[ovirt-users] ksmd high cpu usage from almost a week with just one vm running
Doron Fediuck
dfediuck at redhat.com
Sun Dec 7 16:58:50 UTC 2014
Hi,
First of all you need to remember this is accounting all available memory
cache included, so what you see as 22 may not be what mom is using.
Additionally some of the calculations take time for ksm, so it takes time
for everything to stabilize once you hit a peak.
----- Original Message -----
> From: "mad Engineer" gmail.com>
> To: "Doron Fediuck"
> Cc: "Markus Stockhausen" <stockhausen at collogia.de>, "users" ovirt.org>, "Martin Sivak" <msivak at redhat.com>,
> "Roy Golan" <rgolan at redhat.com>
> Sent: Sunday, December 7, 2014 6:52:16 PM
> Subject: Re: [ovirt-users] ksmd high cpu usage from almost a week with just one vm running
>
> Thanks Doron,
> Can you confirm this behaviour,i changed (defvar
> ksm_free_percent 0.10) and restarted vdsm and now ksmd is behaving
> normally.But i don't understand why its behaving aggressively when
> free RAM percentages is 22% even though its close to 20 :)
>
> Regards
>
> On Sun, Dec 7, 2014 at 6:13 PM, Doron Fediuck wrote:
> > Hi,
> > you can see all the relevant definitions in mom's ksm policy.
> > The trigger to run ksm is defined here:
> > https://github.com/oVirt/vdsm/blob/master/vdsm/mom.d/03-ksm.policy#L23
> >
> > You can change this setting (in each host you have) to something that
> > suits your load. We have the below bug opened and hopefully handle it
> > in one of the next versions.
> > https://bugzilla.redhat.com/show_bug.cgi?id=1026294
> >
> > Doron
> >
> > ----- Original Message -----
> >> From: "mad Engineer" gmail.com>
> >> To: "Markus Stockhausen" <stockhausen at collogia.de>
> >> Cc: "users" ovirt.org>
> >> Sent: Saturday, December 6, 2014 6:13:20 PM
> >> Subject: Re: [ovirt-users] ksmd high cpu usage from almost a week with
> >> just one vm running
> >>
> >> Thanks for the info Markus
> >>
> >> free -g
> >> total used free shared buffers cached
> >> Mem: 47 32 14 0 0 0
> >>
> >> % of usage is 68 .
> >>
> >> Why is ksmd not sleeping.Do you have any idea?
> >> regards,
> >>
> >>
> >> On Sat, Dec 6, 2014 at 8:45 PM, Markus Stockhausen
> >> <stockhausen at collogia.de> wrote:
> >> > Memory usage > 80%: ksm kicks in. There it will run at full speed until
> >> > usage is below 80%. There is an open BZ from me. Bad behaviour is
> >> > controlled
> >> > by mom.
> >> >
> >> > Markus
> >> >
> >> > Am 06.12.2014 15:58 schrieb mad Engineer gmail.com>:
> >> >
> >> > Hello All,
> >> > I am using centos6.5 x64 on a server with 48 G RAM and 8
> >> > Cores.Managed by Ovirt
> >> > There is only one running VM with RAM 34 G and with 6 VCPU (pinned to
> >> > proper numa nodes)
> >> >
> >> > from top
> >> >
> >> > top - 06:42:48 up 67 days, 20:05, 1 user, load average: 0.26, 0.20,
> >> > 0.17
> >> > Tasks: 285 total, 2 running, 282 sleeping, 0 stopped, 1 zombie
> >> > Cpu(s): 1.0%us, 1.4%sy, 0.0%ni, 97.5%id, 0.1%wa, 0.0%hi, 0.0%si,
> >> > 0.0%st
> >> > Mem: 49356468k total, 33977684k used, 15378784k free, 142812k buffers
> >> > Swap: 12337144k total, 0k used, 12337144k free, 343052k cached
> >> >
> >> > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> >> > 101 root 25 5 0 0 0 R 27.4 0.0 5650:04 [ksmd]
> >> > 26004 vdsm 0 -20 3371m 64m 9400 S 9.8 0.1 1653:27
> >> > /usr/bin/python /usr/share/vdsm/vdsm --pidfile /var/run/vdsm/vdsmd.pid
> >> > 20963 qemu 20 0 38.5g 33g 6792 S 3.9 71.6 5225:43
> >> > /usr/libexec/qemu-kvm -name Cinder -S -M rhel6.5.0 -cpu Nehalem
> >> > -enable-kvm -m 34096 -realtime mlock=off -smp
> >> > 6,maxcpus=160,sockets=80,c
> >> >
> >> > from /sys/kernel/mm/ksm
> >> > pages_unshared 7602322
> >> > pages_shared 207023
> >> > pages_to_scan 64
> >> > pages_volatile 31678
> >> >
> >> > Any idea why ksmd is not coming to normal CPU usage ,on a different
> >> > server ksmd was disabled and for testing when i enabled it initially
> >> > CPU usage was high but later settled down to 3% ,in that host i have 4
> >> > VMs running.
> >> >
> >> > Before turning off ksmd can any one help me find out why ksmd is
> >> > behaving like this.Initially it had 2 virtual machines,because of high
> >> > CPU utilization of this guest other is migrated to another host.
> >> >
> >> > Thanks
> >> > _______________________________________________
> >> > Users mailing list
> >> > Users at ovirt.org
> >> > http://lists.ovirt.org/mailman/listinfo/users
> >> _______________________________________________
> >> Users mailing list
> >> Users at ovirt.org
> >> http://lists.ovirt.org/mailman/listinfo/users
> >>
>
More information about the Users
mailing list