[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Condor-users] AMD Opteron Crashes




On Mar 7, 2005, at 11:35 AM, Steffen Grunewald wrote:

On Mon, Mar 07, 2005 at 11:21:15AM +0100, Steffen Prohaska wrote:
Prashant,

On Mar 7, 2005, at 8:04 AM, Prashant Lal wrote:

Yes in my cluster also it is working fine.

May I know what the error actually you are getting?

Using linux-glibc23 on x86_64 I don't get a real error. SchedLog only tells that the Starter died with a SEGFAULT.

3/7 11:12:39 Starter pid 26885 died on signal 11 (signal 11)

The last lines in the StarterLog are

...
3/7 11:12:39 (fd:11) Doing CONDOR_register_starter_info
3/7 11:12:39 (fd:11) ShouldTransferFiles is "NO", NOT transfering files
3/7 11:12:39 (fd:11) Submit UidDomain: "zib.de"
3/7 11:12:39 (fd:11) Local UidDomain: "zib.de"
3/7 11:12:39 (fd:11) Initialized user_priv as "bzfproha"


No error is reported, the starter silently dies.

Did you try to increase the verbosity level? (STARTER_DEBUG = D_ALL, or even ALL_DEBUG = D_ALL)

Yes, STARTER_DEBUG = D_ALL is set.

	Steffen

--
Steffen Prohaska <prohaska@xxxxxx>  <http://www.zib.de/prohaska/>
Zuse Institute Berlin, Takustraße 7, D-14195 Berlin-Dahlem, Germany
+49 (30) 841 85-337, fax -107
1024D/DA749299 print 8B59 83A8 A43D E0E2 DEDB   D479 3157 2FEA DA74 9299

Attachment: PGP.sig
Description: This is a digitally signed message part