Goblin Valley (Jan 29 2009)

The replica mysql database on sidious recovered more or less just fine. It may be ever so slightly out of sync with the master database. This means we'll probably rebuild it during the next weekly outage just to be sure.

The scheduling server was up and down yesterday afternoon and this morning. The scheduler CGIs have been segfaulting and adding core dumps caused the system to grind to a halt, needing a reboot. Turns out the problem wasn't in the CGI, but in apache itself (or the fastcgi module). This has been a problem in the past. We seem to have to tweak various apache parameters at random times, based on a chaotic, unpredictable equation involving current resources/demands, mysql health, network health, system health, various queue sizes, etc. Simply reducing the MaxClients to a much lower number caused the segfaults to disappear while still servicing all incoming requests.

We're running low on data to send out, and we're in a murky period where the weekend is rapidly approaching and we are still awaiting the latest shipment of raw data drives from Arecibo. We could pull up as-yet-unanalysed data from our archives, but the offsite storage archive (HPSS) is undergoing several upgrades and have been offline for days. We'll see how this all pans out...

- Matt

____________
-- BOINC/SETI@home network/web/science/development person
-- "Any idiot can have a good idea. What is hard is to do it." - Jeanne-Claude

Thanks Matt as always for the update.

Seems a little quiet round here these days. Only 1 post yesterday!

I hope work doesn't run out. Still that will give em something to moan about over in NC :-)
____________

Thanks for the info Matt.

Any part of Southern Utah you have not been to???

And one more question..........is AstroPulse a dead project now???

____________
Boinc....Boinc....Boinc....Boinc....

In other words, SETI may have absolutely no work to send out over part of the weekend and possibly even into next week.

Thanks for the info Matt.

Any part of Southern Utah you have not been to???

And one more question..........is AstroPulse a dead project now???

In other words, SETI may have absolutely no work to send out over part of the weekend and possibly even into next week.

I hope new work arrives tomorrow, if not I think this will be the first time I have ever seen Seti run out of work. I will not be one to moan because I think the whole crew does a great job at the lab. Sometimes you can't help delays with the mail and courier services as annoying as it is.

This is when a 4+ day cache comes in handy. I should be fine until about Wednesday, even though it's only a 4-day cache.

We could pull up as-yet-unanalysed data from our archives,

Wouldn't that be everything from day 1 to now?

Seems like for the first time in a very long time, I am going to run out of work, should be in about 5 hours time.

Ah well, will give the computer a nice rest as it has been crunching 24/7 for the last 2 years solid! Give or take the inevitable occasional windows reboot required.

Will be patient until it can send some work, seems to have gone through the 4 day cache fast though.

Happy SuperBowl day :-)
____________

Seems like there is a small amount of work filtering through, since my last post I have got a few tasks come in.
____________

Seems like there is a small amount of work filtering through, since my last post I have got a few tasks come in.

Server Status as of 1 Feb 20:00:10 as of * 47 minutes says there are 33,474 Results ready to send. Spliters are spliting the last 5 channels at present, tape 18dc08aa is upto chanel 13. Cricket Graph says as of Feb 1 11:52:22

Average bits in Cur: 28.43 Mbits/sec
Average bits out Curr: 14.45 Mbits/sec

This is my 2 cents worth for the crunchers that like technical information
7 new data tapes have been added while I've been typing this post. A big thank you to the person who has come to the lab to add the work to queue on a Sunday morning. I didn't think we will run out of work now. Thank you again to the staff member that came into the lab
____________

Live in NZ y not join Smile City?

I think the main reason is because to date we simply don't have enough computing power to keep up with the data volume. If there is another reason please correct me.

I'd have to disagree with that. I remember a post by Matt a long time ago asking for assistance at Beta when developing the enhanced workunits or SETI would run out of work. That's why I asked NEZ to attach to Beta and he graciously complied.

I think the main reason is because to date we simply don't have enough computing power to keep up with the data volume.

7 new data tapes have been added while I've been typing this post. A big thank you to the person who has come to the lab to add the work to queue on a Sunday morning. I didn't think we will run out of work now. Thank you again to the staff member that came into the lab

Do the staff have access to an internal graph like Scarecrow's?



See how the clear trendline jumps on 17 December (CUDA v6.05 day), declines again as the bugs come to light, then starts to climb strongly on 21 January (CUDA v6.08 day).

We're now returning consistently double the number of results we were before CUDA.

Matt, soon after the first CUDA launch, you did a quick snapshot and came up with a figure of 3% of results returned having been processed by a CUDA application. Would you have a moment to re-run that query now we seem to be in full production?