Re: Libvirt, quemu, ceph write cache settings

[Maciej Gałkiewicz <macias@xxxxxxxxxxxxxxx>]

On 18 July 2013 00:04, Josh Durgin <josh.durgin@xxxxxxxxxxx> wrote:

You can verify that rbd_cache = true is set with the admin socket
command 'config get rbd_cache'. You'd need to set

   admin socket = /path/to/socket

in ceph.conf, then reattach the rbd device. librados will create the
admin socket as long as the user running qemu isn't prevented by unix
permissions, selinux, apparmor, etc.

Works like a charm.

 

ceph.conf has entry:
[client]
   rbd_cache = true

The ceph.conf entry isn't needed since qemu 1.2 when you've got
cache=setting in the qemu command line.

I have created VM with KVM 1.1.2 and all I had was rbd_cache configured in ceph.conf. Cache option in libvirt set to "none":

<disk type="network" device="disk">

      <driver name="qemu" type="raw" cache="none"/>

      <source name="cinder_volumes/volume-f81d6108-d8c9-4e06-94ef-02b1943a873d" protocol="rbd"/>

      <auth username="cinder_volumes">

        <secret type="ceph" uuid="9481a373-bef5-07e9-d156-d7d37bfed894"/>

      </auth>

      <target bus="virtio" dev="vda"/>

      <serial>f81d6108-d8c9-4e06-94ef-02b1943a873d</serial>

    </disk>

    <disk type="network" device="disk">

      <driver name="qemu" type="raw" cache="none"/>

      <source name="cinder_volumes/volume-9ab3e9b3-e153-447c-ab1d-2f8f9bae095c" protocol="rbd"/>

      <auth username="cinder_volumes">

        <secret type="ceph" uuid="9481a373-bef5-07e9-d156-d7d37bfed894"/>

      </auth>

      <target bus="virtio" dev="vdb"/>

      <serial>9ab3e9b3-e153-447c-ab1d-2f8f9bae095c</serial>

    </disk> 

Config settings received from admin socket show that cache is enabled. I thought that without configuring libvirt with cache options it is not possible to force kvm to use it. Can you explain it a little bit why it works or claims to work?

regards

--
Maciej Gałkiewicz
Shelly Cloud Sp. z o. o., Sysadmin
http://shellycloud.com/, macias@xxxxxxxxxxxxxxx
KRS: 0000440358 REGON: 101504426

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com