Messages in this thread | | | From | Tyler Earman <> | Date | Sun, 24 Apr 2011 14:15:54 -0500 | Subject | Massive load average spikes tracing the cause |
| |
Please CC me if you would.
Basically, I'm running a machine that will have massive load average spikes (up into the 5-10 range on a 2 CPU machine) at seemingly random intervals. I've tried most normal tracing conventions but now I'm going to have to delve into the kernel to find out exactly what's going on here.
The kernel does softlock occasionally on this event, but the CPU usage stays very low (1-10%).
I'm guessing this is an I/O lockup somewhere, but the question is /where/.
So, in short, how would I go about hooking into the kernel directly to try and find these problems? Is there a way to watch just about everything going on when these events happen?
Thanks for the help, Tyler
| |