summaryrefslogtreecommitdiffstats
path: root/usr.sbin/pmcstat
Commit message (Collapse)AuthorAgeFilesLines
...
* Add the -m option to pmcstat.attilio2008-11-254-11/+69
| | | | | | | | | This option prints the list of sampled PCs along with the function name, the start and end addresses of this where their live within. Reviewed by: jkoshy Tested by: gnn Sponsored by: Nokia
* As a matter of good programming style, stop PMCs before releasingjkoshy2008-11-191-0/+3
| | | | them.
* - Avoid a spurious error when a command line is specified withoutjkoshy2008-10-072-5/+6
| | | | | any process scope PMCs. - Change the -c '*' option to denote non-halted CPUs.
* Bring the usage message in sync with the manual page.jkoshy2008-09-191-1/+2
|
* Add an example illustrating the use sleep(1) for performing timedjkoshy2008-09-191-2/+7
| | | | measurements.
* Fix a regression: attach process PMCs to the process created whenjkoshy2008-07-011-2/+2
| | | | a command line is specified.
* Document messages printed in verbose mode.jkoshy2008-06-291-2/+36
| | | | Requested by: Fabien Thomas <fabien.thomas at netasq dot com>
* Fix 'make checkdpadd'.jkoshy2008-02-221-1/+1
|
* Fix non-SMP kernel regression introduced in the previous commit.jkim2008-01-101-4/+7
| | | | Reviewed by: jkoshy
* Introduce pmcstat(8) changes for summarizing hwpmc(4) callchain records injkoshy2007-12-075-209/+1075
| | | | | | | | in textual form and in gmon.out format. Update manual page. Sponsored by: FreeBSD Foundation and Google Inc.
* When printing the contents of a HWPMC log in human readable form:jkoshy2007-12-031-3/+8
| | | | | | | | | - Print a warning if the version number recorded in the log is not what the tool expects. - Print a tidier error message when an unrecognized event is encountered in the log. - Don't print a spurious 'Unknown error: 0' when exiting after a parse error.
* Fixed "make checkdpadd" (missing library dependencies).ru2007-10-011-1/+1
| | | | Approved by: re (kensmith)
* MFP4: Enhancements to pmcstat(8):jkoshy2007-04-274-69/+184
| | | | | | | | | | - Allow the "-t" option to take a regular expression naming command line processes to attach process PMCs to. - Update the manual page and add an example showing the use of the new functionality. - Update the (c) year on the affected source files.
* MFP4: Enhancements and bug-fixes to pmcstat(8):jkoshy2007-04-223-126/+224
| | | | | | | | | | | | | | | | - The '-c' option now takes a comma-separated list of CPU numbers, or a literal '*' denoting all CPUs in the system. Subsequent system PMCs are allocated on the CPUs so specified. Change the default behaviour to allocate system PMCs on all CPUs, not just CPU 0. Update the manual page and add an example of how to use the new functionality. - Attach PMCs to a (commandline) child process more reliably. This fixes a long standing bug in counting events incurred by short-lived processes.
* Correct a sanity check.jkoshy2007-04-211-1/+1
|
* Markup fixes.ru2006-09-291-4/+5
|
* Line up usage output.ru2006-09-291-1/+1
|
* When printing a map, print the number of samples recorded by each gmon.out file.jkoshy2006-04-051-5/+18
| | | | MFC after: 1 week
* - Teach pmcstat(8) to log over the network; the -O option nowjkoshy2006-04-023-24/+107
| | | | | | | | | | | takes a host:port specification. - Update the manual page and add an example showing how log over the network using pmcstat(8) and nc(1). Document the current inability to process logs in cross-platform manner. - Have pmcstat_open_log() call err(3) directly in case of an error; this simplifies error handling in its caller. MFC after: 1 week
* MFP4: Support for profiling dynamically loaded objects.jkoshy2006-03-264-447/+986
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Kernel changes: Inform hwpmc of executable objects brought into the system by kldload() and mmap(), and of their removal by kldunload() and munmap(). A helper function linker_hwpmc_list_objects() has been added to "sys/kern/kern_linker.c" and is used by hwpmc to retrieve the list of currently loaded kernel modules. The unused `MAPPINGCHANGE' event has been deprecated in favour of separate `MAP_IN' and `MAP_OUT' events; this change reduces space wastage in the log. Bump the hwpmc's ABI version to "2.0.00". Teach hwpmc(4) to handle the map change callbacks. Change the default per-cpu sample buffer size to hold 32 samples (up from 16). Increment __FreeBSD_version. libpmc(3) changes: Update libpmc(3) to deal with the new events in the log file; bring the pmclog(3) manual page in sync with the code. pmcstat(8) changes: Introduce new options to pmcstat(8): "-r" (root fs path), "-M" (mapfile name), "-q"/"-v" (verbosity control). Option "-k" now takes a kernel directory as its argument but will also work with the older invocation syntax. Rework string handling in pmcstat(8) to use an opaque type for interned strings. Clean up ELF parsing code and add support for tracking dynamic object mappings reported by a v2.0.00 hwpmc(4). Report statistics at the end of a log conversion run depending on the requested verbosity level. Reviewed by: jhb, dds (kernel parts of an earlier patch) Tested by: gallatin (earlier patch)
* When generating profiles (-g) warn about shared objects that werejkoshy2005-12-251-4/+12
| | | | not found.
* - Don't print an errno string when reporting dropped samples.jkoshy2005-12-241-3/+4
| | | | | - Prevent an unsuccessful exec() of a target program from triggering a false 'dropped samples' message.
* Warn the user if the kernel driver dropped samples or ran out of event buffersjkoshy2005-10-211-2/+27
| | | | during a data collection run.
* Handle 32 bit executables better on AMD64 platforms.jkoshy2005-10-181-30/+69
|
* Document pmcstat's inability to handle 32 bit executables on thejkoshy2005-10-181-0/+4
| | | | | | AMD64 while I work on a fix. Noticed by: ps
* Determine where the runtime loader got mapped to when a dynamicallyjkoshy2005-09-141-85/+119
| | | | | | | | linked process was exec()'ed, and map samples in that address range into the appropriate buckets in the runtime loader's profile. Improve a few comments. MFC after: 3 days
* Fix a bug that caused generated gmon.out profiles to be out ofjkoshy2005-09-131-10/+31
| | | | | | | whack. Use saturating arithmetic when incrementing a bucket. Improve a few comments. MFC after: 3 days
* Improve an error message.jkoshy2005-09-051-2/+2
| | | | MFC after: 3 days
* Correctly print system-wide PMC counts for short-lived command lines.jkoshy2005-08-041-0/+3
| | | | | Reported by: cracauer MFC after: 3 days
* Sync usage message with the code and manual page.jkoshy2005-07-231-0/+1
| | | | Submitted by: maxim
* Fix spelling error in sample command.rwatson2005-07-131-1/+1
| | | | MFC after: 3 days
* Fix a bug that affected on-the-fly gmon.out file generation.jkoshy2005-07-093-12/+9
| | | | Approved by: re (scottl)
* Add examples illustrating how to record system-wide profiles andjkoshy2005-07-011-3/+18
