On 12/05/2010 09:16 PM, Chen Guo wrote: > Before saying anything else, I should note that for mutexes, on 4 > threads 20% of the time there's a segfault on a seemingly innocuous > line in queue_insert (): > node->queued = true
It does sound like mutexes are the way to go, and that this bug needs to be fixed. I assume that this is the call to queue_insert from queue_check_insert_parent? What's the backtrace? (And what patch are you using, to get mutexes?)
