Up (Dec 07 2010)

Message boards : Technical News : Up (Dec 07 2010)
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5

AuthorMessage
rob smith Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer moderator
Volunteer tester

Send message
Joined: 7 Mar 03
Posts: 19956
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1055682 - Posted: 13 Dec 2010, 18:16:26 UTC - in response to Message 1055680.  

The trouble with a drive failure in a RAID is that it can take some time to get things back on an even keel once the drive has either been removed or replaced. Its wise not to make too much of a demand on the array while this is automagic restructuring of the array is taking place.
So take a deep breath and be patient.
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1055682 · Report as offensive
Profile Jaye Ellen

Send message
Joined: 29 Nov 08
Posts: 26
Credit: 20,945,032
RAC: 45
United States
Message 1055693 - Posted: 13 Dec 2010, 18:49:37 UTC - in response to Message 1055677.  

Sorry about the double-post; I looked for the original posting but for whatever reason missed it. Thank you for the update on Worf's status!

Jaye Ellen
ID: 1055693 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 21400
Credit: 261,360,520
RAC: 489
Australia
Message 1055728 - Posted: 13 Dec 2010, 22:07:15 UTC - in response to Message 1055692.  

what am I doing wrong? Removed and reinstalled twice, can not get any work units. It is a small, slow machind but it WAS doing something for the cause, but now it does absolutely nothing. Any help is mucdh appreciated!

Jaye Ellen Burke

This is a question that should've been placed in the Number Crunching forum but if you had bothered to read the other posts in this thread you would've have posted this in the first place.

Cheers.
ID: 1055728 · Report as offensive
Profile Matt Lebofsky
Volunteer moderator
Project administrator
Project developer
Project scientist
Avatar

Send message
Joined: 1 Mar 99
Posts: 1444
Credit: 957,058
RAC: 0
United States
Message 1055763 - Posted: 14 Dec 2010, 0:02:45 UTC

It's late in the day so I don't feel like starting another thread, but the raid resync finished up and I just fired up the splitters. We'll see how this goes. I'm not entirely certain we're out of the woods yet.

- 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
ID: 1055763 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1055765 - Posted: 14 Dec 2010, 0:11:50 UTC - in response to Message 1055763.  

Thanks for the update Matt,

Claggy
ID: 1055765 · Report as offensive
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14349
Credit: 200,643,578
RAC: 874
United Kingdom
Message 1055769 - Posted: 14 Dec 2010, 0:30:24 UTC - in response to Message 1055763.  
Last modified: 14 Dec 2010, 0:33:11 UTC

It's late in the day so I don't feel like starting another thread, but the raid resync finished up and I just fired up the splitters. We'll see how this goes. I'm not entirely certain we're out of the woods yet.

- Matt

Matt, do you have time to check the upload servers? Still nothing shifting here, and not as much as I'd expect on Cricket, either.

Edit - OK, they seem to have started just as I typed. Now we just have congestion ;-)
ID: 1055769 · Report as offensive
Profile RottenMutt
Avatar

Send message
Joined: 15 Mar 01
Posts: 1011
Credit: 230,314,058
RAC: 0
United States
Message 1055775 - Posted: 14 Dec 2010, 1:18:18 UTC - in response to Message 1055763.  
Last modified: 14 Dec 2010, 2:18:13 UTC

It's late in the day so I don't feel like starting another thread, but the raid resync finished up and I just fired up the splitters. We'll see how this goes. I'm not entirely certain we're out of the woods yet.

- Matt

One word, ZFS.

ZFS don't need to rebuild the empty space. Does this server have a hardware raid solution? I thing software raid is faster now, especially since multiple core processors. Also in the same sence that software modems gave you a lower ping in on line games.
ID: 1055775 · Report as offensive
Profile RottenMutt
Avatar

Send message
Joined: 15 Mar 01
Posts: 1011
Credit: 230,314,058
RAC: 0
United States
Message 1055778 - Posted: 14 Dec 2010, 1:40:15 UTC - in response to Message 1055515.  

FYI, a disk failure on worf (the raw data storage server) which locked up the RAID requiring a cold reboot (and nobody is around/able to get up to the lab to do so). Only public downside is we ran out of work to send. This'll get fixed Monday morning.

