On Mon, Nov 24, 2014 at 11:33:35PM -0500, Theodore Ts'o wrote:
> On Tue, Nov 25, 2014 at 12:52:39PM +1100, Dave Chinner wrote:
> > > +static void flush_sb_dirty_time(struct super_block *sb)
> > > +{
> ...
> > > +}
> >
> > This just seems wrong to me, not to mention extremely expensive when we ha
On Tue 25-11-14 12:57:16, Ted Tso wrote:
> On Tue, Nov 25, 2014 at 06:19:27PM +0100, Jan Kara wrote:
> > Actually, I'd also prefer to do the writing from iput_final(). My main
> > reason is that shrinker starts behaving very differently when you put
> > inodes with I_DIRTY_TIME to the LRU. See in
On Tue, Nov 25, 2014 at 06:30:40PM +0100, Jan Kara wrote:
> This would be possible and as Boaz says, it might be possible to reuse
> the same list_head in the inode for this. Getting rid of the full scan of
> all superblock inodes would be nice (as the scan gets really expensive for
> large numbe
On Tue, Nov 25, 2014 at 06:19:27PM +0100, Jan Kara wrote:
> Actually, I'd also prefer to do the writing from iput_final(). My main
> reason is that shrinker starts behaving very differently when you put
> inodes with I_DIRTY_TIME to the LRU. See inode_lru_isolate() and in
> particular:
>
On Mon 24-11-14 23:33:35, Ted Tso wrote:
> On Tue, Nov 25, 2014 at 12:52:39PM +1100, Dave Chinner wrote:
> > > +static void flush_sb_dirty_time(struct super_block *sb)
> > > +{
> ...
> > > +}
> >
> > This just seems wrong to me, not to mention extremely expensive when we have
> > millions of cac
On Mon 24-11-14 23:33:35, Ted Tso wrote:
> On Tue, Nov 25, 2014 at 12:52:39PM +1100, Dave Chinner wrote:
> > Eviction is too late for this. I'm pretty sure that it won't get
> > this far as iput_final() should catch the I_DIRTY_TIME in the !drop
> > case via write_inode_now().
>
> Actually, the tr
On 11/25/2014 06:33 AM, Theodore Ts'o wrote:
<>
>
> I was concerned about putting them on the dirty inode list because it
> would be extra inodes for the writeback threads would have to skip
> over and ignore (since they would not be dirty in the inde or data
> pages sense).
>
> Another solution
On Tue, Nov 25, 2014 at 12:52:39PM +1100, Dave Chinner wrote:
> > +static void flush_sb_dirty_time(struct super_block *sb)
> > +{
...
> > +}
>
> This just seems wrong to me, not to mention extremely expensive when we have
> millions of cached inodes on the superblock.
#1, It only gets called on
On Fri, Nov 21, 2014 at 02:59:22PM -0500, Theodore Ts'o wrote:
> Add a new mount option which enables a new "lazytime" mode. This mode
> causes atime, mtime, and ctime updates to only be made to the
> in-memory version of the inode. The on-disk times will only get
> updated when (a) if the inode
