I recently migrated to Proxmox after some issues with a previous hypervisor, however with SyS/OVH's default installation settings, it appears the IO can get very high (from 15-20%+ when cloning a disk and, according to a client, they can feel the VM's performance degrade greatly when doing something as simple as downloading a file on the VM).
I was looking through this thread https://forum.proxmox.com/threads/very-slow-disk-io-on-ovh-dedicated-server.10804/ and I wasn't sure whether the VHDs I use need to have read/write cache enabled on them? Or whether it's the physical disks that need to have read/write cache enabled on them.
On the VHDs I use 'Default (No Cache)' however on the physical disks they are enabled. I am using SyS/OVH's default RAID 1 settings that come pre-installed with their Proxmox 3.4 installer.
Apologies for being a newbie, however any help would be incredibly appreciated! Many thanks
EDIT: It might also be important to add that before the migration (I'm using the exact same machine before the migration as I am now with Proxmox), when using my previous hypervisor, there were no IO issues or slowness issues. Also anything as simple as a single client unpacking a ZIP archive will cause the whole machine to slow down - so it must be a disk issue of sorts (definitely an IO delay seeing as the percentage goes high during this)
I was looking through this thread https://forum.proxmox.com/threads/very-slow-disk-io-on-ovh-dedicated-server.10804/ and I wasn't sure whether the VHDs I use need to have read/write cache enabled on them? Or whether it's the physical disks that need to have read/write cache enabled on them.
On the VHDs I use 'Default (No Cache)' however on the physical disks they are enabled. I am using SyS/OVH's default RAID 1 settings that come pre-installed with their Proxmox 3.4 installer.
Apologies for being a newbie, however any help would be incredibly appreciated! Many thanks
EDIT: It might also be important to add that before the migration (I'm using the exact same machine before the migration as I am now with Proxmox), when using my previous hypervisor, there were no IO issues or slowness issues. Also anything as simple as a single client unpacking a ZIP archive will cause the whole machine to slow down - so it must be a disk issue of sorts (definitely an IO delay seeing as the percentage goes high during this)
root@ns3281890:~# pveperf /vz/
CPU BOGOMIPS: 57600.96
REGEX/SECOND: 1568483
HD SIZE: 1809.63 GB (/dev/mapper/pve-data)
BUFFERED READS: 25.38 MB/sec
AVERAGE SEEK TIME: 28.34 ms
FSYNCS/SECOND: 85.89
DNS EXT: 68.86 ms
DNS INT: 1.56 ms (ovh.com)
root@ns3281890:~# hdparm -W /dev/sd[abcd]
/dev/sda:
write-caching = 1 (on)
/dev/sdb:
write-caching = 1 (on)
root@ns3281890:~# mount
sysfs on /sys type sysfs (rw,nosuid,nodev,noexec,relatime)
proc on /proc type proc (rw,nosuid,nodev,noexec,relatime)
udev on /dev type devtmpfs (rw,relatime,size=10240k,nr_inodes=4110943,mode=755)
devpts on /dev/pts type devpts (rw,nosuid,noexec,relatime,gid=5,mode=620,ptmxmode=000)
tmpfs on /run type tmpfs (rw,nosuid,noexec,relatime,size=3290944k,mode=755)
/dev/md2 on / type ext3 (rw,relatime,errors=remount-ro,user_xattr,acl,barrier=0,data=ordered)
tmpfs on /run/lock type tmpfs (rw,nosuid,nodev,noexec,relatime,size=5120k)
tmpfs on /run/shm type tmpfs (rw,nosuid,nodev,noexec,relatime,size=7000900k)
fusectl on /sys/fs/fuse/connections type fusectl (rw,relatime)
/dev/mapper/pve-data on /var/lib/vz type ext3 (rw,relatime,errors=continue,user_xattr,acl,barrier=0,data=ordered)
rpc_pipefs on /var/lib/nfs/rpc_pipefs type rpc_pipefs (rw,relatime)
binfmt_misc on /proc/sys/fs/binfmt_misc type binfmt_misc (rw,nosuid,nodev,noexec,relatime)
/dev/fuse on /etc/pve type fuse (rw,nosuid,nodev,relatime,user_id=0,group_id=0,default_permissions,allow_other)
beancounter on /proc/vz/beancounter type cgroup (rw,relatime,blkio,name=beancounter)
container on /proc/vz/container type cgroup (rw,relatime,freezer,devices,name=container)
fairsched on /proc/vz/fairsched type cgroup (rw,relatime,cpuacct,cpu,cpuset,name=fairsched)
Last edited: