Linux and UNIX Man Pages

Linux & Unix Commands - Search Man Pages

trace-cmd-mem(1) [centos man page]

TRACE-CMD-MEM(1)														  TRACE-CMD-MEM(1)

NAME
trace-cmd-mem - show memory usage of certain kmem events SYNOPSIS
trace-cmd mem [OPTIONS][input-file] DESCRIPTION
The trace-cmd(1) mem requires a trace-cmd record that enabled the following events: kmalloc kmalloc_node kfree kmem_cache_alloc kmem_cache_alloc_node kmem_cache_alloc_free It then reads the amount requested and the ammount freed as well as the functions that called the allocation. It then reports the final amount of bytes requested and allocated, along with the total amount allocated and requested, as well as the max allocation and requested during the run. It reports the amount of wasted bytes (allocated - requested) that was not freed, as well as the max wasted amount during the run. The list is sorted by descending order of wasted bytes after the run. Function Waste Alloc req TotAlloc TotReq MaxAlloc MaxReq MaxWaste -------- ----- ----- --- -------- ------ -------- ------ -------- rb_allocate_cpu_buffer 768 2304 1536 2304 1536 2304 1536 768 alloc_pipe_info 400 1152 752 1152 752 1152 752 400 instance_mkdir 252 544 292 544 292 544 292 252 __d_alloc 215 1086560 1086345 1087208 1086993 1086560 1086345 215 get_empty_filp 72 2304 2232 4864 4712 4864 4712 152 mm_alloc 40 960 920 960 920 960 920 40 prepare_creds 32 192 160 1728 1440 1728 1440 288 tracing_buffers_open 8 32 24 32 24 32 24 8 do_brk 0 0 0 368 368 368 368 0 journal_add_journal_head 0 6048 6048 6048 6048 6048 6048 0 journal_start 0 0 0 1224 1224 48 48 0 __rb_allocate_pages 0 3289856 3289856 3289856 3289856 3289856 3289856 0 anon_vma_alloc 0 0 0 936 936 864 864 0 [...] OPTIONS
-i input-file By default, trace-cmd hist will read the file trace.dat. But the -i option open up the given input-file instead. Note, the input file may also be specified as the last item on the command line. SEE ALSO
trace-cmd(1), trace-cmd-record(1), trace-cmd-report(1), trace-cmd-start(1), trace-cmd-stop(1), trace-cmd-extract(1), trace-cmd-reset(1), trace-cmd-hist(1), trace-cmd-split(1), trace-cmd-listen(1) AUTHOR
Written by Steven Rostedt, <rostedt@goodmis.org[1]> RESOURCES
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git COPYING
Copyright (C) 2013 Red Hat, Inc. Free use of this software is granted under the terms of the GNU Public License (GPL). NOTES
1. rostedt@goodmis.org mailto:rostedt@goodmis.org 06/11/2014 TRACE-CMD-MEM(1)

Check Out this Related Man Page

TRACE-CMD-SPLIT(1)														TRACE-CMD-SPLIT(1)

NAME
trace-cmd-split - split a trace.dat file into smaller files SYNOPSIS
trace-cmd split [OPTIONS] [start-time [end-time]] DESCRIPTION
The trace-cmd(1) split is used to break up a trace.dat into small files. The start-time specifies where the new file will start at. Using trace-cmd-report(1) and copying the time stamp given at a particular event, can be used as input for either start-time or end-time. The split will stop creating files when it reaches an event after end-time. If only the end-time is needed, use 0.0 as the start-time. If start-time is left out, then the split will start at the beginning of the file. If end-time is left out, then split will continue to the end unless it meets one of the requirements specified by the options. OPTIONS
-i file If this option is not specified, then the split command will look for the file named trace.dat. This options will allow the reading of another file other than trace.dat. -o file By default, the split command will use the input file name as a basis of where to write the split files. The output file will be the input file with an attached '.#' to the end: trace.dat.1, trace.dat.2, etc. This option will change the name of the base file used. -o file will create file.1, file.2, etc. -s seconds This specifies how many seconds should be recorded before the new file should stop. -m milliseconds This specifies how many milliseconds should be recorded before the new file should stop. -u microseconds This specifies how many microseconds should be recorded before the new file should stop. -e events This specifies how many events should be recorded before the new file should stop. -p pages This specifies the number of pages that should be recorded before the new file should stop. Note: only one of *-p*, *-e*, *-u*, *-m*, *-s* may be specified at a time. If *-p* is specified, then *-c* is automatically set. -r This option causes the break up to repeat until end-time is reached (or end of the input if end-time is not specified). trace-cmd split -r -e 10000 This will break up trace.dat into several smaller files, each with at most 10,000 events in it. -c This option causes the above break up to be per CPU. trace-cmd split -c -p 10 This will create a file that has 10 pages per each CPU from the input. SEE ALSO
trace-cmd(1), trace-cmd-record(1), trace-cmd-report(1), trace-cmd-start(1), trace-cmd-stop(1), trace-cmd-extract(1), trace-cmd-reset(1), trace-cmd-list(1), trace-cmd-listen(1) AUTHOR
Written by Steven Rostedt, <rostedt@goodmis.org[1]> RESOURCES
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git COPYING
Copyright (C) 2010 Red Hat, Inc. Free use of this software is granted under the terms of the GNU Public License (GPL). NOTES
1. rostedt@goodmis.org mailto:rostedt@goodmis.org 06/11/2014 TRACE-CMD-SPLIT(1)
Man Page