PPD on avg going down?

Come join the... uh... er... fold.

Moderators: just brew it!, farmpuma

PPD on avg going down?

Postposted on Tue Mar 10, 2009 9:24 am

Hey all, I've noticed a trend on my folding farm thats alarming. I used to get about 2k-2.5k PPD out of each node but I'm not getting anywhere near that anymore, its been like that last couple weeks. Anyone else notice this or is it just me?

Image
Image
Shinare
Gerbil XP
 
Posts: 352
Joined: Wed Jul 06, 2005 12:48 pm

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 10:06 am

Yes, I have noticed as well. At least in my case, it appears to be due in large part to the fact that I am getting a lot of SMP WUs that use the a1 core instead of the a2 core.
(this space intentionally left blank)
just brew it!
Administrator
Gold subscriber
 
 
Posts: 37658
Joined: Tue Aug 20, 2002 10:51 pm
Location: Somewhere, having a beer

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 10:37 am

Yha, I've been nailed by this too, 2 and 3 day units, where there use to be mainly 15hr ones.
Intel Q6600 g0 @ 3.2Ghz Turniq 120 Heatsink BFG 260 OC MaxCore
2x2gb OCZ Platinums @ 1:1 XFX 680i motherboard Corsair 520hx Antec 900


Image
Patonb
Gerbil
 
Posts: 37
Joined: Sat Jan 24, 2009 12:20 pm
Location: Ottawa, Canada there eh

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 10:42 am

Yup, seeing the same as well. I'm even getting given 4 processor a1 units on my core i7 920 which usually does very nicely on 8 processor a2s which drops me by about 6k PPD.
notfred
Grand Gerbil Poohbah
 
Posts: 3729
Joined: Tue Aug 10, 2004 10:10 am
Location: Ottawa, Canada

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 1:21 pm

Yah, its just killin' me.. :)

My wife made my buy furniture instead of the stack of 4850's I had in my wishlist. *cry*
Image
Shinare
Gerbil XP
 
Posts: 352
Joined: Wed Jul 06, 2005 12:48 pm

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 6:21 pm

I'm getting lots of "Attempt #xx to get work failed, and no other work to do", and have about a quarter of my available cores twiddling their thumbs :(

Bruce
Bruce
Gerbil Elite
 
Posts: 500
Joined: Thu Dec 27, 2001 7:00 pm
Location: New Zealand

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 6:48 pm

I get that for about 10 attempts a try on my single core clients. GPU never has an issue.

It's also unable to upload a bunch of WU's from the same period, error 503, but afaik that just means the server isn't accept/giving out WU's anymore, so I think I've lost those points.
Q9550 @ stock | 8GB DDR2 1066 5-5-5-15 | Gainward GTX 460 GS GLH | Asus P5Q SE/R | Scythe Mugen | OCZ StealthXstream 600w | Antec 300 | Zalman ZM-MFC1+ | 1TB WD Caivar Black | Audigy SE 7.1 | Logitech X-540 | HG281D 28" | Razer Diamondback| Win7x64
silent ninjah
Gerbil First Class
 
Posts: 177
Joined: Sun Oct 16, 2005 9:10 am
Location: Scotland

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 7:30 pm

It seems that some F@H WU servers are having problems in the past month.

I have been encounter connection issues with only certain Project groups, while others are working fine.
Ivy Bridge i5-3570K@4.0Ghz, Gigabyte Z77X-UD3H, 2x4GiB of PC-12800, EVGA 660Ti, Corsair CX-600 and Fractal Refined R4 (W). Kentsfield Q6600@3Ghz, HD 4850 2x2GiB PC2-6400, Gigabyte EP45-DS4P, OCZ Modstream 700W, and PC-7B.
Krogoth
Maximum Gerbil
Silver subscriber
 
 
Posts: 4402
Joined: Tue Apr 15, 2003 3:20 pm
Location: somewhere on Core Prime

Re: PPD on avg going down?

Postposted on Tue Mar 10, 2009 8:44 pm

My SMP client has had diminishing returns as well recently, but the GPU clients are keeping my PPD high.
Image
Momento Mori
Gerbil First Class
 
Posts: 192
Joined: Tue Sep 09, 2008 5:25 pm
Location: Northeast Ohio

Re: PPD on avg going down?

Postposted on Wed Mar 11, 2009 7:50 am

Yep, the single core client has been getting the redheaded bastard stepchild treatment from the servers for several weeks now. And lately it's been worse. The majority of the time the client connects to the server, but fails to be given a work unit because the server is to busy or having issues.

Also, I have three (on three different machines) DGromacs from 128.59.74.4 which has been in fail/reject mode for over a week or more. Plus I had two DGromacs (on two different machines) from 128.143.48.226 fail to upload because the server didn't like them, but gave no reason why they were defective. Both work units ran with no errors or other indications of a problem. And both of the machines had finished and uploaded several of the same work units with no issues. I suspect, "garbage in, garbage out."

The GPU server has been sending out the 511 point sloow on Nvidia work units the majority of the time for a while and has lately mixed in some also slowish on Nvidia 420 point work units.

On the upside, and I hesitate to mention it, the SMP server has been treating both of my 5.91 windows clients quite well lately.
Image Image
.* * M-51 * *. .The Whirlpool Galaxy.
farmpuma
Minister of Gerbil Affairs
Silver subscriber
 
 
Posts: 2315
Joined: Mon Mar 22, 2004 12:33 am
Location: Soybean field, IN, USA, Earth .. just a bit south of John .. err .... Fart Wayne, Indiana

Re: PPD on avg going down?

Postposted on Wed Mar 11, 2009 8:02 am

farmpuma wrote:Yep, the single core client has been getting the redheaded bastard stepchild treatment from the servers for several weeks now. And lately it's been worse. The majority of the time the client connects to the server, but fails to be given a work unit because the server is to busy or having issues.
The fatter Gromacs C WUs seem to have dried up and I have been getting some slow but small ones. :-? I also have a WU stuck for more than 2 weeks to the point I just said "screw it" and trashed it.
Image
The Model M is not for the faint of heart. You either like them or hate them.

Gerbils unite! Fold for UnitedGerbilNation, team 2630.
Flying Fox
Gerbil God
 
Posts: 24369
Joined: Mon May 24, 2004 2:19 am


Return to TR Distributed Computing Effort

Who is online

Users browsing this forum: No registered users and 1 guest