Gluster v 3.3 with KVM and High Availability

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 12 Jul 2012, Brian Candler wrote:
> Oh OK, sorry. What's the underlying technology that the gluster brick is on? 
> Is it a plain old HD or HD RAID array - and does it have battery-backed
> cache? Or is it something fancy like SSDs?

	Our Gluster test bricks are currently two identical Dell
PE 2950's with PERC 6/i (LSI MegaRAID SAS 1078) controllers with
battery backed cache and 4x 146GB 15k SAS drives in a hardware
RAID-5 (I know, not ideal; but these machines are only being used
temporarily as test machines).  The Gluster volume is a simple
mirror between the two machines.

	Our production machines, which are most likely going to
be wiped of their DRBD/HA cluster/iSCSI stack and used with
Gluster moving forward, are Dell PE R610's with the PERC H700
(newer LSI MegaRAID SAS 2108) with battery backed cache and 6x
600GB 10k SAS drives in a hardware RAID-10 (yay!).

	I'll be curious to see how much faster (if any) things
are on the production grade machines.  Our 1Gbps Ethernet
connections are already approaching the limit anyway, so we'll
probably need to move to 10Gbps Ethernet or 40Gbps Infiniband to
realize a noticeable speed increase.

-- 
Mark Nipper
nipsy at bitgnome.net (XMPP)
+1 979 575 3193
-
"On two occasions I have been asked, ? 'Pray, Mr. Babbage, if you
put into the machine wrong figures, will the right answers come
out?'  In one case a member of the Upper, and in the other a
member of the Lower House put this question.  I am not able
rightly to apprehend the kind of confusion of ideas that could
provoke such a question."
 -- Charles Babbage


[Index of Archives]     [Gluster Development]     [Linux Filesytems Development]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux