LLRnet servers for NPLB

[IronBits]

Ok, fixed the problem and now you will only see hrs 00-23 for a given day.
Would anyone mind if I processed the results files at midnight instead of 7am?

[mdettweiler]

Originally Posted by IronBits

Ok, fixed the problem and now you will only see hrs 00-23 for a given day.
Would anyone mind if I processed the results files at midnight instead of 7am?

Nope, no problem with that for me. In fact, it might actually be *more* convenient to do them at midnight, now that I think about it...

[gd_barnes]

Originally Posted by IronBits

Ok, fixed the problem and now you will only see hrs 00-23 for a given day.
Would anyone mind if I processed the results files at midnight instead of 7am?

The new page now looks great!

Processing results at midnight your time works for me. It'll be 1 AM here and 2 AM where Max is.

For everyone's reference, David's new cutoff on daily LLRNet results will be 7 AM GMT now.

[IronBits]

Thanks Gary, I'm still working out the numbers to take (total done for the day) - (the previous hours total), so I can post the real total amount of knpairs returned each hour so you don't have to do the math. This way you can find out if you have boxen not working

If that doesn't work out, then I'll just leave it showing the total knpairs returned for each user and let you folks do the math, until I can figure something else out.

Starting the web page stats 2 minutes after midnight will simplify the math.
If no knpairs are returned within the 1st 2 minutes of moving results.txt, then those users won't show up until the next run at 0100 hrs.
Make sense?

The web page will update at 2 minutes after midnight.
Results.txt will be moved out of there and processed, with .csv sent to the import directory at midnight.
I'll have to go over to that Server and edit crontab so it processes the .csv sometime after midnight as well.

edit:
crontab done

[gd_barnes]

Originally Posted by IronBits

Thanks Gary, I'm still working out the numbers to take (total done for the day) - (the previous hours total), so I can post the real total amount of knpairs returned each hour so you don't have to do the math. This way you can find out if you have boxen not working

If that doesn't work out, then I'll just leave it showing the total knpairs returned for each user and let you folks do the math, until I can figure something else out.

Starting the web page stats 2 minutes after midnight will simplify the math.
If no knpairs are returned within the 1st 2 minutes of moving results.txt, then those users won't show up until the next run at 0100 hrs.
Make sense?

The web page will update at 2 minutes after midnight.
Results.txt will be moved out of there and processed, with .csv sent to the import directory at midnight.
I'll have to go over to that Server and edit crontab so it processes the .csv sometime after midnight as well.

edit:
crontab done

Hum...I'm having the same problem again...with the date showing on 3 lines as well as multiple days showing. It's strange that it was correct for a while and then went back to the old way.

[IronBits]

I can not make any of the columns (in FF 3+ or IE7+) resize by shrinking the size of the browser window.

Fine, I'll removed the DATE column then.

http://nplb.ironbits.net/progress_400.html

This is only temporary until I can figure out how to get it into a database, or/and get php to parse a .csv properly...

[gd_barnes]

Would it create a problem if I renumbered the servers here? Port 5000 should be near the bottom; perhaps #4; and the others moved up.


Gary

[mdettweiler]

Originally Posted by gd_barnes

Would it create a problem if I renumbered the servers here? Port 5000 should be near the bottom; perhaps #4; and the others moved up.


Gary

No, no problem--as far as I know, there isn't anything that depends on the numbers of the servers in this thread.

[em99010pepe]

C443 has left ~9200 pairs although the work available is behind G4000 one (with 43k pairs left) I advise people to move a few cores to the latter. Thank you.

Carlos

[gd_barnes]

Originally Posted by em99010pepe

C443 has left ~9200 pairs although the work available is behind G4000 one (with 43k pairs left) I advise people to move a few cores to the latter. Thank you.

Carlos

I'm not sure what you mean. Are there ranges in C443 that are both lower and higher than G4000?

I just now checked and C443 is currently handing out n=569344 so it has quite a bit to go to get to n=570K.


Gary

[em99010pepe]

Originally Posted by gd_barnes

I'm not sure what you mean. Are there ranges in C443 that are both lower and higher than G4000?

I just now checked and C443 is currently handing out n=569344 so it has quite a bit to go to get to n=570K.


Gary

All ranges are lower, I just though we could move a few cores to help G4000.
Not too much, it's only 9 days on my Q6600.