An odd result

Dave Burbank
Dave Burbank
Joined: 30 Jan 06
Posts: 275
Credit: 1,548,376
RAC: 0
Topic 194128

I took a bit of a break from E@H, but now that winter is back in full force I've been crunching away to help keep the place warm :) So its good to be back.

Have a look at this WU

Host 1595633 has an unusually fast crunch time for this WU. Normally I'd think it was just a highly overclocked computer, but looking at the result page for this host does not support that idea.

Also note that the host is only claiming 41.70 credits for that WU, although I'm not sure if that's unusual.

I'm new to S5R4, so I'm not sure if WU's can end early or something similar, and I'm just being dense. Just wanted to point this out.

There are 10^11 stars in the galaxy. That used to be a huge number. But it's only a hundred billion. It's less than the national deficit! We used to call them astronomical numbers. Now we should call them economical numbers. - Richard Feynman

Joined: 8 May 05
Posts: 927
Credit: 9,352,143
RAC: 0

An odd result


My guess is there was some kind of glitch on the host which caused it to reset the accumulated CPU Time at some point during the run.

If you look through the stderr data for the task you find there were a lot of lost CC heartbeat events during the run.

Doing a little ballpark calculating:

The average run time for the host is around 25 Ksecs. so;

((25 K - 15 K) / 25 K)) * 842 = ~336

So now looking through the stderr data closer we see there was a lost heartbeat event between skypoints 366 and 367. Since my time estimations are crude, this is probably when the CPU Time reset occurred.


Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.