Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-29 Thread Ray Lee
On Nov 29, 2007 9:11 AM, <[EMAIL PROTECTED]> wrote: > > These are good points. However, on the Slack 10.2 box I repeated these > measurements with all userspace code quiesced. No daemons running except > for those that are kernel threads. Secondly, I do run dynticks kernels on > other Slackware 10

Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-29 Thread Ray Lee
On Nov 28, 2007 6:44 PM, <[EMAIL PROTECTED]> wrote: > I built the same dynticks-enabled 2.6.23.9 kernel on a nearly identical > system with minor changes to reflect the slightly different hardware. > These two systems have identical MSI E7210 MasterX FA6R motherboards (same > model and revision.) T

Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-28 Thread Ingo Molnar
* Andrew Morton <[EMAIL PROTECTED]> wrote: > On Mon, 26 Nov 2007 20:36:32 -0600 (CST) [EMAIL PROTECTED] wrote: > > > Question: Why is ksoftirqd eating about 5 to 10 percent of my CPU on an idle > > system? The problem occurs if I config the kernel with tickless > > support (i.e. CONFIG_TICK_ONES

Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-27 Thread Andrew Morton
On Mon, 26 Nov 2007 22:36:17 -0600 Robert Hancock <[EMAIL PROTECTED]> wrote: > [EMAIL PROTECTED] wrote: > > Question: Why is ksoftirqd eating about 5 to 10 percent of my CPU on an idle > > system? The problem occurs if I config the kernel with tickless > > support (i.e. CONFIG_TICK_ONESHOT=y). (T

Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-27 Thread Andrew Morton
On Mon, 26 Nov 2007 20:36:32 -0600 (CST) [EMAIL PROTECTED] wrote: > Question: Why is ksoftirqd eating about 5 to 10 percent of my CPU on an idle > system? The problem occurs if I config the kernel with tickless > support (i.e. CONFIG_TICK_ONESHOT=y). (Thanks to "oprofile" for putting me > onto th

Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-27 Thread Robert Hancock
[EMAIL PROTECTED] wrote: Hello Robert, I've attached additional detail on the config of the misbehaving system including output from oprofile and PowerTop. PowerTop output leads me to believe that maybe this is an interaction between my bridged ethernet setup and dynticks? Hmmm... Don't know a

Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-26 Thread Arjan van de Ven
On Mon, 26 Nov 2007 22:36:17 -0600 Robert Hancock <[EMAIL PROTECTED]> wrote: > [EMAIL PROTECTED] wrote: > > Question: Why is ksoftirqd eating about 5 to 10 percent of my CPU > > on an idle system? The problem occurs if I config the kernel with > > tickless support (i.e. CONFIG_TICK_ONESHOT=y). (T

Re: Dynticks Causing High Context Switch Rate in ksoftirqd

2007-11-26 Thread Robert Hancock
[EMAIL PROTECTED] wrote: Question: Why is ksoftirqd eating about 5 to 10 percent of my CPU on an idle system? The problem occurs if I config the kernel with tickless support (i.e. CONFIG_TICK_ONESHOT=y). (Thanks to "oprofile" for putting me onto this.) I have noted this same problem on kernel v