From mboxrd@z Thu Jan  1 00:00:00 1970
From: Steven Whitehouse <swhiteho@redhat.com>
Date: Tue, 03 Mar 2009 11:24:37 +0000
Subject: [Cluster-devel] Re: [PATCH] GFS2: Pagecache usage optimization on
	GFS2
In-Reply-To: <6.0.0.20.2.20090302151159.059ed288@172.19.0.2>
References: <6.0.0.20.2.20090302151159.059ed288@172.19.0.2>
Message-ID: <1236079477.3563.0.camel@localhost.localdomain>
List-Id: <cluster-devel.redhat.com>
To: cluster-devel.redhat.com
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit

Hi,

Looks good! Applied to the -nmw git tree. Thanks,

Steve.

On Tue, 2009-03-03 at 11:45 +0900, Hisashi Hifumi wrote:
> Hi.
> 
> I introduced "is_partially_uptodate" aops for GFS2.
> 
> A page can have multiple buffers and even if a page is not uptodate, some buffers 
> can be uptodate on pagesize != blocksize environment.
> This aops checks that all buffers which correspond to a part of a file 
> that we want to read are uptodate. If so, we do not have to issue actual 
> read IO to HDD even if a page is not uptodate because the portion we 
> want to read are uptodate. 
> "block_is_partially_uptodate" function is already used by ext2/3/4.
> With the following patch random read/write mixed workloads or random read after 
> random write workloads can be optimized and we can get performance improvement.
> 
> I did a performance test using the sysbench.
> 
> #sysbench --num-threads=16 --max-requests=200000 --test=fileio --file-num=1 
> --file-block-size=8K --file-total-size=2G --file-test-mode=rndrw --file-fsync-freq=0 
> --file-rw-ratio=1 run
> 
> -2.6.29-rc6
> Test execution summary:
>     total time:                          202.6389s
>     total number of events:              200000
>     total time taken by event execution: 2580.0480
>     per-request statistics:
>          min:                            0.0000s
>          avg:                            0.0129s
>          max:                            49.5852s
>          approx.  95 percentile:         0.0462s
> 
> 
> -2.6.29-rc6-patched
> Test execution summary:
>     total time:                          177.8639s
>     total number of events:              200000
>     total time taken by event execution: 2419.0199
>     per-request statistics:
>          min:                            0.0000s
>          avg:                            0.0121s
>          max:                            52.4306s
>          approx.  95 percentile:         0.0444s
> 
> 
> arch: ia64
> pagesize: 16k
> blocksize: 4k
> 
> 
> Please merge following patch.
> Thanks.
> 
> Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp>
> 
> diff -Nrup linux-2.6.29-rc6.org/fs/gfs2/ops_address.c linux-2.6.29-rc6/fs/gfs2/ops_address.c
> --- linux-2.6.29-rc6.org/fs/gfs2/ops_address.c	2009-03-02 09:26:07.000000000 +0900
> +++ linux-2.6.29-rc6/fs/gfs2/ops_address.c	2009-03-02 09:47:28.000000000 +0900
> @@ -1096,6 +1096,7 @@ static const struct address_space_operat
>  	.releasepage = gfs2_releasepage,
>  	.direct_IO = gfs2_direct_IO,
>  	.migratepage = buffer_migrate_page,
> +	.is_partially_uptodate = block_is_partially_uptodate,
>  };
>  
>  static const struct address_space_operations gfs2_ordered_aops = {
> @@ -1111,6 +1112,7 @@ static const struct address_space_operat
>  	.releasepage = gfs2_releasepage,
>  	.direct_IO = gfs2_direct_IO,
>  	.migratepage = buffer_migrate_page,
> +	.is_partially_uptodate = block_is_partially_uptodate,
>  };
>  
>  static const struct address_space_operations gfs2_jdata_aops = {
> @@ -1125,6 +1127,7 @@ static const struct address_space_operat
>  	.bmap = gfs2_bmap,
>  	.invalidatepage = gfs2_invalidatepage,
>  	.releasepage = gfs2_releasepage,
> +	.is_partially_uptodate = block_is_partially_uptodate,
>  };
>  
>  void gfs2_set_aops(struct inode *inode)
>