In reviewing the CIFs performance white paper on the NAC website (http://www.netapp.com/technology/level3/3015.html), I'm unclear on what type of NetBench test is being run. Specifically, I'm not sure if the paper describes NetBench Disk Mix or Random Read/Write tests.

NetBench Disk Mix.

I'd thought that the graphs pertained to the Disk Mix test but block size variation test (section 3.1 in above paper) made me think that perhaps Random Read/Write test was being described (Disk Mix does not allow the I/O block size to be varied?

The block size variation did not pertain to the I/O block sizes generated by NetBench, but instead referred to the NTFS block size used when initializing the file system on the Compaq. The results shown in the paper indicate that there is a performance advantage to specifying a file system block size of 4-KB for NTFS, instead of the default 8-KB, but that the difference was very small.

... Second, I'm wondering if there is any info or experiences regarding how many http op/s can a Netapp Web filer support?

We're actually in the final stages of preparing SPECweb benchmark results for submission to SPEC. "Stay tuned!"

-- Andy

Andy Watson Director, Technical Marketing watson@netapp.com Network Appliance +1 408 367 3220 voice 2770 San Tomas Expressway +1 408 367 3151 fax Santa Clara, CA 95051 http://www.netapp.com/

"It's really stupid to be an intellectual when you're young. You should be an intellectual when you're a hundred years old and can't feel anything anymore." -- a character in Bruce Sterling's novel, HOLY FIRE