Displaying 7 results from an estimated 7 matches for "walltimestamp".
2007 Jul 25
2
proc:::exit not firing
...begin script ---
proc:::signal-send
/args[1]->pr_pid == $target/
{
last_signal = args[2];
last_signal_sender_pid = pid;
last_signal_sender_name = execname;
}
proc:::exit
/pid == $target && args[0] == CLD_EXITED/
{
printf( "%Y normal exit.", walltimestamp );
ustack();
}
proc:::exit
/pid == $target && args[0] == CLD_KILLED/
{
printf( "%Y exited by signal. signal=%d, sent by=%s (%d)",
walltimestamp,
last_signal,
last_signal_sender_name,...
2008 Nov 08
4
Variable mpid - what is it?
DTraceToolkit has a dtrace script (Proc/pidpersec.d) that refers to a
variable mpid as below
profile:::tick-1sec
{
printf("%-22Y %8d %6d\n", walltimestamp, `mpid, pids);
pids = 0;
}
Where is `mpid getting picked from (it isn''t declared anywhere else)?
What does the character ` in `mpid signify?
I do not see any reference to this variable in the dtrace manual/user-guide.
-Shiv
2006 Oct 24
15
How to emit associative array after ^C
Boy am I a dummy. I want to simply dump out unfreed allocations when I terminate the script. What''s the secret sauce?
#!/usr/sbin/dtrace -s
pid$1::MyAlloc:return
{
bufs[arg1] = walltimestamp;
}
pid$1::MyFree:entry
/bufs[arg0]/
{
bufs[arg0] = 0;
}
This message posted from opensolaris.org
2008 Feb 12
1
measuring sleep time in synchronization objects
...semaphore, i.e., as a result of sem_wait() call. In order to measure this, I
wrote a script with sched:::sleep and sched:wakeup probes enabled, as shown
below:
sched:::sleep
/execname == "myexecname"/
{
ustack();
bedtime[curlwpsinfo->pr_addr,curlwpsinfo->pr_stype] = walltimestamp;
}
sched:::wakeup
/bedtime[args[0]->pr_addr,args[0]->pr_stype]/
{
@sleeptime[execname,args[0]->pr_lwpid,args[0]->pr_addr,args[0]->pr_stype] =
sum(walltimestamp - bedtime[args[0]->pr_addr,args[0]->pr_stype]);
bedtime[args[0]->pr_addr,args[0]->pr_stype] = 0;...
2008 Apr 20
1
dtrace script to monitor file access
...ntry, syscall::creat:entry,
syscall::open64:entry, syscall::creat64:entry,
syscall::unlink:entry, syscall::rename:entry
/strstr(stringof(copyinstr(arg0)), $1) != NULL/
{
printf("%Y %5d %5d %5d %5d %-12s %-10s %25s %s\n",
walltimestamp, gid, uid, pid, ppid, execname, probefunc, cwd, stringof(copyinstr(arg0)));
}
The script is invoked with:
./lsfacc ''"userfile"''
Is this a good approach or is there a better one?
Occassionally the script produces errors that look like:
dtrace: err...
2007 Feb 12
17
NFS/ZFS performance problems - txg_wait_open() deadlocks?
Hi.
System is snv_56 sun4u sparc SUNW,Sun-Fire-V440, zil_disable=1
We see many operation on nfs clients to that server really slow (like 90 seconds for unlink()).
It''s not a problem with network, there''s also plenty oc CPU available.
Storage isn''t saturated either.
First strange thing - normally on that server nfsd has about 1500-2500 number of threads.
I did
2007 May 02
41
gzip compression throttles system?
I just had a quick play with gzip compression on a filesystem and the
result was the machine grinding to a halt while copying some large
(.wav) files to it from another filesystem in the same pool.
The system became very unresponsive, taking several seconds to echo
keystrokes. The box is a maxed out AMD QuadFX, so it should have plenty
of grunt for this.
Comments?
Ian