Thanks to all the people who responded. I believe this is the complete
list, but please accept my apologies in advance if your not listed.
//Contributors//
From: Basile STARYNKEVITCH <basile@soleil.serma.cea.fr>
From: dnewcomb@whale.st.usm.edu (Donald R. Newcomb)
From: Bob.Smith@lambada.oit.unc.edu
From: Jan Hoenisch <jan@rst.inri.com>
From: jon@flood.COM (Jon Strabala)
From: gt1111a@prism.gatech.EDU (Vincent Fox)
From: Shane.Sigler@Corp.Sun.COM (Shane Sigler)
From: hitz@spike.netapp.com (Dave Hitz)
From: szymon@uci.agh.edu.pl (Szymon Sokol)
From: brada@sesinc.com (Brad Albom)
//Main Points//
1. There is a consensus that the Presto card does actually help. Of course
the amount of help is site dependent. A typical figure was 3x increase
on NFS writes (with no help for read).
2. There is a persistant rumor of a Sun white paper for the Presto card.
I have called our favorite VAR, but no results yet. (opinion: Sun really
needs to set these up for FTP access).
3. There is a competing product from Auspex, which is supposed to be
quite good.
4. There is a competing/related product from Network Appliance Corporation
which sounds quite interesting. (Contact Dave Hitz for 1st hand report).
//Wrapup//
In our case, the presto card was supposed to help w/database performance.
We use Sybase on raw partitions, and I'm not convinced presto helps this
scenario. I'm trying to schedule some downtime to test this theory.
Thanks again to all of you who wrote.
-- =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= Guy Cole (KQ6J) * "Expert Plain And Fancy Bit Twiddling" * guycole@netcom.com Check Six! (619) 789-8106 * P.O. Box 2269, Ramona, CA. 92065 * CIS:71046,1405
This archive was generated by hypermail 2.1.2 : Fri Sep 28 2001 - 23:08:10 CDT