Re: [OpenWrt-Devel] rt61pci performance

2010-11-28 Thread Scott Nicholas
I fixed it, maybe. On Fri, Nov 26, 2010 at 1:52 PM, Scott Nicholas wrote: > On Fri, Nov 26, 2010 at 4:39 AM, Helmut Schaa > wrote: >> >> Btw. did you check if hardware crypto is working fine? If hw crypto doesn't >> work it would fall back to software which could explain such a CPU >> utilizati

Re: [OpenWrt-Devel] rt61pci performance

2010-11-25 Thread Helmut Schaa
Am Donnerstag 21 Oktober 2010 schrieb scott.nicho...@scottn.us: > rt2x00/rt61pci wireless driver eats all the CPU. Any other boards use this? > Anyone with experience with this driver know if there was a better version > than the current compat-wireless in svn? Scott, could you please try if the p

Re: [OpenWrt-Devel] rt61pci performance

2010-11-19 Thread Scott Nicholas
I've an idea... On Fri, Oct 22, 2010 at 5:56 AM, Helmut Schaa wrote: > Hi, > > CC'ed rt2x00 list ... > > Am Donnerstag 21 Oktober 2010 schrieb Scott Nicholas: >> On Thu, Oct 21, 2010 at 12:25 PM, Helmut Schaa >> wrote: >> > I fully agree. The same also applies to rt2800pci SoCs (rt305x) which ar

Re: [OpenWrt-Devel] rt61pci performance

2010-10-22 Thread Felix Fietkau
On 2010-10-22 1:33 PM, Florian Fainelli wrote: > You can use oprofile on MIPS32 4Kc platforms without problems. This should > help > providing some insight about where most of the time is spent. MIPS 4Kc does not have generic performance counters, so oprofile will not be very accurate, and there

Re: [OpenWrt-Devel] rt61pci performance

2010-10-22 Thread Helmut Schaa
Hi, CC'ed rt2x00 list ... Am Donnerstag 21 Oktober 2010 schrieb Scott Nicholas: > On Thu, Oct 21, 2010 at 12:25 PM, Helmut Schaa > wrote: > > I fully agree. The same also applies to rt2800pci SoCs (rt305x) which are > > working quite good already (in terms of WiFi) but also show more CPU usage >

Re: [OpenWrt-Devel] rt61pci performance

2010-10-21 Thread Scott Nicholas
Helmut, On Thu, Oct 21, 2010 at 12:25 PM, Helmut Schaa wrote: > I fully agree. The same also applies to rt2800pci SoCs (rt305x) which are > working quite good already (in terms of WiFi) but also show more CPU usage > then the legacy drivers. > > IMO it would really make sense to work on improving

Re: [OpenWrt-Devel] rt61pci performance

2010-10-21 Thread Helmut Schaa
Hi, Am Donnerstag 21 Oktober 2010 schrieb Florian Fainelli: > On Thursday 21 October 2010 13:43:17 scott.nicho...@scottn.us wrote: > > That's what I was afraid of. Tho there is some CPU usage with legacy driver > > using 2.4 kernel, it is sooo much worse with rt2x00. Softirqs take 50% and > > kern

Re: [OpenWrt-Devel] rt61pci performance

2010-10-21 Thread scott . nicholas
-- From: Florian Fainelli Sender: Florian Fainelli To: openwrt-devel@lists.openwrt.org To: scott.nicho...@scottn.us Subject: Re: [OpenWrt-Devel] rt61pci performance Sent: Oct 21, 2010 7:35 AM Hello Scott, On Thursday 21 October 2010 13:08:47 scott.nicho...@scottn.us wrote: > rt2x00/rt61pci wire

[OpenWrt-Devel] rt61pci performance

2010-10-21 Thread scott . nicholas
rt2x00/rt61pci wireless driver eats all the CPU. Any other boards use this? Anyone with experience with this driver know if there was a better version than the current compat-wireless in svn? Sent via BlackBerry Bold 9700 ___ openwrt-devel mailing list