Re: [PATCH V2 01/20] blk-mq-sched: fix scheduler bad performance

2017-08-23 Thread Ming Lei
On Wed, Aug 09, 2017 at 12:11:18AM -0700, Omar Sandoval wrote: > On Wed, Aug 09, 2017 at 10:32:52AM +0800, Ming Lei wrote: > > On Wed, Aug 9, 2017 at 8:11 AM, Omar Sandoval wrote: > > > On Sat, Aug 05, 2017 at 02:56:46PM +0800, Ming Lei wrote: > > >> When hw queue is busy, we

Re: [PATCH V2 01/20] blk-mq-sched: fix scheduler bad performance

2017-08-21 Thread Ming Lei
On Wed, Aug 09, 2017 at 12:11:18AM -0700, Omar Sandoval wrote: > On Wed, Aug 09, 2017 at 10:32:52AM +0800, Ming Lei wrote: > > On Wed, Aug 9, 2017 at 8:11 AM, Omar Sandoval wrote: > > > On Sat, Aug 05, 2017 at 02:56:46PM +0800, Ming Lei wrote: > > >> When hw queue is busy, we

Re: [PATCH V2 01/20] blk-mq-sched: fix scheduler bad performance

2017-08-09 Thread Omar Sandoval
On Wed, Aug 09, 2017 at 10:32:52AM +0800, Ming Lei wrote: > On Wed, Aug 9, 2017 at 8:11 AM, Omar Sandoval wrote: > > On Sat, Aug 05, 2017 at 02:56:46PM +0800, Ming Lei wrote: > >> When hw queue is busy, we shouldn't take requests from > >> scheduler queue any more, otherwise

Re: [PATCH V2 01/20] blk-mq-sched: fix scheduler bad performance

2017-08-08 Thread Ming Lei
On Wed, Aug 9, 2017 at 8:11 AM, Omar Sandoval wrote: > On Sat, Aug 05, 2017 at 02:56:46PM +0800, Ming Lei wrote: >> When hw queue is busy, we shouldn't take requests from >> scheduler queue any more, otherwise IO merge will be >> difficult to do. >> >> This patch fixes the

Re: [PATCH V2 01/20] blk-mq-sched: fix scheduler bad performance

2017-08-08 Thread Omar Sandoval
On Sat, Aug 05, 2017 at 02:56:46PM +0800, Ming Lei wrote: > When hw queue is busy, we shouldn't take requests from > scheduler queue any more, otherwise IO merge will be > difficult to do. > > This patch fixes the awful IO performance on some > SCSI devices(lpfc, qla2xxx, ...) when

[PATCH V2 01/20] blk-mq-sched: fix scheduler bad performance

2017-08-05 Thread Ming Lei
When hw queue is busy, we shouldn't take requests from scheduler queue any more, otherwise IO merge will be difficult to do. This patch fixes the awful IO performance on some SCSI devices(lpfc, qla2xxx, ...) when mq-deadline/kyber is used by not taking requests if hw queue is busy. Reviewed-by: