summaryrefslogtreecommitdiffstats
path: root/documentation/profile-manual/profile-manual-usage.xml
diff options
context:
space:
mode:
Diffstat (limited to 'documentation/profile-manual/profile-manual-usage.xml')
-rw-r--r--documentation/profile-manual/profile-manual-usage.xml3685
1 files changed, 3685 insertions, 0 deletions
diff --git a/documentation/profile-manual/profile-manual-usage.xml b/documentation/profile-manual/profile-manual-usage.xml
new file mode 100644
index 0000000000..5577b1b001
--- /dev/null
+++ b/documentation/profile-manual/profile-manual-usage.xml
@@ -0,0 +1,3685 @@
1<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.2//EN"
2"http://www.oasis-open.org/docbook/xml/4.2/docbookx.dtd"
3[<!ENTITY % poky SYSTEM "../poky.ent"> %poky; ] >
4
5<chapter id='profile-manual-usage'>
6
7<title>Basic Usage (with examples) for each of the Yocto Tracing Tools</title>
8
9<para>
10 This chapter presents basic usage examples for each of the tracing
11 tools.
12</para>
13
14<section id='profile-manual-perf'>
15 <title>perf</title>
16
17 <para>
18 The 'perf' tool is the profiling and tracing tool that comes
19 bundled with the Linux kernel.
20 </para>
21
22 <para>
23 Don't let the fact that it's part of the kernel fool you into thinking
24 that it's only for tracing and profiling the kernel - you can indeed
25 use it to trace and profile just the kernel, but you can also use it
26 to profile specific applications separately (with or without kernel
27 context), and you can also use it to trace and profile the kernel
28 and all applications on the system simultaneously to gain a system-wide
29 view of what's going on.
30 </para>
31
32 <para>
33 In many ways, perf aims to be a superset of all the tracing and profiling
34 tools available in Linux today, including all the other tools covered
35 in this HOWTO. The past couple of years have seen perf subsume a lot
36 of the functionality of those other tools and, at the same time, those
37 other tools have removed large portions of their previous functionality
38 and replaced it with calls to the equivalent functionality now
39 implemented by the perf subsystem. Extrapolation suggests that at
40 some point those other tools will simply become completely redundant
41 and go away; until then, we'll cover those other tools in these pages
42 and in many cases show how the same things can be accomplished in
43 perf and the other tools when it seems useful to do so.
44 </para>
45
46 <para>
47 The coverage below details some of the most common ways you'll likely
48 want to apply the tool; full documentation can be found either within
49 the tool itself or in the man pages at
50 <ulink url='http://linux.die.net/man/1/perf'>perf(1)</ulink>.
51 </para>
52
53 <section id='perf-setup'>
54 <title>Setup</title>
55
56 <para>
57 For this section, we'll assume you've already performed the basic
58 setup outlined in the General Setup section.
59 </para>
60
61 <para>
62 In particular, you'll get the most mileage out of perf if you
63 profile an image built with INHIBIT_PACKAGE_STRIP = "1" in your
64 local.conf.
65 </para>
66
67 <para>
68 perf runs on the target system for the most part. You can archive
69 profile data and copy it to the host for analysis, but for the
70 rest of this document we assume you've ssh'ed to the host and
71 will be running the perf commands on the target.
72 </para>
73 </section>
74
75 <section id='perf-basic-usage'>
76 <title>Basic Usage</title>
77
78 <para>
79 The perf tool is pretty much self-documenting. To remind yourself
80 of the available commands, simply type 'perf', which will show you
81 basic usage along with the available perf subcommands:
82 <literallayout class='monospaced'>
83 root@crownbay:~# perf
84
85 usage: perf [--version] [--help] COMMAND [ARGS]
86
87 The most commonly used perf commands are:
88 annotate Read perf.data (created by perf record) and display annotated code
89 archive Create archive with object files with build-ids found in perf.data file
90 bench General framework for benchmark suites
91 buildid-cache Manage build-id cache.
92 buildid-list List the buildids in a perf.data file
93 diff Read two perf.data files and display the differential profile
94 evlist List the event names in a perf.data file
95 inject Filter to augment the events stream with additional information
96 kmem Tool to trace/measure kernel memory(slab) properties
97 kvm Tool to trace/measure kvm guest os
98 list List all symbolic event types
99 lock Analyze lock events
100 probe Define new dynamic tracepoints
101 record Run a command and record its profile into perf.data
102 report Read perf.data (created by perf record) and display the profile
103 sched Tool to trace/measure scheduler properties (latencies)
104 script Read perf.data (created by perf record) and display trace output
105 stat Run a command and gather performance counter statistics
106 test Runs sanity tests.
107 timechart Tool to visualize total system behavior during a workload
108 top System profiling tool.
109
110 See 'perf help COMMAND' for more information on a specific command.
111 </literallayout>
112 </para>
113
114 <section id='using-perf-to-do-basic-profiling'>
115 <title>Using perf to do Basic Profiling</title>
116
117 <para>
118 As a simple test case, we'll profile the 'wget' of a fairly large
119 file, which is a minimally interesting case because it has both
120 file and network I/O aspects, and at least in the case of standard
121 Yocto images, it's implemented as part of busybox, so the methods
122 we use to analyze it can be used in a very similar way to the whole
123 host of supported busybox applets in Yocto.
124 <literallayout class='monospaced'>
125 root@crownbay:~# rm linux-2.6.19.2.tar.bz2; \
126 wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
127 </literallayout>
128 The quickest and easiest way to get some basic overall data about
129 what's going on for a particular workload is to profile it using
130 'perf stat'. 'perf stat' basically profiles using a few default
131 counters and displays the summed counts at the end of the run:
132 <literallayout class='monospaced'>
133 root@crownbay:~# perf stat wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
134 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
135 linux-2.6.19.2.tar.b 100% |***************************************************| 41727k 0:00:00 ETA
136
137 Performance counter stats for 'wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>':
138
139 4597.223902 task-clock # 0.077 CPUs utilized
140 23568 context-switches # 0.005 M/sec
141 68 CPU-migrations # 0.015 K/sec
142 241 page-faults # 0.052 K/sec
143 3045817293 cycles # 0.663 GHz
144 &lt;not supported&gt; stalled-cycles-frontend
145 &lt;not supported&gt; stalled-cycles-backend
146 858909167 instructions # 0.28 insns per cycle
147 165441165 branches # 35.987 M/sec
148 19550329 branch-misses # 11.82% of all branches
149
150 59.836627620 seconds time elapsed
151 </literallayout>
152 Many times such a simple-minded test doesn't yield much of
153 interest, but sometimes it does (see Real-world Yocto bug
154 (slow loop-mounted write speed)).
155 </para>
156
157 <para>
158 Also, note that 'perf stat' isn't restricted to a fixed set of
159 counters - basically any event listed in the output of 'perf list'
160 can be tallied by 'perf stat'. For example, suppose we wanted to
161 see a summary of all the events related to kernel memory
162 allocation/freeing along with cache hits and misses:
163 <literallayout class='monospaced'>
164 root@crownbay:~# perf stat -e kmem:* -e cache-references -e cache-misses wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
165 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
166 linux-2.6.19.2.tar.b 100% |***************************************************| 41727k 0:00:00 ETA
167
168 Performance counter stats for 'wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>':
169
170 5566 kmem:kmalloc
171 125517 kmem:kmem_cache_alloc
172 0 kmem:kmalloc_node
173 0 kmem:kmem_cache_alloc_node
174 34401 kmem:kfree
175 69920 kmem:kmem_cache_free
176 133 kmem:mm_page_free
177 41 kmem:mm_page_free_batched
178 11502 kmem:mm_page_alloc
179 11375 kmem:mm_page_alloc_zone_locked
180 0 kmem:mm_page_pcpu_drain
181 0 kmem:mm_page_alloc_extfrag
182 66848602 cache-references
183 2917740 cache-misses # 4.365 % of all cache refs
184
185 44.831023415 seconds time elapsed
186 </literallayout>
187 So 'perf stat' gives us a nice easy way to get a quick overview of
188 what might be happening for a set of events, but normally we'd
189 need a little more detail in order to understand what's going on
190 in a way that we can act on in a useful way.
191 </para>
192
193 <para>
194 To dive down into a next level of detail, we can use 'perf
195 record'/'perf report' which will collect profiling data and
196 present it to use using an interactive text-based UI (or
197 simply as text if we specify --stdio to 'perf report').
198 </para>
199
200 <para>
201 As our first attempt at profiling this workload, we'll simply
202 run 'perf record', handing it the workload we want to profile
203 (everything after 'perf record' and any perf options we hand
204 it - here none - will be executed in a new shell). perf collects
205 samples until the process exits and records them in a file named
206 'perf.data' in the current working directory.
207 <literallayout class='monospaced'>
208 root@crownbay:~# perf record wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
209
210 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
211 linux-2.6.19.2.tar.b 100% |************************************************| 41727k 0:00:00 ETA
212 [ perf record: Woken up 1 times to write data ]
213 [ perf record: Captured and wrote 0.176 MB perf.data (~7700 samples) ]
214 </literallayout>
215 To see the results in a 'text-based UI' (tui), simply run
216 'perf report', which will read the perf.data file in the current
217 working directory and display the results in an interactive UI:
218 <literallayout class='monospaced'>
219 root@crownbay:~# perf report
220 </literallayout>
221 </para>
222
223 <para>
224 <imagedata fileref="figures/perf-wget-flat-stripped.png" width="6in" depth="7in" align="center" scalefit="1" />
225 </para>
226
227 <para>
228 The above screenshot displays a 'flat' profile, one entry for
229 each 'bucket' corresponding to the functions that were profiled
230 during the profiling run, ordered from the most popular to the
231 least (perf has options to sort in various orders and keys as
232 well as display entries only above a certain threshold and so
233 on - see the perf documentation for details). Note that this
234 includes both userspace functions (entries containing a [.]) and
235 kernel functions accounted to the process (entries containing
236 a [k]). (perf has command-line modifiers that can be used to
237 restrict the profiling to kernel or userspace, among others).
238 </para>
239
240 <para>
241 Notice also that the above report shows an entry for 'busybox',
242 which is the executable that implements 'wget' in Yocto, but that
243 instead of a useful function name in that entry, it displays
244 a not-so-friendly hex value instead. The steps below will show
245 how to fix that problem.
246 </para>
247
248 <para>
249 Before we do that, however, let's try running a different profile,
250 one which shows something a little more interesting. The only
251 difference between the new profile and the previous one is that
252 we'll add the -g option, which will record not just the address
253 of a sampled function, but the entire callchain to the sampled
254 function as well:
255 <literallayout class='monospaced'>
256 root@crownbay:~# perf record -g wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
257 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
258 linux-2.6.19.2.tar.b 100% |************************************************| 41727k 0:00:00 ETA
259 [ perf record: Woken up 3 times to write data ]
260 [ perf record: Captured and wrote 0.652 MB perf.data (~28476 samples) ]
261
262
263 root@crownbay:~# perf report
264 </literallayout>
265 </para>
266
267 <para>
268 <imagedata fileref="figures/perf-wget-g-copy-to-user-expanded-stripped.png" width="6in" depth="7in" align="center" scalefit="1" />
269 </para>
270
271 <para>
272 Using the callgraph view, we can actually see not only which
273 functions took the most time, but we can also see a summary of
274 how those functions were called and learn something about how the
275 program interacts with the kernel in the process.
276 </para>
277
278 <para>
279 Notice that each entry in the above screenshot now contains a '+'
280 on the left-hand side. This means that we can expand the entry and
281 drill down into the callchains that feed into that entry.
282 Pressing 'enter' on any one of them will expand the callchain
283 (you can also press 'E' to expand them all at the same time or 'C'
284 to collapse them all).
285 </para>
286
287 <para>
288 In the screenshot above, we've toggled the __copy_to_user_ll()
289 entry and several subnodes all the way down. This lets us see
290 which callchains contributed to the profiled __copy_to_user_ll()
291 function which contributed 1.77% to the total profile.
292 </para>
293
294 <para>
295 As a bit of background explanation for these callchains, think
296 about what happens at a high level when you run wget to get a file
297 out on the network. Basically what happens is that the data comes
298 into the kernel via the network connection (socket) and is passed
299 to the userspace program 'wget' (which is actually a part of
300 busybox, but that's not important for now), which takes the buffers
301 the kernel passes to it and writes it to a disk file to save it.
302 </para>
303
304 <para>
305 The part of this process that we're looking at in the above call
306 stacks is the part where the kernel passes the data it's read from
307 the socket down to wget i.e. a copy-to-user.
308 </para>
309
310 <para>
311 Notice also that here there's also a case where the hex value
312 is displayed in the callstack, here in the expanded
313 sys_clock_gettime() function. Later we'll see it resolve to a
314 userspace function call in busybox.
315 </para>
316
317 <para>
318 <imagedata fileref="figures/perf-wget-g-copy-from-user-expanded-stripped.png" width="6in" depth="7in" align="center" scalefit="1" />
319 </para>
320
321 <para>
322 The above screenshot shows the other half of the journey for the
323 data - from the wget program's userspace buffers to disk. To get
324 the buffers to disk, the wget program issues a write(2), which
325 does a copy-from-user to the kernel, which then takes care via
326 some circuitous path (probably also present somewhere in the
327 profile data), to get it safely to disk.
328 </para>
329
330 <para>
331 Now that we've seen the basic layout of the profile data and the
332 basics of how to extract useful information out of it, let's get
333 back to the task at hand and see if we can get some basic idea
334 about where the time is spent in the program we're profiling,
335 wget. Remember that wget is actually implemented as an applet
336 in busybox, so while the process name is 'wget', the executable
337 we're actually interested in is busybox. So let's expand the
338 first entry containing busybox:
339 </para>
340
341 <para>
342 <imagedata fileref="figures/perf-wget-busybox-expanded-stripped.png" width="6in" depth="7in" align="center" scalefit="1" />
343 </para>
344
345 <para>
346 Again, before we expanded we saw that the function was labeled
347 with a hex value instead of a symbol as with most of the kernel
348 entries. Expanding the busybox entry doesn't make it any better.
349 </para>
350
351 <para>
352 The problem is that perf can't find the symbol information for the
353 busybox binary, which is actually stripped out by the Yocto build
354 system.
355 </para>
356
357 <para>
358 One way around that is to put the following in your local.conf
359 when you build the image:
360 <literallayout class='monospaced'>
361 INHIBIT_PACKAGE_STRIP = "1"
362 </literallayout>
363 However, we already have an image with the binaries stripped,
364 so what can we do to get perf to resolve the symbols? Basically
365 we need to install the debuginfo for the busybox package.
