[Top] [All Lists]

Re: Terrible performance of sequential O_DIRECT 4k writes in SAN environ

To: Dave Chinner <david@xxxxxxxxxxxxx>
Subject: Re: Terrible performance of sequential O_DIRECT 4k writes in SAN environment. ~3 times slower then Solars 10 with the same HBA/Storage.
From: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Mon, 20 Jan 2014 05:58:55 -0800
Cc: Sergey Meirovich <rathamahata@xxxxxxxxx>, Christoph Hellwig <hch@xxxxxxxxxxxxx>, xfs@xxxxxxxxxxx, Jan Kara <jack@xxxxxxx>, linux-scsi <linux-scsi@xxxxxxxxxxxxxxx>, Linux Kernel Mailing List <linux-kernel@xxxxxxxxxxxxxxx>, Gluk <git.user@xxxxxxxxx>
Delivered-to: xfs@xxxxxxxxxxx
In-reply-to: <20140115220721.GY3469@dastard>
References: <CA+QCeVQRrqx=CrxyuAe7k0e0y4Nqo7x_8jtkuD99VM8L9Dxp+g@xxxxxxxxxxxxxx> <20140106201032.GA13491@xxxxxxxxxxxxx> <20140107155830.GA28395@xxxxxxxxxxxxx> <CA+QCeVRiwHU+C5utaLQXf_MpjoYMYEF4LKRyDPaqcd=H6n-RRw@xxxxxxxxxxxxxx> <20140108140307.GA588@xxxxxxxxxxxxx> <CA+QCeVRuvNtZ8+9D-NtMOD=B9UEA5HMvKaGdXOQCjO-KTnZdbw@xxxxxxxxxxxxxx> <20140115220721.GY3469@dastard>
User-agent: Mutt/1.5.21 (2010-09-15)
On Thu, Jan 16, 2014 at 09:07:21AM +1100, Dave Chinner wrote:
> Yes, I think it can be done relatively simply. We'd have to change
> the code in xfs_file_aio_write_checks() to check whether EOF zeroing
> was required rather than always taking an exclusive lock (for block
> aligned IO at EOF sub-block zeroing isn't required),

That's not even required for supporting aio appends, just a further
optimization for it.

> and then we'd
> have to modify the direct IO code to set the is_async flag
> appropriately. We'd probably need a new flag to say tell the DIO
> code that AIO beyond EOF is OK, but that isn't hard to do....

Yep, need a flag to allow appending writes and then defer them.

> Christoph, are you going to get any time to look at doing this in
> the next few days?

I'll probably need at least another week before I can get to it.  If you
wanna pick it up before than feel free.

<Prev in Thread] Current Thread [Next in Thread>