What's the policy WRT integer overflow in aggregations? From what I
can tell, it's just silently ignored. Is this the de facto policy?
(I can't find any mention of it in the dtrace doc nor in the
dtrace-discuss archives.)
For example, /usr/src/uts/common/dtrace/dtrace.c defines this function:
Dan Price pointed out the confusing wording in the The planned
implementation invovles paragraph. Here's a better version:
SUMMARY
This fast-track enhances the DTrace utility to address an
existing RFE[1] requesting an aggregating function to calculate
standard
On 11/1/07, Alexander Kolbasov [EMAIL PROTECTED] wrote:
SUMMARY
This fast-track enhances the DTrace utility to address an
existing RFE[1] requesting an aggregating function to calculate
standard deviation, similar to the current aggregating function
for
I've been looking at this bug. What I think needs to be done is the following:
- In dt_proc_control(), create a separate dtrace handle with the
destructive option set.
- In dt_proc_bp_create() (or the equivalent-but-renamed function), do
something similar to the following instead of creating a
Sorry for the delay in the reply.
On Jan 7, 2008 1:27 PM, Adam Leventhal [EMAIL PROTECTED] wrote:
On Sun, Jan 06, 2008 at 08:37:32PM -0500, Chad Mynhier wrote:
I've been looking at this bug. What I think needs to be done is the
following:
[snip]
I've tried the above, and I see
On Feb 7, 2008 8:00 PM, Adam Leventhal [EMAIL PROTECTED] wrote:
Congratulations and thanks to Chad Mynhier for a substantial contribution
to DTrace! Chad has fixed a couple of bugs and added a standard deviation
aggregation action.
Chad, nice work; now how about an update to the wiki
come up to speed on understanding the Intel architecture
segmentation stuff, so I'm hoping someone can help out here.)
Thanks,
Chad Mynhier
___
dtrace-discuss mailing list
dtrace-discuss@opensolaris.org
On Thu, Apr 3, 2008 at 9:51 AM, Jonathan Adams [EMAIL PROTECTED] wrote:
I did notice that in .../uts/common/dtrace/dtrace.c you did:
9580 +case DTRACEACT_BRENDAN:
9581 +size = sizeof (uint64_t);
9582 +break;
On Thu, Apr 10, 2008 at 1:12 AM, Adam Leventhal [EMAIL PROTECTED] wrote:
On Apr 9, 2008, at 6:01 PM, Chad Mynhier [EMAIL PROTECTED] wrote:
I've written this tutorial, to be found here:
http://www.solarisinternals.com/wiki/index.php/DTrace_Topics_Adding_An_Action.
(I could move
Hey, Jon,
On Mon, Jul 14, 2008 at 5:42 AM, Jon Haslam [EMAIL PROTECTED] wrote:
3. Co-existence with existing tools
The provider has priority over per-LWP libcpc usage (i.e. cputrack)
for access to counters. In the same manner as cpustat, enabling probes
causes all existing per-LWP counter
Hey, Jon,
On Tue, Jul 15, 2008 at 11:15 AM, Jon Haslam [EMAIL PROTECTED] wrote:
Hi Chad,
Only one of cpustat and DTrace may use the counter hardware at any one
time.
Ownership of the counters is given on a first-come, first-served basis.
I'm curious, how does DTrace interact with DTrace
On Thu, Jul 24, 2008 at 2:12 PM, Chris Kiick [EMAIL PROTECTED] wrote:
Hi,
Searched for similar errors and nothing came up. Anybody know what this is?
When using aggregate stddev, and then trying to print it at END, using
printa, I get this error:
dtrace: processing aborted: Invalid return
On Fri, Jul 25, 2008 at 2:31 PM, Jonathan Adams [EMAIL PROTECTED] wrote:
On Thu, Jul 24, 2008 at 12:12:01PM -0700, Chris Kiick wrote:
Hi,
Searched for similar errors and nothing came up. Anybody know what this
is?
When using aggregate stddev, and then trying to print it at END, using
On Fri, Jul 25, 2008 at 3:08 PM, chris kiick [EMAIL PROTECTED] wrote:
On Fri, Jul 25, 2008 at 03:05:06PM -0500, Chad Mynhier wrote:
Chris, have you filed a bug for this? If not, I can do so. If so,
could you give me the number?
Thanks,
Chad
Hot off the press: CR6730130: dtrace missing
On Thu, Aug 7, 2008 at 4:31 PM, Mark Harrison [EMAIL PROTECTED] wrote:
Hi all,
I'm trying to write a dtrace script to print a list of files uploaded via
sftp. I have it working pretty well, except after the script has been running
for a few minutes, I get the dtrace: processing aborted: Abort
On Fri, Aug 8, 2008 at 10:07 AM, Mark Harrison [EMAIL PROTECTED] wrote:
As a workaround, you might try running with the -w flag (permit
destructive actions.) This will skip the deadman timeout processing.
(This will only work if you're running as root, though.)
I may end up doing that. I'm
On Fri, Aug 15, 2008 at 3:21 AM, [EMAIL PROTECTED] wrote:
Hi,
I am facing another problem with pid provider. I'd like to trace my
application but would like to not to trace libc and libnsl. I could use
predicate like /probemod != libc probemod != libnsl/ but having this
dtrace keeps
2008/8/15 [EMAIL PROTECTED]:
Původní zpráva
Od: Chad Mynhier [EMAIL PROTECTED]
Předmět: Re: [dtrace-discuss] pid: excluding libraries, modules
Datum: 15.8.2008 14:04:25
On Fri, Aug 15, 2008 at 3:21 AM, [EMAIL PROTECTED
2008/8/15 Chad Mynhier [EMAIL PROTECTED]:
I've not dug into the gmatch(3GEN) code yet, but I'd guess that it's
not matching because of the fully-qualified pathnames. Is this a bug
that just needs a basename(3C) call?
(I went looking for a bug that matches this, but I couldn't find
anything
for everything.
On Thu, Sep 18, 2008 at 9:00 PM, Aubrey Li [EMAIL PROTECTED] wrote:
On Fri, Sep 19, 2008 at 12:20 AM, Chad Mynhier [EMAIL PROTECTED] wrote:
On Wed, Sep 17, 2008 at 9:43 PM, Aubrey Li [EMAIL PROTECTED] wrote:
I didn't dig into the dtrace problem, just wonder is this expected
Executive summary:
If PR_KLC is set for a process, should Prelease() cause the process to
be killed?
Details:
I've been looking at 6712247 (dtrace -c runs the program despite
errors), and it looks like libdtrace expects Prelease() to terminate
a process if PR_KLC is set. The code that shows
I've done a clean build of fresh sources pulled down, and I'm getting
core dumps using the version of libdtrace that was built from a full
nightly (with no error messages.)
Here's what I see on a system bfu'd from these archives:
# dtrace -n syscall:::entry
Segmentation Fault - core dumped
#
On Thu, Oct 9, 2008 at 12:47 AM, Jonathan Adams [EMAIL PROTECTED] wrote:
On Wed, Oct 08, 2008 at 10:26:02PM -0400, Chad Mynhier wrote:
I've done a clean build of fresh sources pulled down, and I'm getting
core dumps using the version of libdtrace that was built from a full
nightly
On Mon, Oct 20, 2008 at 11:33 AM, P. Remek [EMAIL PROTECTED] wrote:
Hi,
I am using pid provider and I have noticed that return probe is not fired when
leaving function with variable number of arguments using va_start and va_stop.
Having such code:
log() {
va_start(ap, fmt);
Contributed by Chad Mynhier [EMAIL PROTECTED].
Doh!)
Chad
___
dtrace-discuss mailing list
dtrace-discuss@opensolaris.org
One of the scripts in the DTrace manual contains a bug. (I searched
the archives for this list but didn't find any previous mention of
this.)
In the chapter for the sched provider, this script is presented as a
way to measure CPU latency:
On Thu, Dec 11, 2008 at 11:53 AM, Chad Mynhier cmynh...@gmail.com wrote:
Doh! I'll point out my own bug:
This script should actually be the following:
#!/usr/sbin/dtrace -qs
sched:::enqueue
{
self-ts
On Sat, Jan 17, 2009 at 12:43 AM, Qihua Wu dtrace...@gmail.com wrote:
I want to trace function whose name has certain value, such as read or
write. But seems dtrace can't replace the variable with the value I passed
in.
