RHCS/GFS Design considerations

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

 



We have three RHCS 4/GFS clusters set up for various tiers of storage,
attached to a FC SAN. I will be adding additional workloads to these
clusters and updating to RHEL5, and would like advice and thoughts on
various designs. 

In the current configuration, there are 2 nodes per cluster with 4GB RAM
each. I will be taking this to a minimum of 3 nodes per cluster. Two
clusters (1st Tier and Backup) serve 1 SAMBA share each with
approximately 1x2TB chunk of SAN stroage. The other cluster hosts 13
SAMBA shares with a mix of standard FC (1x6TB,2X1TB) and FC-SATA
(10x2TB).

The nodes all run low on memory, and occasionally run out of memory and
cause problems where the entire cluster needs to be rebooted. As I add
additional storage, I am debating if I should go with 1 large cluster
per tier of storage, or seperate clusters for each application, per
tier. There is an obvious cost advantage to one large cluster, where I
could use a few failover nodes for the entire cluster, instead of each
individual cluster having its own failover nodes. On the downside, any
change could potentially bring down the entire cluster, and therefore
the tier for every application.

My ideal option would be to have a set of failover servers that
participate in every cluster. Does RHCS support a single server or set
of servers shared between different clusters? I think you are limited to
failover domains in a single cluster.

Does anyone have experience/advice with a similar setup? Also, any
suggestions on RAM would be nice, so I can prevent the servers from
running low on memory. The file sizes range from a few KB, to a few
hundred MB. The total number of files and directories in the largest
filesystem is 1,883,912 files, with approx. 50,000 directories off the
root filesystem.

Thanks
Danny Wall



#####################################
This message is for the named person's use only.  It may
contain confidential, proprietary, or legally privileged
information.  No confidentiality or privilege is waived or
lost by any mistransmission.  If you receive this message
in error, please immediately delete it and all copies of it
from your system, destroy any hard copies of it, and notify
the sender.  You must not, directly or indirectly, use,
disclose, distribute, print, or copy any part of this message
if you are not the intended recipient.  Health First reserves
the right to monitor all e-mail communications through its
networks.  Any views or opinions expressed in this message
are solely those of the individual sender, except (1) where
the message states such views or opinions are on behalf of
a particular entity;  and (2) the sender is authorized by
the entity to give such views or opinions.
#####################################


--
Linux-cluster mailing list
Linux-cluster@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/linux-cluster

[Index of Archives]     [Corosync Cluster Engine]     [GFS]     [Linux Virtualization]     [Centos Virtualization]     [Centos]     [Linux RAID]     [Fedora Users]     [Fedora SELinux]     [Big List of Linux Books]     [Yosemite Camping]

  Powered by Linux