Message boards :
Number crunching :
Even if there's no "real work", may I suggest a "real test"?
Message board moderation
| Author | Message |
|---|---|
|
Send message Joined: 18 Sep 04 Posts: 47 Credit: 1,886,234 RAC: 0 |
Much has changed since there was real work in the pipline - the severs have moved, looks like project directories have changed, etc... There have been a couple of small bursts of WU's for testing, but, as many people have the resource for LHC set really high, when work is available, it goes to only a few machines. As a result, not many of the clients have been tested, and there probably hasn't been that much of a load on the servers. Last time there was "real work" most of the WU's I got were ghosts.. (like 15 of 20) How about using old data for a real test run before new data hits the pipline? I'm thinking on the order of 100K WUs. Work out stuff now before real data is comprimised, is all I'm suggesting... (on both the client and server end) |
|
Send message Joined: 28 Jul 05 Posts: 37 Credit: 504,361 RAC: 3,746  
|
Much has changed since there was real work in the pipline - the severs have moved, looks like project directories have changed, etc... I agree 100% with what you are saying  Have A Crunching Good day |
 caspr Send message Joined: 26 Apr 06 Posts: 89 Credit: 309,235 RAC: 0 |
How about using old data for a real test run before new data hits the pipline? I'm thinking on the order of 100K WUs. Work out stuff now before real data is comprimised, is all I'm suggesting... (on both the client and server end) Yep I second that, what did they call it over at APS a couple weeks ago?... A "BOOM" test, to see if the servers could stand the load. A clear conscience is usually the sign of a bad memory  |
|
Send message Joined: 31 Dec 05 Posts: 68 Credit: 8,691 RAC: 0 |
How about using old data for a real test run before new data hits the pipline? I'm thinking on the order of 100K WUs. To what purpose? Presumably the project is issuing the WUs it feels are necessary for testing. The client hasn't changed. It has been a long time since I got any LHC WUs (because my machine doesn't run 24x7), but the last thing I want is to run a bunch of pointless WUs when I could be doing real science on another project. (Of course if Neasna and Alex think it is necessary (and not just "fun") to do a volume / stress test, I'm happy to crunch test WUs.) |
|
Send message Joined: 18 Sep 04 Posts: 47 Credit: 1,886,234 RAC: 0 |
Seems that "outstanding work" is still at ~35 days after 1000 test WU's were released. Could it be the "ghost" problem as the numbers haven't changed much today? I think doing a real load test would be a good thing for this project. It's no more "wasted cycles" than SETI which seems to crunch the same data over and over, and infact would be good for this project. New servers in a new location on the net, and only testing with enough work to last less than 10 minutes and takes days to come back isn't really a valid test for when a real dump of work becomes available, IMHO. Nows the time to really test the infrastructure, and not when real data might be lost/delayed. |
Neasan Send message Joined: 30 Nov 06 Posts: 234 Credit: 11,078 RAC: 0 |
Seems that "outstanding work" is still at ~35 days after 1000 test WU's were released. Could it be the "ghost" problem as the numbers haven't changed much today? Some of are them new WUs sent on the 16th and some of them are ones taken by users who have queued them without being able to process them in time.
Get out of my head ;-) Look we know you want to get crunching but this is out of our hands it is up to the scientists to submit work when they need it, they have said they are working on a large batch but when that appears we don't know. |
|
caspr Send message Joined: 26 Apr 06 Posts: 89 Credit: 309,235 RAC: 0 |
NEASAN,Sorry for being a pain, BUT, Do 1 get 1 insted of get 100 do 10 seemes to be a little better for the project....I may be wrong, please correct me if I am.:0{ A clear conscience is usually the sign of a bad memory |
Magic Quantum Mechanic Send message Joined: 24 Oct 04 Posts: 1117 Credit: 49,723,831 RAC: 13,891 
|
I didn't get anything again  And mine run 24/7 since the beginning. This is part of what it says......... 7/20/2007 5:56:33 AM|lhcathome|Reason: To fetch work 7/20/2007 5:56:33 AM|lhcathome|Requesting 172800 seconds of new work 7/20/2007 5:56:44 AM|lhcathome|Scheduler request succeeded 7/20/2007 5:56:46 AM|lhcathome|Started download of file sixtrack_4.67_windows_intelx86.exe 7/20/2007 5:56:46 AM|lhcathome|Started download of file bottomOverlay_1.02_.tga 7/20/2007 5:56:50 AM|lhcathome|Finished download of file bottomOverlay_1.02_.tga 7/20/2007 5:56:50 AM|lhcathome|Throughput 16631 bytes/sec 7/20/2007 5:56:50 AM|lhcathome|Started download of file courier_16_bold_1.01_.tga 7/20/2007 5:56:50 AM|lhcathome|Checksum or signature error for bottomOverlay_1.02_.tga 7/20/2007 5:56:51 AM|lhcathome|Unrecoverable error for result 7/20/2007 6:02:12 AM|lhcathome|Reason: To fetch work 7/20/2007 6:02:12 AM|lhcathome|Requesting 172800 seconds of new work, and reporting 5 completed tasks 7/20/2007 6:02:17 AM|lhcathome|Scheduler request succeeded 7/20/2007 6:02:17 AM|lhcathome|Message from server: No work sent 7/20/2007 6:02:17 AM|lhcathome|Message from server: (reached daily quota of 10 results) Just a bunch of nothing. (of course the message page is 10 times more than this) Just "client error"  Volunteer Mad Scientist For Life |
|
Send message Joined: 1 Sep 04 Posts: 101 Credit: 1,395,204 RAC: 0 |
magic if you really want an answer. DONT use that font. |
 Send message Joined: 14 Jul 05 Posts: 275 Credit: 49,291 RAC: 0
|
Is LHC server code still super-outdated, or have you upgraded already? My patch to the server code that limits the amount of workunits a host can have at a time has made it to the official code. It would be definitely useful here... |
|
Magic Quantum Mechanic Send message Joined: 24 Oct 04 Posts: 1117 Credit: 49,723,831 RAC: 13,891
|
watnou, Actually they just appear on their own.........I think they are hungry for some LHC WU's  Volunteer Mad Scientist For Life |
|
Send message Joined: 26 Aug 05 Posts: 18 Credit: 37,965 RAC: 0 |
I didn't get anything again Magic, Have you tried the "Skip Image File Verification" setting in the general boinc preferences? I know it's hard to test given the shortage of WUs, but it's worth a try. What other projects are you connected to? |
|
Magic Quantum Mechanic Send message Joined: 24 Oct 04 Posts: 1117 Credit: 49,723,831 RAC: 13,891
|
I never noticed that before so I just checked mine and it says "no" I also saw in my "messages" several more errors after it tried to download some here. (I also run Einstein)  Volunteer Mad Scientist For Life |
©2024 CERN