Message boards :
Number crunching :
The Server Issues / Outages Thread - Panic Mode On! (119)
Message board moderation
Previous · 1 . . . 79 · 80 · 81 · 82 · 83 · 84 · 85 . . . 107 · Next
Author | Message |
---|---|
Unixchick Send message Joined: 5 Mar 12 Posts: 815 Credit: 2,361,516 RAC: 22 |
What the meow??? not false. I think they are forcing early resends. I just got a bunch... #3 without a timeout or error. |
kittyman Send message Joined: 9 Jul 00 Posts: 51468 Credit: 1,018,363,574 RAC: 1,004 |
Must be so. I see we are back over 2 million out in the field again. None came my way, unfortunately. Meow. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
Results out in the field 1,998,795 As of 16 Apr 2020, 10:40:04 UTC Results out in the field 2,019,818 As of 17 Apr 2020, 17:40:03 UTC So we are back above 2mil again ! I think AstroPulse in the field has gone up too Does someone have a link to the server graphs please ?... [Edit] Found them https://munin.kiska.pw/munin/setiathome-day.htmlhttps://munin.kiska.pw/munin/setiathome-day.html |
Bart Send message Joined: 23 Apr 03 Posts: 17 Credit: 3,080,489 RAC: 27 |
What the meow??? I just got 100 forced re-sends without timeout errors... |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
We were getting extra re-sends around 24 hours before the timeouts, it looks like Eric, or whoever, has increased that to 72 Hours |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
|
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
Forced resends?? They trying to speed up the returns so they can turn off the servers quicker?? |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
Forced resends?? They trying to speed up the returns so they can turn off the servers quicker?? They're trying to speed up the returns so that they can get the science completed quicker. |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
But, if they do not direct those resends to trusted computers, known for quick returns, they are not gaining anything at all, by seeding random crunchers with thousands of resends. I made the same proposal few days before and i was called elitist, etc. But is the logical way. |
Unixchick Send message Joined: 5 Mar 12 Posts: 815 Credit: 2,361,516 RAC: 22 |
If they are sending resends early thus shortening the deadline, they don't need to send to specific machines. The resends of the resends will be sent quicker. Thus they avoid the whole who to send it to can-of-worms (you know someone would complain). |
Zalster Send message Joined: 27 May 99 Posts: 5517 Credit: 528,817,460 RAC: 242 |
They're trying to speed up the returns so that they can get the science completed quicker. Go give Dr. A posts on how he plans on analyzing the data a read. I have. They aren't going to have this done anytime in any kind of near future. |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13746 Credit: 208,696,464 RAC: 304 |
If they are sending resends early thus shortening the deadline, they don't need to send to specific machines. The resends of the resends will be sent quicker. Thus they avoid the whole who to send it to can-of-worms (you know someone would complain).Unless one of them goes to a zombie machine that happens to make contact at that time. Makes more sense to reduce the Deadline for resends, and resend ones after they've been out for a month, not just a few days before they are due to being resent after already being out there for 3 months. But i guess every little bit does help. Grant Darwin NT |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
They're trying to speed up the returns so that they can get the science completed quicker. From what I have seen of DA's ability to write a simple web page https://scienceunited.org/trac/wiki/ProjectPeople, I'm not very confident of that ! |
W-K 666 Send message Joined: 18 May 99 Posts: 19078 Credit: 40,757,560 RAC: 67 |
Forced resends?? They trying to speed up the returns so they can turn off the servers quicker?? Not convinced this will work.Looking at my tasks, if the forced resend hasn't been returned before the original deadline, the normal sequence still kicks in and sends another task out, a _3, to another host. So now the WU is waiting for two tasks before it can be assimilated and purged. A failure to think the problem though, again. |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
The Minimum Quorum is still 2, But the Replication is now > Quorum So only 1 more task is needed to reach Quorum, unless a tie-breaker is needed, which could be any of the results "in the field", including the Expired one. |
Unixchick Send message Joined: 5 Mar 12 Posts: 815 Credit: 2,361,516 RAC: 22 |
This is pure speculation on my part. They did a batch of resends 24 hours before the deadline... then today they did a batch of resends 3 days before the deadline... maybe next they will do a batch of resends 5 days before the deadline etc...I'm guessing they will just do this in waves as the bunch they sent out today will ripple. There will be resends triggered from errors or non matching from this action they took today, when that dies down they can do another batch. |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
If they are sending resends early thus shortening the deadline, they don't need to send to specific machines. The resends of the resends will be sent quicker. Thus they avoid the whole who to send it to can-of-worms (you know someone would complain).Unless one of them goes to a zombie machine that happens to make contact at that time. Maybe Eric is taking things in "baby steps", I assume that it's probably Eric running the scripts. He may want to see the results of increasing from 24h to 72h, before going to a larger value eg 168h or greater. |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13746 Credit: 208,696,464 RAC: 304 |
My Pendings (& to a lesser extent Inconclusives) are slowly falling. But my Valids keep increasing. They're Valid, but still waiting for another Result (or two) to be returned. Late May, early June for the vast majority before they are resent. A couple for mid June. Grant Darwin NT |
Keith T. Send message Joined: 23 Aug 99 Posts: 962 Credit: 537,293 RAC: 9 |
My Pendings (& to a lesser extent Inconclusives) are slowly falling. But my Valids keep increasing. They're Valid, but still waiting for another Result (or two) to be returned. Late May, early June for the vast majority before they are resent. A couple for mid June. I just looked at your computers, it looks like we have already gone up to 7 days before deadline. https://setiathome.berkeley.edu/workunit.php?wuid=3911459894 |
Ville Saari Send message Joined: 30 Nov 00 Posts: 1158 Credit: 49,177,052 RAC: 82,530 |
It would be smarter to send those n days after the last scheduler contact of the pending cruncher than n days before the deadline. If a host hasn't contacted the servers after the faucets were closed, the task is unlikely to be returned and should be resent now even if its deadline is in June. |
©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.