White Papers
Table Of Contents
- Executive Summary (updated May 2011)
- 1. Introduction
- 2. Dell NFS Storage Solution Technical Overview
- 3. NFS Storage Solution with High Availability
- 4. Evaluation
- 5. Performance Benchmark Results (updated May 2011)
- 6. Comparison of the NSS Solution Offerings
- 7. Conclusion
- 8. References
- Appendix A: NSS-HA Recipe (updated May 2011)
- A.1. Pre-install preparation
- A.2. Server side hardware set-up
- A.3. Initial software configuration on each PowerEdge R710
- A.4. Performance tuning on the server
- A.5. Storage hardware set-up
- A.6. Storage Configuration
- A.7. NSS HA Cluster setup
- A.8. Quick test of HA set-up
- A.9. Useful commands and references
- A.10. Performance tuning on clients (updated May 2011)
- A.11. Example scripts and configuration files
- Appendix B: Medium to Large Configuration Upgrade
- Appendix C: Benchmarks and Test Tools
Dell HPC NFS Storage Solution - High Availability Configurations
Page 48
- Clients will be able to access the file system, so use rg_test with care and ONLY
for debugging. clustat and clusvcadm should manage the cluster and cluster
service during normal operation.
rg_test test /etc/cluster/cluster.conf status service HA_service
rg_test test /etc/cluster/cluster.conf stop service HA_service
clusvcadm –e HA_service
9) To turn or reboot the active or passive server, it must first leave the cluster gracefully. Else the
other server will assume that it has died and fence it. To leave the cluster gracefully, run the
following sequence of commands.
fence_tool leave
service rgmanager stop
cman_tool leave remove
service cman stop
10) A very good FAQ on Red Hat Cluster Suite is at http://sources.redhat.com/cluster/wiki/FAQ
A.10. Performance tuning on clients (updated May 2011)
1) If the clients access the NFS server via 10GbE, configure the MTU on the 10GbE device to be 8192
for all the clients. Note that the switches need to be configured to support large MTU as well.
On the client, if the value of MTU is not specified in /etc/sysconfig/network-
scripts/ifcfg-ethX,
echo “MTU=8192” >> /etc/sysconfig/network-scripts/ifcfg-ethX,
Otherwise change the old value to 8192 in /etc/sysconfig/network-scripts/ifcfg-ethX.
where ifcfg-ethX if the 10GbE network interface.
Restart the networking services. service network restart
2) If the clients access the NFS server via 10GbE, the Ethernet switches on the fabric should have flow
control disabled. The following instructions are for the PowerConnect 6248 and the PowerConnect
8024 and can be used as a reference.
Start a console session to the switch and type the following commands in sequence:
console>enable
console#configure
console(config)#no flowcontrol
In order to verify the setting of the option, type the following command:
console#show interface status
A message of “Flow Control:Disabled” will be printed out.
3) For each client, Add the following to /etc/sysctl.conf
# increasing the default TCP receive memory size
net.ipv4.tcp_rmem = 4096 2621440 16777216