Messages in this thread | | | Date | Thu, 18 Dec 2008 15:37:52 +0100 | From | Ingo Molnar <> | Subject | Re: [Bug #12208] uml is very slow on 2.6.28 host |
| |
* Mike Galbraith <efault@gmx.de> wrote:
> On Tue, 2008-12-16 at 16:27 +0100, Miklos Szeredi wrote: > > > Is there a way to trace what is happening in the scheduler? > > Sure. Ingo has a script for gathering info (attached), if you run it, > please gzip up the output and send me a copy offline to eyeball. > > There's also ftrace, but I've not tried that yet, so can't offer any > advice, I use primitive but effective time_after() + printk() with klogd > wakeup disabled (deadlock).
btw., there's a recent commit:
32a7600: printk: make printk more robust by not allowing recursion
since then printk shouldnt deadlock anymore, even if called from within the scheduler.
Btw., ftrace_printk() can be used similarly (and you can capture it nonstop via /debug/tracing/trace_pipe), and should not deadlock either.
Ingo
| |