Message boards :
Technical News :
Carousel (Nov 03 2008)
Message board moderation
Author | Message |
---|---|
Matt Lebofsky Send message Joined: 1 Mar 99 Posts: 1444 Credit: 957,058 RAC: 0 |
Yeesh - another rocky weekend, but nothing out the ordinary. One download server got a headache, the schedule process felt sick for a while, the workunit storage filled up again thus blocking the splitters... At least we don't have those Astropulse download spikes anymore, but we're still at a loss to exactly explain why bruno is so overloaded - and therefore why the queues can't seem to drain as fast as they used to. Anecdotal evidence shows the mysql database may seem fine on the surface but is about to collapse any second, and all those extra milliseconds it takes to respond is causing bruno's processes to get all gummed up. In any case I put some effort into moving as many of these processes elsewhere. I also asked Dave for a BOINC feature request - a file_deleter command line option where you can state "only delete results" or "only delete workunits" so you can have file_deleters running on more appropriate systems. It's raining here in the Bay Area - and this wet weather is very much welcome given a ridiculously long summer of drought and fire, but rain also means our air conditioner isn't working as efficiently. So we got the server closet temperature to worry about on top of everything else. - 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 |
Dr. C.E.T.I. Send message Joined: 29 Feb 00 Posts: 16019 Credit: 794,685 RAC: 0 |
. . . a Prayer has been Issued form this House to Berkeley's [re: the rain / air conditioner] Thanks for the Post Matt . . . Keep up the great work Sir! BOINC Wiki . . . Science Status Page . . . |
Gary Charpentier Send message Joined: 25 Dec 00 Posts: 30639 Credit: 53,134,872 RAC: 32 |
Yeesh - another rocky weekend, but nothing out the ordinary. One download server got a headache, the schedule process felt sick for a while, the workunit storage filled up again thus blocking the splitters... At least we don't have those Astropulse download spikes anymore, but we're still at a loss to exactly explain why bruno is so overloaded - and therefore why the queues can't seem to drain as fast as they used to. Anecdotal evidence shows the mysql database may seem fine on the surface but is about to collapse any second, and all those extra milliseconds it takes to respond is causing bruno's processes to get all gummed up. In any case I put some effort into moving as many of these processes elsewhere. I also asked Dave for a BOINC feature request - a file_deleter command line option where you can state "only delete results" or "only delete workunits" so you can have file_deleters running on more appropriate systems. Thanks for the updates. Down south we need the rain too. But the Sierra needs tons of snow. Too bad that the humidity lowers the efficiency of the A/C and the cooler weather likely means the building A/C doesn't do as much dehumidifying. Just make sure the condensate drip pipe is open and some bug hasn't made it a nest! Bruno's gum. If I understand Bruno goes into a wait state for the database to finish the insert? Is this something that a larger cache between the processes might clear? Something that a few more threads might clear? Or is it a timing issue where inserting more delay (counter intuitive I know) might clear up a bursting or race issue? I'm not sure how the processes signal each other but are there sufficient resources in those tables? I believe you have updated O/S's recently, did all the tuned queue sizes make it into the new version? Did an update make an opaque queue element bigger and the change the tuning? Just thinking out loud. I'm sure you have thought of all these. Gary |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
Thanks for the updates it's great to hear what's happen in the lab. Thanz to the team that brought the server back to life over weekend of the (1st/2nd Nov) |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.