Messages in this thread | | | Date | Mon, 10 Jan 2000 11:09:40 -0800 (PST) | From | Robert Dinse <> | Subject | SS-10 SMP Sparc Linux 2.2.14 spin_lock hang. |
| |
Had another crash of SS-10 w quad RTK-625 CPU's and 384MB of RAM running Apache 1.3.3p3 under Sparc-32 linux 2.2.14 SMP.
spin_lock_irqsave(e8c3066c) CPU#0 stuck at f00c3f10, owner PC(00000000):CPU(0) spin_lock(f014b49ac) CPU#1 stuck at f002e3d8, owner PC(f002e3d8):CPU(0) spin_lock(f014b49ac) CPU#2 stuck at f002e3d8, owner PC(f002e3d8):CPU(0) spin_lock(f014b49ac) CPU#3 stuck at f002e3d8, owner PC(f002e3d8):CPU(0)
>>PC; f00c3f10 <rpc_clnt_sigunmask+30/94> <===== >>PC; 00000000 Before first symbol Trace; e8c3066c Before first symbol >>PC; f002e3d8 <patchme_store_new_current+9c/338> <===== >>PC; f002e3d8 <patchme_store_new_current+9c/338> <===== Trace; 0000000f014b49ac <END_OF_CODE+e112f7648/????> >>PC; f002e3d8 <patchme_store_new_current+9c/338> <===== >>PC; f002e3d8 <patchme_store_new_current+9c/338> <===== Trace; 0000000f014b49ac <END_OF_CODE+e112f7648/????> >>PC; f002e3d8 <patchme_store_new_current+9c/338> <===== >>PC; f002e3d8 <patchme_store_new_current+9c/338> <===== Trace; 0000000f014b49ac <END_OF_CODE+e112f7648/????>
There are some things in common with the last crash, CPU 0 was stuck at f00c3f10 in both crashes. CPUs 1, 2, and 3, stuck at f002e3d8 in both crashes.
Configuration is same as last two crashes I posted. The above sequence of messages just prints over and over again about once a second.
In addition to the crashes being less frequent than under 2.2.13, the pattern is also different. Under 2.2.13, most of the time all of the CPU's would be hung on spin_lock() mesages and spin_lock_irqsave() would show up relatively in infrequently. Now one CPU always hung on spin_lock_irqsave with the other three on spin_lock.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |