Re: [PATCH] xfs: idle aild if the AIL is pushed up to the target LSN

2016-04-27 Thread Dave Chinner
On Wed, Apr 27, 2016 at 08:31:38PM +0200, Lucas Stach wrote: > Am Dienstag, den 26.04.2016, 09:08 +1000 schrieb Dave Chinner: > [...] > > > > > > > > > > > That said, I'm not sure whether there's a notable benefit of > > > > idling > > > > for > > > > 50ms over just scheduling out when we've hit

Re: [PATCH] xfs: idle aild if the AIL is pushed up to the target LSN

2016-04-27 Thread Lucas Stach
Am Dienstag, den 26.04.2016, 09:08 +1000 schrieb Dave Chinner: [...] > > > > > > > > That said, I'm not sure whether there's a notable benefit of > > > idling > > > for > > > 50ms over just scheduling out when we've hit the target lsn. It > > > seems > > > like that anybody who pushes the target

Re: [PATCH] xfs: idle aild if the AIL is pushed up to the target LSN

2016-04-25 Thread Dave Chinner
On Mon, Apr 25, 2016 at 08:11:37PM +0200, Lucas Stach wrote: > Am Montag, den 25.04.2016, 10:24 -0400 schrieb Brian Foster: > > On Mon, Apr 25, 2016 at 09:42:43AM +0200, Lucas Stach wrote: > > > > > > The current logic only idles aild if the AIL is empty, rescheduling > > > the worker with a timeo

Re: [PATCH] xfs: idle aild if the AIL is pushed up to the target LSN

2016-04-25 Thread Lucas Stach
Am Montag, den 25.04.2016, 10:24 -0400 schrieb Brian Foster: > On Mon, Apr 25, 2016 at 09:42:43AM +0200, Lucas Stach wrote: > > > > The current logic only idles aild if the AIL is empty, rescheduling > > the worker with a timeout of 50ms otherwise. If the target LSN > > isn't > > moved forward, th

Re: [PATCH] xfs: idle aild if the AIL is pushed up to the target LSN

2016-04-25 Thread Brian Foster
On Mon, Apr 25, 2016 at 09:42:43AM +0200, Lucas Stach wrote: > The current logic only idles aild if the AIL is empty, rescheduling > the worker with a timeout of 50ms otherwise. If the target LSN isn't > moved forward, the worker will not make any progress as it only > pushes the AIL up to the targ

[PATCH] xfs: idle aild if the AIL is pushed up to the target LSN

2016-04-25 Thread Lucas Stach
The current logic only idles aild if the AIL is empty, rescheduling the worker with a timeout of 50ms otherwise. If the target LSN isn't moved forward, the worker will not make any progress as it only pushes the AIL up to the target LSN, leading to the empty AIL condition to only be met after the l