similar to: Some results using DTrace for measuring PostgreSQL performance

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;

while trying to use the USDT made available to us in Postgresql database I have problems enabling them. On my database server I ran 1024+ PG processes (1024 clients). The server is a 8 core T2000 @1000MHz. 32GB. 7 storage arrays. Solaris 10 Update 4. Home compiled PG 8.3 beta 1 (optimized binary for T1 chip) with DTrace probes enabled. When running without enabling the probes I have approx 25%

I''m trying to time a function within Firefoxwith a pid$target probe [2]. e.g dtrace -Zqw -x dynvarsize=64m -x evaltime=preinit -p 13954 -s menu- construct.d -s sigcont.d elapsed: 12.7942481ms cpu : 7.7911194ms count : 40 times I''m also measuring Firefox startup time by running it arguments like this: ... file:///Users/joelr/work/mozilla/startup/startup.html#`python

For those who may have missed the news, the DTrace movers and shakers have moved over to a new mailing list; you can sign up at http://dtrace.org/blogs/mailing-list/ And there will be a conference dedicated to DTrace on April 3rd in San Francisco, more information here: http://wiki.smartos.org/display/DOC/dtrace.conf -- best regards, Deirdr? Straughan SmartOS Community Manager Joyent cell

(Apologies to anyone who follows me on Twitter and therefore will have seen this multiple times already.) Joyent will be offering training in DTrace: Core Features and Performance Analysis trainer: Brendan Gregg <http://dtrace.org/blogs/brendan/> (San Francisco, Sept 6-7), Max Bruning <http://wiki.smartos.org/display/DOC/Max+Bruning> (Geneva, Sept 13-14) This course introduces

I''m pleased to pass along news that the Mac OS X DTrace port has been updated in 10.5.3 to fix the issue that caused timer based probes not to fire in the presence of certain untraceable applications. http://blogs.sun.com/ahl/entry/apple_updates_dtrace A big thank you to the folks at Apple for addressing the problem. Adam -- Adam Leventhal, Fishworks

The sched provider defines the stable "lgrp" variable that is the lgroup of the current CPU. This is mostly interesting when we can compare it with the actual thread home lgroup, so I''d like to extend the lwpsinfo_t structure with the new pr_lgrp field which will be implemented using translator. This will match the addition of the pr_lgrp field to the proc(4) lwpsinfo_t

Hi, I am fairly new to DTrace, and wanted to ask something regarding synchronization objects. I have a multithreaded C++ program in which I use semaphores (POSIX version) for synchronization. I was interested in using DTrace to figure out the total time for which each thread in my application sleeps, blocked on a semaphore, i.e., as a result of sem_wait() call. In order to measure this, I

I''d like to prepend TRACE_ to the macro names generated by dtrace -h. For example, change POSTGRESQL_LWLOCK_ACQUIRE(arg0, arg1) to TRACE_POSTGRESQL_LWLOCK_ACQUIRE(arg0, arg1) and still keep postgresql as the provider name. The reason for doing this is to make it clear that the macros are used for (D)tracing. In this particular case, without TRACE_, it appears like the macro is used

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

All, With Jon Haslam''s exciting news about the DTrace doc wiki (if you haven''t seen it yet, make your way to http://wikis.sun.com/display/DTrace), and with some of the discussion with the Apple folks, I''m wondering if the time isn''t right for something of a DTrace summit, perhaps as an unconference. The idea here would not be a DTrace user group (though that

DTrace folks, I''m pleased to introduce a potential new DTrace-sponsored project: the Erlang DTrace provider. To be good OpenSolaris citizens, we want to put the formation of this officially sponsored project to a vote -- as outlined in the OpenSolaris Constitution -- so here are the details for the new Project, as prepared by the Project Team: Name : Erlang DTrace Integration

To remember all dtrace actions, aggregations and variables is a headache, even worse, they are not include in dtrace(1M) now. So here is a chance to have a CLI RFE - to have something like "dtrace --actions", which will list all actions, like this page: http://developers.sun.com/solaris/articles/dtrace_quickref/dtrace_functions.html "dtrace --aggregations", lists all

The open solaris dtrace page (http://www.opensolaris.org/os/community/dtrace/) has a bad link to the DTrace Guide(http://docs.sun.com/db/doc/817-6223). This message posted from opensolaris.org

Dear dtrace Experts, I have seen some dtrace utilities like opensnoop and execsnoop etc. My interest is to write a simple script that can snoop the files which uses the 3 syscalls like open,create,unlink. I have gone through dtrace oneliners that can do the same : dtrace -n ''syscall::open*:entry { printf("%s %s",execname,copyinstr(arg0));}'' dtrace -n

Hi, I am using anon dtrace followed with normal dtrace to collect the data of all fork,exec,exit . I found that dtrace could not be able to collect all the data. Lot of pids are missing. This happence when we boot the system and expect dtrace to collect all the fork , exec & exit it collects data but not all the pids are collected. Any inputs in this regard will be of great help. thanks

Hi all, I''m trying to run dtrace -c on a program that takes command-line arguments... is there any way to tell dtrace where its args let off and the target''s begin, or will I have to write a shell script that checks for ''--'' or some such? Thanks, Ryan -- This message posted from opensolaris.org

> > From: vikram b > > Date: October 22, 2009 12:31:53 AM PDT > > To: dtrace-discuss at opensolaris.org > > Subject: [dtrace-discuss] dtrace problem > > > > Hi All, > > I am running dtrace on linux !! got it working some how. > > dtrace -l shows a big list.. but many issues > > > > 1. says : failed to grab process > >

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

According to this page, http://www.apple.com/macosx/technology/unix.html In addition, Java, Ruby, Python, and Perl have been extended to support DTrace, providing unprecedented access for monitoring the performance characteristics of those languages. When I do dtrace -l | grep -i perl on MacOSX 10.5.2. I don''t see any perl providers so I am not sure how I could monitor perl scripts via