Here is my get_ltrace.sh script (at the end).

So I read the preempt_max_latency (to see if its changed) before
I copy the latency_trace output. I am not so sure that cat is
really doing an "atomic" read when some of the latency traces
are over 300 Kbytes in length.

Also note that some of the files were empty :-(. I don't think
I've seen that symptom before.

Note that the preempt_max_latency value DID match the last line of
the trace output in the example I described. It is just the header
that had some stale data in it.

  --Mark

--- get_ltrace.sh ---

#!/bin/sh

let MAX=`cat /proc/sys/kernel/preempt_max_latency`
let I=0 J=1
let MP=${1:-1000}
echo "Current Maximum is $MAX, limit will be $MP."
while (( I < 100 )) ; do
    sleep 1s
    let NOW=`cat /proc/sys/kernel/preempt_max_latency`
    if (( MAX != NOW )) ; then
        echo "New trace $I w/ $NOW usec latency."
        cat /proc/latency_trace > lt.`printf "%02d" $I`
#       sync ; sync
        let I++
        let MAX=NOW
    elif (( J++ >= 10 )) ; then
        if (( MAX != MP )) ; then
            echo "Resetting max latency from $MAX to $MP."
            echo $MP > /proc/sys/kernel/preempt_max_latency
            let MAX=$MP
        else
            echo "No new latency samples at `date`."
        fi
        let J=1
# else do nothing...
    fi
done

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/