GNU/Linux S5R3 App 4.14 available for Beta test

Bikeman (Heinz-Bernd Eggenstein)
Bikeman (Heinz-...
Moderator
Joined: 28 Aug 06
Posts: 3522
Credit: 686209377
RAC: 552085

RE: RE: RE: reiserfs,

Message 74673 in response to message 74671

Quote:
Quote:
Quote:
reiserfs, but it gives me no problem with either SETI and QMC.

Well, the immediate syncing is a new feature, currently probably unique to E@h. ReiserFS is rather unusual, in fact I have not used it for years (and not tested the App on this); this might be the reason for the problems you see. Try to switch off syncing.

BM

I'm also using reiserfs and the next WU that gets downloaded will be crunched by the 4.14 app, so we might see if I get this error too.

Btw, Bernd, did you read my report about a lot of errors with the 4.09 app on a system under heavy load in the 4.09 thread? Since the code didn't change so much, this might still be relevant with 4.14.

cu,
Michael

I'm using ReiserFs (it used to be Suse's default FS some time ago IIRC) without any problem so far with 4.14 on one host. So it's not a general ReiserFS problem .

CU

H-B

Donald A. Tevault
Donald A. Tevault
Joined: 17 Feb 06
Posts: 439
Credit: 73516529
RAC: 0

RE: RE: RE: RE: reise

Message 74674 in response to message 74673

Quote:
Quote:
Quote:
Quote:
reiserfs, but it gives me no problem with either SETI and QMC.

Well, the immediate syncing is a new feature, currently probably unique to E@h. ReiserFS is rather unusual, in fact I have not used it for years (and not tested the App on this); this might be the reason for the problems you see. Try to switch off syncing.

BM

I'm also using reiserfs and the next WU that gets downloaded will be crunched by the 4.14 app, so we might see if I get this error too.

Btw, Bernd, did you read my report about a lot of errors with the 4.09 app on a system under heavy load in the 4.09 thread? Since the code didn't change so much, this might still be relevant with 4.14.

cu,
Michael

I'm using ReiserFs (it used to be Suse's default FS some time ago IIRC) without any problem so far with 4.14 on one host. So it's not a general ReiserFS problem .

CU

H-B

Same here. I have ReiserFS installed on several machines. Two are currently running, happily crunching away with the Einstein 4.14 app. So far, no problems at all.

tullio
tullio
Joined: 22 Jan 05
Posts: 2118
Credit: 61407735
RAC: 0

All I can say is that 4.02 is

All I can say is that 4.02 is crunching the same WU that gave errors in 4.14 with no problem at all. All went well up to 4.12.
Tullio

M. Schmitt
M. Schmitt
Joined: 27 Jun 05
Posts: 478
Credit: 15872262
RAC: 0

RE: RE: Bernd, did you

Message 74676 in response to message 74672

Quote:
Quote:
Bernd, did you read my report about a lot of errors with the 4.09 app on a system under heavy load in the 4.09 thread? Since the code didn't change so much, this might still be relevant with 4.14.

I read it. The signal handler used in 4.14 is supposed to give some more information about what's happening there. Actually I'm hoping this error occurs with a 4.14 App. Maybe you can help reproduce it?

BM

While running one 4.09 and one 4.12 WU, I tried really hard to reproduce the error, but without luck. I managed to reach an average 1 minute load of about 12 and system again was barely responsive sometimes. But responsiveness was better than last time when the errors occurred.

Maybe I must concentrate on disk I/O on the reiserfs, where the BOINC folder is located and not generally shared over all disks. I'll give this another try, probably at the weekend.

cu,
Michael

Mikie Tim T
Mikie Tim T
Joined: 22 Jan 05
Posts: 105
Credit: 263777741
RAC: 0

I started 87897850 with 4.09,

I started 87897850 with 4.09, but finished it with 4.14. It ran and validated successfully, and this system runs reiserfs as well. The time dropped noticeably from 4.09 as well.

th3
th3
Joined: 24 Aug 06
Posts: 208
Credit: 2208434
RAC: 0

Hope things get sorted out

Hope things get sorted out fast so a new official GNU/Linux app can come out soon, the linux rig that used to be #2 has dropped to #19 since S5R3 started, linux users have taken a serious RAC drop with 4.02.

The performance of 4.12/4.14 is beautiful, my xeon reached #80 in the top hosts list today. Doesnt sound very impressive maybe, but considered its only a single socket dual core i think its great. But... Without 4.02 it wouldnt be possible for my rig to go there, single socket quads running Linux/4.02 have fallen out of the Top100 at an increasing rate.

Donald A. Tevault
Donald A. Tevault
Joined: 17 Feb 06
Posts: 439
Credit: 73516529
RAC: 0

You might know, right after

You might know, right after I'd said that I'd never had trouble with the 4.14 app and ReiserFS, two 4.14 workunits simultaneously fail on my Compaq dual-processor P-III 733 machine.

For anyone who needs to look at this, its ID number is 764145.

For the record, it's running Feisty Fawn Ubuntu from a SCSI hard drive that's formatted with ReiserFS. I don't know that it is Reiser-related, but wanted to let everyone know just-in-case.

th3
th3
Joined: 24 Aug 06
Posts: 208
Credit: 2208434
RAC: 0

Maybe give 4.12 a try, its as

Maybe give 4.12 a try, its as fast as 4.14 and hopefully doesnt have this problem...

4.12

Donald A. Tevault
Donald A. Tevault
Joined: 17 Feb 06
Posts: 439
Credit: 73516529
RAC: 0

RE: Maybe give 4.12 a try,

Message 74681 in response to message 74680

Quote:

Maybe give 4.12 a try, its as fast as 4.14 and hopefully doesnt have this problem...

4.12

I'll keep that in mind. But, since this is the only problem I've had with 4.14 so far, I'll give this machine one more chance, first.

Bikeman (Heinz-Bernd Eggenstein)
Bikeman (Heinz-...
Moderator
Joined: 28 Aug 06
Posts: 3522
Credit: 686209377
RAC: 552085

And after all, this is beta

And after all, this is beta software, so basically every error detected here will actually help to improve the app. This means running the risk of losing a few credits but every undetected error that goes into production might cost you credits as well (or wasted electricity, if you are not afetr credits).

CU

Bikeman

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.