home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!cs.utexas.edu!zaphod.mps.ohio-state.edu!pacific.mps.ohio-state.edu!linac!att!bu.edu!cvbnet!wookie!miarrobi
- From: miarrobi@cvbnet.prime.com (Mike Iarrobino)
- Newsgroups: comp.sys.sun.hardware
- Subject: Re: NFS Performance?
- Keywords: NFS performance
- Message-ID: <4273@cvbnetPrime.COM>
- Date: 11 Nov 92 14:33:44 GMT
- References: <1992Nov9.190220.12769@shearson.com>
- Sender: postnews@cvbnetPrime.COM
- Reply-To: miarrobi@cvbnet.prime.com
- Lines: 14
-
- > fgreco@shearson.com (Frank Greco) writes:
- > Given the same parameters (RAM, kernel config, etc), can I expect a
- > Legato board to give me *significantly* higher performance than what
- > naked NFS gives me?
-
- The Prestoserve board should improve NFS write performance (when installed
- on the NFS server) on sequential writes. It works by buffering up write requests
- and providing immediate responses to the client. It uses battery backup to
- prevent the loss of data in the event of a server failure (system crash, power
- loss, etc). It does little or nothing to improve read performance.
-
- In real life situations the actual performance benefits you see will depend on
- your mix of read vs. write requests. When you have a large amount of writes
- you should see a noticable improvement in performance.
-