similar to: dtrace and Xorg don''t always mix

We are using following dtrace script to analyze an application. However we see different number of lwp_yield and yield calls reported depending on whether we trace mutex_lock or mutex_unlock or not. The number reported when we are not tracing mutex_lock or mutex_unlock is higher. What could be going on here and which one is the correct number. This is on S10 U2. Thanks, Rao.

i am doing reads and writes to /dev/rdsk/c0t2d0s4 using dtrace to see how much time it took for ssdread and ssdwrite. It shows very small number 4 or 5. #pragma D option flowindent syscall::pread:entry { self->trace = 1; self->size = arg2; } syscall::pwrite:entry { self->trace = 1; self->size = arg2; } fbt:ssd:ssdread:entry /self->trace/ { self->start = timestamp;

[1] Predicates in one-liners I would like to list the probe modules in my executable and then dynamically create a dscript to trace execution of those modules alone (by excluding the 3rd party and system libraries). I tried the below script without success. The conditional given in the predicate is not taking effect. Why is this so ? $ dtrace -ln ''pid$target:::

Hello Srikant - A quantization distributes the results of your aggregation into ranges ordered by a power-of-two. Presumably what you''d do in your script is capture the inclusive elapsed time of each function call in your library, then use this quantization to see how tightly-banded the times are. Perhaps there''s some blocking I/O in some of your calls, for example, in which

hi, I am trying to find out the avg cpu time spent in each of my user methods (exclusive of other methods invoked by a method). Hence the following snippet failed miserably: ----------------------- pid$target:a.out::entry { time[probefunc] = timestamp;} pid$target:a.out::return { @spent[probefunc] = avg(timestamp - time[probefunc]);} END { printa(@spent);}

Hello all, I saw this question about a year back in the archive[1], but with no final answer. I would like to trace shmget calls and also get the id of the shared memory segment. That script looked like[2], but we dont get the id since arg1 is the errno value. How do i access the shm id, i would need this to debug a customer problem but i don''t have time to learn it the hard

Hi, I am kind of new to DTrace , I have written a script to time function calls in our application library , Wanted to know how to interpret the output from quantize of the elapsed time in each function call , here is a sample Here is the entry and return function for the library that is being traced pid$1:libswduar::entry { duarEntry[probefunc] = timestamp;

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?

Whilst trying out some D to get an insight into what is the most common reason for a given function to return, I have bumped into an error I don''t understand. The first take on what I was trying to do was: # dtrace -n ''fbt:ip:ip_input:return{@home[arg0] = count();}'' and all was well. The next step was: # dtrace -n

I''d like to be able to dynamically read external configuration files within a dtrace script. I know dtrace allows inclusion of C header files but only at the preprocessing stage. What we need to do is dynamically enable/disable probes based on current application settings. I''d rather not have a bunch of independant scripts running and being started and killed whenever the

Hello, I''m using the below dtrace script to capture the flow and times of kernel functions, from an ioctl() call. After an entry into restorectx(), the trace of startimestamp - vtimestamp makes a dramatic jump downwards. Here''s the snippet showing the jump... 6 -> di_checkmem 8 220176600 6 <- di_checkmem

[Perhaps someone could rename this list to dtrace-matt-problems-discuss?] If I run this script against my binary (which contains a USDT probe called ''concurrentq-latency''): ::: / probename == "concurrentq-latency" / { printf("[%s]:[%s]:[%s]\n", probeprov, probefunc, probename); } I get this output: dtrace: script ''testq.d'' matched 46056

I recently did a backport of a couple of networking bug fixes from s10x_u4_b6 to s10x_u3_b10. I patched just /platform/i86pc/kernel/unix and /platform/i86pc/kernel/amd64/unix in my existing u3 OS image and I''m seeing this dtrace problem when running any dtrace script: NODE hcb101 ~ $ ./tcpstat.sh dtrace: failed to compile script /dev/fd/10: "/usr/lib/dtrace/procfs.d", line

everyone Here: How do you do! dtrace is interesting. I am studing how to write dtrace script and analyze situation. I read dtrace_example.pdf and 819-6959.pdf document more than five times with careful. because I am newbie to studing dtrace.so I still don''t know how to begin. for question: 1. What consumes time? 2. Which system call(s) consume(s) time?

So I realize this is somewhat stupid, and I''ve actually gotten myself out of kmdb to kill my dtrace script but this has happened in the past and I''m wondering if there''s any better way around it than hitting :c a bunch of times. Say you set a breakpoint() to fire in a common function. This will drop you into kmdb where you can do some debugging, you take a look around

Just showing someone how great DTrace is and then we spot something I do not understand. Of course it can be a major misunderstanding of myself. Would appreciate another (expert) look upon this. The goal we try to achieve is trying to get insight if there is a bursty nature in the time slot when system calls are done. Following DTrace snippet is tried: dtrace -q -p 3173 -n

A user has asked us to find out who is changing one of their files and how it is being changed. I came up with the script below: #!/usr/sbin/dtrace -s #pragma D option quiet BEGIN { printf("\n Timestamp gid uid pid ppid execname function current directory file name\n\n"); } syscall::open:entry,

hi fnds, i want to print the filenames on which the stat system call is acting when a stat system call is invoked. can anyone can help me this regard. Thanks jeevan

Hi i''m trying to write my first dtrace script apparently i bit off a bit more than i can chew, i want to track io over sockets, i found your socketsize.d that gave me how to track writes, but i''m at a loss how to track reads, frankly i don''t see how your write tracker works because it uses a probe in a function that only takes two arguments but you grab size of write

I''m trying to profile the time spent in libc functions in a large build job (building Perl), and I have trouble getting ufunc and func working. (func() is not strictly needed; I was just hoping to use it in order to profile idle time.) Here''s the story. I''ve written a dtrace script to start a separate dtrace process for each invoked command: int fileid;