- Matt

No hot spare! Never seen a degraded array which needed a reboot.
ID: 1055778 · Report as offensive
Profile RottenMutt
Avatar

Send message
Joined: 15 Mar 01
Posts: 1011
Credit: 230,314,058
RAC: 0
United States
Message 1055802 - Posted: 14 Dec 2010, 3:41:34 UTC - in response to Message 1055778.  
Last modified: 14 Dec 2010, 4:00:01 UTC

lots of work is flowing out, looks like the splitters kept running at least for a while when the hiccup happened.

edit, results ready to send is building. one has to wonder why the download server can't keep up, denial of service as has been posted many times before sounds like the culprit.
ID: 1055802 · Report as offensive
Josef W. Segur
Volunteer developer
Volunteer tester

Send message
Joined: 30 Oct 99
Posts: 4504
Credit: 1,414,761
RAC: 0
United States
Message 1055844 - Posted: 14 Dec 2010, 5:54:12 UTC - in response to Message 1055802.  

...results ready to send is building. one has to wonder why the download server can't keep up, denial of service as has been posted many times before sounds like the culprit.

?? There's no reason to think the download servers couldn't deliver more work if the download link could handle it. In the first 5 hours after the splitters were turned on, the Schedulers told hosts to download more work than the link can handle. It would have taken over 116 Mbps of bandwidth to actually get the increase in "Results out in the field" delivered. The splitters are of course producing new work even faster, that's where the growth in ready to send comes from.
                                                                    Joe
ID: 1055844 · Report as offensive
David S
Volunteer tester
Avatar

Send message
Joined: 4 Oct 99
Posts: 18352
Credit: 27,761,924
RAC: 12
United States
Message 1055915 - Posted: 14 Dec 2010, 11:39:03 UTC
Last modified: 14 Dec 2010, 11:43:55 UTC

It looks like something happened again overnight. Ready to send is back down to 1 as of 0530 CST. Four splitters are showing "Not running." [edit]That's four out of five mb splitters down, in addition to the two ap splitters that were disabled last night and still are.[/edit]

It appears I got one new task, though.

David
David
Sitting on my butt while others boldly go,
Waiting for a message from a small furry creature from Alpha Centauri.

ID: 1055915 · Report as offensive
-ShEm-
Volunteer tester

Send message
Joined: 25 Feb 00
Posts: 139
Credit: 4,129,448
RAC: 0
Message 1055917 - Posted: 14 Dec 2010, 11:48:33 UTC - in response to Message 1055915.  
Last modified: 14 Dec 2010, 11:50:35 UTC

It looks like something happened again overnight. Ready to send is back down to 1 as of 0530 CST. Four splitters are showing "Not running." [edit]That's four out of five mb splitters down, in addition to the two ap splitters that were disabled last night and still are.[/edit]

It appears I got one new task, though.

David

Look a few cm's to the right of where you looked and all will be revealed (hint: Splitter Status - MB-tape-progress)
ID: 1055917 · Report as offensive
Profile soft^spirit
Avatar

Send message
Joined: 18 May 99
Posts: 6497
Credit: 34,134,168
RAC: 0
United States
Message 1055921 - Posted: 14 Dec 2010, 12:14:14 UTC

What strikes me is with the splitters offline (empty it appears, except for AP)
that the bandwidth has stayed maxed for over 2 hours.
Janice
ID: 1055921 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 21400
Credit: 261,360,520
RAC: 489
Australia
Message 1055922 - Posted: 14 Dec 2010, 12:15:03 UTC - in response to Message 1055917.  

It looks like something happened again overnight. Ready to send is back down to 1 as of 0530 CST. Four splitters are showing "Not running." [edit]That's four out of five mb splitters down, in addition to the two ap splitters that were disabled last night and still are.[/edit]

It appears I got one new task, though.

David

Look a few cm's to the right of where you looked and all will be revealed (hint: Splitter Status - MB-tape-progress)

Yep Oscar sure made short work of those files but I'm sure that someone will throw several more in in the morning. ;)

Cheers.
ID: 1055922 · Report as offensive
Profile AnneBrodie
Avatar

Send message
Joined: 16 Jul 00
Posts: 4
Credit: 246,319
RAC: 0
United Kingdom
Message 1056097 - Posted: 14 Dec 2010, 21:04:26 UTC - in response to Message 1053678.  

Einsein defo slows my computer up.
'In the depths of the lunatic asylum, the Bossybabe is queen' Shakespeare [not Bill - his sister]
ID: 1056097 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5

Message boards : Technical News : Up (Dec 07 2010)


 
©2021 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.