Re: [PATCH 05/11] direct-io: only inc/dec inode->i_dio_count for file systems

2015-02-05 Thread Mike Snitzer
On Thu, Oct 24, 2013 at 5:49 AM, Jens Axboe wrote: > On Thu, Oct 24 2013, Christoph Hellwig wrote: >> On Thu, Oct 24, 2013 at 10:46:00AM +0100, Jens Axboe wrote: >> > On Thu, Oct 24 2013, Jens Axboe wrote: >> > > We don't need truncate protection for block devices, so add a flag >> > > bypassing t

Re: [PATCH 05/11] direct-io: only inc/dec inode->i_dio_count for file systems

2013-10-24 Thread Jens Axboe
On Thu, Oct 24 2013, Christoph Hellwig wrote: > On Thu, Oct 24, 2013 at 10:46:00AM +0100, Jens Axboe wrote: > > On Thu, Oct 24 2013, Jens Axboe wrote: > > > We don't need truncate protection for block devices, so add a flag > > > bypassing this cache line dirtying twice for every IO. This easily >

Re: [PATCH 05/11] direct-io: only inc/dec inode->i_dio_count for file systems

2013-10-24 Thread Christoph Hellwig
On Thu, Oct 24, 2013 at 10:46:00AM +0100, Jens Axboe wrote: > On Thu, Oct 24 2013, Jens Axboe wrote: > > We don't need truncate protection for block devices, so add a flag > > bypassing this cache line dirtying twice for every IO. This easily > > contributes to 5-10% of the CPU time on high IOPS O_

Re: [PATCH 05/11] direct-io: only inc/dec inode->i_dio_count for file systems

2013-10-24 Thread Jens Axboe
On Thu, Oct 24 2013, Jens Axboe wrote: > We don't need truncate protection for block devices, so add a flag > bypassing this cache line dirtying twice for every IO. This easily > contributes to 5-10% of the CPU time on high IOPS O_DIRECT testing. There's a merge error in this patch, please find th

[PATCH 05/11] direct-io: only inc/dec inode->i_dio_count for file systems

2013-10-24 Thread Jens Axboe
We don't need truncate protection for block devices, so add a flag bypassing this cache line dirtying twice for every IO. This easily contributes to 5-10% of the CPU time on high IOPS O_DIRECT testing. Cc: Christoph Hellwig Cc: Al Viro Signed-off-by: Jens Axboe --- fs/block_dev.c | 3 ++-