Date: Sat, 21 Aug 2010 12:35:16 +0300 From: Andriy Gapon <avg@icyb.net.ua> To: Doug Barton <dougb@FreeBSD.org> Cc: freebsd-current@FreeBSD.org Subject: Re: Latest intr problems Message-ID: <4C6F9DD4.3050205@icyb.net.ua> In-Reply-To: <alpine.BSF.2.00.1008210028530.1718@qbhto.arg> References: <alpine.BSF.2.00.1008201701001.19740@qbhto.arg> <4C6F772A.5020703@icyb.net.ua> <4C6F7BD1.4030009@icyb.net.ua> <alpine.BSF.2.00.1008210028530.1718@qbhto.arg>
next in thread | previous in thread | raw e-mail | index | archive | help
on 21/08/2010 10:33 Doug Barton said the following: > On Sat, 21 Aug 2010, Andriy Gapon wrote: > >>> I think that for such amount of data it is better to use links >>> (perhaps a >>> service like pastebin) rather than inlining it. > > No problem: > http://people.freebsd.org/~dougb/intr-out.txt Thanks a lot! Can you try, for the sake of experiment, to reproduce the problem with hw.acpi.cpu.cx_lowest=C1 ? I feel like you might be having a problem with clocks... BTW, if you run procstat -k 11 a few times during the condition, does TID 100006 typically have or not have "lock_mtx softclock" substring in its stack? -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4C6F9DD4.3050205>