.6.24rc7 tree. This is a candidte for 2.6.25.
This work w
On Jan 15, 2008 4:36 AM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
> Andrew,
>
> This patchset mainly polishes the writeback queuing policies.
Anyone know which tree is this patched based out of?
> The main goals are:
>
> (1) small files should not be starved by big dirty files
> (2) sync as fast a
On Jan 15, 2008 7:01 PM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
> Basically I think rbtree is an overkill to do time based ordering.
> Sorry, Michael. But s_dirty would be enough for that. Plus, s_more_io
> provides fair queuing between small/large files, and s_more_io_wait
> provides waiting mech
When I boot my system with 2.6.24-rc6 everything is great. When I apply the mm1
patch I crash with the output below. Anyone seen this before?
Starting sendmail: Unable to handle kernel paging request at 00010013
RIP:
[] restore_i387_ia32+0x1f/0x150
PGD 47e134067 PUD 0
Oops: [1] SM
On Jan 17, 2008 1:41 AM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
> On Tue, Jan 15, 2008 at 12:09:21AM -0800, Michael Rubin wrote:
> The main benefit of rbtree is possibly better support of future policies.
> Can you demonstrate an example?
These are ill-formed thoughts as of now on
On Jan 17, 2008 9:01 PM, David Chinner <[EMAIL PROTECTED]> wrote:
First off thank you for the very detailed reply. This rocks and gives
me much to think about.
> On Thu, Jan 17, 2008 at 01:07:05PM -0800, Michael Rubin wrote:
> This seems suboptimal for large files. If you keep feed
On Jan 17, 2008 8:56 PM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
Once again thanks for the speedy replies. :-)
> On Thu, Jan 17, 2008 at 01:07:05PM -0800, Michael Rubin wrote:
> Suppose we want to grant longer expiration window for temp files,
> adding a new list named s_dirty_tmp
On Jan 15, 2008 4:36 AM, Fengguang Wu <[EMAIL PROTECTED]> wrote:
> Andrew,
>
> This patchset mainly polishes the writeback queuing policies.
> The main goals are:
>
> (1) small files should not be starved by big dirty files
> (2) sync as fast as possible for not-blocked inodes/pages
> - don't l
On Jan 18, 2008 12:54 AM, David Chinner <[EMAIL PROTECTED]> wrote:
> At this point, I'd say it is best to leave it to the filesystem and
> the elevator to do their jobs properly.
Amen.
mrubin
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [E
21 matches
Mail list logo
