AF:
NF:0
PS:10
SRH:1
SFN:
DSR:
MID:<20080627181122.48654ca2@ripper.onstor.net>
CFG:
PT:0
S:andy.sharp@onstor.com
RQ:
SSV:onstor-exch02.onstor.net
NSV:
SSH:
R:<jobi.ariyamannil@onstor.com>
MAID:1
X-Sylpheed-Privacy-System:
X-Sylpheed-Sign:0
SCF:#mh/Mailbox/sent
RMID:#imap/andys@onstor.net@onstor-exch02.onstor.net/INBOX	0	BB375AF679D4A34E9CA8DFA650E2B04E0AAC59F2@onstor-exch02.onstor.net
X-Sylpheed-End-Special-Headers: 1
Date: Fri, 27 Jun 2008 18:11:31 -0700
From: Andrew Sharp <andy.sharp@onstor.com>
To: "Jobi Ariyamannil" <jobi.ariyamannil@onstor.com>
Subject: Re: one more change we discussed during triage meeting
Message-ID: <20080627181131.06af487e@ripper.onstor.net>
In-Reply-To: <BB375AF679D4A34E9CA8DFA650E2B04E0AAC59F2@onstor-exch02.onstor.net>
References: <BB375AF679D4A34E9CA8DFA650E2B04E0AAC59F2@onstor-exch02.onstor.net>
Organization: Onstor
X-Mailer: Sylpheed-Claws 2.6.0 (GTK+ 2.8.20; x86_64-pc-linux-gnu)
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit

Put the integrate together and run it by Jonathon for review.

Cheers,

a

On Fri, 27 Jun 2008 17:59:36 -0700 "Jobi Ariyamannil"
<jobi.ariyamannil@onstor.com> wrote:

> Hi Andy,
> 
>  
> 
> I need to integrate one more change to the beta branch since my other
> fixes have a lot of dependencies on that.
> 
> We discussed this one during triage meeting.
> 
>  
> 
> Regards,
> 
> Jobi
> 
>  
> 
> Change 29706 by jobia@jobi:jobi2 on 2008/06/16 13:18:54
> 
>  
> 
>            TED00024253 Csoak: Too many exceptions due to
> fs_volReadWriteQueue:
> 
>            Unable to send the read requests to the storage
> 
>  
> 
>            Read ahead user data pages during log replay.
> 
>            Read aheads issued during log replay can benefit from I/O
> coalescing.
> 
>            User data is read in as meta data buffer during log replay,
> so remove
> 
>            all the unnecessary code causing confusion.
> 
>            Purge the user data buffers from cache after zero fill. 
> 
>            Add flush record for the first page of user files since
> they could have
> 
>            transactions in the log. 
> 
>            Instead of syncing the complete buffer cache after log
> replay, just
> 
>            sync the user data buffers which are zero filled.
> 
>  
> 
>            Reviewed by JonG.
> 
>  
> 
> Affected files ...
> 
>  
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-buf.c#64 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-buf.h#23 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-log-replay.c#19 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-log.c#18 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-log.h#9 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-rdwr.c#17 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-rdwr.h#9 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-trashcan.c#11 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-vol-log.c#16 edit
> 
> ... //depot/dev/nfx-tree/code/sm-fs/fs-zeroFill.c#4 edit
> 
