Re: [patch] Converting writeback linked lists to a tree based data structure

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

To: David Chinner <dgc@...>

Cc: Fengguang Wu <wfg@...>, Michael Rubin <mrubin@...>, Peter Zijlstra <a.p.zijlstra@...>, <linux-kernel@...>, <linux-mm@...>

Subject: Re: [patch] Converting writeback linked lists to a tree based data structure

Date: Wednesday, January 16, 2008 - 4:13 am

On Wed, 16 Jan 2008 18:55:38 +1100 David Chinner <dgc@sgi.com> wrote:

quoted text> On Tue, Jan 15, 2008 at 07:44:15PM -0800, Andrew Morton wrote:
> > On Wed, 16 Jan 2008 11:01:08 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
> > 
> > > On Tue, Jan 15, 2008 at 09:53:42AM -0800, Michael Rubin wrote:
> > > > On Jan 15, 2008 12:46 AM, Peter Zijlstra <a.p.zijlstra@chello.nl> 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 was done before Fengguang's patches. I am trying to test
> > > > Fengguang's for comparison but am having problems with getting mm1 to
> > > > boot on my systems.
> > > 
> > > Yeah, they are independent ones. The initial motivation is to fix the
> > > bug "sluggish writeback on small+large files". Michael introduced
> > > a new rbtree, and me introduced a new list(s_more_io_wait).
> > > 
> > > 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 mechanism for blocked inodes.
> > > 
> > > The time ordered rbtree may delay io for a blocked inode simply by
> > > modifying its dirtied_when and reinsert it. But it would no longer be
> > > that easy if it is to be ordered by location.
> > 
> > What does the term "ordered by location" mean?  Attemting to sort inodes by
> > physical disk address?  By using their i_ino as a key?
> > 
> > That sounds optimistic.
> 
> In XFS, inode number is an encoding of it's location on disk, so
> ordering inode writeback by inode number *does* make sense.

This code is mainly concerned with writing pagecache data, not inodes.
--
unsubscribe noticeTo unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:

[patch] Converting writeback linked lists to a tree based da..., Michael Rubin, (Tue Jan 15, 4:09 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Thu Jan 17, 5:41 am)

Re: [patch] Converting writeback linked lists to a tree base..., Michael Rubin, (Thu Jan 17, 5:07 pm)

Re: [patch] Converting writeback linked lists to a tree base..., David Chinner, (Fri Jan 18, 1:01 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Fri Jan 18, 1:41 am)

Re: [patch] Converting writeback linked lists to a tree base..., Michael Rubin, (Fri Jan 18, 1:38 am)

Re: [patch] Converting writeback linked lists to a tree base..., David Chinner, (Fri Jan 18, 4:54 am)

Re: [patch] Converting writeback linked lists to a tree base..., Michael Rubin, (Fri Jan 18, 5:26 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Fri Jan 18, 12:56 am)

Re: [patch] Converting writeback linked lists to a tree base..., Michael Rubin, (Fri Jan 18, 2:43 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Fri Jan 18, 5:32 am)

Re: [patch] Converting writeback linked lists to a tree base..., Andi Kleen, (Fri Jan 18, 1:41 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Fri Jan 18, 2:01 am)

Re: [patch] Converting writeback linked lists to a tree base..., Mike Waychison, (Fri Jan 18, 3:48 am)

Re: [patch] Converting writeback linked lists to a tree base..., Peter Zijlstra, (Tue Jan 15, 4:46 am)

Re: [patch] Converting writeback linked lists to a tree base..., Michael Rubin, (Tue Jan 15, 1:53 pm)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Tue Jan 15, 11:01 pm)

Re: [patch] Converting writeback linked lists to a tree base..., Michael Rubin, (Wed Jan 16, 2:55 pm)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Wed Jan 16, 11:31 pm)

Re: [patch] Converting writeback linked lists to a tree base..., Andrew Morton, (Tue Jan 15, 11:44 pm)

Re: [patch] Converting writeback linked lists to a tree base..., David Chinner, (Wed Jan 16, 3:55 am)

Re: [patch] Converting writeback linked lists to a tree base..., Andrew Morton, (Wed Jan 16, 4:13 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Wed Jan 16, 9:06 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Wed Jan 16, 12:25 am)

Re: [patch] Converting writeback linked lists to a tree base..., Andrew Morton, (Wed Jan 16, 12:42 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Wed Jan 16, 12:55 am)

Re: [patch] Converting writeback linked lists to a tree base..., Andrew Morton, (Wed Jan 16, 1:51 am)

Re: [patch] Converting writeback linked lists to a tree base..., Fengguang Wu, (Wed Jan 16, 5:07 am)

Re: [patch] Converting writeback linked lists to a tree base..., Mike Waychison, (Fri Jan 18, 3:36 am)


linux-kernel:
Greg Kroah-Hartman	[PATCH 001/196] Chinese: Add the known_regression URI to the HOWTO
Andrew Morton	-mm merge plans for 2.6.23
david	Re: Dual-Licensing Linux Kernel with GPL V2 and GPL V3
Bart Van Assche	Integration of SCST in the mainstream Linux kernel
git:

linux-netdev:
Gerrit Renker	[PATCH 27/37] dccp: Integration of dynamic feature activation - part 2 (server side)
David Miller	Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock().
PJ Waskiewicz	[ANNOUNCE] ixgbe: Data Center Bridging (DCB) support for ixgbe
David Miller	Re: [GIT]: Networking
openbsd-misc:

Re: [patch] Converting writeback linked lists to a tree based data structure

Online users