[Linux-cluster] DRBD with GFS applicable for this scenario?
zaeem.arshad at gmail.com
Fri Jan 29 05:33:48 UTC 2010
On Thu, Jan 28, 2010 at 3:44 PM, Gordan Bobic <gordan at bobich.net> wrote:
You have made interesting observations. Let me see if I can answer these.
> Hmm... What sort of ping time do you get? I presume you have established
> that it is on the sensible side.
It's 7 ms to be precise. I was assuming the distance to be around 35km
but it seems less.
> In terms of performance you will need to make sure that machines tend to
> access only their own sub-paths on the file system (e.g. spool/1 and
> spool/2, and server 1 doesn't touch spool/2 until server 2 goes down).
> Otherwise the performance is going to be attrocious since file locks will
> end up bouncing between the machines. These normally live in cache on a
> conventional file system so if they have to start getting exchanged at most
> accesses you are looking at a latency degradation from ~ 50ns down to some
> milliseconds. If your connectivity is VERY good, if it's 35km I would be
> surprised if your latencies are better than 10ms, which you'll feel even on
> the disk latency, let along memory latency - we are talking 200,000x slower
> in the best case scenario.
I think this is how DRBD works. It will usually read/write to the
local device first and in case of local device failure will it switch
over to the other block over IP. I'd be surprised if it doesn't do
> So you propose to have a quorum disk on site 2? OK, that works. The problem
> is that fencing works by one server fencing another, not itself. So you'll
> still need a reliable OOB fencing mechanism such as the one I described.
Yeah. I can probably use the following heuristics to make sure I fall
back to primary
Check if QD is accessible at SAN2 5
yahoo check 3
POPXYZ check 2
Volume X visible on SAN1 by Mail1 4
By using these heuristics and associated scores, I am able to decide
which server has quorum. I am also looking into the OOB fencing idea
too. One question that pops in my mind is that while I will have only
2 nodes in the DRBD volume, will more than 2 cluster members be able
to access the GFS volume on top of the DRBD volume?
More information about the Linux-cluster