HowTo:OpenfilerVersusDedicated

From Greg Porter's Wiki

Jump to: navigation, search

Contents

Openfiler performance - Openfiler iSCSI performance compared to "real" iSCSI arrays like Equallogic and NetApp in simple tests with virtualization

Discussion of test configuration

In all my examples on these wiki pages, I have used simple examples.

I have 2 XenServer hosts, in a simple resource pool, sonnected to iSCSI shared storage. One Windows 2003 virtual machine lives in the pool.

For these tests, I will continue to use this test set up. I will run the Windows vm on a SR hosted on my Openfiler host, and use iometer from within the vm to report I/O statistics.

I will then move that same Windows vm to a SR hosted on other "real" filers, and run the same tests with iometer.

This is not a particularly rigorous test suite (you can say that again), but it will hopefully show whether or not Openfiler is in the same league as a "real" array, or if Openfiler performance is particularly worse (or better) than a "real" array.

Iometer is very configurable. I have set my test instance on Iometer as follows:

  • Latest iometer (version 2006.07.27, the latest is stale, but still works)
  • 10 workers set to running against the vm's C: drive
  • Iometer "Access Specifications" set to "All in one" (percentage of read/write and block size)

Windows 2003 running iometer against a SR hosted on Openfiler iSCSI

Test host:

  • Openfiler v2.3, 64 bit, patched
  • Dell 6950, quad socket of dual-core AMD Opteron(tm) Processor 8212 at 2.0 GHz
  • 32 GHz of RAM
  • One Broadcom Corporation NetXtreme II BCM5708 Gigabit Ethernet NIC

That's a darn good server, probably better than it needs to be for Openfiler use. Oh well, that's one I had laying around.

  • One 200GB iSCSI LUN presented to XenServer, target configuration all default

Virtual Machine:

  • Windows 2003 32 bit, fully patched
  • 1 CPU
  • 512 MB RAM
  • No application but iometer running

Iometer configuration:

  • Latest iometer (version 2006.07.27, the latest is stale, but still works)
  • 10 workers set to running against the vm's C: drive
  • Iometer "Access Specifications" set to "All in one" (percentage of read/write and block size)
Iometer running on Windows against Openfiler, about 6000 I/O's a second

Interestingly, the load on the Openfiler server goes way up during iSCSI I/O operations. I guess that's what hardware initiators are for.

Openfiler status during Iometer run

Windows 2003 running iometer against a SR hosted on Equallogic iSCSI

Same test, same everything, but now against a Dell/Equallogic PS5000E, 2GB cache, 2 controllers, 8 1TB SATA drives in RAID-5, presenting one 200GB LUN to XenServer.

Note that this is an entry level iSCSI array, using SATA and not very many spindles.

Connecting an Equallogic LUN

Iometer on the vm (on the Equallogic hosted SR) runs a bit slower than on Openfiler. Something like 5000 I/O's per second.

A bit slower

Conclusion

My pretty spiffy Openfiler server compares favorably to my entry level Equallogic PS5000E in simple tests.

I can't use this as a basis for any conclusive statements like "Openfiler kicks butt" or "Dell sucks", but it is interesting to note that Openfiler running on (good) commodity hardware isn't significantly worse than a dedicated filer, and in some cases may actually be a bit better.

To sum it up: Openfiler can hold its own against the Dell/Equallogic PS5000E.

Personal tools