• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

You know that 8 processor Sparc .........

C

ColinP

Golden Member
Well,

turns out it had a friend !!!!!!!!!!!!!!

Another 8 Sparc processors to SETI.....
These are a bit slower though, so probably only 6or7WU/day in the week and 10WU/day at the weekend...

🙂

Col
 
Col: All the WU's count so it's all good. I'm sure that pair will not hurt yours or the teams stats at the end of the week.

Congrats!

Rob
 
Just a quick question. How do you run SETI? Do you run 8 different instances out of 8 different directories, or does it just run one instance faster than it would if it were a uniprocessor machine? Or something else? Thx.
 
I run 8 instances in 8 directories... There is no performance loss as you would see on a current Intel type system (BP6 , VP6 etc)..

Here's the crontab file which starts/stops them...

# crontab -l adm
#ident "@(#)adm 1.5 92/07/14 SMI" /* SVr4.0 1.2 */
#
# The adm crontab file should contain startup of performance collection if
# the profiling and performance feature has been installed.
#
51 16 * * * cd /usr/local/ites1;./ites -proxy 87.0.30.40:5512 &
52 16 * * * cd /usr/local/ites2;./ites -proxy 87.0.30.40:5512 &
53 16 * * * cd /usr/local/ites3;./ites -proxy 87.0.30.40:5512 &
54 16 * * * cd /usr/local/ites4;./ites -proxy 87.0.30.40:5512 &
55 16 * * * cd /usr/local/ites5;./ites -proxy 87.0.30.40:5512 &
56 16 * * * cd /usr/local/ites6;./ites -proxy 87.0.30.40:5512 &
57 16 * * * cd /usr/local/ites7;./ites -proxy 87.0.30.40:5512 &
58 16 * * * cd /usr/local/ites8;./ites -proxy 87.0.30.40:5512 &
01 08 * * 1-5 kill `cat /usr/local/ites1/pid.sah`
02 08 * * 1-5 kill `cat /usr/local/ites2/pid.sah`
03 08 * * 1-5 kill `cat /usr/local/ites3/pid.sah`
04 08 * * 1-5 kill `cat /usr/local/ites4/pid.sah`
05 08 * * 1-5 kill `cat /usr/local/ites5/pid.sah`
06 08 * * 1-5 kill `cat /usr/local/ites6/pid.sah`
07 08 * * 1-5 kill `cat /usr/local/ites7/pid.sah`
08 08 * * 1-5 kill `cat /usr/local/ites8/pid.sah`


So, they all start just before 5pm every day and are stopped Monday-Friday just after 8.00am.
They run all weekend..

🙂

later

Col
 
ColinP
I thought you were going to give us some bad news when I saw the title ,but instead I got a pleasent surprise .....sorted geazer!😉.
BTW
6or7WU/day in the week and 10WU/day at the weekend...

Lol ,that's nearly my total output😛 ,don't listem to BT btw ,give them to me 😉 hehe

BT
LMAO 🙂 ,nah should go to me ,I need them more😛😉
 
Hmmm....6or7WU/day.....you arn't trying hard enough Colin P. With that many processors, even a small overclock would boost WU rates, right?
 
Sukhoi: I bet Poof would try if she could get her hands on it! 🙂

BT: LOL, I was thinking of making the same suggestion! No reason for Colinp to have his name associated with such low production! 😀
 
FreeFrag
Do you run SETI? if so I guess you are already a member of Overclockers Au? why not join us instead?😉
(btw that was a team that I inavertantly triggered by posting a recruiting message at the Overclockers Au forum!😱.The team sprung up days after I posted that thread!lol)
 
FreeFrag - there are a lot of reasons. One, with mission critical servers, or database crunchers, you don't want downtime. While for you 'n me, crashing once a week, or once every couple weeks we can deal with (heck, a lot deal with daily, or multiple times daily); overclocking dramatically increases the chances of instability, especially in servers.

With one CPU, it's easy to find the max limit of the processor. Just go up, 'n up, 'n up, keeping the PCI/AGP busses as close to spec as possible, OC the FSB and the multiplier. Two CPU's gets tougher. Not all will OC as far....so no problem, just go as high as the one that overclocks the least...right? Wrong. There are cases where they won't overlock as far combined as they did without both in there. Throw 8 processors in there, and then you're in a doosy.

Plus, most servers don't have FSB or multiplier adjustment options, so you're outta luck there. And then, there's data corruption. Though your system might be stable, ie, never crashing, it could still be making an "of by one" error occasionally. Prime95 is an excellent test for this kinda thing. It might change just one bit in a file you save, no big deal...but it is when running important stuff.

There are just as many reasons NOT to overclock as there are TOO overclock. In the server/workstation world, sometimes the reasons not to are more important....for me, I like to overclock my home systems, nothing mission critical there 😉
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top