Panic Mode On (113) Server Problems?

Message boards : Number crunching : Panic Mode On (113) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 28 · 29 · 30 · 31 · 32 · 33 · 34 . . . 37 · Next

AuthorMessage
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13854
Credit: 208,696,464
RAC: 304
Australia
Message 1963035 - Posted: 3 Nov 2018, 0:13:40 UTC - in response to Message 1963017.  

I am just curious to know why we need the work units purged results to clear? These will probably take 24 hours. Apart from people having lots of results in their accounts I cannot see any other major issue, unless we run out of disk space.
It's more that records in the database tables need to clear - and in particular, the indexes to the records need to be shrunk until they fit in RAM (not on disk). Otherwise, they will be unutterably slow.

Does purging affect the re-sending of timed out/ inconclusive WUs?
Over the last few days, I've noted very few re-sends in my caches. Often there will be groups of 2-5 with the odd one here & there but lately there's been only the odd one or two here & there. At present I've got 4 in one cache, and 0 in the other; normally i'd expect 1-2 dozen in each cache..
Grant
Darwin NT
ID: 1963035 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1963039 - Posted: 3 Nov 2018, 0:36:06 UTC - in response to Message 1963035.  

It's more that records in the database tables need to clear - and in particular, the indexes to the records need to be shrunk until they fit in RAM (not on disk). Otherwise, they will be unutterably slow.

Does purging affect the re-sending of timed out/ inconclusive WUs?
Over the last few days, I've noted very few re-sends in my caches. Often there will be groups of 2-5 with the odd one here & there but lately there's been only the odd one or two here & there. At present I've got 4 in one cache, and 0 in the other; normally i'd expect 1-2 dozen in each cache..


. . I can only comment on my slow machines, the tasks on the faster units just come and go pretty quickly, I don't take much notice. But what I am seeing are small groups of resends from the end of August and early September, after the WOW event I am guessing. Not dozens but regular small groups of 2 or 3.

Stephen

. .
ID: 1963039 · Report as offensive
Profile Brent Norman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester

Send message
Joined: 1 Dec 99
Posts: 2786
Credit: 685,657,289
RAC: 835
Canada
Message 1963051 - Posted: 3 Nov 2018, 1:27:26 UTC - in response to Message 1963035.  

Purging is the tasks list we get to see after they have been validated assimilated and files removed.
I believe it is set to 7 days for MB and 2 days for AP.

It would be nice if the limit was 6 days, so that the big surge of tasks after maintenance is removed before the next round comes in.
ID: 1963051 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1963052 - Posted: 3 Nov 2018, 1:34:43 UTC - in response to Message 1963051.  

Purging is the tasks list we get to see after they have been validated assimilated and files removed.
I believe it is set to 7 days for MB and 2 days for AP.

It would be nice if the limit was 6 days, so that the big surge of tasks after maintenance is removed before the next round comes in.

+1
I think that would be a splendid development too. I never can catch up since my previous week's task list runs into the next maintenance. The only time I see my task list diminish is when there is a long project upset.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1963052 · Report as offensive
Profile Unixchick Project Donor
Avatar

Send message
Joined: 5 Mar 12
Posts: 815
Credit: 2,361,516
RAC: 22
United States
Message 1963058 - Posted: 3 Nov 2018, 1:49:52 UTC - in response to Message 1963051.  

Purging is the tasks list we get to see after they have been validated assimilated and files removed.
I believe it is set to 7 days for MB and 2 days for AP.

It would be nice if the limit was 6 days, so that the big surge of tasks after maintenance is removed before the next round comes in.


How weird. my task list for validated tasks is only 24 hours long... MB or AP
ID: 1963058 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1643
Credit: 12,921,799
RAC: 89
New Zealand
Message 1963060 - Posted: 3 Nov 2018, 1:53:18 UTC - in response to Message 1963017.  

I am just curious to know why we need the work units purged results to clear? These will probably take 24 hours. Apart from people having lots of results in their accounts I cannot see any other major issue, unless we run out of disk space.
It's more that records in the database tables need to clear - and in particular, the indexes to the records need to be shrunk until they fit in RAM (not on disk). Otherwise, they will be unutterably slow.

If it can't fit into RAM where does it go?
ID: 1963060 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1963061 - Posted: 3 Nov 2018, 1:54:30 UTC - in response to Message 1963058.  

LOL. You only have 16 tasks outstanding in the database. I have 55,000 outstanding in the database.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1963061 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1963062 - Posted: 3 Nov 2018, 1:56:27 UTC - in response to Message 1963060.  

I am just curious to know why we need the work units purged results to clear? These will probably take 24 hours. Apart from people having lots of results in their accounts I cannot see any other major issue, unless we run out of disk space.
It's more that records in the database tables need to clear - and in particular, the indexes to the records need to be shrunk until they fit in RAM (not on disk). Otherwise, they will be unutterably slow.

If it can't fit into RAM where does it go?

If the indexes can't fit into RAM, they have to be read off slow drive storage. Thus unutterably slow as Richard described.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1963062 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1643
Credit: 12,921,799
RAC: 89
New Zealand
Message 1963069 - Posted: 3 Nov 2018, 2:53:20 UTC - in response to Message 1963062.  

I am just curious to know why we need the work units purged results to clear? These will probably take 24 hours. Apart from people having lots of results in their accounts I cannot see any other major issue, unless we run out of disk space.
It's more that records in the database tables need to clear - and in particular, the indexes to the records need to be shrunk until they fit in RAM (not on disk). Otherwise, they will be unutterably slow.

If it can't fit into RAM where does it go?

If the indexes can't fit into RAM, they have to be read off slow drive storage. Thus unutterably slow as Richard described.

Thanks Keith. I guess if people want it they could start a fundraiser
ID: 1963069 · Report as offensive
Profile Unixchick Project Donor
Avatar

Send message
Joined: 5 Mar 12
Posts: 815
Credit: 2,361,516
RAC: 22
United States
Message 1963073 - Posted: 3 Nov 2018, 4:10:29 UTC - in response to Message 1963061.  
Last modified: 3 Nov 2018, 4:13:34 UTC

LOL. You only have 16 tasks outstanding in the database. I have 55,000 outstanding in the database.


Hey... be nice... my mac mini is proud of every one of the tasks it does. It may be old and slow but it has done a bunch of WUs over many years.

But I'm still not sure why you see more than 24 hours of valids? Maybe your machine spits them out so fast that you have a long list of pending... just wanting around on the partner machine (probably something slow like mine).

It wouldn't cost the db much to show me more than 24 hours of history.

edit : ah my misunderstanding. thought you guys were talking about valids, not pendings
ID: 1963073 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51478
Credit: 1,018,363,574
RAC: 1,004
United States
Message 1963076 - Posted: 3 Nov 2018, 4:30:57 UTC - in response to Message 1963069.  


Thanks Keith. I guess if people want it they could start a fundraiser

Many of us would respond if we only knew it would improve things.
I, for example, have donated towards specific ends.
I await further introductions towards a new improvement.
"Time is simply the mechanism that keeps everything from happening all at once."

ID: 1963076 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1963078 - Posted: 3 Nov 2018, 4:56:10 UTC - in response to Message 1963058.  

Purging is the tasks list we get to see after they have been validated assimilated and files removed.
I believe it is set to 7 days for MB and 2 days for AP.

It would be nice if the limit was 6 days, so that the big surge of tasks after maintenance is removed before the next round comes in.


How weird. my task list for validated tasks is only 24 hours long... MB or AP


. . Pretty much what I am seeing too.

Stephen

.
ID: 1963078 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1963079 - Posted: 3 Nov 2018, 4:57:49 UTC - in response to Message 1963060.  

I am just curious to know why we need the work units purged results to clear? These will probably take 24 hours. Apart from people having lots of results in their accounts I cannot see any other major issue, unless we run out of disk space.
It's more that records in the database tables need to clear - and in particular, the indexes to the records need to be shrunk until they fit in RAM (not on disk). Otherwise, they will be unutterably slow.

If it can't fit into RAM where does it go?


. . Umm, it is on disk. That is what makes access to it slow ...

Stephen

. .
ID: 1963079 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1963080 - Posted: 3 Nov 2018, 4:59:01 UTC - in response to Message 1963061.  

LOL. You only have 16 tasks outstanding in the database. I have 55,000 outstanding in the database.


. . Now I am LOL, that is the output of a small country ... :)

Stephen

:)
ID: 1963080 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1963084 - Posted: 3 Nov 2018, 5:35:52 UTC - in response to Message 1963073.  
Last modified: 3 Nov 2018, 5:57:25 UTC

LOL. You only have 16 tasks outstanding in the database. I have 55,000 outstanding in the database.


