Mailinglist Archive: opensuse-ha (30 mails)

< Previous Next >
Re: [opensuse-ha] ext4 failure on cluster
On 8/15/14, 8:03 AM, Lars Marowsky-Bree wrote:
On 2014-08-15T07:57:31, Ron Kerry <rkerry@xxxxxxx> wrote:

True enough, but the performance of an active-active HA configuration with
two or more nodes serving NFS or CIFS can be well in excess of what a single
server is capable of doing. This all depends on the underlying disk
hardware. Many time that hardware may be capable of far more bandwidth than
a single server can drive by itself. In this active-active clustered
environment the performance achievable by any single node will be less than
what it can do on its own, but the combined performance of many nodes to the
same shared-clustered disk will be able to reach the bandwidth capability of
the underlying disk hardware.

... but in this case, the shared storage is provided by drbd, so the
*write* performance of the combined setup is limited to the slowest of
the two disks, and the network interconnect, and also reduced by the
locking needed by OCFS2.

Read-performance could theoretically benefit, yes.

There's however also the higher complexity of an active/active
environment, and the tighter coupling of the nodes which reduces their
ability to cope with faults.

Personally, I'd probably avoid this setup, unless there was a really
substantial reason for it.


I missed that the underlying storage was DRBD. I agree totally, there is little benefit to this sort of configuration - performance or availability except for certain particular sorts of workloads and failure scenarios.

--

Ron Kerry rkerry@xxxxxxx
Global Product Support - SGI Federal

--
To unsubscribe, e-mail: opensuse-ha+unsubscribe@xxxxxxxxxxxx
To contact the owner, e-mail: opensuse-ha+owner@xxxxxxxxxxxx

< Previous Next >
List Navigation
Follow Ups