On Thu, Jul 11, 2002 at 12:33:30AM -0700, Darren Pilgrim wrote: > Richard Sharpe wrote: > > > > On Thu, 11 Jul 2002, Darren Pilgrim wrote: > > > > > Richard Sharpe wrote: > > > > On Wed, 10 Jul 2002, Darren Pilgrim wrote:
... > > > > > > Even with just one connection per machine, though, you're still going > > > to have a significant amount of swappable memory in idle smbd > > > processes. > > > > Yes, I agree. Something that I would like to do more about by making sure > > that as much as possible is shared. > > At over 4MB per process (4252K each on my server), I should hope that > most of it is already shared. With my testing last night, 350 clients each writing used ~700M of cache (with was the data being writen) and only ~100M of active memory. There was only a nominal amount swapped (probably getty and friends), so the number of shared pages is actually quite high with ~2.1M of resident mem showing for each process. If it were otherwise I would have quickly burned the 1G in the test server. The only thing I managed to exhaust was mbuf clusters, and that was on the clients first and finally on the server after a bit. Thanks to everybody for their input and suggestions, and I'll let you know how it works in the "wild" :). -- Chad David [EMAIL PROTECTED] www.FreeBSD.org [EMAIL PROTECTED] ACNS Inc. Calgary, Alberta Canada To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