366 </para>
367
368 <para>
369 To generate the debug info for the packages in the image, we can
370 add dbg-pkgs to EXTRA_IMAGE_FEATURES in local.conf. For example:
371 <literallayout class='monospaced'>
372 EXTRA_IMAGE_FEATURES = "debug-tweaks tools-profile dbg-pkgs"
373 </literallayout>
374 Additionally, in order to generate the type of debuginfo that
375 perf understands, we also need to add the following to local.conf:
376 <literallayout class='monospaced'>
377 PACKAGE_DEBUG_SPLIT_STYLE = 'debug-file-directory'
378 </literallayout>
379 Once we've done that, we can install the debuginfo for busybox.
380 The debug packages once built can be found in
381 build/tmp/deploy/rpm/* on the host system. Find the
382 busybox-dbg-...rpm file and copy it to the target. For example:
383 <literallayout class='monospaced'>
384 [trz@empanada core2]$ scp /home/trz/yocto/crownbay-tracing-dbg/build/tmp/deploy/rpm/core2_32/busybox-dbg-1.20.2-r2.core2_32.rpm root@192.168.1.31:
385 root@192.168.1.31's password:
386 busybox-dbg-1.20.2-r2.core2_32.rpm 100% 1826KB 1.8MB/s 00:01
387 </literallayout>
388 Now install the debug rpm on the target:
389 <literallayout class='monospaced'>
390 root@crownbay:~# rpm -i busybox-dbg-1.20.2-r2.core2_32.rpm
391 </literallayout>
392 Now that the debuginfo is installed, we see that the busybox
393 entries now display their functions symbolically:
394 </para>
395
396 <para>
397 <imagedata fileref="figures/perf-wget-busybox-debuginfo.png" width="6in" depth="7in" align="center" scalefit="1" />
398 </para>
399
400 <para>
401 If we expand one of the entries and press 'enter' on a leaf node,
402 we're presented with a menu of actions we can take to get more
403 information related to that entry:
404 </para>
405
406 <para>
407 <imagedata fileref="figures/perf-wget-busybox-dso-zoom-menu.png" width="6in" depth="2in" align="center" scalefit="1" />
408 </para>
409
410 <para>
411 One of these actions allows us to show a view that displays a
412 busybox-centric view of the profiled functions (in this case we've
413 also expanded all the nodes using the 'E' key):
414 </para>
415
416 <para>
417 <imagedata fileref="figures/perf-wget-busybox-dso-zoom.png" width="6in" depth="7in" align="center" scalefit="1" />
418 </para>
419
420 <para>
421 Finally, we can see that now that the busybox debuginfo is
422 installed, the previously unresolved symbol in the
423 sys_clock_gettime() entry mentioned previously is now resolved,
424 and shows that the sys_clock_gettime system call that was the
425 source of 6.75% of the copy-to-user overhead was initiated by
426 the handle_input() busybox function:
427 </para>
428
429 <para>
430 <imagedata fileref="figures/perf-wget-g-copy-to-user-expanded-debuginfo.png" width="6in" depth="7in" align="center" scalefit="1" />
431 </para>
432
433 <para>
434 At the lowest level of detail, we can dive down to the assembly
435 level and see which instructions caused the most overhead in a
436 function. Pressing 'enter' on the 'udhcpc_main' function, we're
437 again presented with a menu:
438 </para>
439
440 <para>
441 <imagedata fileref="figures/perf-wget-busybox-annotate-menu.png" width="6in" depth="2in" align="center" scalefit="1" />
442 </para>
443
444 <para>
445 Selecting 'Annotate udhcpc_main', we get a detailed listing of
446 percentages by instruction for the udhcpc_main function. From the
447 display, we can see that over 50% of the time spent in this
448 function is taken up by a couple tests and the move of a
449 constant (1) to a register:
450 </para>
451
452 <para>
453 <imagedata fileref="figures/perf-wget-busybox-annotate-udhcpc.png" width="6in" depth="7in" align="center" scalefit="1" />
454 </para>
455
456 <para>
457 As a segue into tracing, let's try another profile using a
458 different counter, something other than the default 'cycles'.
459 </para>
460
461 <para>
462 The tracing and profiling infrastructure in Linux has become
463 unified in a way that allows us to use the same tool with a
464 completely different set of counters, not just the standard
465 hardware counters that traditional tools have had to restrict
466 themselves to (of course the traditional tools can also make use
467 of the expanded possibilities now available to them, and in some
468 cases have, as mentioned previously).
469 </para>
470
471 <para>
472 We can get a list of the available events that can be used to
473 profile a workload via 'perf list':
474 <literallayout class='monospaced'>
475 root@crownbay:~# perf list
476
477 List of pre-defined events (to be used in -e):
478 cpu-cycles OR cycles [Hardware event]
479 stalled-cycles-frontend OR idle-cycles-frontend [Hardware event]
480 stalled-cycles-backend OR idle-cycles-backend [Hardware event]
481 instructions [Hardware event]
482 cache-references [Hardware event]
483 cache-misses [Hardware event]
484 branch-instructions OR branches [Hardware event]
485 branch-misses [Hardware event]
486 bus-cycles [Hardware event]
487 ref-cycles [Hardware event]
488
489 cpu-clock [Software event]
490 task-clock [Software event]
491 page-faults OR faults [Software event]
492 minor-faults [Software event]
493 major-faults [Software event]
494 context-switches OR cs [Software event]
495 cpu-migrations OR migrations [Software event]
496 alignment-faults [Software event]
497 emulation-faults [Software event]
498
499 L1-dcache-loads [Hardware cache event]
500 L1-dcache-load-misses [Hardware cache event]
501 L1-dcache-prefetch-misses [Hardware cache event]
502 L1-icache-loads [Hardware cache event]
503 L1-icache-load-misses [Hardware cache event]
504 .
505 .
506 .
507 rNNN [Raw hardware event descriptor]
508 cpu/t1=v1[,t2=v2,t3 ...]/modifier [Raw hardware event descriptor]
509 (see 'perf list --help' on how to encode it)
510
511 mem:&lt;addr&gt;[:access] [Hardware breakpoint]
512
513 sunrpc:rpc_call_status [Tracepoint event]
514 sunrpc:rpc_bind_status [Tracepoint event]
515 sunrpc:rpc_connect_status [Tracepoint event]
516 sunrpc:rpc_task_begin [Tracepoint event]
517 skb:kfree_skb [Tracepoint event]
518 skb:consume_skb [Tracepoint event]
519 skb:skb_copy_datagram_iovec [Tracepoint event]
520 net:net_dev_xmit [Tracepoint event]
521 net:net_dev_queue [Tracepoint event]
522 net:netif_receive_skb [Tracepoint event]
523 net:netif_rx [Tracepoint event]
524 napi:napi_poll [Tracepoint event]
525 sock:sock_rcvqueue_full [Tracepoint event]
526 sock:sock_exceed_buf_limit [Tracepoint event]
527 udp:udp_fail_queue_rcv_skb [Tracepoint event]
528 hda:hda_send_cmd [Tracepoint event]
529 hda:hda_get_response [Tracepoint event]
530 hda:hda_bus_reset [Tracepoint event]
531 scsi:scsi_dispatch_cmd_start [Tracepoint event]
532 scsi:scsi_dispatch_cmd_error [Tracepoint event]
533 scsi:scsi_eh_wakeup [Tracepoint event]
534 drm:drm_vblank_event [Tracepoint event]
535 drm:drm_vblank_event_queued [Tracepoint event]
536 drm:drm_vblank_event_delivered [Tracepoint event]
537 random:mix_pool_bytes [Tracepoint event]
538 random:mix_pool_bytes_nolock [Tracepoint event]
539 random:credit_entropy_bits [Tracepoint event]
540 gpio:gpio_direction [Tracepoint event]
541 gpio:gpio_value [Tracepoint event]
542 block:block_rq_abort [Tracepoint event]
543 block:block_rq_requeue [Tracepoint event]
544 block:block_rq_issue [Tracepoint event]
545 block:block_bio_bounce [Tracepoint event]
546 block:block_bio_complete [Tracepoint event]
547 block:block_bio_backmerge [Tracepoint event]
548 .
549 .
550 writeback:writeback_wake_thread [Tracepoint event]
551 writeback:writeback_wake_forker_thread [Tracepoint event]
552 writeback:writeback_bdi_register [Tracepoint event]
553 .
554 .
555 writeback:writeback_single_inode_requeue [Tracepoint event]
556 writeback:writeback_single_inode [Tracepoint event]
557 kmem:kmalloc [Tracepoint event]
558 kmem:kmem_cache_alloc [Tracepoint event]
559 kmem:mm_page_alloc [Tracepoint event]
560 kmem:mm_page_alloc_zone_locked [Tracepoint event]
561 kmem:mm_page_pcpu_drain [Tracepoint event]
562 kmem:mm_page_alloc_extfrag [Tracepoint event]
563 vmscan:mm_vmscan_kswapd_sleep [Tracepoint event]
564 vmscan:mm_vmscan_kswapd_wake [Tracepoint event]
565 vmscan:mm_vmscan_wakeup_kswapd [Tracepoint event]
566 vmscan:mm_vmscan_direct_reclaim_begin [Tracepoint event]
567 .
568 .
569 module:module_get [Tracepoint event]
570 module:module_put [Tracepoint event]
571 module:module_request [Tracepoint event]
572 sched:sched_kthread_stop [Tracepoint event]
573 sched:sched_wakeup [Tracepoint event]
574 sched:sched_wakeup_new [Tracepoint event]
575 sched:sched_process_fork [Tracepoint event]
576 sched:sched_process_exec [Tracepoint event]
577 sched:sched_stat_runtime [Tracepoint event]
578 rcu:rcu_utilization [Tracepoint event]
579 workqueue:workqueue_queue_work [Tracepoint event]
580 workqueue:workqueue_execute_end [Tracepoint event]
581 signal:signal_generate [Tracepoint event]
582 signal:signal_deliver [Tracepoint event]
583 timer:timer_init [Tracepoint event]
584 timer:timer_start [Tracepoint event]
585 timer:hrtimer_cancel [Tracepoint event]
586 timer:itimer_state [Tracepoint event]
587 timer:itimer_expire [Tracepoint event]
588 irq:irq_handler_entry [Tracepoint event]
589 irq:irq_handler_exit [Tracepoint event]
590 irq:softirq_entry [Tracepoint event]
591 irq:softirq_exit [Tracepoint event]
592 irq:softirq_raise [Tracepoint event]
593 printk:console [Tracepoint event]
594 task:task_newtask [Tracepoint event]
595 task:task_rename [Tracepoint event]
596 syscalls:sys_enter_socketcall [Tracepoint event]
597 syscalls:sys_exit_socketcall [Tracepoint event]
598 .
599 .
600 .
601 syscalls:sys_enter_unshare [Tracepoint event]
602 syscalls:sys_exit_unshare [Tracepoint event]
603 raw_syscalls:sys_enter [Tracepoint event]
604 raw_syscalls:sys_exit [Tracepoint event]
605 </literallayout>
606 </para>
607
608 <informalexample>
609 <emphasis>Tying it Together:</emphasis> These are exactly the same set of events defined
610 by the trace event subsystem and exposed by
611 ftrace/tracecmd/kernelshark as files in
612 /sys/kernel/debug/tracing/events, by SystemTap as
613 kernel.trace("tracepoint_name") and (partially) accessed by LTTng.
614 </informalexample>
615
616 <para>
617 Only a subset of these would be of interest to us when looking at
618 this workload, so let's choose the most likely subsystems
619 (identified by the string before the colon in the Tracepoint events)
620 and do a 'perf stat' run using only those wildcarded subsystems:
621 <literallayout class='monospaced'>
622 root@crownbay:~# perf stat -e skb:* -e net:* -e napi:* -e sched:* -e workqueue:* -e irq:* -e syscalls:* wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
623 Performance counter stats for 'wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>':
624
625 23323 skb:kfree_skb
626 0 skb:consume_skb
627 49897 skb:skb_copy_datagram_iovec
628 6217 net:net_dev_xmit
629 6217 net:net_dev_queue
630 7962 net:netif_receive_skb
631 2 net:netif_rx
632 8340 napi:napi_poll
633 0 sched:sched_kthread_stop
634 0 sched:sched_kthread_stop_ret
635 3749 sched:sched_wakeup
636 0 sched:sched_wakeup_new
637 0 sched:sched_switch
638 29 sched:sched_migrate_task
639 0 sched:sched_process_free
640 1 sched:sched_process_exit
641 0 sched:sched_wait_task
642 0 sched:sched_process_wait
643 0 sched:sched_process_fork
644 1 sched:sched_process_exec
645 0 sched:sched_stat_wait
646 2106519415641 sched:sched_stat_sleep
647 0 sched:sched_stat_iowait
648 147453613 sched:sched_stat_blocked
649 12903026955 sched:sched_stat_runtime
650 0 sched:sched_pi_setprio
651 3574 workqueue:workqueue_queue_work
652 3574 workqueue:workqueue_activate_work
653 0 workqueue:workqueue_execute_start
654 0 workqueue:workqueue_execute_end
655 16631 irq:irq_handler_entry
656 16631 irq:irq_handler_exit
657 28521 irq:softirq_entry
658 28521 irq:softirq_exit
659 28728 irq:softirq_raise
660 1 syscalls:sys_enter_sendmmsg
661 1 syscalls:sys_exit_sendmmsg
662 0 syscalls:sys_enter_recvmmsg
663 0 syscalls:sys_exit_recvmmsg
664 14 syscalls:sys_enter_socketcall
665 14 syscalls:sys_exit_socketcall
666 .
667 .
668 .
669 16965 syscalls:sys_enter_read
670 16965 syscalls:sys_exit_read
671 12854 syscalls:sys_enter_write
672 12854 syscalls:sys_exit_write
673 .
674 .
675 .
676
677 58.029710972 seconds time elapsed
678 </literallayout>
679 Let's pick one of these tracepoints and tell perf to do a profile
680 using it as the sampling event:
681 <literallayout class='monospaced'>
682 root@crownbay:~# perf record -g -e sched:sched_wakeup wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
683 </literallayout>
684 </para>
685
686 <para>
687 <imagedata fileref="figures/sched-wakeup-profile.png" width="6in" depth="7in" align="center" scalefit="1" />
688 </para>
689
690 <para>
691 The screenshot above shows the results of running a profile using
692 sched:sched_switch tracepoint, which shows the relative costs of
693 various paths to sched_wakeup (note that sched_wakeup is the
694 name of the tracepoint - it's actually defined just inside
695 ttwu_do_wakeup(), which accounts for the function name actually
696 displayed in the profile:
697 <literallayout class='monospaced'>
698 /*
699 * Mark the task runnable and perform wakeup-preemption.
700 */
701 static void
702 ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
703 {
704 trace_sched_wakeup(p, true);
705 .
706 .
707 .
708 }
709 </literallayout>
710 A couple of the more interesting callchains are expanded and
711 displayed above, basically some network receive paths that
712 presumably end up waking up wget (busybox) when network data is
713 ready.
714 </para>
715
716 <para>
717 Note that because tracepoints are normally used for tracing,
718 the default sampling period for tracepoints is 1 i.e. for
719 tracepoints perf will sample on every event occurrence (this
720 can be changed using the -c option). This is in contrast to
721 hardware counters such as for example the default 'cycles'
722 hardware counter used for normal profiling, where sampling
723 periods are much higher (in the thousands) because profiling should
724 have as low an overhead as possible and sampling on every cycle
725 would be prohibitively expensive.
726 </para>
727 </section>
728
729 <section id='using-perf-to-do-basic-tracing'>
730 <title>Using perf to do Basic Tracing</title>
731
732 <para>
733 Profiling is a great tool for solving many problems or for
734 getting a high-level view of what's going on with a workload or
735 across the system. It is however by definition an approximation,
736 as suggested by the most prominent word associated with it,
737 'sampling'. On the one hand, it allows a representative picture of
738 what's going on in the system to be cheaply taken, but on the other
739 hand, that cheapness limits its utility when that data suggests a
740 need to 'dive down' more deeply to discover what's really going
741 on. In such cases, the only way to see what's really going on is
742 to be able to look at (or summarize more intelligently) the
743 individual steps that go into the higher-level behavior exposed
744 by the coarse-grained profiling data.
745 </para>
746
747 <para>
748 As a concrete example, we can trace all the events we think might
749 be applicable to our workload:
750 <literallayout class='monospaced'>
751 root@crownbay:~# perf record -g -e skb:* -e net:* -e napi:* -e sched:sched_switch -e sched:sched_wakeup -e irq:*
752 -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write
753 wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
754 </literallayout>
755 We can look at the raw trace output using 'perf script' with no
756 arguments:
757 <literallayout class='monospaced'>
758 root@crownbay:~# perf script
759
760 perf 1262 [000] 11624.857082: sys_exit_read: 0x0
761 perf 1262 [000] 11624.857193: sched_wakeup: comm=migration/0 pid=6 prio=0 success=1 target_cpu=000
762 wget 1262 [001] 11624.858021: softirq_raise: vec=1 [action=TIMER]
763 wget 1262 [001] 11624.858074: softirq_entry: vec=1 [action=TIMER]
764 wget 1262 [001] 11624.858081: softirq_exit: vec=1 [action=TIMER]
765 wget 1262 [001] 11624.858166: sys_enter_read: fd: 0x0003, buf: 0xbf82c940, count: 0x0200
766 wget 1262 [001] 11624.858177: sys_exit_read: 0x200
767 wget 1262 [001] 11624.858878: kfree_skb: skbaddr=0xeb248d80 protocol=0 location=0xc15a5308
768 wget 1262 [001] 11624.858945: kfree_skb: skbaddr=0xeb248000 protocol=0 location=0xc15a5308
769 wget 1262 [001] 11624.859020: softirq_raise: vec=1 [action=TIMER]
770 wget 1262 [001] 11624.859076: softirq_entry: vec=1 [action=TIMER]
771 wget 1262 [001] 11624.859083: softirq_exit: vec=1 [action=TIMER]
772 wget 1262 [001] 11624.859167: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
773 wget 1262 [001] 11624.859192: sys_exit_read: 0x1d7
774 wget 1262 [001] 11624.859228: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
775 wget 1262 [001] 11624.859233: sys_exit_read: 0x0
776 wget 1262 [001] 11624.859573: sys_enter_read: fd: 0x0003, buf: 0xbf82c580, count: 0x0200
777 wget 1262 [001] 11624.859584: sys_exit_read: 0x200
778 wget 1262 [001] 11624.859864: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
779 wget 1262 [001] 11624.859888: sys_exit_read: 0x400
780 wget 1262 [001] 11624.859935: sys_enter_read: fd: 0x0003, buf: 0xb7720000, count: 0x0400
781 wget 1262 [001] 11624.859944: sys_exit_read: 0x400
782 </literallayout>
783 This gives us a detailed timestamped sequence of events that
784 occurred within the workload with respect to those events.
785 </para>
786
787 <para>
788 In many ways, profiling can be viewed as a subset of tracing -
789 theoretically, if you have a set of trace events that's sufficient
790 to capture all the important aspects of a workload, you can derive
791 any of the results or views that a profiling run can.
792 </para>
793
794 <para>
795 Another aspect of traditional profiling is that while powerful in
796 many ways, it's limited by the granularity of the underlying data.
797 Profiling tools offer various ways of sorting and presenting the
798 sample data, which make it much more useful and amenable to user
799 experimentation, but in the end it can't be used in an open-ended
800 way to extract data that just isn't present as a consequence of
801 the fact that conceptually, most of it has been thrown away.
802 </para>
803
804 <para>
805 Full-blown detailed tracing data does however offer the opportunity
806 to manipulate and present the information collected during a
807 tracing run in an infinite variety of ways.
808 </para>
809
810 <para>
811 Another way to look at it is that there are only so many ways that
812 the 'primitive' counters can be used on their own to generate
813 interesting output; to get anything more complicated than simple
814 counts requires some amount of additional logic, which is typically
815 very specific to the problem at hand. For example, if we wanted to
816 make use of a 'counter' that maps to the value of the time
817 difference between when a process was scheduled to run on a
818 processor and the time it actually ran, we wouldn't expect such
819 a counter to exist on its own, but we could derive one called say
820 'wakeup_latency' and use it to extract a useful view of that metric
821 from trace data. Likewise, we really can't figure out from standard
822 profiling tools how much data every process on the system reads and
823 writes, along with how many of those reads and writes fail
824 completely. If we have sufficient trace data, however, we could
825 with the right tools easily extract and present that information,
826 but we'd need something other than pre-canned profiling tools to
827 do that.
828 </para>
829
830 <para>
831 Luckily, there is a general-purpose way to handle such needs,
832 called 'programming languages'. Making programming languages
833 easily available to apply to such problems given the specific
834 format of data is called a 'programming language binding' for
835 that data and language. Perf supports two programming language
836 bindings, one for Python and one for Perl.
837 </para>
838
839 <informalexample>
840 <emphasis>Tying it Together:</emphasis> Language bindings for manipulating and
841 aggregating trace data are of course not a new
842 idea. One of the first projects to do this was IBM's DProbes
843 dpcc compiler, an ANSI C compiler which targeted a low-level
844 assembly language running on an in-kernel interpreter on the
845 target system. This is exactly analagous to what Sun's DTrace
846 did, except that DTrace invented its own language for the purpose.
847 Systemtap, heavily inspired by DTrace, also created its own
848 one-off language, but rather than running the product on an
849 in-kernel interpreter, created an elaborate compiler-based
850 machinery to translate its language into kernel modules written
851 in C.
852 </informalexample>
853
854 <para>
855 Now that we have the trace data in perf.data, we can use
856 'perf script -g' to generate a skeleton script with handlers
857 for the read/write entry/exit events we recorded:
858 <literallayout class='monospaced'>
859 root@crownbay:~# perf script -g python
860 generated Python script: perf-script.py
861 </literallayout>
862 The skeleton script simply creates a python function for each
863 event type in the perf.data file. The body of each function simply
864 prints the event name along with its parameters. For example:
865 <literallayout class='monospaced'>
866 def net__netif_rx(event_name, context, common_cpu,
867 common_secs, common_nsecs, common_pid, common_comm,
868 skbaddr, len, name):
869 print_header(event_name, common_cpu, common_secs, common_nsecs,
870 common_pid, common_comm)
871
872 print "skbaddr=%u, len=%u, name=%s\n" % (skbaddr, len, name),
873 </literallayout>
874 We can run that script directly to print all of the events
875 contained in the perf.data file:
876 <literallayout class='monospaced'>
877 root@crownbay:~# perf script -s perf-script.py
878
879 in trace_begin
880 syscalls__sys_exit_read 0 11624.857082795 1262 perf nr=3, ret=0
881 sched__sched_wakeup 0 11624.857193498 1262 perf comm=migration/0, pid=6, prio=0, success=1, target_cpu=0
882 irq__softirq_raise 1 11624.858021635 1262 wget vec=TIMER
883 irq__softirq_entry 1 11624.858074075 1262 wget vec=TIMER
884 irq__softirq_exit 1 11624.858081389 1262 wget vec=TIMER
885 syscalls__sys_enter_read 1 11624.858166434 1262 wget nr=3, fd=3, buf=3213019456, count=512
886 syscalls__sys_exit_read 1 11624.858177924 1262 wget nr=3, ret=512
887 skb__kfree_skb 1 11624.858878188 1262 wget skbaddr=3945041280, location=3243922184, protocol=0
888 skb__kfree_skb 1 11624.858945608 1262 wget skbaddr=3945037824, location=3243922184, protocol=0
889 irq__softirq_raise 1 11624.859020942 1262 wget vec=TIMER
890 irq__softirq_entry 1 11624.859076935 1262 wget vec=TIMER
891 irq__softirq_exit 1 11624.859083469 1262 wget vec=TIMER
892 syscalls__sys_enter_read 1 11624.859167565 1262 wget nr=3, fd=3, buf=3077701632, count=1024
893 syscalls__sys_exit_read 1 11624.859192533 1262 wget nr=3, ret=471
894 syscalls__sys_enter_read 1 11624.859228072 1262 wget nr=3, fd=3, buf=3077701632, count=1024
895 syscalls__sys_exit_read 1 11624.859233707 1262 wget nr=3, ret=0
896 syscalls__sys_enter_read 1 11624.859573008 1262 wget nr=3, fd=3, buf=3213018496, count=512
897 syscalls__sys_exit_read 1 11624.859584818 1262 wget nr=3, ret=512
898 syscalls__sys_enter_read 1 11624.859864562 1262 wget nr=3, fd=3, buf=3077701632, count=1024
899 syscalls__sys_exit_read 1 11624.859888770 1262 wget nr=3, ret=1024
900 syscalls__sys_enter_read 1 11624.859935140 1262 wget nr=3, fd=3, buf=3077701632, count=1024
901 syscalls__sys_exit_read 1 11624.859944032 1262 wget nr=3, ret=1024
902 </literallayout>
903 That in itself isn't very useful; after all, we can accomplish
904 pretty much the same thing by simply running 'perf script'
905 without arguments in the same directory as the perf.data file.
906 </para>
907
908 <para>
909 We can however replace the print statements in the generated
910 function bodies with whatever we want, and thereby make it
911 infinitely more useful.
912 </para>
913
914 <para>
915 As a simple example, let's just replace the print statements in
916 the function bodies with a simple function that does nothing but
917 increment a per-event count. When the program is run against a
918 perf.data file, each time a particular event is encountered,
919 a tally is incremented for that event. For example:
920 <literallayout class='monospaced'>
921 def net__netif_rx(event_name, context, common_cpu,
922 common_secs, common_nsecs, common_pid, common_comm,
923 skbaddr, len, name):
924 inc_counts(event_name)
925 </literallayout>
926 Each event handler function in the generated code is modified
927 to do this. For convenience, we define a common function called
928 inc_counts() that each handler calls; inc_counts() simply tallies
929 a count for each event using the 'counts' hash, which is a
930 specialized hash function that does Perl-like autovivification, a
931 capability that's extremely useful for kinds of multi-level
932 aggregation commonly used in processing traces (see perf's
933 documentation on the Python language binding for details):
934 <literallayout class='monospaced'>
935 counts = autodict()
936
937 def inc_counts(event_name):
938 try:
939 counts[event_name] += 1
940 except TypeError:
941 counts[event_name] = 1
942 </literallayout>
943 Finally, at the end of the trace processing run, we want to
944 print the result of all the per-event tallies. For that, we
945 use the special 'trace_end()' function:
946 <literallayout class='monospaced'>
947 def trace_end():
948 for event_name, count in counts.iteritems():
949 print "%-40s %10s\n" % (event_name, count)
950 </literallayout>
951 The end result is a summary of all the events recorded in the
952 trace:
953 <literallayout class='monospaced'>
954 skb__skb_copy_datagram_iovec 13148
955 irq__softirq_entry 4796
956 irq__irq_handler_exit 3805
957 irq__softirq_exit 4795
958 syscalls__sys_enter_write 8990
959 net__net_dev_xmit 652
960 skb__kfree_skb 4047
961 sched__sched_wakeup 1155
962 irq__irq_handler_entry 3804
963 irq__softirq_raise 4799
964 net__net_dev_queue 652
965 syscalls__sys_enter_read 17599
966 net__netif_receive_skb 1743
967 syscalls__sys_exit_read 17598
968 net__netif_rx 2
969 napi__napi_poll 1877
970 syscalls__sys_exit_write 8990
971 </literallayout>
972 Note that this is pretty much exactly the same information we get
973 from 'perf stat', which goes a little way to support the idea
974 mentioned previously that given the right kind of trace data,
975 higher-level profiling-type summaries can be derived from it.
976 </para>
977
978 <para>
979 Documentation on using the
980 <ulink url='http://linux.die.net/man/1/perf-script-python'>'perf script' python binding</ulink>.
981 </para>
982 </section>
983
984 <section id='system-wide-tracing-and-profiling'>
985 <title>System-Wide Tracing and Profiling</title>
986
987 <para>
988 The examples so far have focused on tracing a particular program or
989 workload - in other words, every profiling run has specified the
990 program to profile in the command-line e.g. 'perf record wget ...'.
991 </para>
992
993 <para>
994 It's also possible, and more interesting in many cases, to run a
995 system-wide profile or trace while running the workload in a
996 separate shell.
997 </para>
998
999 <para>
1000 To do system-wide profiling or tracing, you typically use
1001 the -a flag to 'perf record'.
1002 </para>
1003
1004 <para>
1005 To demonstrate this, open up one window and start the profile
1006 using the -a flag (press Ctrl-C to stop tracing):
1007 <literallayout class='monospaced'>
1008 root@crownbay:~# perf record -g -a
1009 ^C[ perf record: Woken up 6 times to write data ]
1010 [ perf record: Captured and wrote 1.400 MB perf.data (~61172 samples) ]
1011 </literallayout>
1012 In another window, run the wget test:
1013 <literallayout class='monospaced'>
1014 root@crownbay:~# wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>
1015 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
1016 linux-2.6.19.2.tar.b 100% |*******************************| 41727k 0:00:00 ETA
1017 </literallayout>
1018 Here we see entries not only for our wget load, but for other
1019 processes running on the system as well:
1020 </para>
1021
1022 <para>
1023 <imagedata fileref="figures/perf-systemwide.png" width="6in" depth="7in" align="center" scalefit="1" />
1024 </para>
1025
1026 <para>
1027 In the snapshot above, we can see callchains that originate in
1028 libc, and a callchain from Xorg that demonstrates that we're
1029 using a proprietary X driver in userspace (notice the presence
1030 of 'PVR' and some other unresolvable symbols in the expanded
1031 Xorg callchain).
1032 </para>
1033
1034 <para>
1035 Note also that we have both kernel and userspace entries in the
1036 above snapshot. We can also tell perf to focus on userspace but
1037 providing a modifier, in this case 'u', to the 'cycles' hardware
1038 counter when we record a profile:
1039 <literallayout class='monospaced'>
1040 root@crownbay:~# perf record -g -a -e cycles:u
1041 ^C[ perf record: Woken up 2 times to write data ]
1042 [ perf record: Captured and wrote 0.376 MB perf.data (~16443 samples) ]
1043 </literallayout>
1044 </para>
1045
1046 <para>
1047 <imagedata fileref="figures/perf-report-cycles-u.png" width="6in" depth="7in" align="center" scalefit="1" />
1048 </para>
1049
1050 <para>
1051 Notice in the screenshot above, we see only userspace entries ([.])
1052 </para>
1053
1054 <para>
1055 Finally, we can press 'enter' on a leaf node and select the 'Zoom
1056 into DSO' menu item to show only entries associated with a
1057 specific DSO. In the screenshot below, we've zoomed into the
1058 'libc' DSO which shows all the entries associated with the
1059 libc-xxx.so DSO.
1060 </para>
1061
1062 <para>
1063 <imagedata fileref="figures/perf-systemwide-libc.png" width="6in" depth="7in" align="center" scalefit="1" />
1064 </para>
1065
1066 <para>
1067 We can also use the system-wide -a switch to do system-wide
1068 tracing. Here we'll trace a couple of scheduler events:
1069 <literallayout class='monospaced'>
1070 root@crownbay:~# perf record -a -e sched:sched_switch -e sched:sched_wakeup
1071 ^C[ perf record: Woken up 38 times to write data ]
1072 [ perf record: Captured and wrote 9.780 MB perf.data (~427299 samples) ]
1073 </literallayout>
1074 We can look at the raw output using 'perf script' with no
1075 arguments:
1076 <literallayout class='monospaced'>
1077 root@crownbay:~# perf script
1078
1079 perf 1383 [001] 6171.460045: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1080 perf 1383 [001] 6171.460066: sched_switch: prev_comm=perf prev_pid=1383 prev_prio=120 prev_state=R+ ==> next_comm=kworker/1:1 next_pid=21 next_prio=120
1081 kworker/1:1 21 [001] 6171.460093: sched_switch: prev_comm=kworker/1:1 prev_pid=21 prev_prio=120 prev_state=S ==> next_comm=perf next_pid=1383 next_prio=120
1082 swapper 0 [000] 6171.468063: sched_wakeup: comm=kworker/0:3 pid=1209 prio=120 success=1 target_cpu=000
1083 swapper 0 [000] 6171.468107: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/0:3 next_pid=1209 next_prio=120
1084 kworker/0:3 1209 [000] 6171.468143: sched_switch: prev_comm=kworker/0:3 prev_pid=1209 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
1085 perf 1383 [001] 6171.470039: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1086 perf 1383 [001] 6171.470058: sched_switch: prev_comm=perf prev_pid=1383 prev_prio=120 prev_state=R+ ==> next_comm=kworker/1:1 next_pid=21 next_prio=120
1087 kworker/1:1 21 [001] 6171.470082: sched_switch: prev_comm=kworker/1:1 prev_pid=21 prev_prio=120 prev_state=S ==> next_comm=perf next_pid=1383 next_prio=120
1088 perf 1383 [001] 6171.480035: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1089 </literallayout>
1090 </para>
1091
1092 <section id='perf-filtering'>
1093 <title>Filtering</title>
1094
1095 <para>
1096 Notice that there are a lot of events that don't really have
1097 anything to do with what we're interested in, namely events
1098 that schedule 'perf' itself in and out or that wake perf up.
1099 We can get rid of those by using the '--filter' option -
1100 for each event we specify using -e, we can add a --filter
1101 after that to filter out trace events that contain fields
1102 with specific values:
1103 <literallayout class='monospaced'>
1104 root@crownbay:~# perf record -a -e sched:sched_switch --filter 'next_comm != perf &amp;&amp; prev_comm != perf' -e sched:sched_wakeup --filter 'comm != perf'
1105 ^C[ perf record: Woken up 38 times to write data ]
1106 [ perf record: Captured and wrote 9.688 MB perf.data (~423279 samples) ]
1107
1108
1109 root@crownbay:~# perf script
1110
1111 swapper 0 [000] 7932.162180: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/0:3 next_pid=1209 next_prio=120
1112 kworker/0:3 1209 [000] 7932.162236: sched_switch: prev_comm=kworker/0:3 prev_pid=1209 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
1113 perf 1407 [001] 7932.170048: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1114 perf 1407 [001] 7932.180044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1115 perf 1407 [001] 7932.190038: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1116 perf 1407 [001] 7932.200044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1117 perf 1407 [001] 7932.210044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1118 perf 1407 [001] 7932.220044: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1119 swapper 0 [001] 7932.230111: sched_wakeup: comm=kworker/1:1 pid=21 prio=120 success=1 target_cpu=001
1120 swapper 0 [001] 7932.230146: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/1:1 next_pid=21 next_prio=120
1121 kworker/1:1 21 [001] 7932.230205: sched_switch: prev_comm=kworker/1:1 prev_pid=21 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120
1122 swapper 0 [000] 7932.326109: sched_wakeup: comm=kworker/0:3 pid=1209 prio=120 success=1 target_cpu=000
1123 swapper 0 [000] 7932.326171: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/0:3 next_pid=1209 next_prio=120
1124 kworker/0:3 1209 [000] 7932.326214: sched_switch: prev_comm=kworker/0:3 prev_pid=1209 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
1125 </literallayout>
1126 In this case, we've filtered out all events that have 'perf'
1127 in their 'comm' or 'comm_prev' or 'comm_next' fields. Notice
1128 that there are still events recorded for perf, but notice
1129 that those events don't have values of 'perf' for the filtered
1130 fields. To completely filter out anything from perf will
1131 require a bit more work, but for the purpose of demonstrating
1132 how to use filters, it's close enough.
1133 </para>
1134
1135 <informalexample>
1136 <emphasis>Tying it Together:</emphasis> These are exactly the same set of event
1137 filters defined by the trace event subsystem. See the
1138 ftrace/tracecmd/kernelshark section for more discussion about
1139 these event filters.
1140 </informalexample>
1141
1142 <informalexample>
1143 <emphasis>Tying it Together:</emphasis> These event filters are implemented by a
1144 special-purpose pseudo-interpreter in the kernel and are an
1145 integral and indispensable part of the perf design as it
1146 relates to tracing. kernel-based event filters provide a
1147 mechanism to precisely throttle the event stream that appears
1148 in user space, where it makes sense to provide bindings to real
1149 programming languages for postprocessing the event stream.
1150 This architecture allows for the intelligent and flexible
1151 partitioning of processing between the kernel and user space.
1152 Contrast this with other tools such as SystemTap, which does
1153 all of its processing in the kernel and as such requires a
1154 special project-defined language in order to accommodate that
1155 design, or LTTng, where everything is sent to userspace and
1156 as such requires a super-efficient kernel-to-userspace
1157 transport mechanism in order to function properly. While
1158 perf certainly can benefit from for instance advances in
1159 the design of the transport, it doesn't fundamentally depend
1160 on them. Basically, if you find that your perf tracing
1161 application is causing buffer I/O overruns, it probably
1162 means that you aren't taking enough advantage of the
1163 kernel filtering engine.
1164 </informalexample>
1165 </section>
1166 </section>
1167
1168 <section id='using-dynamic-tracepoints'>
1169 <title>Using Dynamic Tracepoints</title>
1170
1171 <para>
1172 perf isn't restricted to the fixed set of static tracepoints
1173 listed by 'perf list'. Users can also add their own 'dynamic'
1174 tracepoints anywhere in the kernel. For instance, suppose we
1175 want to define our own tracepoint on do_fork(). We can do that
1176 using the 'perf probe' perf subcommand:
1177 <literallayout class='monospaced'>
1178 root@crownbay:~# perf probe do_fork
1179 Added new event:
1180 probe:do_fork (on do_fork)
1181
1182 You can now use it in all perf tools, such as:
1183
1184 perf record -e probe:do_fork -aR sleep 1
1185 </literallayout>
1186 Adding a new tracepoint via 'perf probe' results in an event
1187 with all the expected files and format in
1188 /sys/kernel/debug/tracing/events, just the same as for static
1189 tracepoints (as discussed in more detail in the trace events
1190 subsystem section:
1191 <literallayout class='monospaced'>
1192 root@crownbay:/sys/kernel/debug/tracing/events/probe/do_fork# ls -al
1193 drwxr-xr-x 2 root root 0 Oct 28 11:42 .
1194 drwxr-xr-x 3 root root 0 Oct 28 11:42 ..
1195 -rw-r--r-- 1 root root 0 Oct 28 11:42 enable
1196 -rw-r--r-- 1 root root 0 Oct 28 11:42 filter
1197 -r--r--r-- 1 root root 0 Oct 28 11:42 format
1198 -r--r--r-- 1 root root 0 Oct 28 11:42 id
1199
1200 root@crownbay:/sys/kernel/debug/tracing/events/probe/do_fork# cat format
1201 name: do_fork
1202 ID: 944
1203 format:
1204 field:unsigned short common_type; offset:0; size:2; signed:0;
1205 field:unsigned char common_flags; offset:2; size:1; signed:0;
1206 field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
1207 field:int common_pid; offset:4; size:4; signed:1;
1208 field:int common_padding; offset:8; size:4; signed:1;
1209
1210 field:unsigned long __probe_ip; offset:12; size:4; signed:0;
1211
1212 print fmt: "(%lx)", REC->__probe_ip
1213 </literallayout>
1214 We can list all dynamic tracepoints currently in existence:
1215 <literallayout class='monospaced'>
1216 root@crownbay:~# perf probe -l
1217 probe:do_fork (on do_fork)
1218 probe:schedule (on schedule)
1219 </literallayout>
1220 Let's record system-wide ('sleep 30' is a trick for recording
1221 system-wide but basically do nothing and then wake up after
1222 30 seconds):
1223 <literallayout class='monospaced'>
1224 root@crownbay:~# perf record -g -a -e probe:do_fork sleep 30
1225 [ perf record: Woken up 1 times to write data ]
1226 [ perf record: Captured and wrote 0.087 MB perf.data (~3812 samples) ]
1227 </literallayout>
1228 Using 'perf script' we can see each do_fork event that fired:
1229 <literallayout class='monospaced'>
1230 root@crownbay:~# perf script
1231
1232 # ========
1233 # captured on: Sun Oct 28 11:55:18 2012
1234 # hostname : crownbay
1235 # os release : 3.4.11-yocto-standard
1236 # perf version : 3.4.11
1237 # arch : i686
1238 # nrcpus online : 2
1239 # nrcpus avail : 2
1240 # cpudesc : Intel(R) Atom(TM) CPU E660 @ 1.30GHz
1241 # cpuid : GenuineIntel,6,38,1
1242 # total memory : 1017184 kB
1243 # cmdline : /usr/bin/perf record -g -a -e probe:do_fork sleep 30
1244 # event : name = probe:do_fork, type = 2, config = 0x3b0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern
1245 = 0, id = { 5, 6 }
1246 # HEADER_CPU_TOPOLOGY info available, use -I to display
1247 # ========
1248 #
1249 matchbox-deskto 1197 [001] 34211.378318: do_fork: (c1028460)
1250 matchbox-deskto 1295 [001] 34211.380388: do_fork: (c1028460)
1251 pcmanfm 1296 [000] 34211.632350: do_fork: (c1028460)
1252 pcmanfm 1296 [000] 34211.639917: do_fork: (c1028460)
1253 matchbox-deskto 1197 [001] 34217.541603: do_fork: (c1028460)
1254 matchbox-deskto 1299 [001] 34217.543584: do_fork: (c1028460)
1255 gthumb 1300 [001] 34217.697451: do_fork: (c1028460)
1256 gthumb 1300 [001] 34219.085734: do_fork: (c1028460)
1257 gthumb 1300 [000] 34219.121351: do_fork: (c1028460)
1258 gthumb 1300 [001] 34219.264551: do_fork: (c1028460)
1259 pcmanfm 1296 [000] 34219.590380: do_fork: (c1028460)
1260 matchbox-deskto 1197 [001] 34224.955965: do_fork: (c1028460)
1261 matchbox-deskto 1306 [001] 34224.957972: do_fork: (c1028460)
1262 matchbox-termin 1307 [000] 34225.038214: do_fork: (c1028460)
1263 matchbox-termin 1307 [001] 34225.044218: do_fork: (c1028460)
1264 matchbox-termin 1307 [000] 34225.046442: do_fork: (c1028460)
1265 matchbox-deskto 1197 [001] 34237.112138: do_fork: (c1028460)
1266 matchbox-deskto 1311 [001] 34237.114106: do_fork: (c1028460)
1267 gaku 1312 [000] 34237.202388: do_fork: (c1028460)
1268 </literallayout>
1269 And using 'perf report' on the same file, we can see the
1270 callgraphs from starting a few programs during those 30 seconds:
1271 </para>
1272
1273 <para>
1274 <imagedata fileref="figures/perf-probe-do_fork-profile.png" width="6in" depth="7in" align="center" scalefit="1" />
1275 </para>
1276
1277 <informalexample>
1278 <emphasis>Tying it Together:</emphasis> The trace events subsystem accomodate static
1279 and dynamic tracepoints in exactly the same way - there's no
1280 difference as far as the infrastructure is concerned. See the
1281 ftrace section for more details on the trace event subsystem.
1282 </informalexample>
1283
1284 <informalexample>
1285 <emphasis>Tying it Together:</emphasis> Dynamic tracepoints are implemented under the
1286 covers by kprobes and uprobes. kprobes and uprobes are also used
1287 by and in fact are the main focus of SystemTap.
1288 </informalexample>
1289 </section>
1290 </section>
1291
1292 <section id='perf-documentation'>
1293 <title>Documentation</title>
1294
1295 <para>
1296 Online versions of the man pages for the commands discussed in this
1297 section can be found here:
1298 <itemizedlist>
1299 <listitem><para>The <ulink url='http://linux.die.net/man/1/perf-stat'>'perf stat' manpage</ulink>.
1300 </para></listitem>
1301 <listitem><para>The <ulink url='http://linux.die.net/man/1/perf-record'>'perf record' manpage</ulink>.
1302 </para></listitem>
1303 <listitem><para>The <ulink url='http://linux.die.net/man/1/perf-report'>'perf report' manpage</ulink>.
1304 </para></listitem>
1305 <listitem><para>The <ulink url='http://linux.die.net/man/1/perf-probe'>'perf probe' manpage</ulink>.
1306 </para></listitem>
1307 <listitem><para>The <ulink url='http://linux.die.net/man/1/perf-script'>'perf script' manpage</ulink>.
1308 </para></listitem>
1309 <listitem><para>Documentation on using the
1310 <ulink url='http://linux.die.net/man/1/perf-script-python'>'perf script' python binding</ulink>.
1311 </para></listitem>
1312 <listitem><para>The top-level
1313 <ulink url='http://linux.die.net/man/1/perf'>perf(1) manpage</ulink>.
1314 </para></listitem>
1315 </itemizedlist>
1316 </para>
1317
1318 <para>
1319 Normally, you should be able to invoke the man pages via perf
1320 itself e.g. 'perf help' or 'perf help record'.
1321 </para>
1322
1323 <para>
1324 However, by default Yocto doesn't install man pages, but perf
1325 invokes the man pages for most help functionality. This is a bug
1326 and is being addressed by a Yocto bug:
1327 <ulink url='https://bugzilla.yoctoproject.org/show_bug.cgi?id=3388'>Bug 3388 - perf: enable man pages for basic 'help' functionality</ulink>.
1328 </para>
1329
1330 <para>
1331 The man pages in text form, along with some other files, such as
1332 a set of examples, can be found in the 'perf' directory of the
1333 kernel tree:
1334 <literallayout class='monospaced'>
1335 tools/perf/Documentation
1336 </literallayout>
1337 There's also a nice perf tutorial on the perf wiki that goes
1338 into more detail than we do here in certain areas:
1339 <ulink url='https://perf.wiki.kernel.org/index.php/Tutorial'>Perf Tutorial</ulink>
1340 </para>
1341 </section>
1342</section>
1343
1344<section id='profile-manual-ftrace'>
1345 <title>ftrace</title>
1346
1347 <para>
1348 'ftrace' literally refers to the 'ftrace function tracer' but in
1349 reality this encompasses a number of related tracers along with
1350 the infrastructure that they all make use of.
1351 </para>
1352
1353 <section id='ftrace-setup'>
1354 <title>Setup</title>
1355
1356 <para>
1357 For this section, we'll assume you've already performed the basic
1358 setup outlined in the General Setup section.
1359 </para>
1360
1361 <para>
1362 ftrace, trace-cmd, and kernelshark run on the target system,
1363 and are ready to go out-of-the-box - no additional setup is
1364 necessary. For the rest of this section we assume you've ssh'ed
1365 to the host and will be running ftrace on the target. kernelshark
1366 is a GUI application and if you use the '-X' option to ssh you
1367 can have the kernelshark GUI run on the target but display
1368 remotely on the host if you want.
1369 </para>
1370 </section>
1371
1372 <section id='basic-ftrace-usage'>
1373 <title>Basic ftrace usage</title>
1374
1375 <para>
1376 'ftrace' essentially refers to everything included in
1377 the /tracing directory of the mounted debugfs filesystem
1378 (Yocto follows the standard convention and mounts it
1379 at /sys/kernel/debug). Here's a listing of all the files
1380 found in /sys/kernel/debug/tracing on a Yocto system:
1381 <literallayout class='monospaced'>
1382 root@sugarbay:/sys/kernel/debug/tracing# ls
1383 README kprobe_events trace
1384 available_events kprobe_profile trace_clock
1385 available_filter_functions options trace_marker
1386 available_tracers per_cpu trace_options
1387 buffer_size_kb printk_formats trace_pipe
1388 buffer_total_size_kb saved_cmdlines tracing_cpumask
1389 current_tracer set_event tracing_enabled
1390 dyn_ftrace_total_info set_ftrace_filter tracing_on
1391 enabled_functions set_ftrace_notrace tracing_thresh
1392 events set_ftrace_pid
1393 free_buffer set_graph_function
1394 </literallayout>
1395 The files listed above are used for various purposes -
1396 some relate directly to the tracers themselves, others are
1397 used to set tracing options, and yet others actually contain
1398 the tracing output when a tracer is in effect. Some of the
1399 functions can be guessed from their names, others need
1400 explanation; in any case, we'll cover some of the files we
1401 see here below but for an explanation of the others, please
1402 see the ftrace documentation.
1403 </para>
1404
1405 <para>
1406 We'll start by looking at some of the available built-in
1407 tracers.
1408 </para>
1409
1410 <para>
1411 cat'ing the 'available_tracers' file lists the set of
1412 available tracers:
1413 <literallayout class='monospaced'>
1414 root@sugarbay:/sys/kernel/debug/tracing# cat available_tracers
1415 blk function_graph function nop
1416 </literallayout>
1417 The 'current_tracer' file contains the tracer currently in
1418 effect:
1419 <literallayout class='monospaced'>
1420 root@sugarbay:/sys/kernel/debug/tracing# cat current_tracer
1421 nop
1422 </literallayout>
1423 The above listing of current_tracer shows that
1424 the 'nop' tracer is in effect, which is just another
1425 way of saying that there's actually no tracer
1426 currently in effect.
1427 </para>
1428
1429 <para>
1430 echo'ing one of the available_tracers into current_tracer
1431 makes the specified tracer the current tracer:
1432 <literallayout class='monospaced'>
1433 root@sugarbay:/sys/kernel/debug/tracing# echo function > current_tracer
1434 root@sugarbay:/sys/kernel/debug/tracing# cat current_tracer
1435 function
1436 </literallayout>
1437 The above sets the current tracer to be the
1438 'function tracer'. This tracer traces every function
1439 call in the kernel and makes it available as the
1440 contents of the 'trace' file. Reading the 'trace' file
1441 lists the currently buffered function calls that have been
1442 traced by the function tracer:
1443 <literallayout class='monospaced'>
1444 root@sugarbay:/sys/kernel/debug/tracing# cat trace | less
1445
1446 # tracer: function
1447 #
1448 # entries-in-buffer/entries-written: 310629/766471 #P:8
1449 #
1450 # _-----=&gt; irqs-off
1451 # / _----=&gt; need-resched
1452 # | / _---=&gt; hardirq/softirq
1453 # || / _--=&gt; preempt-depth
1454 # ||| / delay
1455 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
1456 # | | | |||| | |
1457 &lt;idle&gt;-0 [004] d..1 470.867169: ktime_get_real &lt;-intel_idle
1458 &lt;idle&gt;-0 [004] d..1 470.867170: getnstimeofday &lt;-ktime_get_real
1459 &lt;idle&gt;-0 [004] d..1 470.867171: ns_to_timeval &lt;-intel_idle
1460 &lt;idle&gt;-0 [004] d..1 470.867171: ns_to_timespec &lt;-ns_to_timeval
1461 &lt;idle&gt;-0 [004] d..1 470.867172: smp_apic_timer_interrupt &lt;-apic_timer_interrupt
1462 &lt;idle&gt;-0 [004] d..1 470.867172: native_apic_mem_write &lt;-smp_apic_timer_interrupt
1463 &lt;idle&gt;-0 [004] d..1 470.867172: irq_enter &lt;-smp_apic_timer_interrupt
1464 &lt;idle&gt;-0 [004] d..1 470.867172: rcu_irq_enter &lt;-irq_enter
1465 &lt;idle&gt;-0 [004] d..1 470.867173: rcu_idle_exit_common.isra.33 &lt;-rcu_irq_enter
1466 &lt;idle&gt;-0 [004] d..1 470.867173: local_bh_disable &lt;-irq_enter
1467 &lt;idle&gt;-0 [004] d..1 470.867173: add_preempt_count &lt;-local_bh_disable
1468 &lt;idle&gt;-0 [004] d.s1 470.867174: tick_check_idle &lt;-irq_enter
1469 &lt;idle&gt;-0 [004] d.s1 470.867174: tick_check_oneshot_broadcast &lt;-tick_check_idle
1470 &lt;idle&gt;-0 [004] d.s1 470.867174: ktime_get &lt;-tick_check_idle
1471 &lt;idle&gt;-0 [004] d.s1 470.867174: tick_nohz_stop_idle &lt;-tick_check_idle
1472 &lt;idle&gt;-0 [004] d.s1 470.867175: update_ts_time_stats &lt;-tick_nohz_stop_idle
1473 &lt;idle&gt;-0 [004] d.s1 470.867175: nr_iowait_cpu &lt;-update_ts_time_stats
1474 &lt;idle&gt;-0 [004] d.s1 470.867175: tick_do_update_jiffies64 &lt;-tick_check_idle
1475 &lt;idle&gt;-0 [004] d.s1 470.867175: _raw_spin_lock &lt;-tick_do_update_jiffies64
1476 &lt;idle&gt;-0 [004] d.s1 470.867176: add_preempt_count &lt;-_raw_spin_lock
1477 &lt;idle&gt;-0 [004] d.s2 470.867176: do_timer &lt;-tick_do_update_jiffies64
1478 &lt;idle&gt;-0 [004] d.s2 470.867176: _raw_spin_lock &lt;-do_timer
1479 &lt;idle&gt;-0 [004] d.s2 470.867176: add_preempt_count &lt;-_raw_spin_lock
1480 &lt;idle&gt;-0 [004] d.s3 470.867177: ntp_tick_length &lt;-do_timer
1481 &lt;idle&gt;-0 [004] d.s3 470.867177: _raw_spin_lock_irqsave &lt;-ntp_tick_length
1482 .
1483 .
1484 .
1485 </literallayout>
1486 Each line in the trace above shows what was happening in
1487 the kernel on a given cpu, to the level of detail of
1488 function calls. Each entry shows the function called,
1489 followed by its caller (after the arrow).
1490 </para>
1491
1492 <para>
1493 The function tracer gives you an extremely detailed idea
1494 of what the kernel was doing at the point in time the trace
1495 was taken, and is a great way to learn about how the kernel
1496 code works in a dynamic sense.
1497 </para>
1498
1499 <informalexample>
1500 <emphasis>Tying it Together:</emphasis> The ftrace function tracer is also
1501 available from within perf, as the ftrace:function tracepoint.
1502 </informalexample>
1503
1504 <para>
1505 It is a little more difficult to follow the call chains than
1506 it needs to be - luckily there's a variant of the function
1507 tracer that displays the callchains explicitly, called the
1508 'function_graph' tracer:
1509 <literallayout class='monospaced'>
1510 root@sugarbay:/sys/kernel/debug/tracing# echo function_graph &gt; current_tracer
1511 root@sugarbay:/sys/kernel/debug/tracing# cat trace | less
1512
1513 tracer: function_graph
1514
1515 CPU DURATION FUNCTION CALLS
1516 | | | | | | |
1517 7) 0.046 us | pick_next_task_fair();
1518 7) 0.043 us | pick_next_task_stop();
1519 7) 0.042 us | pick_next_task_rt();
1520 7) 0.032 us | pick_next_task_fair();
1521 7) 0.030 us | pick_next_task_idle();
1522 7) | _raw_spin_unlock_irq() {
1523 7) 0.033 us | sub_preempt_count();
1524 7) 0.258 us | }
1525 7) 0.032 us | sub_preempt_count();
1526 7) + 13.341 us | } /* __schedule */
1527 7) 0.095 us | } /* sub_preempt_count */
1528 7) | schedule() {
1529 7) | __schedule() {
1530 7) 0.060 us | add_preempt_count();
1531 7) 0.044 us | rcu_note_context_switch();
1532 7) | _raw_spin_lock_irq() {
1533 7) 0.033 us | add_preempt_count();
1534 7) 0.247 us | }
1535 7) | idle_balance() {
1536 7) | _raw_spin_unlock() {
1537 7) 0.031 us | sub_preempt_count();
1538 7) 0.246 us | }
1539 7) | update_shares() {
1540 7) 0.030 us | __rcu_read_lock();
1541 7) 0.029 us | __rcu_read_unlock();
1542 7) 0.484 us | }
1543 7) 0.030 us | __rcu_read_lock();
1544 7) | load_balance() {
1545 7) | find_busiest_group() {
1546 7) 0.031 us | idle_cpu();
1547 7) 0.029 us | idle_cpu();
1548 7) 0.035 us | idle_cpu();
1549 7) 0.906 us | }
1550 7) 1.141 us | }
1551 7) 0.022 us | msecs_to_jiffies();
1552 7) | load_balance() {
1553 7) | find_busiest_group() {
1554 7) 0.031 us | idle_cpu();
1555 .
1556 .
1557 .
1558 4) 0.062 us | msecs_to_jiffies();
1559 4) 0.062 us | __rcu_read_unlock();
1560 4) | _raw_spin_lock() {
1561 4) 0.073 us | add_preempt_count();
1562 4) 0.562 us | }
1563 4) + 17.452 us | }
1564 4) 0.108 us | put_prev_task_fair();
1565 4) 0.102 us | pick_next_task_fair();
1566 4) 0.084 us | pick_next_task_stop();
1567 4) 0.075 us | pick_next_task_rt();
1568 4) 0.062 us | pick_next_task_fair();
1569 4) 0.066 us | pick_next_task_idle();
1570 ------------------------------------------
1571 4) kworker-74 =&gt; &lt;idle&gt;-0
1572 ------------------------------------------
1573
1574 4) | finish_task_switch() {
1575 4) | _raw_spin_unlock_irq() {
1576 4) 0.100 us | sub_preempt_count();
1577 4) 0.582 us | }
1578 4) 1.105 us | }
1579 4) 0.088 us | sub_preempt_count();
1580 4) ! 100.066 us | }
1581 .
1582 .
1583 .
1584 3) | sys_ioctl() {
1585 3) 0.083 us | fget_light();
1586 3) | security_file_ioctl() {
1587 3) 0.066 us | cap_file_ioctl();
1588 3) 0.562 us | }
1589 3) | do_vfs_ioctl() {
1590 3) | drm_ioctl() {
1591 3) 0.075 us | drm_ut_debug_printk();
1592 3) | i915_gem_pwrite_ioctl() {
1593 3) | i915_mutex_lock_interruptible() {
1594 3) 0.070 us | mutex_lock_interruptible();
1595 3) 0.570 us | }
1596 3) | drm_gem_object_lookup() {
1597 3) | _raw_spin_lock() {
1598 3) 0.080 us | add_preempt_count();
1599 3) 0.620 us | }
1600 3) | _raw_spin_unlock() {
1601 3) 0.085 us | sub_preempt_count();
1602 3) 0.562 us | }
1603 3) 2.149 us | }
1604 3) 0.133 us | i915_gem_object_pin();
1605 3) | i915_gem_object_set_to_gtt_domain() {
1606 3) 0.065 us | i915_gem_object_flush_gpu_write_domain();
1607 3) 0.065 us | i915_gem_object_wait_rendering();
1608 3) 0.062 us | i915_gem_object_flush_cpu_write_domain();
1609 3) 1.612 us | }
1610 3) | i915_gem_object_put_fence() {
1611 3) 0.097 us | i915_gem_object_flush_fence.constprop.36();
1612 3) 0.645 us | }
1613 3) 0.070 us | add_preempt_count();
1614 3) 0.070 us | sub_preempt_count();
1615 3) 0.073 us | i915_gem_object_unpin();
1616 3) 0.068 us | mutex_unlock();
1617 3) 9.924 us | }
1618 3) + 11.236 us | }
1619 3) + 11.770 us | }
1620 3) + 13.784 us | }
1621 3) | sys_ioctl() {
1622 </literallayout>
1623 As you can see, the function_graph display is much easier to
1624 follow. Also note that in addition to the function calls and
1625 associated braces, other events such as scheduler events
1626 are displayed in context. In fact, you can freely include
1627 any tracepoint available in the trace events subsystem described
1628 in the next section by simply enabling those events, and they'll
1629 appear in context in the function graph display. Quite a
1630 powerful tool for understanding kernel dynamics.
1631 </para>
1632
1633 <para>
1634 Also notice that there are various annotations on the left
1635 hand side of the display. For example if the total time it
1636 took for a given function to execute is above a certain
1637 threshold, an exclamation point or plus sign appears on the
1638 left hand side. Please see the ftrace documentation for
1639 details on all these fields.
1640 </para>
1641 </section>
1642
1643 <section id='the-trace-events-subsystem'>
1644 <title>The 'trace events' Subsystem</title>
1645
1646 <para>
1647 One especially important directory contained within
1648 the /sys/kernel/debug/tracing directory is the 'events'
1649 subdirectory, which contains representations of every
1650 tracepoint in the system. Listing out the contents of
1651 the 'events' subdirectory, we see mainly another set of
1652 subdirectories:
1653 <literallayout class='monospaced'>
1654 root@sugarbay:/sys/kernel/debug/tracing# cd events
1655 root@sugarbay:/sys/kernel/debug/tracing/events# ls -al
1656 drwxr-xr-x 38 root root 0 Nov 14 23:19 .
1657 drwxr-xr-x 5 root root 0 Nov 14 23:19 ..
1658 drwxr-xr-x 19 root root 0 Nov 14 23:19 block
1659 drwxr-xr-x 32 root root 0 Nov 14 23:19 btrfs
1660 drwxr-xr-x 5 root root 0 Nov 14 23:19 drm
1661 -rw-r--r-- 1 root root 0 Nov 14 23:19 enable
1662 drwxr-xr-x 40 root root 0 Nov 14 23:19 ext3
1663 drwxr-xr-x 79 root root 0 Nov 14 23:19 ext4
1664 drwxr-xr-x 14 root root 0 Nov 14 23:19 ftrace
1665 drwxr-xr-x 8 root root 0 Nov 14 23:19 hda
1666 -r--r--r-- 1 root root 0 Nov 14 23:19 header_event
1667 -r--r--r-- 1 root root 0 Nov 14 23:19 header_page
1668 drwxr-xr-x 25 root root 0 Nov 14 23:19 i915
1669 drwxr-xr-x 7 root root 0 Nov 14 23:19 irq
1670 drwxr-xr-x 12 root root 0 Nov 14 23:19 jbd
1671 drwxr-xr-x 14 root root 0 Nov 14 23:19 jbd2
1672 drwxr-xr-x 14 root root 0 Nov 14 23:19 kmem
1673 drwxr-xr-x 7 root root 0 Nov 14 23:19 module
1674 drwxr-xr-x 3 root root 0 Nov 14 23:19 napi
1675 drwxr-xr-x 6 root root 0 Nov 14 23:19 net
1676 drwxr-xr-x 3 root root 0 Nov 14 23:19 oom
1677 drwxr-xr-x 12 root root 0 Nov 14 23:19 power
1678 drwxr-xr-x 3 root root 0 Nov 14 23:19 printk
1679 drwxr-xr-x 8 root root 0 Nov 14 23:19 random
1680 drwxr-xr-x 4 root root 0 Nov 14 23:19 raw_syscalls
1681 drwxr-xr-x 3 root root 0 Nov 14 23:19 rcu
1682 drwxr-xr-x 6 root root 0 Nov 14 23:19 rpm
1683 drwxr-xr-x 20 root root 0 Nov 14 23:19 sched
1684 drwxr-xr-x 7 root root 0 Nov 14 23:19 scsi
1685 drwxr-xr-x 4 root root 0 Nov 14 23:19 signal
1686 drwxr-xr-x 5 root root 0 Nov 14 23:19 skb
1687 drwxr-xr-x 4 root root 0 Nov 14 23:19 sock
1688 drwxr-xr-x 10 root root 0 Nov 14 23:19 sunrpc
1689 drwxr-xr-x 538 root root 0 Nov 14 23:19 syscalls
1690 drwxr-xr-x 4 root root 0 Nov 14 23:19 task
1691 drwxr-xr-x 14 root root 0 Nov 14 23:19 timer
1692 drwxr-xr-x 3 root root 0 Nov 14 23:19 udp
1693 drwxr-xr-x 21 root root 0 Nov 14 23:19 vmscan
1694 drwxr-xr-x 3 root root 0 Nov 14 23:19 vsyscall
1695 drwxr-xr-x 6 root root 0 Nov 14 23:19 workqueue
1696 drwxr-xr-x 26 root root 0 Nov 14 23:19 writeback
1697 </literallayout>
1698 Each one of these subdirectories corresponds to a
1699 'subsystem' and contains yet again more subdirectories,
1700 each one of those finally corresponding to a tracepoint.
1701 For example, here are the contents of the 'kmem' subsystem:
1702 <literallayout class='monospaced'>
1703 root@sugarbay:/sys/kernel/debug/tracing/events# cd kmem
1704 root@sugarbay:/sys/kernel/debug/tracing/events/kmem# ls -al
1705 drwxr-xr-x 14 root root 0 Nov 14 23:19 .
1706 drwxr-xr-x 38 root root 0 Nov 14 23:19 ..
1707 -rw-r--r-- 1 root root 0 Nov 14 23:19 enable
1708 -rw-r--r-- 1 root root 0 Nov 14 23:19 filter
1709 drwxr-xr-x 2 root root 0 Nov 14 23:19 kfree
1710 drwxr-xr-x 2 root root 0 Nov 14 23:19 kmalloc
1711 drwxr-xr-x 2 root root 0 Nov 14 23:19 kmalloc_node
1712 drwxr-xr-x 2 root root 0 Nov 14 23:19 kmem_cache_alloc
1713 drwxr-xr-x 2 root root 0 Nov 14 23:19 kmem_cache_alloc_node
1714 drwxr-xr-x 2 root root 0 Nov 14 23:19 kmem_cache_free
1715 drwxr-xr-x 2 root root 0 Nov 14 23:19 mm_page_alloc
1716 drwxr-xr-x 2 root root 0 Nov 14 23:19 mm_page_alloc_extfrag
1717 drwxr-xr-x 2 root root 0 Nov 14 23:19 mm_page_alloc_zone_locked
1718 drwxr-xr-x 2 root root 0 Nov 14 23:19 mm_page_free
1719 drwxr-xr-x 2 root root 0 Nov 14 23:19 mm_page_free_batched
1720 drwxr-xr-x 2 root root 0 Nov 14 23:19 mm_page_pcpu_drain
1721 </literallayout>
1722 Let's see what's inside the subdirectory for a specific
1723 tracepoint, in this case the one for kmalloc:
1724 <literallayout class='monospaced'>
1725 root@sugarbay:/sys/kernel/debug/tracing/events/kmem# cd kmalloc
1726 root@sugarbay:/sys/kernel/debug/tracing/events/kmem/kmalloc# ls -al
1727 drwxr-xr-x 2 root root 0 Nov 14 23:19 .
1728 drwxr-xr-x 14 root root 0 Nov 14 23:19 ..
1729 -rw-r--r-- 1 root root 0 Nov 14 23:19 enable
1730 -rw-r--r-- 1 root root 0 Nov 14 23:19 filter
1731 -r--r--r-- 1 root root 0 Nov 14 23:19 format
1732 -r--r--r-- 1 root root 0 Nov 14 23:19 id
1733 </literallayout>
1734 The 'format' file for the tracepoint describes the event
1735 in memory, which is used by the various tracing tools
1736 that now make use of these tracepoint to parse the event
1737 and make sense of it, along with a 'print fmt' field that
1738 allows tools like ftrace to display the event as text.
1739 Here's what the format of the kmalloc event looks like:
1740 <literallayout class='monospaced'>
1741 root@sugarbay:/sys/kernel/debug/tracing/events/kmem/kmalloc# cat format
1742 name: kmalloc
1743 ID: 313
1744 format:
1745 field:unsigned short common_type; offset:0; size:2; signed:0;
1746 field:unsigned char common_flags; offset:2; size:1; signed:0;
1747 field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
1748 field:int common_pid; offset:4; size:4; signed:1;
1749 field:int common_padding; offset:8; size:4; signed:1;
1750
1751 field:unsigned long call_site; offset:16; size:8; signed:0;
1752 field:const void * ptr; offset:24; size:8; signed:0;
1753 field:size_t bytes_req; offset:32; size:8; signed:0;
1754 field:size_t bytes_alloc; offset:40; size:8; signed:0;
1755 field:gfp_t gfp_flags; offset:48; size:4; signed:0;
1756
1757 print fmt: "call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", REC->call_site, REC->ptr, REC->bytes_req, REC->bytes_alloc,
1758 (REC->gfp_flags) ? __print_flags(REC->gfp_flags, "|", {(unsigned long)(((( gfp_t)0x10u) | (( gfp_t)0x40u) | (( gfp_t)0x80u) | ((
1759 gfp_t)0x20000u) | (( gfp_t)0x02u) | (( gfp_t)0x08u)) | (( gfp_t)0x4000u) | (( gfp_t)0x10000u) | (( gfp_t)0x1000u) | (( gfp_t)0x200u) | ((
1760 gfp_t)0x400000u)), "GFP_TRANSHUGE"}, {(unsigned long)((( gfp_t)0x10u) | (( gfp_t)0x40u) | (( gfp_t)0x80u) | (( gfp_t)0x20000u) | ((
1761 gfp_t)0x02u) | (( gfp_t)0x08u)), "GFP_HIGHUSER_MOVABLE"}, {(unsigned long)((( gfp_t)0x10u) | (( gfp_t)0x40u) | (( gfp_t)0x80u) | ((
1762 gfp_t)0x20000u) | (( gfp_t)0x02u)), "GFP_HIGHUSER"}, {(unsigned long)((( gfp_t)0x10u) | (( gfp_t)0x40u) | (( gfp_t)0x80u) | ((
1763 gfp_t)0x20000u)), "GFP_USER"}, {(unsigned long)((( gfp_t)0x10u) | (( gfp_t)0x40u) | (( gfp_t)0x80u) | (( gfp_t)0x80000u)), GFP_TEMPORARY"},
1764 {(unsigned long)((( gfp_t)0x10u) | (( gfp_t)0x40u) | (( gfp_t)0x80u)), "GFP_KERNEL"}, {(unsigned long)((( gfp_t)0x10u) | (( gfp_t)0x40u)),
1765 "GFP_NOFS"}, {(unsigned long)((( gfp_t)0x20u)), "GFP_ATOMIC"}, {(unsigned long)((( gfp_t)0x10u)), "GFP_NOIO"}, {(unsigned long)((
1766 gfp_t)0x20u), "GFP_HIGH"}, {(unsigned long)(( gfp_t)0x10u), "GFP_WAIT"}, {(unsigned long)(( gfp_t)0x40u), "GFP_IO"}, {(unsigned long)((
1767 gfp_t)0x100u), "GFP_COLD"}, {(unsigned long)(( gfp_t)0x200u), "GFP_NOWARN"}, {(unsigned long)(( gfp_t)0x400u), "GFP_REPEAT"}, {(unsigned
1768 long)(( gfp_t)0x800u), "GFP_NOFAIL"}, {(unsigned long)(( gfp_t)0x1000u), "GFP_NORETRY"}, {(unsigned long)(( gfp_t)0x4000u), "GFP_COMP"},
1769 {(unsigned long)(( gfp_t)0x8000u), "GFP_ZERO"}, {(unsigned long)(( gfp_t)0x10000u), "GFP_NOMEMALLOC"}, {(unsigned long)(( gfp_t)0x20000u),
1770 "GFP_HARDWALL"}, {(unsigned long)(( gfp_t)0x40000u), "GFP_THISNODE"}, {(unsigned long)(( gfp_t)0x80000u), "GFP_RECLAIMABLE"}, {(unsigned
1771 long)(( gfp_t)0x08u), "GFP_MOVABLE"}, {(unsigned long)(( gfp_t)0), "GFP_NOTRACK"}, {(unsigned long)(( gfp_t)0x400000u), "GFP_NO_KSWAPD"},
1772 {(unsigned long)(( gfp_t)0x800000u), "GFP_OTHER_NODE"} ) : "GFP_NOWAIT"
1773 </literallayout>
1774 The 'enable' file in the tracepoint directory is what allows
1775 the user (or tools such as trace-cmd) to actually turn the
1776 tracepoint on and off. When enabled, the corresponding
1777 tracepoint will start appearing in the ftrace 'trace'
1778 file described previously. For example, this turns on the
1779 kmalloc tracepoint:
1780 <literallayout class='monospaced'>
1781 root@sugarbay:/sys/kernel/debug/tracing/events/kmem/kmalloc# echo 1 > enable
1782 </literallayout>
1783 At the moment, we're not interested in the function tracer or
1784 some other tracer that might be in effect, so we first turn
1785 it off, but if we do that, we still need to turn tracing on in
1786 order to see the events in the output buffer:
1787 <literallayout class='monospaced'>
1788 root@sugarbay:/sys/kernel/debug/tracing# echo nop > current_tracer
1789 root@sugarbay:/sys/kernel/debug/tracing# echo 1 > tracing_on
1790 </literallayout>
1791 Now, if we look at the the 'trace' file, we see nothing
1792 but the kmalloc events we just turned on:
1793 <literallayout class='monospaced'>
1794 root@sugarbay:/sys/kernel/debug/tracing# cat trace | less
1795 # tracer: nop
1796 #
1797 # entries-in-buffer/entries-written: 1897/1897 #P:8
1798 #
1799 # _-----=&gt; irqs-off
1800 # / _----=&gt; need-resched
1801 # | / _---=&gt; hardirq/softirq
1802 # || / _--=&gt; preempt-depth
1803 # ||| / delay
1804 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
1805 # | | | |||| | |
1806 dropbear-1465 [000] ...1 18154.620753: kmalloc: call_site=ffffffff816650d4 ptr=ffff8800729c3000 bytes_req=2048 bytes_alloc=2048 gfp_flags=GFP_KERNEL
1807 &lt;idle&gt;-0 [000] ..s3 18154.621640: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d555800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1808 &lt;idle&gt;-0 [000] ..s3 18154.621656: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d555800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1809 matchbox-termin-1361 [001] ...1 18154.755472: kmalloc: call_site=ffffffff81614050 ptr=ffff88006d5f0e00 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_KERNEL|GFP_REPEAT
1810 Xorg-1264 [002] ...1 18154.755581: kmalloc: call_site=ffffffff8141abe8 ptr=ffff8800734f4cc0 bytes_req=168 bytes_alloc=192 gfp_flags=GFP_KERNEL|GFP_NOWARN|GFP_NORETRY
1811 Xorg-1264 [002] ...1 18154.755583: kmalloc: call_site=ffffffff814192a3 ptr=ffff88001f822520 bytes_req=24 bytes_alloc=32 gfp_flags=GFP_KERNEL|GFP_ZERO
1812 Xorg-1264 [002] ...1 18154.755589: kmalloc: call_site=ffffffff81419edb ptr=ffff8800721a2f00 bytes_req=64 bytes_alloc=64 gfp_flags=GFP_KERNEL|GFP_ZERO
1813 matchbox-termin-1361 [001] ...1 18155.354594: kmalloc: call_site=ffffffff81614050 ptr=ffff88006db35400 bytes_req=576 bytes_alloc=1024 gfp_flags=GFP_KERNEL|GFP_REPEAT
1814 Xorg-1264 [002] ...1 18155.354703: kmalloc: call_site=ffffffff8141abe8 ptr=ffff8800734f4cc0 bytes_req=168 bytes_alloc=192 gfp_flags=GFP_KERNEL|GFP_NOWARN|GFP_NORETRY
1815 Xorg-1264 [002] ...1 18155.354705: kmalloc: call_site=ffffffff814192a3 ptr=ffff88001f822520 bytes_req=24 bytes_alloc=32 gfp_flags=GFP_KERNEL|GFP_ZERO
1816 Xorg-1264 [002] ...1 18155.354711: kmalloc: call_site=ffffffff81419edb ptr=ffff8800721a2f00 bytes_req=64 bytes_alloc=64 gfp_flags=GFP_KERNEL|GFP_ZERO
1817 &lt;idle&gt;-0 [000] ..s3 18155.673319: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d555800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1818 dropbear-1465 [000] ...1 18155.673525: kmalloc: call_site=ffffffff816650d4 ptr=ffff8800729c3000 bytes_req=2048 bytes_alloc=2048 gfp_flags=GFP_KERNEL
1819 &lt;idle&gt;-0 [000] ..s3 18155.674821: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d554800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1820 &lt;idle&gt;-0 [000] ..s3 18155.793014: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d554800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1821 dropbear-1465 [000] ...1 18155.793219: kmalloc: call_site=ffffffff816650d4 ptr=ffff8800729c3000 bytes_req=2048 bytes_alloc=2048 gfp_flags=GFP_KERNEL
1822 &lt;idle&gt;-0 [000] ..s3 18155.794147: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d555800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1823 &lt;idle&gt;-0 [000] ..s3 18155.936705: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d555800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1824 dropbear-1465 [000] ...1 18155.936910: kmalloc: call_site=ffffffff816650d4 ptr=ffff8800729c3000 bytes_req=2048 bytes_alloc=2048 gfp_flags=GFP_KERNEL
1825 &lt;idle&gt;-0 [000] ..s3 18155.937869: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d554800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1826 matchbox-termin-1361 [001] ...1 18155.953667: kmalloc: call_site=ffffffff81614050 ptr=ffff88006d5f2000 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_KERNEL|GFP_REPEAT
1827 Xorg-1264 [002] ...1 18155.953775: kmalloc: call_site=ffffffff8141abe8 ptr=ffff8800734f4cc0 bytes_req=168 bytes_alloc=192 gfp_flags=GFP_KERNEL|GFP_NOWARN|GFP_NORETRY
1828 Xorg-1264 [002] ...1 18155.953777: kmalloc: call_site=ffffffff814192a3 ptr=ffff88001f822520 bytes_req=24 bytes_alloc=32 gfp_flags=GFP_KERNEL|GFP_ZERO
1829 Xorg-1264 [002] ...1 18155.953783: kmalloc: call_site=ffffffff81419edb ptr=ffff8800721a2f00 bytes_req=64 bytes_alloc=64 gfp_flags=GFP_KERNEL|GFP_ZERO
1830 &lt;idle&gt;-0 [000] ..s3 18156.176053: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d554800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1831 dropbear-1465 [000] ...1 18156.176257: kmalloc: call_site=ffffffff816650d4 ptr=ffff8800729c3000 bytes_req=2048 bytes_alloc=2048 gfp_flags=GFP_KERNEL
1832 &lt;idle&gt;-0 [000] ..s3 18156.177717: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d555800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1833 &lt;idle&gt;-0 [000] ..s3 18156.399229: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d555800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1834 dropbear-1465 [000] ...1 18156.399434: kmalloc: call_site=ffffffff816650d4 ptr=ffff8800729c3000 bytes_http://rostedt.homelinux.com/kernelshark/req=2048 bytes_alloc=2048 gfp_flags=GFP_KERNEL
1835 &lt;idle&gt;-0 [000] ..s3 18156.400660: kmalloc: call_site=ffffffff81619b36 ptr=ffff88006d554800 bytes_req=512 bytes_alloc=512 gfp_flags=GFP_ATOMIC
1836 matchbox-termin-1361 [001] ...1 18156.552800: kmalloc: call_site=ffffffff81614050 ptr=ffff88006db34800 bytes_req=576 bytes_alloc=1024 gfp_flags=GFP_KERNEL|GFP_REPEAT
1837 </literallayout>
1838 To again disable the kmalloc event, we need to send 0 to the
1839 enable file:
1840 <literallayout class='monospaced'>
1841 root@sugarbay:/sys/kernel/debug/tracing/events/kmem/kmalloc# echo 0 > enable
1842 </literallayout>
1843 You can enable any number of events or complete subsystems
1844 (by using the 'enable' file in the subsystem directory) and
1845 get an arbitrarily fine-grained idea of what's going on in the
1846 system by enabling as many of the appropriate tracepoints
1847 as applicable.
1848 </para>
1849
1850 <para>
1851 A number of the tools described in this HOWTO do just that,
1852 including trace-cmd and kernelshark in the next section.
1853 </para>
1854
1855 <informalexample>
1856 <emphasis>Tying it Together:</emphasis> These tracepoints and their representation
1857 are used not only by ftrace, but by many of the other tools
1858 covered in this document and they form a central point of
1859 integration for the various tracers available in Linux.
1860 They form a central part of the instrumentation for the
1861 following tools: perf, lttng, ftrace, blktrace and SystemTap
1862 </informalexample>
1863
1864 <informalexample>
1865 <emphasis>Tying it Together:</emphasis> Eventually all the special-purpose tracers
1866 currently available in /sys/kernel/debug/tracing will be
1867 removed and replaced with equivalent tracers based on the
1868 'trace events' subsystem.
1869 </informalexample>
1870 </section>
1871
1872 <section id='trace-cmd-kernelshark'>
1873 <title>trace-cmd/kernelshark</title>
1874
1875 <para>
1876 trace-cmd is essentially an extensive command-line 'wrapper'
1877 interface that hides the details of all the individual files
1878 in /sys/kernel/debug/tracing, allowing users to specify
1879 specific particular events within the
1880 /sys/kernel/debug/tracing/events/ subdirectory and to collect
1881 traces and avoid having to deal with those details directly.
1882 </para>
1883
1884 <para>
1885 As yet another layer on top of that, kernelshark provides a GUI
1886 that allows users to start and stop traces and specify sets
1887 of events using an intuitive interface, and view the
1888 output as both trace events and as a per-CPU graphical
1889 display. It directly uses 'trace-cmd' as the plumbing
1890 that accomplishes all that underneath the covers (and
1891 actually displays the trace-cmd command it uses, as we'll see).
1892 </para>
1893
1894 <para>
1895 To start a trace using kernelshark, first start kernelshark:
1896 <literallayout class='monospaced'>
1897 root@sugarbay:~# kernelshark
1898 </literallayout>
1899 Then bring up the 'Capture' dialog by choosing from the
1900 kernelshark menu:
1901 <literallayout class='monospaced'>
1902 Capture | Record
1903 </literallayout>
1904 That will display the following dialog, which allows you to
1905 choose one or more events (or even one or more complete
1906 subsystems) to trace:
1907 </para>
1908
1909 <para>
1910 <imagedata fileref="figures/kernelshark-choose-events.png" width="6in" depth="6in" align="center" scalefit="1" />
1911 </para>
1912
1913 <para>
1914 Note that these are exactly the same sets of events described
1915 in the previous trace events subsystem section, and in fact
1916 is where trace-cmd gets them for kernelshark.
1917 </para>
1918
1919 <para>
1920 In the above screenshot, we've decided to explore the
1921 graphics subsystem a bit and so have chosen to trace all
1922 the tracepoints contained within the 'i915' and 'drm'
1923 subsystems.
1924 </para>
1925
1926 <para>
1927 After doing that, we can start and stop the trace using
1928 the 'Run' and 'Stop' button on the lower right corner of
1929 the dialog (the same button will turn into the 'Stop'
1930 button after the trace has started):
1931 </para>
1932
1933 <para>
1934 <imagedata fileref="figures/kernelshark-output-display.png" width="6in" depth="6in" align="center" scalefit="1" />
1935 </para>
1936
1937 <para>
1938 Notice that the right-hand pane shows the exact trace-cmd
1939 command-line that's used to run the trace, along with the
1940 results of the trace-cmd run.
1941 </para>
1942
1943 <para>
1944 Once the 'Stop' button is pressed, the graphical view magically
1945 fills up with a colorful per-cpu display of the trace data,
1946 along with the detailed event listing below that:
1947 </para>
1948
1949 <para>
1950 <imagedata fileref="figures/kernelshark-i915-display.png" width="6in" depth="7in" align="center" scalefit="1" />
1951 </para>
1952
1953 <para>
1954 Here's another example, this time a display resulting
1955 from tracing 'all events':
1956 </para>
1957
1958 <para>
1959 <imagedata fileref="figures/kernelshark-all.png" width="6in" depth="7in" align="center" scalefit="1" />
1960 </para>
1961
1962 <para>
1963 The tool is pretty self-explanatory, but for more detailed
1964 information on navigating through the data, see the
1965 <ulink url='http://rostedt.homelinux.com/kernelshark/'>kernelshark website</ulink>.
1966 </para>
1967 </section>
1968
1969 <section id='ftrace-documentation'>
1970 <title>Documentation</title>
1971
1972 <para>
1973 The documentation for ftrace can be found in the kernel
1974 Documentation directory:
1975 <literallayout class='monospaced'>
1976 Documentation/trace/ftrace.txt
1977 </literallayout>
1978 The documentation for the trace event subsystem can also
1979 be found in the kernel Documentation directory:
1980 <literallayout class='monospaced'>
1981 Documentation/trace/events.txt
1982 </literallayout>
1983 There is a nice series of articles on using
1984 ftrace and trace-cmd at LWN:
1985 <itemizedlist>
1986 <listitem><para><ulink url='http://lwn.net/Articles/365835/'>Debugging the kernel using Ftrace - part 1</ulink>
1987 </para></listitem>
1988 <listitem><para><ulink url='http://lwn.net/Articles/366796/'>Debugging the kernel using Ftrace - part 2</ulink>
1989 </para></listitem>
1990 <listitem><para><ulink url='http://lwn.net/Articles/370423/'>Secrets of the Ftrace function tracer</ulink>
1991 </para></listitem>
1992 <listitem><para><ulink url='https://lwn.net/Articles/410200/'>trace-cmd: A front-end for Ftrace</ulink>
1993 </para></listitem>
1994 </itemizedlist>
1995 </para>
1996
1997 <para>
1998 There's more detailed documentation kernelshark usage here:
1999 <ulink url='http://rostedt.homelinux.com/kernelshark/'>KernelShark</ulink>
2000 </para>
2001
2002 <para>
2003 An amusing yet useful README (a tracing mini-HOWTO) can be
2004 found in /sys/kernel/debug/tracing/README.
2005 </para>
2006 </section>
2007</section>
2008
2009<section id='profile-manual-systemtap'>
2010 <title>systemtap</title>
2011
2012 <para>
2013 SystemTap is a system-wide script-based tracing and profiling tool.
2014 </para>
2015
2016 <para>
2017 SystemTap scripts are C-like programs that are executed in the
2018 kernel to gather/print/aggregate data extracted from the context
2019 they end up being invoked under.
2020 </para>
2021
2022 <para>
2023 For example, this probe from the
2024 <ulink url='http://sourceware.org/systemtap/tutorial/'>SystemTap tutorial</ulink>
2025 simply prints a line every time any process on the system open()s
2026 a file. For each line, it prints the executable name of the
2027 program that opened the file, along with its PID, and the name
2028 of the file it opened (or tried to open), which it extracts
2029 from the open syscall's argstr.
2030 <literallayout class='monospaced'>
2031 probe syscall.open
2032 {
2033 printf ("%s(%d) open (%s)\n", execname(), pid(), argstr)
2034 }
2035
2036 probe timer.ms(4000) # after 4 seconds
2037 {
2038 exit ()
2039 }
2040 </literallayout>
2041 Normally, to execute this probe, you'd simply install
2042 systemtap on the system you want to probe, and directly run
2043 the probe on that system e.g. assuming the name of the file
2044 containing the above text is trace_open.stp:
2045 <literallayout class='monospaced'>
2046 # stap trace_open.stp
2047 </literallayout>
2048 What systemtap does under the covers to run this probe is 1)
2049 parse and convert the probe to an equivalent 'C' form, 2)
2050 compile the 'C' form into a kernel module, 3) insert the
2051 module into the kernel, which arms it, and 4) collect the data
2052 generated by the probe and display it to the user.
2053 </para>
2054
2055 <para>
2056 In order to accomplish steps 1 and 2, the 'stap' program needs
2057 access to the kernel build system that produced the kernel
2058 that the probed system is running. In the case of a typical
2059 embedded system (the 'target'), the kernel build system
2060 unfortunately isn't typically part of the image running on
2061 the target. It is normally available on the 'host' system
2062 that produced the target image however; in such cases,
2063 steps 1 and 2 are executed on the host system, and steps
2064 3 and 4 are executed on the target system, using only the
2065 systemtap 'runtime'.
2066 </para>
2067
2068 <para>
2069 The systemtap support in Yocto assumes that only steps
2070 3 and 4 are run on the target; it is possible to do
2071 everything on the target, but this section assumes only
2072 the typical embedded use-case.
2073 </para>
2074
2075 <para>
2076 So basically what you need to do in order to run a systemtap
2077 script on the target is to 1) on the host system, compile the
2078 probe into a kernel module that makes sense to the target, 2)
2079 copy the module onto the target system and 3) insert the
2080 module into the target kernel, which arms it, and 4) collect
2081 the data generated by the probe and display it to the user.
2082 </para>
2083
2084 <section id='systemtap-setup'>
2085 <title>Setup</title>
2086
2087 <para>
2088 Those are a lot of steps and a lot of details, but
2089 fortunately Yocto includes a script called 'crosstap'
2090 that will take care of those details, allowing you to
2091 simply execute a systemtap script on the remote target,
2092 with arguments if necessary.
2093 </para>
2094
2095 <para>
2096 In order to do this from a remote host, however, you
2097 need to have access to the build for the image you
2098 booted. The 'crosstap' script provides details on how
2099 to do this if you run the script on the host without having
2100 done a build:
2101 <note>
2102 SystemTap, which uses 'crosstap', assumes you can establish an
2103 ssh connection to the remote target.
2104 Please refer to the crosstap wiki page for details on verifying
2105 ssh connections at
2106 <ulink url='https://wiki.yoctoproject.org/wiki/Tracing_and_Profiling#systemtap'></ulink>.
2107 Also, the ability to ssh into the target system is not enabled
2108 by default in *-minimal images.
2109 </note>
2110 <literallayout class='monospaced'>
2111 $ crosstap root@192.168.1.88 trace_open.stp
2112
2113 Error: No target kernel build found.
2114 Did you forget to create a local build of your image?
2115
2116 'crosstap' requires a local sdk build of the target system
2117 (or a build that includes 'tools-profile') in order to build
2118 kernel modules that can probe the target system.
