Hello everyone,
i've a running KVM instance, ran by Openstack. The command used is (checked from ps auxwww):
/usr/bin/kvm -S -M pc-1.0 -enable-kvm -m 4096 -smp 4,sockets=4,cores=1,threads=1 -name instance-0000001b -uuid 598878a6-a5dc-4e15-ab17-3ab8b954f00a -nodefconfig -nodefaults -chardev socket,id=charmonitor,path=/var/lib/libvirt/qemu/instance-0000001b.monitor,server,nowait -mon chardev=charmonitor,id=monitor,mode=control -rtc base=utc -no-shutdown -drive file=/var/lib/nova/instances/instance-0000001b/disk,if=none,id=drive-virtio-disk0,format=qcow2,cache=none -device virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0,bootindex=1 -netdev tap,fd=21,id=hostnet0 -device virtio-net-pci,netdev=hostnet0,id=net0,mac=fa:16:3e:75:90:da,bus=pci.0,addr=0x3 -chardev file,id=charserial0,path=/var/lib/nova/instances/instance-0000001b/console.log -device isa-serial,chardev=charserial0,id=serial0 -chardev pty,id=charserial1 -device isa-serial,chardev=charserial1,id=serial1 -usb -device usb-tablet,id=input0 -vnc 0.0.0.0:2 -k en-us -vga cirrus -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x5
I've seen that just running an apt-get install it takes some time to read package list and then unpack packages etc.. Now I've tried to scp from an OpenVZ vm from our old servers to this VM, both has 4GB of ram and 4 cores, host machines has both an i7 cpu and 16gb ram.
The file i was trying to transfer is a 86GB tarball, during transfer the source vm has a load of 0.7, the destination vm was around 4-5 and it was incredibly slow. I've tried to run an iostat -xN and i got this:
Linux 3.2.0-29-virtual (closr) 08/10/2012 _x86_64_ (4 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
7.29 0.03 2.65 29.57 0.04 60.43
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await r_await w_await svctm %util
vda 0.28 0.86 3.38 41.49 92.50 20128.00 901.15 97.54 2173.44 379.09 2319.82 16.75 75.15
2300 as w_await seems a bit high to me. It was also taking about 20 seconds to open a new screen and spawn a shell but cpu load wasn't high, about 50% of one core.
Instance disk file is on a RAID1 md array and iostat -xN on host is this:
Linux 3.2.0-27-generic (server2.visup.it) 08/10/2012 _x86_64_ (8 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
1.22 0.00 0.53 1.18 0.00 97.07
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await r_await w_await svctm %util
sdb 0.66 14.74 1.23 26.54 91.37 1844.22 139.42 0.62 22.44 14.23 22.82 9.30 25.84
sda 0.65 14.74 1.25 26.53 87.71 1844.22 139.07 0.63 22.56 14.86 22.92 9.37 26.03
md3 0.00 0.00 3.85 21.28 178.98 1728.10 151.80 0.00 0.00 0.00 0.00 0.00 0.00
md1 0.00 0.00 0.00 0.00 0.01 0.00 7.97 0.00 0.00 0.00 0.00 0.00 0.00
md127 0.00 0.00 0.00 0.00 0.01 0.00 7.70 0.00 0.00 0.00 0.00 0.00 0.00
md2 0.00 0.00 0.00 0.00 0.01 0.00 8.00 0.00 0.00 0.00 0.00 0.00 0.00
md126 0.00 0.00 0.00 18.19 0.01 114.25 12.56 0.00 0.00 0.00 0.00 0.00 0.00
md0 0.00 0.00 0.01 0.02 0.03 0.08 8.00 0.00 0.00 0.00 0.00 0.00 0.00
main-root 0.00 0.00 3.85 21.10 178.98 1728.10 152.88 2.65 106.18 15.10 122.79 5.09 12.71
the / fs is mounted on main-root lvm partition.
Any idea?
Thanks in advance
Best Regards--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
