Getting CPU is fine. Iam going to submit a patch that will not list an "online" file for cpu0 (if that is not removable), so basically selecting the ones that have "online" file would probably make sense. I don't think the intr part is ok, since /proc/interrupts list even percpu interrupts, there is nothing to migrate there, the numbers I picked are the ones that have scsi controller, eth and serial line irq's, the ones I picked to generate interrupt activity. Cheers, ashok raj - Open Source Technology Center >-----Original Message----- >From: Mark Wong [mailto:markw@xxxxxxxx] >Sent: Wednesday, December 08, 2004 3:01 PM >To: Raj, Ashok >Cc: Joel Schopp; Tom Hanrahan; Luck, Tony; Keshavamurthy, Anil S; hotplug_sig@xxxxxxxxxxxxxx; Shah, >Rajesh >Subject: Re: [Hotplug_sig] Hotplug Testing > >On Wed, Dec 08, 2004 at 10:43:26AM -0800, Ashok Raj wrote: >> On Wed, Dec 08, 2004 at 11:52:53AM -0600, Joel Schopp wrote: >> >> This is the test i use for regression testing on IPF. I havent read >> all the test senarious, but its important to test if irq will migrate to this new >> cpu, and also when the cpu will go away, we can handle without loss of work >> transparently. >> >> Attached is a simple shell script. The only one that is hard coded is the irq numbers >> which can be obtained from /proc/interrupts as well. >> >> SInce IPF we dont support boot cpu removal, (due to restriction with CPEI, btw >> this will go away when platforms support ACPI 3.0) the script doesnt really try >> removing cpu0. >> >> The script is a little flaky, i.e we dont check if current state is offline/online >> etc, it might be better to build those in if we need some robustness. >> >> In addition, i leave some time after an online, before i offline (in parallel >> there are ltptest and some make -j running for load) so we let some work be handled >> on this cpu as well before offlining. >> >> >> hope this helps. >> >> Cheers, >> ashok >> > >Hi Ashok, > >Is doing something horrendous like this ok? > >Mark > >--- do_cpu.orig 2004-12-08 13:43:37.000000000 -0800 >+++ do_cpu 2004-12-08 14:58:14.000000000 -0800 >@@ -5,6 +5,8 @@ > TM_ONLINE=10 # Time delay after an online of cpu > TM_OFFLINE=10 # Time delay after offline of cpu > TM_DLY=30 # Time delay before start of entire new cycle. >+CPUS=`grep processor /proc/cpuinfo | grep -v " 0$" | awk '{print $3}' | xargs` >+IRQS=`grep -e [[:digit:]+]: /proc/interrupts | awk '{print $1}' | sed -e 's/://' | xargs` > > do_clean() > { >@@ -25,7 +27,7 @@ > migrate_irq() > { > MASK=$((1<<$1)) >- for irq in 45 48 49 >+ for irq in $IRQS > do > echo $MASK > /proc/irq/$irq/smp_affinity > done >@@ -53,13 +55,13 @@ > do > CNT=$(($CNT+1)) > echo "Loop Count $CNT" >- for cpu in 1 2 3 >+ for cpu in $CPUS > do > do_offline $cpu > sleep $TM_OFFLINE > done > >- for cpu in 1 2 3 >+ for cpu in $CPUS > do > do_online $cpu > sleep $TM_ONLINE
