similar to: Solaris Dynamic Tracing Guide gets Wikified!

Just to let people know what my big picture is, I''m trying to write a script that will let me run a program, and name a progeny of that program that I want to debug. My script should find the first occurrence of that progeny, and run it until it finishes initializing the runtime linker, but stop it before it runs any shared library startup routines. (Failing that, I''d be okay

everyone, Just out of curiosity, I did a dtrace -n ''syscall:::entry { @num[execname, probefunc] = count(); }'' and looked at the entries produced by ''rm''. I see everything that rm did, *except* the unlinkat - which is unfortunate because I want to trace which processes have deleted which files. So - does dtrace contain unlinkat as a probe for a system call?

I have found that pid provider can not create memcpy:return probe for 64bit process on snv_110. For example, the pid is 10603, I will have following output for dtrace command: #dtrace -n pid10603:libc.so.1:memcpy:return dtrace: invalid probe specifier pid10603:libc.so.1:memcpy:return: probe description pid10603:libc.so.1:memcpy:return does not match any probes This just

Suppose I have a USDT probe in Firefox and that I''m trying to catch the startup with a probe like this: proc:::exec-success /execname == "firefox-bin"/ { start = timestamp; } and stop tracing when Firefox hits this USDT probe: mozilla:::main-entry { exit(0); } How do I put the running firefox-bin into "trace mode" so that my USDT probe fires? Thanks, Joel

My leaky memory says we moved entry-point into some form of debug record in the standard libraries, circa Solaris 8/9. Before that, my group maintained text files that listed all the entry-points and their parameters for libraries like libc.so, so that we could print out parameter values in apptrace(8). There''s a (small) chance the records are complete enough that dtrace could use the

Hi all, We just got a shiny new T5440, and one of the first things I noticed (besides the insane number of hardware contexts), is that dtrace takes 30 seconds to a minute to fire up scripts with 5-6 probes, where our T5220 usually takes under a second. Shutdown is similar, though slightly faster. This is mostly annoying because it takes so long to attach that it''s hard to tell when

This came up as an RFE during the conference (I believe it''s been logged as "4012008: brendan() action needed for DTrace Toolkit".) As everyone here is aware, DTrace is not quite as user friendly as it could be. For the uninitiated, it can be confusing to run a DTrace script and not see the expected output. Brendan Gregg has addressed this in the DTrace Toolkit[1] by

Hi Bryan, > Does that sit well with everyone? Seems fine to me. Just revisiting one of Dragan''s points, though (sorry if I missed the answer) - is there a reason for making this global (via a #pragma) rather than, say, simply providing two functions which print in the different orders? e.g. printa() for sort by sample, printak() for sort by key. My reason for wanting to do both in

Hi all, What is the correct way to give one non-root user the ability to use DTrace with providers running in a process by another user? Through the Web Stack project and some work by Ludovic Champenois and Nasser Nouri, we have done a bit of work to bring together parts of chime, the Web Stack Apache, Ruby and PHP providers, and stuff reused from the DTrace toolkit. It''s in

Hi, Following "anonymous tracing" chapter, I wanna trace kmem_init(), but after reboot, I can''t get anything, why? Here is my short script kmem_init.d: #!/usr/sbin/dtrace -s fbt::kmem_init:entry { stack(); } then I just use: #dtrace -AFs kmem_init.d #reboot #dtrace -ae < got nothing here> Thanks, -Alex This message posted from opensolaris.org

I have added a specification of probes for the fibre channel COMSTAR port provider to the DTrace section of wikis.sun.com. The proposal may be found here: http://wikis.sun.com/display/DTrace/fibre+channel+Provider I welcome feedback regarding this proposal. Thanks, Sam

Hi, I''m trying to trace the io of a given file, but I have a feeling that it''s been done via a script, as such I''d like to be able to tell the names of the calling processe tree, similar to what ptree produces. Is there any way to get this information without running ptree using system()? Thanks, Darren.

Hello, everyone I am a newbie of DTrace and OpenSolaris. Just wondering is it possible to trace every memory read/write of a specific process given the pid? Basically speaking, I want to record the virtual addresses being accessed by the process, using which I will try to do some online analysis. If DTrace does not support this type of instrumentation, will other tools in OpenSolaris help me

Hi All, Can I get Dtrace command, which is useful for regular system administration like performance issue. Advance Thanks Muthu -- This message posted from opensolaris.org

Hi - I''m trying to use plockstat to help identify any mutex contention issues we may have in our c++ app. >From the docs it would appear to be a very useful tool - unfortunately in practice this doesn''t bear out purely because the stack traces produced are limited to being 39/40 characters wide. In general this means that I''m not seeing ~75% of each stack symbol and

Greetings, is there a way to specify probes and other dtrace operations via command line parameters, like " BEGIN { usr_exec=$$1; usr_syscall=$$2; } syscall::usr_syscall:entry /execname == usr_exec && guard++ == 0/ { ... " [this does not work] This would make it possible to create "generic" dtrace scripts. Otherwise, some shellscript with sed-magic would

Hi All, I''ve got a problem when I have USDT probes in a static library and in the application code outside of the library. I build the static library containing some USDT probes, glomming everything together (ld -r) before creating the .a file to preserve the probe symbols. This all works fine. I build an application which also has some USDT probes. When I build the application which

What''s going on? # dtrace -s iotime_all.d 100 dtrace: failed to enable ''iotime_all.d'': DIF program content is invalid The errant script.... #pragma D option quiet BEGIN { stime = timestamp; io_count = 0; } io:::start /args[2]->fi_pathname != "<none>"/ { start[pid, args[2]->fi_pathname, args[0]->b_edev, args[0]->b_blkno,

Hi, I have used dtrace in the past for diagnosing IO/filesystem related issues. So I am a bit familiar with dtrace scripts Now I want to diagnose performance problems in the java area. May be memory leak etc. The hotspot provider is not present. How can I get them? Does someone have any further advice? regards Hans -- This message posted from opensolaris.org

Using the following dtrace command, I can see who''s calling what with lots of +/- numbers: dtrace -n ''fbt:ip:ip_output:entry{@dbtypes[((mblk_t *)arg1)->b_datap->db_type,caller] = count();}'' ...the output is what I want but not how I want to see it. What I''d rather see is the function names associated with caller and for db_type to be output in hex.