Hey... be nice... my mac mini is proud of every one of the tasks it does. It may be old and slow but it has done a bunch of WUs over many years.

But I'm still not sure why you see more than 24 hours of valids? Maybe your machine spits them out so fast that you have a long list of pending... just wanting around on the partner machine (probably something slow like mine).

It wouldn't cost the db much to show me more than 24 hours of history.

edit : ah my misunderstanding. thought you guys were talking about valids, not pendings

My oldest pending was returned 19 July. WU 3058299862

My oldest valid is from 18 July WU 3056429782
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1963084 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1963085 - Posted: 3 Nov 2018, 5:36:50 UTC - in response to Message 1963080.  

LOL. You only have 16 tasks outstanding in the database. I have 55,000 outstanding in the database.


. . Now I am LOL, that is the output of a small country ... :)

Stephen

:)

The effect of 16 gpus running the Linux special app.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1963085 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1963088 - Posted: 3 Nov 2018, 5:50:39 UTC

No, every machine, however minimal, crunches toward the goal. I have 2 Android tablets and a Android phone crunching too. Their output is not even a rounding error compared to the PC's but even they add to my account total.

edit : ah my misunderstanding. thought you guys were talking about valids, not pendings

Every task assigned to your account, In Progress, Pending, Inconclusive, Invalid and Errors have to be held in the database indices. So the larger the quantity of records that have to be pulled the slower the retrieval. If the Results and WU would be purged faster, the smaller the retrieval transaction and my web pages might actually appear when I click on them. I can only wish.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1963088 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13164
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1963089 - Posted: 3 Nov 2018, 6:01:41 UTC

The servers started making progress on the Results awaiting purging around Zulu 3 November today from the Haveland graphs. I could actually pull up my oldest tasks, though it took a minute or so for the web page to appear.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1963089 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1643
Credit: 12,921,799
RAC: 89
New Zealand
Message 1963096 - Posted: 3 Nov 2018, 7:22:02 UTC - in response to Message 1963079.  

I am just curious to know why we need the work units purged results to clear? These will probably take 24 hours. Apart from people having lots of results in their accounts I cannot see any other major issue, unless we run out of disk space.
It's more that records in the database tables need to clear - and in particular, the indexes to the records need to be shrunk until they fit in RAM (not on disk). Otherwise, they will be unutterably slow.

If it can't fit into RAM where does it go?


. . Umm, it is on disk. That is what makes access to it slow ...

Stephen

. .

I thought it was on disk as well
ID: 1963096 · Report as offensive
Profile Jimbocous Project Donor
Volunteer tester
Avatar

Send message
Joined: 1 Apr 13
Posts: 1856
Credit: 268,616,081
RAC: 1,349
United States
Message 1963097 - Posted: 3 Nov 2018, 7:23:12 UTC - in response to Message 1963084.  
Last modified: 3 Nov 2018, 8:12:57 UTC

LOL. You only have 16 tasks outstanding in the database. I have 55,000 outstanding in the database.


Hey... be nice... my mac mini is proud of every one of the tasks it does. It may be old and slow but it has done a bunch of WUs over many years.

But I'm still not sure why you see more than 24 hours of valids? Maybe your machine spits them out so fast that you have a long list of pending... just wanting around on the partner machine (probably something slow like mine).

It wouldn't cost the db much to show me more than 24 hours of history.

edit : ah my misunderstanding. thought you guys were talking about valids, not pendings

My oldest pending was returned 19 July. WU 3058299862

My oldest valid is from 18 July WU 3056429782

Apples and Oranges, I think...
Your oldest pending has only been pending (inconclusive) for 2 hours, as that's when the wingman reported, creating something to be pending rather than in process.
Likewise, your oldest valid has only been valid for 6 hours, as that's when the wingman reported that would compare against two previous results to resolve an inconclusive.
It's the most recent activity that counts, not just yours.
Or did I misunderstand your point?
ID: 1963097 · Report as offensive
Previous · 1 . . . 28 · 29 · 30 · 31 · 32 · 33 · 34 . . . 37 · Next

Message boards : Number crunching : Panic Mode On (113) Server Problems?


 
©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.