Date: Thu, 23 Jan 2003 08:59:53 -0500 (EST) From: Jim Weeks <jim@jwweeks.com> To: freebsd-isp@freebsd.org Subject: Re: tuning suggestions? Message-ID: <20030123084823.U283-100000@veager.jwweeks.com> In-Reply-To: <Pine.WNT.4.51.0301211053340.-575651@hofbbs.hoflink.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Hey again, Many thanks to everyone that replied to this post. Since there doesn't seem to be a lot of information out there about this setting, I wanted to add this info back to the list. I had several people suggest bumping this to 400 "options PMAP_SHPGPERPROC=400". I did just that and it seems to have cured the problem. The only problem I have with the fix is that I don't quite understand how any of us arrived at the 400 number. LINT seems to suggest that bumping this too high when the machine has large amounts of physical memory will cause a boot panic. I wish someone that really understands this would weigh in. Thanks again ;-) -- Jim Weeks I scribbled: >Shortly after making world, striping the kernel, upgrading apache, >and installing WebGUI on a couple of websites (WebGUI requires >mod_perl to preload Apache::Registry), I began to get these two >errors. > >pmap_collect: collecting pv entries -- suggest increasing >PMAP_SHPGPERPROC microuptime() went backwards (613878.982533 -> >613874.389277) > >This machine sees fairly heavy MySql use and moderate httpd load. >It has been faithfully doing its job for a couple of years now from >3.0 - 4.7-stable and has never given a problem. I have read man >tuning, LINT, and searched the archives on these two errors and >really haven't come up with a lot of information. The following >lines from lint are sketchy at best. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-isp" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030123084823.U283-100000>