From owner-freebsd-hackers Thu Nov 20 22:11:33 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id WAA16658 for hackers-outgoing; Thu, 20 Nov 1997 22:11:33 -0800 (PST) (envelope-from owner-freebsd-hackers) Received: from crh.cl.msu.edu (crh.cl.msu.edu [35.8.1.24]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id WAA16650 for ; Thu, 20 Nov 1997 22:11:31 -0800 (PST) (envelope-from henrich@crh.cl.msu.edu) Received: (from henrich@localhost) by crh.cl.msu.edu (8.8.7/8.8.7) id BAA01289; Fri, 21 Nov 1997 01:11:30 -0500 (EST) (envelope-from henrich) Date: Fri, 21 Nov 1997 01:11:30 -0500 (EST) From: Charles Henrich Message-Id: <199711210611.BAA01289@crh.cl.msu.edu> To: jkh@time.cdrom.com, freebsd-hackers@freebsd.org Subject: Re: Serious performance issue with 2.2.5-RELEASE Newsgroups: lists.freebsd.hackers References: <65378m$5qr$1@msunews.cl.msu.edu> X-Newsreader: NN version 6.5.0 CURRENT #1 Sender: owner-freebsd-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In lists.freebsd.hackers you write: >The clear mistake was in hot-upgrading a production machine rather >than installing/upgrading a 2nd box (or, at the very minimum, a second >disk with / and /usr on it) and doing the cut-over as a staged >exercise. Then if you'd seen the 2.2.5 problem here, you'd have >simply switched back to the previous setup and given yourself the >breathing room to puzzle over the new problem scenario at your >leisure. Doing it the way you just did it is, frankly, about as >completely and utterly wrong as it's possible to do things in an ISP >environment and various protruding parts of you now need to be >slapped, if you have someone around to provide this helpful service >for you, so that you don't do something this criminally stupid in a >production environment again. :-) Now Now, not all of us have spare hardware to throw around, besides I've done this on my production news server twice now :) It started life as a 2.2 alpha snap, then a few months back I installed 2.2.2-RELEASE on top of it, and just a few weeks ago 2.2.5 on top of that. So far, everythings been running peachy keen. Granted if I jump major OS revs (3.0) a complete from scratch start is in the plans. Although granted, I dont mind putting myself in situations where I have to completely rebuild a system from scratch in an hour or so, a little pressure never hurt anyone :) >As for your "weird pauses", that's the first I've heard of any such >symptoms and would strongly recommend that you start trying to collect >data during those pauses as to whether it's the interface, DNS, >routes, what exactly "hangs" at the lowest level of this. Same here.. I've been running 2.2.5 (installed ontop of a live filesystem that started life as above) on my very heavily beat news server with zilcho problems. Its been rocking as a matter of fact. I swapped out the de0 card in it just the other day to try out a fxp0 to see if it made any difference (it didnt) but the machine is still humming along great transferring a little over a million articles a day across a 12 disk CCD array across 4 adaptec 2940 scsi controllers. This machine (ALR Revolution MP-Pro) / OS combination is the best I've ever had the pleasure of working on. Everytime I have to go do something under solaris I whine for weeks about it :) [Course right about now flames should erupt from the disks, and the CPU should blast through the front of the case :)] So my rant ends in, again FreeBSD (And by the transitive property, its developers) is the most reliable, high performance, easiest to play with, and funnest (yea its a word, cause I said so :) to play with! Thanks mucho! -Crh -- Charles Henrich Michigan State University henrich@msu.edu http://pilot.msu.edu/~henrich