| | | | | | | | | | how to convert these to gprof(1) flat profiles. Augment description for the '-g' option. Remove superfluous quotes around a macro argument, bump document date [1]. Reminded by: ru [1] Approved by: re (blanket hwpmc)
* Unbreak tinderbox builds. Remove a debug printf.jkoshy2005-07-011-14/+12
| | | | Approved by: re (blanket hwpmc)
* MFP4:jkoshy2005-06-305-349/+1604
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - pmcstat(8) gprof output mode fixes: lib/libpmc/pmclog.{c,h}, sys/sys/pmclog.h: + Add a 'is_usermode' field to the PMCLOG_PCSAMPLE event + Add an 'entryaddr' field to the PMCLOG_PROCEXEC event, so that pmcstat(8) can determine where the runtime loader /libexec/ld-elf.so.1 is getting loaded. sys/kern/kern_exec.c: + Use a local struct to group the entry address of the image being exec()'ed and the process credential changed flag to the exec handling hook inside hwpmc(4). usr.sbin/pmcstat/*: + Support "-k kernelpath", "-D sampledir". + Implement the ELF bits of 'gmon.out' profile generation in a new file "pmcstat_log.c". Move all log related functions to this file. + Move local definitions and prototypes to "pmcstat.h" - Other bug fixes: + lib/libpmc/pmclog.c: correctly handle EOF in pmclog_read(). + sys/dev/hwpmc_mod.c: unconditionally log a PROCEXIT event to all attached PMCs when a process exits. + sys/sys/pmc.h: correct a function prototype. + Improve usage checks in pmcstat(8). Approved by: re (blanket hwpmc)
* - Tidy markup. [1]jkoshy2005-06-241-31/+22
| | | | | | | | | | | | - Remove mention of an unimplemented option. - Clarify the behavior of pmcstat when logging PMCs are requested, but no log output file is specified. - Add a cross-reference to pmclog(3). - Bump document date. Reviewed by: ru Submitted by: ru [1] Approved by: re (blanket hwpmc)
* MFP4:jkoshy2005-06-092-125/+525
| | | | | | | | | | | | | | | | - Implement sampling modes and logging support in hwpmc(4). - Separate MI and MD parts of hwpmc(4) and allow sharing of PMC implementations across different architectures. Add support for P4 (EMT64) style PMCs to the amd64 code. - New pmcstat(8) options: -E (exit time counts) -W (counts every context switch), -R (print log file). - pmc(3) API changes, improve our ability to keep ABI compatibility in the future. Add more 'alias' names for commonly used events. - bug fixes & documentation.
* Neaten usage message.jkoshy2005-05-021-1/+1
|
* Add convenience APIs pmc_width() and pmc_capabilities() to -lpmc.jkoshy2005-05-011-11/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Have pmcstat(8) and pmccontrol(8) use these APIs. Return PMC class-related constants (PMC widths and capabilities) with the OP GETCPUINFO call leaving OP PMCINFO to return only the dynamic information associated with a PMC (i.e., whether enabled, owner pid, reload count etc.). Allow pmc_read() (i.e., OPS PMCRW) on active self-attached PMCs to get upto-date values from hardware since we can guarantee that the hardware is running the correct PMC at the time of the call. Bug fixes: - (x86 class processors) Fix a bug that prevented an RDPMC instruction from being recognized as permitted till after the attached process had context switched out and back in again after a pmc_start() call. Tighten the rules for using RDPMC class instructions: a GETMSR OP is now allowed only after an OP ATTACH has been done by the PMC's owner to itself. OP GETMSR is not allowed for PMCs that track descendants, for PMCs attached to processes other than their owner processes. - (P4/HTT processors only) Fix a bug that caused the MI and MD layers to get out of sync. Add a new MD operation 'get_config()' as part of this fix. - Allow multiple system-mode PMCs at the same row-index but on different CPUs to be allocated. - Reject allocation of an administratively disabled PMC. Misc. code cleanups and refactoring. Improve a few comments.
* Remove superfluous CFLAGS additions. Make 'make checkdpadd' work.jkoshy2005-04-191-4/+2
| | | | | | Use '?=' for the WARNS line. Submitted by: ru
* Bring a working snapshot of hwpmc(4), its associated libraries, userland ↵jkoshy2005-04-193-0/+941
utilities and documentation into -CURRENT. Bump FreeBSD_version. Reviewed by: alc, jhb (kernel changes)
OpenPOWER on IntegriCloud