Messages in this thread | | | Date | Wed, 7 May 2014 18:29:24 +0100 | From | Will Deacon <> | Subject | Re: [patch/rfc] perf on raspberry-pi without overflow interrupt |
| |
Hi Vince,
On Mon, Feb 24, 2014 at 03:37:11PM +0000, Vince Weaver wrote: > On Mon, 24 Feb 2014, Will Deacon wrote: > > On Fri, Jan 17, 2014 at 05:45:04AM +0000, Vince Weaver wrote: > > > On Thu, 16 Jan 2014, Peter Zijlstra wrote: > > > > > > > Yeah I suppose we could do something like that. Maybe something like: > > > > > > > > # cat /sys/bus/event_source/devices/cpu/flags > > > > int precise filter > > > > > > wouldn't that violate the "one value per file" rule? > > > > > > I guess we could also stick it in the mmap page somewhere, as tools like > > > PAPI already have to check there for things like rdpmc support. > > > > > > > > > Anyway, here's a first pass at a generic fix for this issue. I'm sure the > > > code is pretty horrible, I don't usually mess with the perf code at this > > > level. I haven't tested yet as it touched enough files that the rasp-pi > > > is going to take a few hours to finish compiling. > > > > > > Am I on the right track, or totally off here? > > > > Where did we get to with this? If the generic changes are going to take some > > time, I'm happy to take a temporary (non-invasive) fix in the ARM backend while > > you sort out the core. > > OK, let me revisit the patches. The last set of generic ones I sent out > actually was broken on ARM and I've been meaning to straighten things out > and send a proper follow up patch set but got distracted by other perf > related issues.
Any luck with this? I just got (another) report of a PMU with borked interrupts, so a fix would be great if you've got one.
Will
| |