On 12/12/2011 03:09 PM, Christoph Hellwig wrote:
Running the current master tree I reproducibly get the following softlockup when running xfstests 078 on a tcm_loop/iblock device: [ 968.113575] BUG: soft lockup - CPU#0 stuck for 22s! [LIO_iblock:2133] [ 968.116635] CPU 0 [ 968.116635] [ 968.116635] Pid: 2133, comm: LIO_iblock Not tainted 3.2.0-rc4+ #76 Bochs Bochs
On my machine I see: F S UID PID PPID C PRI NI ADDR SZ WCHAN TTY TIME CMD 5 S 0 7 2 0 -40 - - 0 watchd ? 00:00:00 watchdog/0 1 S 0 747 2 0 80 0 - 0 transp ? 00:00:00 LIO_fileio so the watchdog thread has a higher priority compared to LIO_'s worker thread. I don't see any locks which are hold within transport_processing_thread() for a long time. That means that you should be re-scheduled at least between taking a new work item. Is this a NON-PREEMPT config? Sebastian -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
