Machine freezes without (apparent) reason...
Hello, I apologize in advance if the subject I'm about to discuss is not directly related to SuSE Linux. We have in our lab an Opteron machine (Tyan S2882 motherboard, latest BIOS version, 2 Opteron 242 processors and 2 GB of memory) running SuSE Linux 9.0. The system freezes after several hours of being functioning without sending any message, it just stops responding until it is rebooted. I suppose there is a hardware problem but before sending the machine for maintenance I would like to know the cause of the problem. I have searched the suse-amd64 list for related problems, somebody pointed out in a similar case that maybe the memory is damaged so I tested the memory using memtest86 but it did not find errors. Any clue? Thanks. - Jose Luis
On Tue, 18 May 2004, RICARDO CHAVEZ J. L. wrote: Which bios version? I had the same problem with every 1.x At the moment I run latest beta without problems. I would try that. Cheers, Andrej
Hello,
I apologize in advance if the subject I'm about to discuss is not directly related to SuSE Linux. We have in our lab an Opteron machine (Tyan S2882 motherboard, latest BIOS version, 2 Opteron 242 processors and 2 GB of memory) running SuSE Linux 9.0. The system freezes after several hours of being functioning without sending any message, it just stops responding until it is rebooted. I suppose there is a hardware problem but before sending the machine for maintenance I would like to know the cause of the problem. I have searched the suse-amd64 list for related problems, somebody pointed out in a similar case that maybe the memory is damaged so I tested the memory using memtest86 but it did not find errors. Any clue?
Thanks.
- Jose Luis
-- Check the List-Unsubscribe header to unsubscribe For additional commands, email: suse-amd64-help@suse.com
_____________________________________________________________ doc. dr. Andrej Filipcic, E-mail: Andrej.Filipcic@ijs.si Department of Experimental High Energy Physics - F9 Jozef Stefan Institute, Jamova 39, P.o.Box 3000 SI-1001 Ljubljana, Slovenia Tel.: +386-1-477-3674 Fax: +386-1-425-7074 -------------------------------------------------------------
Andrej Filipcic wrote:
On Tue, 18 May 2004, RICARDO CHAVEZ J. L. wrote:
Which bios version? I had the same problem with every 1.x At the moment I run latest beta without problems. I would try that.
Cheers,
Andrej
Hello,
I apologize in advance if the subject I'm about to discuss is not directly related to SuSE Linux. We have in our lab an Opteron machine (Tyan S2882 motherboard, latest BIOS version, 2 Opteron 242 processors and 2 GB of memory) running SuSE Linux 9.0. The system freezes after several hours of being functioning without sending any message, it just stops responding until it is rebooted. I suppose there is a hardware problem but before sending the machine for maintenance I would like to know the cause of the problem. I have searched the suse-amd64 list for related problems, somebody pointed out in a similar case that maybe the memory is damaged so I tested the memory using memtest86 but it did not find errors. Any clue?
Thanks.
- Jose Luis
-- Check the List-Unsubscribe header to unsubscribe For additional commands, email: suse-amd64-help@suse.com
_____________________________________________________________ doc. dr. Andrej Filipcic, E-mail: Andrej.Filipcic@ijs.si Department of Experimental High Energy Physics - F9 Jozef Stefan Institute, Jamova 39, P.o.Box 3000 SI-1001 Ljubljana, Slovenia Tel.: +386-1-477-3674 Fax: +386-1-425-7074 -------------------------------------------------------------
Hi Andrej, The BIOS version is 2.01, I haven't yet tried the newest beta version. Cheers, - Jose Luis
On Tue, May 18, 2004 at 06:52:29PM +0200, RICARDO CHAVEZ J. L. wrote:
I apologize in advance if the subject I'm about to discuss is not directly related to SuSE Linux. We have in our lab an Opteron machine (Tyan S2882 motherboard, latest BIOS version, 2 Opteron 242 processors and 2 GB of memory) running SuSE Linux 9.0. The system freezes after several hours of being functioning without sending any message, it just stops responding until it is rebooted. I suppose there is a hardware problem but before sending the machine for maintenance I would like to know the cause of the problem. I have searched the suse-amd64 list for related problems, somebody pointed out in a similar case that maybe the memory is damaged so I tested the memory using memtest86 but it did not find errors. Any clue?
Do you run 32bit programs a lot? Some early BIOS had bugs that could cause freezes in this area (they missed a required workaround for a CPU issue). If that's the case then an BIOS update should fix it. -Andi
Andi Kleen wrote:
On Tue, May 18, 2004 at 06:52:29PM +0200, RICARDO CHAVEZ J. L. wrote:
I apologize in advance if the subject I'm about to discuss is not directly related to SuSE Linux. We have in our lab an Opteron machine (Tyan S2882 motherboard, latest BIOS version, 2 Opteron 242 processors and 2 GB of memory) running SuSE Linux 9.0. The system freezes after several hours of being functioning without sending any message, it just stops responding until it is rebooted. I suppose there is a hardware problem but before sending the machine for maintenance I would like to know the cause of the problem. I have searched the suse-amd64 list for related problems, somebody pointed out in a similar case that maybe the memory is damaged so I tested the memory using memtest86 but it did not find errors. Any clue?
Do you run 32bit programs a lot? Some early BIOS had bugs that could cause freezes in this area (they missed a required workaround for a CPU issue). If that's the case then an BIOS update should fix it.
-Andi
The machine is part of a cluster, maybe some users are running 32-bit programs, I have updated the BIOS to the latest version but since I have already seen Opteron machines crashing due to 32-bit programs, I will investigate. Thanks for the suggestion. - Jose Luis
Do you have a 3ware RAID card? It may not work with S2882: see http://forums.storagereview.net/index.php?showtopic=14162 RICARDO CHAVEZ J. L. wrote:
Andi Kleen wrote:
On Tue, May 18, 2004 at 06:52:29PM +0200, RICARDO CHAVEZ J. L. wrote:
I apologize in advance if the subject I'm about to discuss is not directly related to SuSE Linux. We have in our lab an Opteron machine (Tyan S2882 motherboard, latest BIOS version, 2 Opteron 242 processors and 2 GB of memory) running SuSE Linux 9.0. The system freezes after several hours of being functioning without sending any message, it just stops responding until it is rebooted. I suppose there is a hardware problem but before sending the machine for maintenance I would like to know the cause of the problem. I have searched the suse-amd64 list for related problems, somebody pointed out in a similar case that maybe the memory is damaged so I tested the memory using memtest86 but it did not find errors. Any clue?
Do you run 32bit programs a lot? Some early BIOS had bugs that could cause freezes in this area (they missed a required workaround for a CPU issue). If that's the case then an BIOS update should fix it.
-Andi
The machine is part of a cluster, maybe some users are running 32-bit programs, I have updated the BIOS to the latest version but since I have already seen Opteron machines crashing due to 32-bit programs, I will investigate. Thanks for the suggestion.
- Jose Luis
participants (4)
-
Andi Kleen -
Andrej Filipcic -
RICARDO CHAVEZ J. L. -
Zhenlei Cai