Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
![]() |
World Community Grid Forums
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Member(s) browsing this thread: Unixchick , TonyEllis |
Thread Status: Active Total posts in this thread: 3315
|
![]() |
Author |
|
alanb1951
Veteran Cruncher Joined: Jan 20, 2006 Post Count: 981 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Adri,
Recognized that machine name :-) It also provided my two recent SIGSEGV examples, but for two different work units; ARP1_0002741_135_1 sent 2023-01-23T18:45:48 returned 2023-01-25T14:08:22 The former task seemed to have been restarted after the third checkpoint and crashed without reaching the next one. The latter crashed after 5 checkpoints. I have seen quite a few SIGSEGV returns for otherwise valid ARP1 units since the start of the migration process (I wasn't recording wingman data until then...), and the vast majority of them were down to a couple of hosts - this is the first time I've seen this one. I guess we'll never know why this happens... Cheers - Al. |
||
|
Grumpy Swede
Master Cruncher Svíþjóð Joined: Apr 10, 2020 Post Count: 2209 Status: Recently Active Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Finally my "Oops" ARP1_0010948_136_3 task, is finished and validated. My old i7-3630QM CPU, isn't the fastest on Earth, but at least I finished this ARP faster than my wingman.
----------------------------------------![]() [Edit 3 times, last edit by Grumpy Swede at Jan 31, 2023 8:31:07 AM] |
||
|
adriverhoef
Master Cruncher The Netherlands Joined: Apr 3, 2009 Post Count: 2171 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Al,
Remember a device called Ryzen-OneHorseShay? Of course you do. ![]() New developments this time, on the one hand there's a SIGSEGV: ARP1_0033822_137_1 Linux Ubuntu Error 2023-01-25T12:41:29 2023-01-26T12:08:18 2.28/2.30 72.8/0.0with one wingman Pending Validation, and on the other hand there's something else: ARP1_0020353_137_0 Linux Ubuntu Error 2023-01-25T12:41:29 2023-01-25T21:53:46 2.69/2.70 84.0/0.0 Here is also one other wingman Pending Validation. Adri |
||
|
alanb1951
Veteran Cruncher Joined: Jan 20, 2006 Post Count: 981 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Adri,
----------------------------------------That second one is interesting, being a data corruption that the software could spot and identify in enough detail! Unfortunately, the same isn't true for SIGSEGV without a symbol table and the source code! :-) I've just looked at my latest wingmen and I note another SIGSEGV (ARP1_0001793_137_0) and an Invalid (ARP1_0005836_138_1) from that name. The former is waiting for another wingman (mine is Pending Validation) and the latter validated with another wingman... For what it's worth, a machine with that name has also been an MCM1 wingman of mine on five occasions and all of them were valid. It looks as if there's something in the ARP1 code that upsets this particular machine, doesn't it? As we don't know anything about the hardware of individual users at WCG it's not possible to get an impression of whether the various other lone SIGSEGVs that I've seen are from one specific hardware set[1] (eg, [if AMD] early Ryzen or Threadripper) or whether it's mostly "random" -- it does tend to mean that even if it could be fixed it won't be :-( Cheers - Al. [1] There have been instances in the past where a project application was more likely to fail on some AMD hardware than Intel... Can't remember off-hand which application(s), though [Edited to note two more failures] [Edit 2 times, last edit by alanb1951 at Feb 1, 2023 1:57:21 AM] |
||
|
Unixchick
Veteran Cruncher Joined: Apr 16, 2020 Post Count: 993 Status: Recently Active Project Badges: ![]() ![]() ![]() ![]() ![]() |
Finally my "Oops" ARP1_0010948_136_3 task, is finished and validated. My old i7-3630QM CPU, isn't the fastest on Earth, but at least I finished this ARP faster than my wingman. ![]() This is the speed of my machine now. It is an upgrade from the machine that did a bunch of ARPs. It isn't so much about the speed as being reliable and getting it done, and you did that well. I know spending the money on the energy is hard at this time Grumpy Swede, so I'm glad you are still participating. I'm enjoying the odd ARP resend when it finds its way to me. I hope the project gets their equipment fixed soon, as I would like to have ARP regularly without manually managing downloads or queue length. |
||
|
Sgt.Joe
Ace Cruncher USA Joined: Jul 4, 2006 Post Count: 7696 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
ARP1_0022054_140_2 in progress.
----------------------------------------Cheers
Sgt. Joe
*Minnesota Crunchers* |
||
|
Mike.Gibson
Ace Cruncher England Joined: Aug 23, 2007 Post Count: 12435 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
I gather that the hold up at Delft is that they needed more data storage than the Uni could allow so they had to get their own storage. This would take time to obtain, install & get approval before operation.
Mike |
||
|
Mike.Gibson
Ace Cruncher England Joined: Aug 23, 2007 Post Count: 12435 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Sgt. Joe's re-send indicates that we are about at the end of the road for resends except for maybe a few that go for a second re-send.
Mike |
||
|
Mike.Gibson
Ace Cruncher England Joined: Aug 23, 2007 Post Count: 12435 Status: Offline Project Badges: ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
We are now in round 3 of the recent releases.
Mike |
||
|
Unixchick
Veteran Cruncher Joined: Apr 16, 2020 Post Count: 993 Status: Recently Active Project Badges: ![]() ![]() ![]() ![]() ![]() |
on my last 2 ARP WUs. Not sure if I'll get any more resends. I'm going to give my machine a good clean and update once they are done. Looking forward to when we get more...
Yet again I hope they take this short (please let it be short) pause time to send out the extremes. |
||
|
|
![]() |