Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2012-03-03 Thread Rafael J. Wysocki
Hi, Sorry for the late respones. On Monday, December 19, 2011, Ulf Hansson wrote: > Guennadi Liakhovetski wrote: > > On Wed, 14 Dec 2011, Rafael J. Wysocki wrote: > > > >> On Wednesday, December 14, 2011, Ulf Hansson wrote: > > > > [snip] > > > >>> 2. > >>> When executing mmc/sd commands/reque

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-19 Thread Ulf Hansson
Guennadi Liakhovetski wrote: On Wed, 14 Dec 2011, Rafael J. Wysocki wrote: On Wednesday, December 14, 2011, Ulf Hansson wrote: [snip] 2. When executing mmc/sd commands/requests the host must always be claimed (and thus the host is always enabled). Why? Why cannot we save some power betwe

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-16 Thread Guennadi Liakhovetski
On Wed, 14 Dec 2011, Rafael J. Wysocki wrote: > On Wednesday, December 14, 2011, Ulf Hansson wrote: [snip] > > 2. > > When executing mmc/sd commands/requests the host must always be claimed > > (and thus the host is always enabled). Why? Why cannot we save some power between IO operations - if

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-14 Thread Rafael J. Wysocki
On Wednesday, December 14, 2011, Ulf Hansson wrote: > > >> You have a point. But I am not convinced. :-) > >> > >> Some host drivers already make use of autosuspend. I think this is most > >> straightforward solution to this problem right now. > > > > The problem is not about _when_ to suspend (

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-14 Thread Linus Walleij
On Wed, Dec 14, 2011 at 11:28 AM, Rafael J. Wysocki wrote: > On Wednesday, December 14, 2011, Linus Walleij wrote: >> But this delta is dependent on a lot of stuff that only the platform >> knows, like nominal CPU frequency, bus speed etc, so certainly the >> platform must be able to modify that

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-14 Thread Ulf Hansson
You have a point. But I am not convinced. :-) Some host drivers already make use of autosuspend. I think this is most straightforward solution to this problem right now. The problem is not about _when_ to suspend (which autosuspend is about), but _what_ _state_ to go when suspended. That's

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-14 Thread Rafael J. Wysocki
On Wednesday, December 14, 2011, Linus Walleij wrote: > On Wed, Dec 14, 2011 at 10:00 AM, Ulf Hansson > wrote: > > Guennadi Liakhovetski wrote: > > > Using PM QoS as you propose, might prevent some hosts from doing > > runtime_suspend|resume completely and thus those might not fulfill power > > c

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-14 Thread Rafael J. Wysocki
On Wednesday, December 14, 2011, Ulf Hansson wrote: > Guennadi Liakhovetski wrote: > > Hi Ulf > > > > On Tue, 13 Dec 2011, Ulf Hansson wrote: > > > >> Guennadi Liakhovetski wrote: > >>> Some MMC hosts implement a fine-grained runtime PM, whereby they > >>> runtime-suspend and -resume the host int

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-14 Thread Linus Walleij
On Wed, Dec 14, 2011 at 10:00 AM, Ulf Hansson wrote: > Guennadi Liakhovetski wrote: > Using PM QoS as you propose, might prevent some hosts from doing > runtime_suspend|resume completely and thus those might not fulfill power > consumption requirements instead. I do not think we can take this dec

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-14 Thread Ulf Hansson
Guennadi Liakhovetski wrote: Hi Ulf On Tue, 13 Dec 2011, Ulf Hansson wrote: Guennadi Liakhovetski wrote: Some MMC hosts implement a fine-grained runtime PM, whereby they runtime-suspend and -resume the host interface on each transfer. This can negatively affect performance, if the user was tr

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-13 Thread Rafael J. Wysocki
On Tuesday, December 13, 2011, Guennadi Liakhovetski wrote: > Hi Ulf > > On Tue, 13 Dec 2011, Ulf Hansson wrote: > > > Guennadi Liakhovetski wrote: > > > Some MMC hosts implement a fine-grained runtime PM, whereby they > > > runtime-suspend and -resume the host interface on each transfer. This ca

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-13 Thread Guennadi Liakhovetski
Hi Ulf On Tue, 13 Dec 2011, Ulf Hansson wrote: > Guennadi Liakhovetski wrote: > > Some MMC hosts implement a fine-grained runtime PM, whereby they > > runtime-suspend and -resume the host interface on each transfer. This can > > negatively affect performance, if the user was trying to transfer da

Re: [PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-13 Thread Ulf Hansson
Guennadi Liakhovetski wrote: Some MMC hosts implement a fine-grained runtime PM, whereby they runtime-suspend and -resume the host interface on each transfer. This can negatively affect performance, if the user was trying to transfer data blocks back-to-back. This patch adds a PM QoS constraint t

[PATCH/RFC] mmc: add a device PM QoS constraint when a host is first claimed

2011-12-12 Thread Guennadi Liakhovetski
Some MMC hosts implement a fine-grained runtime PM, whereby they runtime-suspend and -resume the host interface on each transfer. This can negatively affect performance, if the user was trying to transfer data blocks back-to-back. This patch adds a PM QoS constraint to avoid such a throughput reduc