bash-3.00$ cat d.d
#!/usr/sbin/dtrace -s
#pragma D option flowindent
On Tue, Jan 20, 2009 at 6:23 AM, Chad Mynhier cmynh...@gmail.com wrote:
If you don't care about the stack per se, and if it's available to you
(I don't know off the top of my head which version this went back
into), you could also just aggregate on the kernel function using
'@c[func(arg0
On Wed, Jan 21, 2009 at 3:41 PM, River Tarnell
ri...@loreley.flyingparchment.org.uk wrote:
Edward Pilatowicz:
fsflush isn't a real process. it's actually a bunch of kernel threads
that look like a processes so it can't be grabbed / stopped.
this was my understanding - which makes me wonder
On Sat, Jan 17, 2009 at 5:28 PM, Chad Mynhier cmynh...@gmail.com wrote:
For example, the following works (at least on build
105, I don't have a stock Solaris 10 system handy at the moment):
#!/usr/sbin/dtrace -s
syscall::$1:entry
{
@c[execname,probefunc] = count();
}
# ./count
Are there any subtle reasons why DTrace can't treat stack traces as
first-class objects? They're already slightly better than
second-class objects because we can use them as the key to
aggregations, but we can't assign them as variables.
(Note, I haven't looked closely at the code yet to see
On Wed, Feb 18, 2009 at 1:01 PM, Michael Mueller
m...@michael-mueller-it.de wrote:
Hi all,
Is there some documentation or some example on how to interpret the arg0
.. argn for the aioread, aiowrite, aiowait syscalls? The system call
name for all three seems to be kaio.
Michael
When you
What should the behavior of 'dtrace -c' be when dtrace(1M) exits
before the target command? Should the target process be killed, or
should the target process continue running?
Currently, the target process keeps running, but this also happens in
the case when dtrace(1M) exits with an error (see
On Fri, Mar 20, 2009 at 2:35 PM, Chip Bennett cbenn...@laurustech.com wrote:
What should the behavior of 'dtrace -c' be when dtrace(1M) exits
before the target command? Should the target process be killed, or
should the target process continue running?
Currently, the target process keeps
On Wed, Apr 1, 2009 at 12:41 PM, Michael Schuster
michael.schus...@sun.com wrote:
All,
from reading of the DTrace documentation, eg. at
http://wikis.sun.com/display/DTrace/pid+Provider, I got the impression that
I could do something like
dtrace -n 'pid$target:mylib::entry{}' -c ...
On Wed, Apr 1, 2009 at 1:42 PM, Michael Schuster
michael.schus...@sun.com wrote:
I see similar stuff for my library ... so why would dtrace fail to show
calls into libdladm for a process that's started by dtrace (ie using -c)
(using -Z as someone suggested)
$ dtrace -Z -n
On Wed, Apr 1, 2009 at 4:02 PM, Steve Scargall steve.scarg...@sun.com wrote:
As Pavan suggested DTrace isn't preloading the libraries. Try using the
LD_PRELOAD, LD_PRELOAD_32, or LD_PRELOAD_64 environmental variables to
preload the libraries you need. There's an example on my blog
On Thu, Apr 2, 2009 at 8:34 AM, Pavan Chandrashekar - Sun Microsystems
pavan.chandrashe...@sun.com wrote:
This observation of yours is correct but there is more to the story.
I did the following:
truss -u a.out -u libc -o dladm.log dladm show-link
on both a s10u6 machine and a Nevada build
On Tue, Apr 7, 2009 at 1:39 PM, Brett Monroe mr.bmon...@gmail.com wrote:
Hey all,
This is probably a dumb newbie question but I seem to be misunderstanding
what the copyin function can do. When I run the following one-liner:
dtrace -n 'fbt::sprintf:return {printf(%s
On Fri, Apr 17, 2009 at 6:03 AM, Qihua Wu dtrace...@gmail.com wrote:
Hi, All,
For the following script, I hope the printed number should be sequential and
ordered. But the fact is not, anyone knows the reason or bug?
#!/usr/sbin/dtrace -s
#pragma D option quiet
BEGIN
{
j=0;
}
On Fri, Apr 17, 2009 at 12:32 PM, Priya Krishnan priya.krish...@sun.com wrote:
I want to list/use the nfs probes but I get the error dtrace: failed to
match nfs* No probe matches description. Is there a way to enable nfs
provider probes? My system is running snv_112 (bfu'ed from the gate
On Sat, Apr 18, 2009 at 9:25 AM, Ryan ryanj...@ece.cmu.edu wrote:
Hi all,
Is there any kind of specification that probes from the same script fire in
the order they were declared (modulo predicates, of course)? Google turned up
a ppt from 2005 which suggests they do, but there's nothing in
On Sat, Apr 18, 2009 at 12:48 PM, Ryan ryanj...@ece.cmu.edu wrote:
Hi all,
It seems that 'self' behaves differently in profile and tick probes compared
with regular ones (perhaps because they can interrupt normal dtrace probes?)
For example, the following code does not output anything on my
On Sat, Apr 18, 2009 at 6:57 PM, Ryan ryanj...@ece.cmu.edu wrote:
self variables are thread-local variables, which
are unique to the thread in which they fire. The
thread in which the foo:entry probe fires isn't
the same thread in which the profile probe fires.
I understand that the profile
On Mon, Apr 27, 2009 at 8:31 AM, Renil Thomas thomson_p...@yahoo.co.in wrote:
Hi Experts,
_write
value - Distribution - count
4096 | 0
8192 |@@ 1161825
On Mon, May 11, 2009 at 4:37 PM, Brian Utterback
brian.utterb...@sun.com wrote:
I know this has been asked before, but I can't seem to find the answer.
I have a process I want to trace with the pid provider, but the process gets
started once in a while. There is only one process by its name
On Fri, Jun 5, 2009 at 9:48 AM, Danny Websterdannywebs...@gmail.com wrote:
Hi,
This may be more suited to a general D mailing list, but - i'm trying to
analyse LWP activity on a system, and faltering at the first hurdle. The
lwp_create() call is prototyped as:
klwp_t * lwp_create(void
On Fri, Jun 26, 2009 at 11:55 AM, Ryan Johnsonryanj...@ece.cmu.edu wrote:
Also, is there any documentation for libdtrace other than the programs that
use it?
The tools are a good start. Especially intrstat for what you want to
to, as it consumes aggregation data to print out.
The second
On Fri, Jun 26, 2009 at 2:49 PM, Ryan Johnsonryanj...@ece.cmu.edu wrote:
Chad Mynhier wrote:
If you'd like, I could send you a stripped down consumer so you don't
have to worry much about all the baggage in the code for other
utilities.
That would be really helpful! The dtrace code
want microstate accounting on S10 you
need something else.
Unless it was back ported to S10 without the man page being
updated?
Jim
James Litchfield wrote:
Agreed. I missed that. Since it does only the process,
is that good enough?
Jim
Chad Mynhier wrote:
On Sun, Jul 12
On Tue, Jul 21, 2009 at 2:52 AM, Matt Ingenthronmingenth...@acm.org wrote:
I have a USDT provider in memcached which is defined as either a positive
value returned or -1 if there is no result. From my DTrace script, the value
returned seems to be 4294967295 when I'm expecting a -1 so it
On Tue, Jul 21, 2009 at 12:37 PM, Matt Ingenthronmingenth...@acm.org wrote:
To be more particular, in order to get the types from
the provider, you must
use the args[] array, not the arg? variables. Try
doing:
printf(key is %s, length is %d\n, copyinstr(arg1),
, args[3]);
The DTrace
Actually, this isn't exactly true. There are two things you can do
with the pid provider that allow you to inspect the value of variables
inside functions in certain cases: you can instrument any individual
instruction, and you can access register values via the uregs[] array.
As long as you
On Fri, Jul 24, 2009 at 4:50 PM, Matt Ingenthronmingenth...@acm.org wrote:
Hi,
I have a situation where a DTrace script is printing out extra characters,
despite the copyin() call giving a specific length. Can anyone think of why
this might be?
[ ... ]
memcached*::command-get
/ (signed
On Sun, Jul 26, 2009 at 3:35 PM, Matt Ingenthronmingenth...@acm.org wrote:
Thanks again for the help Chad,
memcached*::command-get
/ (signed int) arg3 != -1 /
{
printf(get %s, FOUND KEY\n,
stringof(copyin(arg1, arg2)));
}
It doesn't look like you're copying in a null
character,
On Sun, Jul 26, 2009 at 6:16 PM, Matt Ingenthronmingenth...@acm.org wrote:
If not, then something like this should work:
this-foo = (char *)alloca(arg2 + 1);
copyinto(arg1, arg2, this-foo);
this-foo[arg2 + 1] = '\0';
printf(%s\n, stringof(this-foo));
Makes sense. Is
On Thu, Jul 30, 2009 at 3:48 PM, Pavel
Filipenskypavel.filipen...@sun.com wrote:
[ ... ]
One of the possibility to synchronize it, is to let the dtrace probe to send
a signal to the user land process via a system() action.
[ ... ]
The problem is that the delay between the event (nfs probe)
On Wed, Aug 12, 2009 at 9:03 AM, Qihua Wudtrace...@gmail.com wrote:
Hi, dtrace experts:
Using pid provider, can we print all the parameters passed to a function?
First need to know is the number of parameters the function has. But which
build in variable could show us the number of
Why not just aggregate on the tuple fd, file name? Something like this:
syscall::read:entry
{
@c[arg0, fds[arg0].fi_pathname] = count();
}
If the output's unsatisfactory, you could always use a printa() in en
END clause to get it into the format you want.
Chad
On Tue, Aug 18, 2009 at
On Mon, Aug 24, 2009 at 2:31 PM, Joel Reymontjoe...@gmail.com wrote:
Here's the full output:
http://pastie.org/593398
You can see that the total should be way higher than 0.81s by eyeballing the
output.
The total should be between 3 and 4 seconds.
You're printing the values incorrectly.
On Mon, Aug 24, 2009 at 3:07 PM, Joel Reymontjoe...@gmail.com wrote:
Any suggestions on how I can figure out the right # of leading 0s?
I really wish dtrace had floating-point printing.
This should do what you want:
printa(%...@09d\n, @int);
i.e., print it in a field 9 characters wide with
...@gmail.com wrote:
Thanks Chad!
How do I pass the 2nd script as argument into the first, though?
Thanks, Joel
On Aug 28, 2009, at 8:52 PM, Chad Mynhier wrote:
You can do this with two separate DTrace invocations. The first
catches the exec of firefox-bin and fires off the second
On Fri, Aug 28, 2009 at 4:44 PM, Nicolas
Williamsnicolas.willi...@sun.com wrote:
On Fri, Aug 28, 2009 at 03:52:01PM -0400, Chad Mynhier wrote:
You can do this with two separate DTrace invocations. The first
catches the exec of firefox-bin and fires off the second. Something
like
On Sat, Sep 5, 2009 at 12:09 AM, Yossi Lev (Sun Labs)yosef@sun.com wrote:
Somebody will have to confirm, but I think global variables are
lock-protected in DTrace, so you should be able to use one to store the
sequence number.
Actually, from messages that I saw in this forum, and my
On Wed, Sep 9, 2009 at 1:42 PM, Joel Reymontjoe...@gmail.com wrote:
What is the hex number after the method, e.g. +0x32f below?
It matches arg0 and I suspect it's the c++ this pointer, aka hidden first
argument.
It matches arg0 to which probe? These look like function offsets.
Chad
I
On Sun, Sep 13, 2009 at 4:54 PM, Yossi Lev (Sun Labs) yosef@sun.com wrote:
My questions:
- If not, do you have any other idea how can I achieve this kind of
dynamically adapting tracing behavior?
For something this complicated, you might want to look at writing your
own DTrace consumer.
On Thu, Sep 17, 2009 at 9:17 AM, Eugenias redtigra...@gmail.com wrote:
Hi,
I'm a nub in dtrace, could you please help me to find the mistake?
I need to implement the logic:
- if PID and TID are defined, fire the probe for the particular thread of
particular process;
- if only PID is
If you're a little more concerned with getting it close to 10 seconds,
you can use something like this:
tick-1s
/ i++ = 10 /
{
exit(0);
}
The reason the tick-10s probe might fire sooner than 10 seconds is
that DTrace will use an existing probe if there is one. If script A
is the first to
On Thu, Dec 3, 2009 at 10:07 PM, Kevin Fitch kfitc...@gmail.com wrote:
I have a situation that I would like to debug with dtrace, but I am not sure
how.
I have a process that kicks off, runs for a few seconds (perhaps
milliseconds) then goes away. And this happens very frequently, think
On Tue, Dec 15, 2009 at 1:38 PM, Hillel (Sabba) Markowitz
sabbahil...@gmail.com wrote:
I attempted to add the dtrace privileges to /etc/user_attr but it does
not appear to work. I found a writeup from 2005 asking about this, but
the answer does not seem to work for me. I set it to
On Wed, Dec 16, 2009 at 1:52 PM, Hillel (Sabba) Markowitz
sabbahil...@gmail.com wrote:
As can be seen, if recursive code is used, the self-ts gets reset to
timestamp with every entry, and the innermost exit causes a time to be
calculated and the ts to be reset. The rest of the returns within
On Wed, Dec 16, 2009 at 2:17 PM, Hillel (Sabba) Markowitz
sabbahil...@gmail.com wrote:
On Wed, Dec 16, 2009 at 2:13 PM, Chad Mynhier cmynh...@gmail.com wrote:
You'll need to keep an array of timestamps indexed on ustackdepth.
Something like this (it appears that ustackdepth on entry doesn't
On Wed, Dec 16, 2009 at 3:19 PM, Hillel (Sabba) Markowitz
sabbahil...@gmail.com wrote:
However, what I am worried about is a set where
-A
-B
-C
-C
-B
-A
-D
-C
-C
-D
This would seem to not aggregate the C as the ustackdepth for the two
usages of C would be different.
On Thu, Dec 17, 2009 at 3:08 PM, Hillel (Sabba) Markowitz
sabbahil...@gmail.com wrote:
On Wed, Dec 16, 2009 at 2:44 PM, Chad Mynhier cmynh...@gmail.com wrote:
#define STACKDEPTHBASE 2
I don't follow why this is set to 2. I included a syscall count to
also see how many times a function
On Mon, Dec 21, 2009 at 8:47 AM, Hillel (Sabba) Markowitz
sabbahil...@gmail.com wrote:
When I tried to set up with a probe at
pid$target::main:entry with a printf inside it, I got no output.
However, I did get a main:return from
pid:target:hello::return
I do not understand why that is
Yep. The system call is lwp_park(). Given that it's a blocking
system call, the time a thread spends here is effectively unbounded.
Chad
On Wed, Feb 3, 2010 at 3:47 PM, Jim Mauro james.ma...@sun.com wrote:
It's used to put threads to sleep that are blocking on user locks
(at least that's my
On Fri, Feb 5, 2010 at 7:10 AM, Ryan Johnson ryanj...@ece.cmu.edu wrote:
Is this a known limitation/bug? For now I'm using the O7 trick and
post-processing to remove the most glaring deficiencies but a real solution
would be nice.
Yes, this is a known limitation. The documentation talks
On Fri, Feb 5, 2010 at 9:40 AM, Ryan Johnson ryanj...@ece.cmu.edu wrote:
On 2/5/2010 1:19 PM, Chad Mynhier wrote:
On Fri, Feb 5, 2010 at 7:10 AM, Ryan Johnsonryanj...@ece.cmu.edu wrote:
Is this a known limitation/bug? For now I'm using the O7 trick and
post-processing to remove the most
On Tue, Mar 2, 2010 at 3:20 AM, Henrik Johansen fi...@hotmail.com wrote:
Hi folks,
While playing around with the FBT provider I came across something I simply
can't figure out how to do.
I would really like to track I/O to some of our zvols - for writes something
like this does the trick
On Wed, Mar 3, 2010 at 2:31 AM, Henrik Johansen fi...@hotmail.com wrote:
But this return what appears to be a hexdump as well as the zvol names and
their read counts
[]
370: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
380: 00 00 00 00 00 00 00
On Tue, Apr 27, 2010 at 11:00 AM, Mark Phalan mark.pha...@sun.com wrote:
Whenever I try to use a wildcard in my dtrace scripts with my USDT
provider I get an error complaining that the set of probes is unstable.
dtrace -n 'foo$target:::bar-* { printf(%d\n, args[0]-i); }' -c /tmp/x
dtrace:
On Tue, May 4, 2010 at 11:23 AM, Yossi Lev yosef@sun.com wrote:
Hi
I'm running a simple DTrace script that has the following clause:
pid$target::ReportTx:entry
/arg1 != 0 this-numEntries != 0/
{
printf(NumEntries: %lld\n, (long long)this-numEntries);
this-entry =
On Tue, May 4, 2010 at 12:58 PM, Yossi Lev yosef@sun.com wrote:
Moreover, I know that the value that I'm getting is valid, because I had the
following printf statement:
pid$target::ReportTx:entry
/arg1 != 0 this-numEntries != 0/
{
printf(NumEntries: %lld\n, (long
It doesn't appear to be documented, but it appears that uregs[R_FP]
will give you the value. (At least on SPARC, you'll need to know
which register the FP is stored in on x86.)
