Message boards : Number crunching : WUs complete without error in just 73 seconds
Message board moderation

To post messages, you must log in.

AuthorMessage
SenrabYar

Send message
Joined: 28 Sep 04
Posts: 2
Credit: 62,367
RAC: 0
Message 8249 - Posted: 1 Jul 2005, 9:25:34 UTC

For the last few hours, one of my machines has been processing sixtrack 4.67 WUs in 73 seconds - one after another - it goes to 99.6% complete after first 5 seconds, then crawls (!) up the rest in the next minute. Meantime, the other "processor" is chewing along as normal.

The Results table show the WU as being perfectly OK - no mention of computation errors.

I realise that there may be some condition checking which decides that this chunk of data isn't worth analysing - but how come this is on every WU I'm getting right now?


<img src="http://seti.mundayweb.com/stats.php?userID=903"><br>
<img src="http://boinc.mundayweb.com/one/stats.php?userID=2034">
ID: 8249 · Report as offensive     Reply Quote
SenrabYar

Send message
Joined: 28 Sep 04
Posts: 2
Credit: 62,367
RAC: 0
Message 8251 - Posted: 1 Jul 2005, 9:34:01 UTC - in response to Message 8249.  

OK problem solved - but someone may want to take note

I rebooted machine - one of the slots had to be manually 'End Now'.

Now it's back to normal.

So something had put that slot into a funny state. Suppose I hadn't noticed - guess the daily limit check would have kicked in.
<img src="http://seti.mundayweb.com/stats.php?userID=903"><br>
<img src="http://boinc.mundayweb.com/one/stats.php?userID=2034">
ID: 8251 · Report as offensive     Reply Quote

Message boards : Number crunching : WUs complete without error in just 73 seconds


©2024 CERN