SCIENTIFIC-LINUX-DEVEL Archives

November 2005

SCIENTIFIC-LINUX-DEVEL@LISTSERV.FNAL.GOV

Options: Use Monospaced Font
Show Text Part by Default
Condense Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Sender:
Maillling list for Scientific Linux developers worldwide <[log in to unmask]>
Date:
Tue, 8 Nov 2005 07:55:10 -0500
MIME-version:
1.0
Reply-To:
Daniel Widyono <[log in to unmask]>
Content-type:
text/plain; charset=us-ascii
Subject:
From:
Daniel Widyono <[log in to unmask]>
Content-disposition:
inline
In-Reply-To:
Organization:
UPenn SEAS CIS Liniac
Comments:
To: Steven Timm <[log in to unmask]> cc: [log in to unmask]
Parts/Attachments:
text/plain (22 lines)
> We are hyper-threaded with 8 effective processor, does that make a 
> difference?  (We found the same thing in Google).

My little experience with HT shows poor performance I/O-wise (worse than
linear scaling, of course, since there was contention -- but this is on
one-year old hardware now), so I would _suspect_ that HT would not help
w.r.t. nfsd count.

> We are having some packet receive errors but nobody can tell us why.
> If there are other ideas on how to tell whether the network card
> is saturated, let me know.

Hopefully others who are more knowledgeable can chime in with better
information in this area...

> No, no jumbo frames.. NFS howto says with TCP this size is OK.

Yeah, sorry, brain fart there. :) Future Googlers: [fake spooky voice] ignore
the suggestion to check MTU size [/voice]

Dan W.

ATOM RSS1 RSS2