NetBSD-Bugs archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

kern/55299: DTrace runs into triple fault



>Number:         55299
>Category:       kern
>Synopsis:       DTrace runs into triple fault
>Confidential:   no
>Severity:       serious
>Priority:       medium
>Responsible:    kern-bug-people
>State:          open
>Class:          sw-bug
>Submitter-Id:   net
>Arrival-Date:   Mon May 25 04:40:00 +0000 2020
>Originator:     Roland Illig
>Release:        8.0
>Organization:
>Environment:
NetBSD nb8.roland-illig.de 8.0 NetBSD 8.0 (GENERIC.PROF) #0: Sun May 17 14:12:24 UTC 2020  rillig%nb8.roland-illig.de@localhost:/home/rillig/proj/src8/sys/arch/amd64/compile/GENERIC.PROF amd64
>Description:
When I wanted to know why some read(2) and write(2) calls were unreasonably slow inside a VirtualBox VM, I was suggested to try DTrace to trace down the root cause.

I tried that, and got a triple fault.

(See https://gnats.netbsd.org/55271 for another try to get to the root cause.)

cat > read-triple-fault.d <<EOF
#pragma D option flowindent

syscall::read:entry
/execname == "wc" && guard++ == 0/
{
        self->traceme = 1;
}

fbt:::
/self->traceme/
{
        printf("%d\n", walltimestamp);
}

syscall::read:return
/self->traceme/
{
        self->traceme = 0;
}
EOF

dtrace -s read-triple-fault.d
wc -l /netbsd

>How-To-Repeat:

>Fix:



Home | Main Index | Thread Index | Old Index