Date: Thu, 6 Feb 2003 08:20:08 -0800 (PST) From: John Baldwin <jhb@FreeBSD.org> To: freebsd-bugs@FreeBSD.org Subject: Re: kern/18524: The current kernel doesn't keep stats on a per c Message-ID: <200302061620.h16GK8IY015026@freefall.freebsd.org>
next in thread | raw e-mail | index | archive | help
The following reply was made to PR kern/18524; it has been noted by GNATS. From: John Baldwin <jhb@FreeBSD.org> To: Arun Sharma <arun@sharma-home.net> Cc: smp@freebsd.org, freebsd-gnats-submit@FreeBSD.org Subject: Re: kern/18524: The current kernel doesn't keep stats on a per c Date: Thu, 06 Feb 2003 11:13:15 -0500 (EST) On 06-Feb-2003 Arun Sharma wrote: > > I'd like to reopen this PR: > > http://www.freebsd.org/cgi/query-pr.cgi?pr=18524 > > and submit a new patch: > > http://www.sharma-home.net/~adsharma/misc/pcpu-cptime.patch > > $ sysctl kern.smp.cpu kern.cp_time > kern.smp.cpu.0.cp_time: 1196 1 2900 351 74120 > kern.smp.cpu.1.cp_time: 1248 3 2837 329 74110 > kern.cp_time: 2444 4 5737 680 148230 > > The ugliest part of this patch is calling mi_cpu_start(cpu). I tried > making the calls in i386/mp_machdep.c, but ran into panics no matter > where I placed the call (mi_cpu_start ends up calling malloc, which may > block, do TLB shoot downs etc). > > So if someone has a better idea about how to arrange for a machine > independent cpu start/stop hook that could make blocking calls, I'd like > to hear about it. Why not stick the cp_time stuff in struct pcpu instead of using an array? -- John Baldwin <jhb@FreeBSD.org> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-bugs" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200302061620.h16GK8IY015026>