Re: Batched ww-mutexes, wound-wait vs wait-die etc.

On Mon, Apr 16, 2018 at 2:15 PM, Thomas Hellstrom wrote: > On 04/16/2018 11:19 AM, Daniel Vetter wrote: >> >> On Mon, Apr 16, 2018 at 10:23 AM, Thomas Hellstrom >> wrote: >>> >>> On 04/14/2018 10:33 AM, Daniel Vetter wrote: Hi Thomas,

Re: Batched ww-mutexes, wound-wait vs wait-die etc.

On 04/16/2018 11:19 AM, Daniel Vetter wrote: On Mon, Apr 16, 2018 at 10:23 AM, Thomas Hellstrom wrote: On 04/14/2018 10:33 AM, Daniel Vetter wrote: Hi Thomas, On Fri, Apr 13, 2018 at 10:23 PM, Thomas Hellstrom wrote: On 04/13/2018 07:13 PM,

Re: Batched ww-mutexes, wound-wait vs wait-die etc.

On Mon, Apr 16, 2018 at 10:23 AM, Thomas Hellstrom wrote: > On 04/14/2018 10:33 AM, Daniel Vetter wrote: >> >> Hi Thomas, >> >> On Fri, Apr 13, 2018 at 10:23 PM, Thomas Hellstrom >> wrote: >>> >>> On 04/13/2018 07:13 PM, Daniel Vetter wrote:

Re: Batched ww-mutexes, wound-wait vs wait-die etc.

On 04/14/2018 10:33 AM, Daniel Vetter wrote: Hi Thomas, On Fri, Apr 13, 2018 at 10:23 PM, Thomas Hellstrom wrote: On 04/13/2018 07:13 PM, Daniel Vetter wrote: On Wed, Apr 11, 2018 at 10:27:06AM +0200, Thomas Hellstrom wrote: 2) Should we add a *real* wound-wait choice

Re: Batched ww-mutexes, wound-wait vs wait-die etc.

Hi Thomas, On Fri, Apr 13, 2018 at 10:23 PM, Thomas Hellstrom wrote: > On 04/13/2018 07:13 PM, Daniel Vetter wrote: >> On Wed, Apr 11, 2018 at 10:27:06AM +0200, Thomas Hellstrom wrote: >>> 2) Should we add a *real* wound-wait choice to our wound-wait mutexes. >>> Otherwise

Re: Batched ww-mutexes, wound-wait vs wait-die etc.

Hi, Daniel, On 04/13/2018 07:13 PM, Daniel Vetter wrote: Hi Thomas, On Wed, Apr 11, 2018 at 10:27:06AM +0200, Thomas Hellstrom wrote: Hi! Thinking of adding ww-mutexes for reservation also of vmwgfx resources, (like surfaces), I became a bit worried that doubling the locks taken during

Re: Batched ww-mutexes, wound-wait vs wait-die etc.

Hi Thomas, On Wed, Apr 11, 2018 at 10:27:06AM +0200, Thomas Hellstrom wrote: > Hi! > > Thinking of adding ww-mutexes for reservation also of vmwgfx resources, > (like surfaces), I became a bit worried that doubling the locks taken during > command submission wouldn't be a good thing.

Batched ww-mutexes, wound-wait vs wait-die etc.

Hi! Thinking of adding ww-mutexes for reservation also of vmwgfx resources, (like surfaces), I became a bit worried that doubling the locks taken during command submission wouldn't be a good thing. Particularly on ESX servers where a high number of virtual machines running graphics on a