[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] Re: [PATCH] Speed up DVB TS stream delivery from <a href="http://www.chistraightenerbuy.com/ghd-hair-straightener-c-3.html"><strong>GHD IV Hot Pink Styler</strong></a> DMA buffer into dvb-core's buffer Subject: Re: [PATCH] Speed up DVB TS stream delivery from DMA buffer into dvb-core's buffer From: Andreas Oberritter <obi@xxxxxxxxxxx> Date: Sun, 10 Apr 2011 14:28:31 +0200 Cc: Mauro Carvalho Chehab <mchehab@xxxxxxxxxx>, Linux Media Mailing List <linux-media@xxxxxxxxxxxxxxx> In-reply-to: <4D9F63E1.6060808@xxxxxxxxxxx> User-agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.15) Gecko/20110406 Lightning/1.0b2 Thunderbird/3.1.9 On 04/08/2011 09:37 PM, Marko Ristola wrote: > > Here is some statistics without likely and with likely functions. > > It seems that using likely() gives better performance with Phenom I too. I'm not sure whether that's the right conclusion. See below. > % Plain knl % No likely % With likely % > dvb_ringbuffer_write 5,9 62,8 8,7 81,3 5,7 79,2 > dvb_dmx_swfilter_packet 1,2 12,8 0,7 6,5 0,8 11,1 > dvb_dmx_swfilter_204 2,3 24,5 1,3 12,1 0,7 9,7 > > > Here "Plain knl %" is "perf top -d 30" percentage. > 24,5 12,1 and 9,7 are percentages without a patch, with basic patch > and last is with "likely" functions using patch. The varying ratio between dvb_ringbuffer_write and dvb_dmx_swfilter_packet, which haven't been modified by the patch, seems to indicate that the numbers were influenced <a href="http://www.chistraightenerbuy.com/ghd-hair-straightener-c-3.html"><strong>ghd hair straighteners</strong></a> by other activities on the system or by the data used during <a href="http://www.chistraightenerbuy.com/ghd-hair-straightener-c-3.html"><strong>cheap ghd straighteners</strong></a> the tests. 8,7% for dvb_ringbuffer_write in test #2 could also indicate a higher data rate than in #1 and #3. However, adding likely() certainly won't do any harm. Feel free to send an incremental patch. Regards, Andreas -- To unsubscribe from this list: send the line "unsubscribe linux-media" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at
http://vger.kernel.org/majordomo-info.html References: [PATCH] Speed up DVB TS stream delivery from DMA buffer into dvb-core's buffer From: Marko Ristola Re: [PATCH] Speed up DVB TS stream delivery from DMA buffer into dvb-core's buffer From: Marko Ristola Prev by Date: Re: [PATCH] Speed up DVB TS stream delivery from DMA buffer into dvb-core's buffer Next by Date: Re: [PATCH 2.6.39] soc_camera: OMAP1: fix missing bytesperline and sizeimage initialization Previous by thread: Re: [PATCH] Speed up DVB TS stream delivery from DMA buffer into dvb-core's buffer Next by thread: Re: [PATCH] Speed up DVB TS stream delivery from DMA buffer into dvb-core's buffer Index(es): Date Thread [Linux Input] [Video for Linux] [Mplayer Users] [Linux USB Devel] [Linux Audio Users] [Photos] [Yosemite Photos] [Linux Kernel] [Linux SCSI] [XFree86] [Devices] [Yosemite Backpacking] [Linux Input] <a href="http://www.htzh.net/view.php?id=20590"><strong>ACER Aspire 5100 Laptop CPU Cooling Fan AB7505UX-EB3 | Super ...</strong></a>
Re: [PATCH] Speed up DVB TS stream delivery from DMA buffer into ...
Threaded Mode