Re: [PATCH 0/6] writeback time order/delay fixes take 3

[Chris Mason <chris.mason@oracle.com>]

On Fri, 24 Aug 2007 21:24:58 +0800
Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
 
> > 2) s_dirty and s_io both become radix trees.  s_dirty is indexed by
> > a sequence number that corresponds to age.  It is treated as a big
> > circular indexed list that can wrap around over time.  Radix tree
> > tags are used both on s_dirty and s_io to flag which inodes are in
> > progress.
> 
> It's meaningless to convert s_io to radix tree. Because inodes on s_io
> will normally be sent to block layer elevators at the same time.

Not entirely, using a radix tree instead lets you tag things instead of
doing the current backflips across three lists.

> 
> Also s_dirty holds 30 seconds of inodes, while s_io only 5 seconds.
> The more inodes, the more chances of good clustering. That's the
> general rule.
> 
> s_dirty is the right place to do address-clustering.
> As for the dirty_expire_interval parameter on dirty age,
> we can apply a simple rule: do one full scan/sweep over the
> fs-address-space in every 30s, syncing all inodes encountered,
> and sparing those newly dirtied in less than 5s. With that rule,
> any inode will get synced after being dirtied for 5-35 seconds.

This gives you an O(inodes dirty) behavior instead of the current O(old
inodes).  It might not matter, but walking the radix tree is more
expensive than walking a list.

But, I look forward to your patches, we can tune from there.

-chris