Re: ext4_fallocate

[Eric Sandeen <sandeen@redhat.com>]

On 07/01/2012 10:16 PM, Zheng Liu wrote:
> On Wed, Jun 27, 2012 at 07:02:45PM -0400, Eric Sandeen wrote:
>> On 6/27/12 3:30 PM, Theodore Ts'o wrote:
>>> A better workload would be to use a blocksize of 4k.  By using a
>>> blocksize of 1024k, it's not surprising that the metadata overhead is
>>> in the noise.
>>>
>>> Try something like this; this will cause the extent tree overhead to
>>> be roughly equal to the data block I/O.
>>>
>>> [global]
>>> rw=randwrite
>>> size=128m
>>> filesize=1g
>>> bs=4k
>>> ioengine=sync
>>> fallocate=1
>>> fsync=1
>>>
>>> [thread1]
>>> filename=testfile
> 
> Hi Eric,
> 
> Could you please run this test with 'journal_async_commit' flag.  In my
> previous test, this feature can dramatically improve the performance of
> uninitialized extent conversion.
> 
> I have sent an email to do a similar test [1].  In that email, I do a
> similar test and the journal_async_commit flag quite can improve the
> performance.

I can try to find time for that, but so far I haven't actually seen any
severe impact of conversion on a non-debug kernel.  And didn't Jan think
that journal_async_commit was fatally flawed?

At this point I think it is up to the proponents of the
expose-stale-data patch to document & demonstrate the workload which
justifies such a change...

-Eric

> 1. http://comments.gmane.org/gmane.linux.file-systems/63569
> 
> Regards,
> Zheng