Hi! > I'm curious - what exactly do people find they can run reliably with no > hangs on a known good system? On ec2 instances I find even runltp -f > syscalls to hang. I know, I know :) I do intend to look into it. But > is there anything people find they can use as a gross "this works on good > kernel, let's see if it breaks on test kernel" metric?
That is probably sched_yield() testcase, the culprit is writing to stderr while plaing the ping pong with sched_yield() which would make the disk writing thread lock (not really kernel bug as the test blocked all cpus but one which on which it plays ping pong with sched_yield()). At least it locks with some older kernels. I will commit a patch that just removes useless printf(). -- Cyril Hrubis [email protected] ------------------------------------------------------------------------------ uberSVN's rich system and user administration capabilities and model configuration take the hassle out of deploying and managing Subversion and the tools developers use with it. Learn more about uberSVN and get a free download at: http://p.sf.net/sfu/wandisco-dev2dev _______________________________________________ Ltp-list mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/ltp-list
