Re: [GIT PULL] Ext3 latency fixes

On Fri, Apr 03 2009, Linus Torvalds wrote:


On Fri, 3 Apr 2009, Theodore Ts'o wrote:

Please pull from:

git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git ext3-latency-fixes

Thanks, pulled. I'll be interested to see how it feels. Will report back
after I've rebuild and gone through a few more emails.

I have one question, didn't see this series before... Ted, what kind of
tests did you run with this and on what? Currently one has to be careful
with WRITE_SYNC, as it also implies an immediate unplug of the device.
So not only does it flag the priority as sync, it'll also kick things
off immediately. We had a nasty regression in performance in a few
revisions of the kernel due to this, sqlite performance was basically 4
times as bad as before we did WRITE_SYNC in sync_dirty_buffer(). So I'd
be curious what kind of testing was done with the patch series before
submitting it.

We should probably just dump the unplug bit from WRITE_SYNC and make
sure we do those explicitly after submission instead.

One thing I started wondering about in your changes to start using
WRITE_SYNC is that I'm getting closer to thinking that we did the whole
WRITE-vs-WRITE_SYNC thing the wrong way around.

Now, it's clearly true that non-synchronous writes are hopefully always
the common case, so in that sense it makes sense to think of "WRITE" as
the default non-critical case, and then make the (fewer) WRITE_SYNC cases
be the special case.

But at the same time, I now suspect that we could actually have solved
this problem more easily by just doing things the other way around: make
the default "WRITE" be the high-priority one (to match "READ"), and then
just explicitly marking the data writes with "WRITE_ASYNC".

Why? Because I think that with all the writes sprinkled around in random
places, it's probably _easier_ to find the bulk writes that cause the
biggest issues, and just fix _those_ to be WRITE_ASYNC. They may be bulk,
they may be the common case, but they also tend to be the case where we
write with generic routines (eg the whole "do_writepages()" thing).

So the VFS layer tends to already do much of the bulk writeout, and maybe
we would have been better off just changing those to ASYNC and leaving any
more specialized cases as the SYNC case? That would have avoided a lot of
this effort at the filesystem level. We'd just assume that the default
filesystem-specific writes tend to all be SYNC.

Makes some sense, but we have to be really careful with SYNC writes.
It's important that it really be things that are immediately waited upon
and not "important" writes, since otherwise it'll wreak havoc with the
responsiveness of our reads.

--
Jens Axboe

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: [GIT PULL] Ext3 latency fixes
    ... the common case, so in that sense it makes sense to think of "WRITE" as ... They may be bulk, ... this effort at the filesystem level. ... filesystem-specific writes tend to all be SYNC. ...
    (Linux-Kernel)
  • Re: 2.6.xx: dirty pages never being syncd to disk?
    ... It appears to cause an immediate "sync" of the file data ... Doing a "sync" or a second run of the program afterwards does ... int main (int argc, char *argv) ... send the line "unsubscribe linux-kernel" in ...
    (Linux-Kernel)
  • how to use "ntpd" to emulate "ntpdate"?
    ... laptop when i wanted to do it manually. ... and the sync was immediate. ... theoretically get the same effect with some variation of "ntpd -q". ...
    (Fedora)
  • Re: how to use "ntpd" to emulate "ntpdate"?
    ... > and the sync was immediate. ... You may be misreading the documentation. ... a one shot bring the time into synchronization at boot time. ...
    (Fedora)
  • Re: Entourage birthdays
    ... Do you have a backup that you could use to replace the contacts? ... you can probably do this with a script. ... Also will it just reload all of them on first sync if I dont change the ... Also the same entries appear in my contacts - how do I bulk remove them as ...
    (microsoft.public.mac.office.entourage)