LLRnet servers for NPLB

[gd_barnes]

I have now swapped the hard drives so that the server is on one of my coolest and most stable machines. Max will get it running sometime later today (Weds).


Gary

[gd_barnes]

Originally Posted by em99010pepe

If you get G4000 up I'll move 7 cores to it (~1600 candidates per day).

Hold off until after Ian has stated that he has connected to it and returned all of his processed pairs. I think he said he had 300+ of them. We don't want a bunch of double-work done on them.

After that, fire away with your cores if you want.

[mdettweiler]

Originally Posted by gd_barnes

Hold off until after Ian has stated that he has connected to it and returned all of his processed pairs. I think he said he had 300+ of them. We don't want a bunch of double-work done on them.

After that, fire away with your cores if you want.

Actually, no need to worry about that. I'll be setting jobMaxTime to 20 days until everyone's given me the OK on their queued results.

Going to go work on it right now...

[mdettweiler]

Okay, G4000 is now officially back online!

I've submitted all me queued k/n pairs; Ian, let me know when you're all set so I can then change the deadline back to 5 days. (As mentioned in my last post, it's currently set to 20 days.)

Carlos and others: feel free to connect as soon as you wish. With the deadline set to 20 days there's no danger of anybody's results expiring for the time being.

[em99010pepe]

Moved 3 cores, more 4 later when I get home.

[MyDogBuster]

Ian, let me know when you're all set so I can then change the deadline back to 5 days.

Max, I've submitted them (some of them twice) and they don't show up anywhere. I just tried one again about 5 minutes ago, just before the 15 minute deadline and nothing. ???????. The one 1 submitted twice doesn't even show up as a rejected pair.

[MyDogBuster]

Okay, right out of an episode of the Twilight Zone, da da da da,
I tried again and this time they were accepted. So I guess I'm all caught up.

I haven't got a clue as to why they worked the second time and not the first.

[em99010pepe]

I'm full power on G4000.
Ian, good to know the results were accepted.

[MyDogBuster]

Ian, good to know the results were accepted

Thanks, I just wish I knew what I did right the second time. 260 results were just too much to throw away.

[em99010pepe]

Hey Lennart, a little push on G4000?

[gd_barnes]

We aren't going to add any more work to G4000 with this drive. Having Carlos and Ian on it should be sufficient. If it looks like IB400 is going to finish before G4000, I'll start moving machines. Regardless of that, we still have the final n=1.8K range that we'll load into IB400 before I would move any of my machines.

As long as you can calculate that port G4000 will finish by Dec. 23rd-24th with its current work and cores, then we won't need anyone more on it. If later, I can always move a few machines.

Edit: What do people think about a rally at this point? I'm thinking now that one won't be necessary. It might even be overly risky. With port G4000 back up, we should have stable ports until the 1st drive is complete (estimated at Dec. 23rd-24th somewhere ~1 week ago) and we have plenty of resources to get there now. The estimate had assumed that Sheep wouldn't be doing any processing and I see now that he is doing ~1500 pairs/day.

Edit 2: Perhaps a rally to kick off the new n>600K drives and to get them rolling fast would be a good option; perhaps the last weekend of Dec. or first weekend of Jan.


Gary