Re: [PATCH v2] usb: musb: ux500: optimize DMA callback routine

2011-08-15 Thread Felipe Balbi
Hi, On Sun, Aug 14, 2011 at 07:50:46PM +0200, Per Forlin wrote: > On 12 August 2011 11:41, Felipe Balbi wrote: > > Hi, > > > > On Mon, Aug 08, 2011 at 01:01:06PM +0200, Per Forlin wrote: > >> From: Per Forlin > >> > >> Skip the use of work queue and call musb_dma_completion() directly from > >>

Re: [PATCH v2] usb: musb: ux500: optimize DMA callback routine

2011-08-14 Thread Per Forlin
On 12 August 2011 11:41, Felipe Balbi wrote: > Hi, > > On Mon, Aug 08, 2011 at 01:01:06PM +0200, Per Forlin wrote: >> From: Per Forlin >> >> Skip the use of work queue and call musb_dma_completion() directly from >> DMA callback context. >> >> Here follows measurements on a Snowball board with on

Re: [PATCH v2] usb: musb: ux500: optimize DMA callback routine

2011-08-12 Thread Felipe Balbi
Hi, On Mon, Aug 08, 2011 at 01:01:06PM +0200, Per Forlin wrote: > From: Per Forlin > > Skip the use of work queue and call musb_dma_completion() directly from > DMA callback context. > > Here follows measurements on a Snowball board with ondemand governor active. > > Performance using work que

[PATCH v2] usb: musb: ux500: optimize DMA callback routine

2011-08-08 Thread Per Forlin
From: Per Forlin Skip the use of work queue and call musb_dma_completion() directly from DMA callback context. Here follows measurements on a Snowball board with ondemand governor active. Performance using work queue: (105 MB) copied, 6.23758 s, 16.8 MB/s (105 MB) copied, 5.7151 s, 18.3 MB/s (1