Chad
On Fri, May 7, 2010 at 3:38 PM, tester solaris.ident...@gmail.com wrote:
Hello,
How can I access frame
On Fri, May 7, 2010 at 3:56 PM, tester solaris.ident...@gmail.com wrote:
Thanks.
Do I need to add stack bias 2047to fp to get actual data?
which is correct?
printf(localvar value is %x\n, (uregs[R_I6]));
or
printf(localvar value is %x\n, uregs[R_I6] + 2047);
I don't think you need to
On Mon, May 10, 2010 at 11:16 AM, Yossi Lev yossi@oracle.com wrote:
Hi
I wondered if given a pointer to an instruction in a user C function,
DTrace can print out the user function name and offset of that
instruction. That is, I'm looking for something like the %a flag but
for user
On Thu, May 20, 2010 at 7:46 AM, tester solaris.ident...@gmail.com wrote:
Hello,
We had a situation on a t5140 running solaris 10 where the load average
from prstat were 20-25,30-40,60-80. We ran a simple dtrace cmd to capture the
jstack using the pid provider using the PID from prstat.
On Mon, May 24, 2010 at 8:56 AM, Mark Phalan mark.pha...@sun.com wrote:
On Mon, 2010-05-24 at 13:42 +0200, Mark Phalan wrote:
On Tue, 2010-05-18 at 17:28 -0400, Angelo Rajadurai wrote:
The way to fix it is to set strsize
#pragma D option strsize=1024 // make sure your string can fit in!
On Tue, May 25, 2010 at 5:13 AM, Mark Phalan mark.pha...@sun.com wrote:
On Mon, 2010-05-24 at 15:16 -0400, Chad Mynhier wrote:
Even though string is a separate type in DTrace, a string is still
just stored as a null-terminated sequence of characters. stringof()
isn't doing anything to null
On Tue, May 25, 2010 at 5:37 AM, Mark Phalan mark.pha...@sun.com wrote:
Another data point. This works fine:
data_string = lltostr(strlen(stringof(copyin((uintptr_t)(*((uint32_t
*)
copyin((uintptr_t)P-data, sizeof (uint32_t, *((uint32_t *)
copyin((uintptr_t)P-length,
On Tue, May 25, 2010 at 10:23 AM, Mark Phalan mark.pha...@sun.com wrote:
On Tue, 2010-05-25 at 09:36 -0400, Chad Mynhier wrote:
OTOH, copyinstr() _does_ take a second argument that specifies a max
length, so the workaround you're looking for is to use that:
data_string = strjoin
I think you're looking for is-enabled probes. See
http://blogs.sun.com/ahl/entry/user_land_tracing_gets_better or the
current DTrace documentation.
Chad
On Fri, Jul 16, 2010 at 10:39 AM, Thomas Maier-Komor
tho...@maier-komor.de wrote:
Hi,
is it somehow possible to conditionally enable a
On Fri, Aug 19, 2011 at 4:34 PM, Lida Horn lida.h...@oracle.com wrote:
I'm looking for an example of how one could write a dtrace probe
that could follow something like a NULL terminated linked list.
If this is a list with short-lived entries (e.g., one of the hash
buckets in the sleep queue),
On Tue, May 22, 2012 at 4:04 PM, chip.benn...@exeloncorp.com wrote:
Often a D program is easier to read if you break up a complex predicate into
separate clauses, but I was wondering if you sacrifice script performance to
do that. For example, the following two D programs do the same thing
Responses inline:
On Thu, May 24, 2012 at 6:56 PM, chip.benn...@exeloncorp.com wrote:
Chad,
That was very helpful, thank-you.
So it sounds like you're saying that if the check expression has no cacheable
components, it doesn't matter if I put the check in the predicate, or if I
break
96 matches
Mail list logo
