On 04.05.2012 [22:28:01 +0200], Peter Zijlstra wrote: > On Fri, 2012-05-04 at 22:14 +0200, Peter Zijlstra wrote: > > > Also, we need to fix this problem at the CPU Hotplug level itself, and > > > not just for the suspend/resume case. Because, we have had numerous bug > > > reports and people complaining about this issue, in various scenarios, > > > including those that didn't involve suspend/resume. > > > > NO, absolutely not and I will NAK any and all such nonsense. WTF is a > > cpuset worth if you can run on random other cpus? > > Sorting your cpuset 'problem' isn't nowhere near enough to make hotplug > 'safe'. unplug also destroys task_struct::cpus_allowed. > > Try it: > > # schedtool -a 2 $$ > # grep Cpus_allowed /proc/self/status > Cpus_allowed: 000004 > # echo 0 > /sys/devices/system/cpu/cpu2/online > # grep Cpus_allowed /proc/self/status > Cpus_allowed: ffffff > > > See, hotplug is destructive, it has to be, there's no saying the cpu > will every come back. I think it's ok for hotplug to be destructive. But I guess I'm not entirely sure why cpusets can't retain user-inputted configuration/policy information even while destroying things currently? And re-instating that policy if possible in the future? > So mucking about trying to make cpusets non-destructive is pointless. > > The real bug is people using hotplug (for all kinds of stupid stuff) and > expecting anything different. Probably true :) -Nish -- Nishanth Aravamudan <nacc@xxxxxxxxxx> IBM Linux Technology Center -- To unsubscribe from this list: send the line "unsubscribe linux-doc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
