Message-ID: <6601abe90907230856q3ee5abe5jc1f7a71d10c5f695@mail.gmail.com>
Date:	Thu, 23 Jul 2009 08:56:31 -0700
From:	Curt Wohlgemuth <curtw@...gle.com>
To:	Theodore Tso <tytso@....edu>
Cc:	"Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>,
	"linux-ext4@...r.kernel.org" <linux-ext4@...r.kernel.org>,
	Eric Sandeen <sandeen@...hat.com>,
	Andreas Dilger <adilger@....com>
Subject: Re: Fallocate and DirectIO

On Tue, Jul 21, 2009 at 6:27 PM, Curt Wohlgemuth<curtw@...gle.com> wrote:
> I spent a bit of time looking at this today.
>
> On Fri, Jun 12, 2009 at 10:33 AM, Theodore Tso<tytso@....edu> wrote:
>> On Fri, Jun 12, 2009 at 06:01:12PM +0530, Aneesh Kumar K.V wrote:
>>> Hi,
>>>
>>> I noticed yesterday that a write to fallocate
>>> space via directIO results in fallback to buffer_IO. ie the userspace
>>> pages get copied to the page cache and then call a sync.
>>>
>>> I guess this defeat the purpose of using directIO. May be we should
>>> consider this a high priority bug.
>
> My simple experiment -- without a journal -- shows that you're
> observation is correct.  *Except* if FALLOC_FL_KEEP_SIZE is used in
> the fallocate() call, in which case the page cache is *not* used.
>
> Pseudo-code example:
>
>  open(O_DIRECT)
>  fallocate(mode, 512MB)
>  while (! written 100MB)
>     write(64K)
>  close()
>
> If mode == FALLOC_FL_KEEP_SIZE, then no page cache is used.
> Otherwise, we *do* go through the page cache.
>
> It comes down to the fact that, since the i_size is not updated with
> KEEP_SIZE, then ext4_get_block() is called with create = 1, since the
> block that's needed is "beyond" the file end.

Ted, given your concerns over the performance impact of updating the
extents during direct I/O writes, it would seem that the fact that
when KEEP_SIZE is specified we do the DMA (and don't go through the
page cache) would be a problem/bug.  At least, it seems that the
performance issue is the same regardless of whether KEEP_SIZE is used
on the fallocate or not: in both we're dealing with an uninitialized
extent.  Do you agree?

I'm exploring (a) what this performance penalty is for the journal
commit; and (b) can we at least avoid the page cache if your
conditions above (no journal commit; no new extent blocks) are met.

Curt

>
>>
>> I agree that many of users of fallocate() feature (i.e. databases) are
>> going to consider this to be a major misfeature.
>
>>
>> There's going to be a major performance hit though --- O_DIRECT is
>> supposed to be synchronous if all of the alignment requirements are
>> met, which means that by the time the write(2) system call returns,
>> the data is guaranteed to be on disk.  But if we need to manipulate
>> the extent tree to indicate that the block is now in use (so the data
>> is actually accessible), do we force a synchronous journal commit or
>> not?  If we don't, then a crash right after an O_DIRECT right into an
>> uninitialized region will cause the data to be "lost" (or at least,
>> unavailable via the read/write system call).  If we do, then the first
>> write into uninitialized block will cause a synchronous journal commit
>> that will be Slow And Painful, and it might destroy most of the
>> performance benefits that might tempt an enterprise database client to
>> use fallocate() in the first place.
>>
>> I wonder how XFS deals with this case?  It's a problem that is going
>> to hit any journalled filesystem that wants to support fallocate() and
>> direct I/O.
>>
>> One thing I can think of potentially doing is to check to see if the
>> extent tree block has already been journalled, and if it is not
>> currently involved the current transaction or the previous committing
>> transaction, *and* if there is space in the extent tree to mark the
>> current unitialized block as initialized (i.e., if the extent needs to
>> be split, there is sufficient space so we don't have to allocate a new
>> leaf block for the extent tree), we could update the leaf block in
>> place and then synchronously write it out, and thus avoid needing to
>> do a synchronous journal commit.
>
> In my example above, when KEEP_SIZE is used, it appears that
> converting the uninit extent to initialized never failed.  I haven't
> waded through ext4_ext_convert_to_initialized() to see how it might
> fail, and tried to get it to do so.
>
> It would be interesting to see if making this work -- having the
> blocks allocated and the buffer mapped -- for O_DIRECT writes in the
> absence of a journal, at least, would be feasible.  It would certainly
> be useful, to us at least.
>
> Thanks,
> Curt
>
>>
>> In any case, adding this support is going to be non-trivial.  If
>> someone has time to work on it in the next 2-3 weeks or so, I can push
>> it to Linus as a bug fix --- but I'm concerned the fixing this may be
>> tricky enough (and the patch invasive enough) that it might be
>> challenging to get this fixed in time for 2.6.31.
>>
>>                                                - Ted
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
>> the body of a message to majordomo@...r.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists