xfs
[Top] [All Lists]

Re: TAKE - O_SYNC delayed alloc fix

To: dxm@xxxxxxxxxxxxxxxxxxxxxxx (Daniel Moore)
Subject: Re: TAKE - O_SYNC delayed alloc fix
From: lord@xxxxxxx
Date: Wed, 07 Jun 2000 18:01:25 -0500
Cc: linux-xfs@xxxxxxxxxxx
In-reply-to: Your message of "Thu, 08 Jun 2000 08:52:23 +1000
Sender: owner-linux-xfs@xxxxxxxxxxx
> O_SYNC implies no delayed-alloc
> 
> Modid:  2.3.99pre2-xfs:slinx:63618a
> Date:  Wed Jun  7 15:51:29 PDT 2000
> Workarea:  snort:/build1/people/dxm/isms/slinx-xfs
> Author:  dxm
> 
> The following file(s) were checked into:
>   bonnie.engr.sgi.com:/isms/slinx/2.3.99pre2-xfs
> 
> linux/fs/page_buf.c - 1.108
http://oss.sgi.com/cgi-bin/cvsweb.cgi/linux-2.4-xfs/> 
linux/fs/page_buf.c.diff?r1=text&tr1=1.108&r2=text&tr2=1.107&f=h
>       - O_SYNC implies no delayed alloc

except you cannot get there anymore if O_SYNC is not set on your I/O,
with delayed allocate enabled XFS calls into pagebuf_generic_file_write_async
unless O_SYNC is set when it calls pagebuf_generic_file_write.

I am currently wading through the two varients of the I/O path and
attempting to consolidate them, stay tuned.

Steve


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