Date: Sun, 1 Jan 2006 17:58:13 -0800 From: Gary Kline <kline@tao.thought.org> To: Tofik Suleymanov <secnews@oxygen.az> Cc: Gary Kline <kline@tao.thought.org>, FreeBSD Mailing List <freebsd-questions@FreeBSD.ORG> Subject: Re: STressing a new server... Message-ID: <20060102015813.GC88240@thought.org> In-Reply-To: <43B86FB3.2010203@oxygen.az> References: <20060101212007.GA87257@thought.org> <43B86FB3.2010203@oxygen.az>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Jan 02, 2006 at 12:11:31AM +0000, Tofik Suleymanov wrote: > Gary Kline wrote: > > > Folks, > > > > When I bought this bare-bones box and plugged in "stuff" > > it took several days of figuring out what benchmark and > > other utilities to run to stress it. After a few weeks of > > pushing the load to 70+, the burning-in was a fair indicator > > that the HW would last. After 4+ years, no prob. Now I > > have a new box, custom built. > > > > Unfortunately, I've lost (or forgotten!) the same of the > > *.sh script and some of the utilities. So what should I > > be running and with an example of args? Last time I believe > > there were 5 or 6 stressors. > > > > Also, what's the memory testor utility calld? I have > > a gig of DDR in this new puppy, and want to be sure that > > every last BIT is good. > > > > Help much appreciated! > > > > gary > > > > > > > > > > > Try to do a make buildworld. Sure; no problem, but I want more. BTW, most of you already know this, but it bears re-stating: even memory and drives that have been well pounded can go bad after N months. That's only happened to me onnce (with memory); a few times with drives. But failures are more likely in the first several days to a week or so. No sense in eating a loss if testing will increase my odds... . gary -- Gary Kline kline@thought.org www.thought.org Public service Unix
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060102015813.GC88240>