On Thu, Mar 18, 2010 at 7:00 AM, <[email protected]> wrote: > >> I have been doing some basic measurements of IMAP NFS usage with >> courier-imap, and I thought I'd post the results in case they're of >> interest. > > This is all great, but as someone who's been running Courier-imap+NetApp > NFS, I can tell you that the problem is not going to be "large numbers of > IMAP clients", but how many of them have huge inboxes (2k messages plus). > That's what generates NFS ops, that's what kills the performance. Way before > any other factors you mentioned below.
I have exactly the same system as you've described. Once an INBOX gets a few thousand messages in it, dumb client (e.g. non-caching webmail) performance suffers. We host websites and email on our NetApps and were surprised to find out that 61% of traffic to our NetApps was POP/IMAP. Another 20% was smtp. The remaining 19% was webservers, cvs/svn/git repo access, and logs/database backups. Originally I would have guessed 50% of the traffic was email related, but it turned out to be 81%. YMMV. -- Regards... Todd I seek the truth...it is only persistence in self-delusion and ignorance that does harm. -- Marcus Aurealius ------------------------------------------------------------------------------ Download Intel® Parallel Studio Eval Try the new software tools for yourself. Speed compiling, find bugs proactively, and fine-tune applications for parallel performance. See why Intel Parallel Studio got high marks during beta. http://p.sf.net/sfu/intel-sw-dev _______________________________________________ Courier-imap mailing list [email protected] Unsubscribe: https://lists.sourceforge.net/lists/listinfo/courier-imap
