Re: STressing a new server...

2006-01-03 Thread Gary Kline
On Mon, Jan 02, 2006 at 10:06:52AM -0800, James Long wrote: A buildworld is indeed an excellent test of memory, CPU, drives and cabling. The memory tester is sysutils/memtest. It's not a very scientific test, but one thing I do is a make -j8 buildworld whilst I do a large tar operation,

Re: STressing a new server...

2006-01-02 Thread James Long
A buildworld is indeed an excellent test of memory, CPU, drives and cabling. The memory tester is sysutils/memtest. It's not a very scientific test, but one thing I do is a make -j8 buildworld whilst I do a large tar operation, optionally with compression. Just anecdotally it appears that tar

STressing a new server...

2006-01-01 Thread Gary Kline
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

Re: STressing a new server...

2006-01-01 Thread Tofik Suleymanov
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

Re: STressing a new server...

2006-01-01 Thread Gary Kline
On Mon, Jan 02, 2006 at 12:11:31AM +, 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

Re: STressing a new server...

2006-01-01 Thread Michael Vince
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

Re: STressing a new server...

2006-01-01 Thread Martin Cracauer
For hardware testing, the best is ports/math/mprime In combination with memtest86, because mprime doesn't sweep all RAM. If you have several processors, be sure to run several instances of mprime (requires copying the whole mprime directory). Martin --

Re: STressing a new server...

2006-01-01 Thread Gary Kline
On Sun, Jan 01, 2006 at 11:20:40PM -0500, Martin Cracauer wrote: For hardware testing, the best is ports/math/mprime In combination with memtest86, because mprime doesn't sweep all RAM. If you have several processors, be sure to run several instances of mprime (requires copying the whole

Re: STressing a new server...

2006-01-01 Thread Martin Cracauer
Gary Kline wrote on Sun, Jan 01, 2006 at 08:31:43PM -0800: On Sun, Jan 01, 2006 at 11:20:40PM -0500, Martin Cracauer wrote: For hardware testing, the best is ports/math/mprime In combination with memtest86, because mprime doesn't sweep all RAM. If you have several processors, be

RE: STressing a new server...

2006-01-01 Thread Ted Mittelstaedt
on the parameters you put into it. Ted -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Gary Kline Sent: Sunday, January 01, 2006 1:20 PM To: FreeBSD Mailing List Subject: STressing a new server... Folks, When I bought this bare-bones box and plugged