2119
2120 Practically speaking, that means you need to do the following:
2121 - If you're running a pre-built image, download the release
2122 and/or BSP tarballs used to build the image.
2123 - If you're working from git sources, just clone the metadata
2124 and BSP layers needed to build the image you'll be booting.
2125 - Make sure you're properly set up to build a new image (see
2126 the BSP README and/or the widely available basic documentation
2127 that discusses how to build images).
2128 - Build an -sdk version of the image e.g.:
2129 $ bitbake core-image-sato-sdk
2130 OR
2131 - Build a non-sdk image but include the profiling tools:
2132 [ edit local.conf and add 'tools-profile' to the end of
2133 the EXTRA_IMAGE_FEATURES variable ]
2134 $ bitbake core-image-sato
2135
2136 Once you've build the image on the host system, you're ready to
2137 boot it (or the equivalent pre-built image) and use 'crosstap'
2138 to probe it (you need to source the environment as usual first):
2139
2140 $ source oe-init-build-env
2141 $ cd ~/my/systemtap/scripts
2142 $ crosstap root@192.168.1.xxx myscript.stp
2143 </literallayout>
2144 So essentially what you need to do is build an SDK image or
2145 image with 'tools-profile' as detailed in the
2146 "<link linkend='profile-manual-general-setup'>General Setup</link>"
2147 section of this manual, and boot the resulting target image.
2148 </para>
2149
2150 <note>
2151 If you have a build directory containing multiple machines,
2152 you need to have the MACHINE you're connecting to selected
2153 in local.conf, and the kernel in that machine's build
2154 directory must match the kernel on the booted system exactly,
2155 or you'll get the above 'crosstap' message when you try to
2156 invoke a script.
2157 </note>
2158 </section>
2159
2160 <section id='running-a-script-on-a-target'>
2161 <title>Running a Script on a Target</title>
2162
2163 <para>
2164 Once you've done that, you should be able to run a systemtap
2165 script on the target:
2166 <literallayout class='monospaced'>
2167 $ cd /path/to/yocto
2168 $ source oe-init-build-env
2169
2170 ### Shell environment set up for builds. ###
2171
2172 You can now run 'bitbake &lt;target&gt;'
2173
2174 Common targets are:
2175 core-image-minimal
2176 core-image-sato
2177 meta-toolchain
2178 adt-installer
2179 meta-ide-support
2180
2181 You can also run generated qemu images with a command like 'runqemu qemux86'
2182 </literallayout>
2183 Once you've done that, you can cd to whatever directory
2184 contains your scripts and use 'crosstap' to run the script:
2185 <literallayout class='monospaced'>
2186 $ cd /path/to/my/systemap/script
2187 $ crosstap root@192.168.7.2 trace_open.stp
2188 </literallayout>
2189 If you get an error connecting to the target e.g.:
2190 <literallayout class='monospaced'>
2191 $ crosstap root@192.168.7.2 trace_open.stp
2192 error establishing ssh connection on remote 'root@192.168.7.2'
2193 </literallayout>
2194 Try ssh'ing to the target and see what happens:
2195 <literallayout class='monospaced'>
2196 $ ssh root@192.168.7.2
2197 </literallayout>
2198 A lot of the time, connection problems are due specifying a
2199 wrong IP address or having a 'host key verification error'.
2200 </para>
2201
2202 <para>
2203 If everything worked as planned, you should see something
2204 like this (enter the password when prompted, or press enter
2205 if it's set up to use no password):
2206 <literallayout class='monospaced'>
2207 $ crosstap root@192.168.7.2 trace_open.stp
2208 root@192.168.7.2's password:
2209 matchbox-termin(1036) open ("/tmp/vte3FS2LW", O_RDWR|O_CREAT|O_EXCL|O_LARGEFILE, 0600)
2210 matchbox-termin(1036) open ("/tmp/vteJMC7LW", O_RDWR|O_CREAT|O_EXCL|O_LARGEFILE, 0600)
2211 </literallayout>
2212 </para>
2213 </section>
2214
2215 <section id='systemtap-documentation'>
2216 <title>Documentation</title>
2217
2218 <para>
2219 The SystemTap language reference can be found here:
2220 <ulink url='http://sourceware.org/systemtap/langref/'>SystemTap Language Reference</ulink>
2221 </para>
2222
2223 <para>
2224 Links to other SystemTap documents, tutorials, and examples can be
2225 found here:
2226 <ulink url='http://sourceware.org/systemtap/documentation.html'>SystemTap documentation page</ulink>
2227 </para>
2228 </section>
2229</section>
2230
2231<section id='profile-manual-oprofile'>
2232 <title>oprofile</title>
2233
2234 <para>
2235 oprofile itself is a command-line application that runs on the
2236 target system.
2237 </para>
2238
2239 <section id='oprofile-setup'>
2240 <title>Setup</title>
2241
2242 <para>
2243 For this section, we'll assume you've already performed the
2244 basic setup outlined in the
2245 "<link linkend='profile-manual-general-setup'>General Setup</link>"
2246 section.
2247 </para>
2248
2249 <para>
2250 For the section that deals with running oprofile from the command-line,
2251 we assume you've ssh'ed to the host and will be running
2252 oprofile on the target.
2253 </para>
2254
2255 <para>
2256 oprofileui (oprofile-viewer) is a GUI-based program that runs
2257 on the host and interacts remotely with the target.
2258 See the oprofileui section for the exact steps needed to
2259 install oprofileui on the host.
2260 </para>
2261 </section>
2262
2263 <section id='oprofile-basic-usage'>
2264 <title>Basic Usage</title>
2265
2266 <para>
2267 Oprofile as configured in Yocto is a system-wide profiler
2268 (i.e. the version in Yocto doesn't yet make use of the
2269 perf_events interface which would allow it to profile
2270 specific processes and workloads). It relies on hardware
2271 counter support in the hardware (but can fall back to a
2272 timer-based mode), which means that it doesn't take
2273 advantage of tracepoints or other event sources for example.
2274 </para>
2275
2276 <para>
2277 It consists of a kernel module that collects samples and a
2278 userspace daemon that writes the sample data to disk.
2279 </para>
2280
2281 <para>
2282 The 'opcontrol' shell script is used for transparently
2283 managing these components and starting and stopping
2284 profiles, and the 'opreport' command is used to
2285 display the results.
2286 </para>
2287
2288 <para>
2289 The oprofile daemon should already be running, but before
2290 you start profiling, you may need to change some settings
2291 and some of these settings may require the daemon to not
2292 be running. One of these settings is the path to the
2293 vmlinux file, which you'll want to set using the --vmlinux
2294 option if you want the kernel profiled:
2295 <literallayout class='monospaced'>
2296 root@crownbay:~# opcontrol --vmlinux=/boot/vmlinux-`uname -r`
2297 The profiling daemon is currently active, so changes to the configuration
2298 will be used the next time you restart oprofile after a --shutdown or --deinit.
2299 </literallayout>
2300 You can check if vmlinux file: is set using opcontrol --status:
2301 <literallayout class='monospaced'>
2302 root@crownbay:~# opcontrol --status
2303 Daemon paused: pid 1334
2304 Separate options: library
2305 vmlinux file: none
2306 Image filter: none
2307 Call-graph depth: 6
2308 </literallayout>
2309 If it's not, you need to shutdown the daemon, add the setting
2310 and restart the daemon:
2311 <literallayout class='monospaced'>
2312 root@crownbay:~# opcontrol --shutdown
2313 Killing daemon.
2314
2315 root@crownbay:~# opcontrol --vmlinux=/boot/vmlinux-`uname -r`
2316 root@crownbay:~# opcontrol --start-daemon
2317 Using default event: CPU_CLK_UNHALTED:100000:0:1:1
2318 Using 2.6+ OProfile kernel interface.
2319 Reading module info.
2320 Using log file /var/lib/oprofile/samples/oprofiled.log
2321 Daemon started.
2322 </literallayout>
2323 If we check the status again we now see our updated settings:
2324 <literallayout class='monospaced'>
2325 root@crownbay:~# opcontrol --status
2326 Daemon paused: pid 1649
2327 Separate options: library
2328 vmlinux file: /boot/vmlinux-3.4.11-yocto-standard
2329 Image filter: none
2330 Call-graph depth: 6
2331 </literallayout>
2332 We're now in a position to run a profile. For that we use
2333 'opcontrol --start':
2334 <literallayout class='monospaced'>
2335 root@crownbay:~# opcontrol --start
2336 Profiler running.
2337 </literallayout>
2338 In another window, run our wget workload:
2339 <literallayout class='monospaced'>
2340 root@crownbay:~# rm linux-2.6.19.2.tar.bz2; wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>; sync
2341 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
2342 linux-2.6.19.2.tar.b 100% |*******************************| 41727k 0:00:00 ETA
2343 </literallayout>
2344 To stop the profile we use 'opcontrol --shutdown', which not
2345 only stops the profile but shuts down the daemon as well:
2346 <literallayout class='monospaced'>
2347 root@crownbay:~# opcontrol --shutdown
2348 Stopping profiling.
2349 Killing daemon.
2350 </literallayout>
2351 Oprofile writes sample data to /var/lib/oprofile/samples,
2352 which you can look at if you're interested in seeing how the
2353 samples are structured. This is also interesting because
2354 it's related to how you dive down to get further details
2355 about specific executables in OProfile.
2356 </para>
2357
2358 <para>
2359 To see the default display output for a profile, simply type
2360 'opreport', which will show the results using the data in
2361 /var/lib/oprofile/samples:
2362 <literallayout class='monospaced'>
2363 root@crownbay:~# opreport
2364
2365 WARNING! The OProfile kernel driver reports sample buffer overflows.
2366 Such overflows can result in incorrect sample attribution, invalid sample
2367 files and other symptoms. See the oprofiled.log for details.
2368 You should adjust your sampling frequency to eliminate (or at least minimize)
2369 these overflows.
2370 CPU: Intel Architectural Perfmon, speed 1.3e+06 MHz (estimated)
2371 Counted CPU_CLK_UNHALTED events (Clock cycles when not halted) with a unit mask of 0x00 (No unit mask) count 100000
2372 CPU_CLK_UNHALT...|
2373 samples| %|
2374 ------------------
2375 464365 79.8156 vmlinux-3.4.11-yocto-standard
2376 65108 11.1908 oprofiled
2377 CPU_CLK_UNHALT...|
2378 samples| %|
2379 ------------------
2380 64416 98.9372 oprofiled
2381 692 1.0628 libc-2.16.so
2382 36959 6.3526 no-vmlinux
2383 4378 0.7525 busybox
2384 CPU_CLK_UNHALT...|
2385 samples| %|
2386 ------------------
2387 2844 64.9612 libc-2.16.so
2388 1337 30.5391 busybox
2389 193 4.4084 ld-2.16.so
2390 2 0.0457 libnss_compat-2.16.so
2391 1 0.0228 libnsl-2.16.so
2392 1 0.0228 libnss_files-2.16.so
2393 4344 0.7467 bash
2394 CPU_CLK_UNHALT...|
2395 samples| %|
2396 ------------------
2397 2657 61.1648 bash
2398 1665 38.3287 libc-2.16.so
2399 18 0.4144 ld-2.16.so
2400 3 0.0691 libtinfo.so.5.9
2401 1 0.0230 libdl-2.16.so
2402 3118 0.5359 nf_conntrack
2403 686 0.1179 matchbox-terminal
2404 CPU_CLK_UNHALT...|
2405 samples| %|
2406 ------------------
2407 214 31.1953 libglib-2.0.so.0.3200.4
2408 114 16.6181 libc-2.16.so
2409 79 11.5160 libcairo.so.2.11200.2
2410 78 11.3703 libgdk-x11-2.0.so.0.2400.8
2411 51 7.4344 libpthread-2.16.so
2412 45 6.5598 libgobject-2.0.so.0.3200.4
2413 29 4.2274 libvte.so.9.2800.2
2414 25 3.6443 libX11.so.6.3.0
2415 19 2.7697 libxcb.so.1.1.0
2416 17 2.4781 libgtk-x11-2.0.so.0.2400.8
2417 12 1.7493 librt-2.16.so
2418 3 0.4373 libXrender.so.1.3.0
2419 671 0.1153 emgd
2420 411 0.0706 nf_conntrack_ipv4
2421 391 0.0672 iptable_nat
2422 378 0.0650 nf_nat
2423 263 0.0452 Xorg
2424 CPU_CLK_UNHALT...|
2425 samples| %|
2426 ------------------
2427 106 40.3042 Xorg
2428 53 20.1521 libc-2.16.so
2429 31 11.7871 libpixman-1.so.0.27.2
2430 26 9.8859 emgd_drv.so
2431 16 6.0837 libemgdsrv_um.so.1.5.15.3226
2432 11 4.1825 libEMGD2d.so.1.5.15.3226
2433 9 3.4221 libfb.so
2434 7 2.6616 libpthread-2.16.so
2435 1 0.3802 libudev.so.0.9.3
2436 1 0.3802 libdrm.so.2.4.0
2437 1 0.3802 libextmod.so
2438 1 0.3802 mouse_drv.so
2439 .
2440 .
2441 .
2442 9 0.0015 connmand
2443 CPU_CLK_UNHALT...|
2444 samples| %|
2445 ------------------
2446 4 44.4444 libglib-2.0.so.0.3200.4
2447 2 22.2222 libpthread-2.16.so
2448 1 11.1111 connmand
2449 1 11.1111 libc-2.16.so
2450 1 11.1111 librt-2.16.so
2451 6 0.0010 oprofile-server
2452 CPU_CLK_UNHALT...|
2453 samples| %|
2454 ------------------
2455 3 50.0000 libc-2.16.so
2456 1 16.6667 oprofile-server
2457 1 16.6667 libpthread-2.16.so
2458 1 16.6667 libglib-2.0.so.0.3200.4
2459 5 8.6e-04 gconfd-2
2460 CPU_CLK_UNHALT...|
2461 samples| %|
2462 ------------------
2463 2 40.0000 libdbus-1.so.3.7.2
2464 2 40.0000 libglib-2.0.so.0.3200.4
2465 1 20.0000 libc-2.16.so
2466 </literallayout>
2467 The output above shows the breakdown or samples by both
2468 number of samples and percentage for each executable.
2469 Within an executable, the sample counts are broken down
2470 further into executable and shared libraries (DSOs) used
2471 by the executable.
2472 </para>
2473
2474 <para>
2475 To get even more detailed breakdowns by function, we need to
2476 have the full paths to the DSOs, which we can get by
2477 using -f with opreport:
2478 <literallayout class='monospaced'>
2479 root@crownbay:~# opreport -f
2480
2481 CPU: Intel Architectural Perfmon, speed 1.3e+06 MHz (estimated)
2482 Counted CPU_CLK_UNHALTED events (Clock cycles when not halted) with a unit mask of 0x00 (No unit mask) count 100000
2483 CPU_CLK_UNHALT...|
2484 samples| %|
2485
2486 464365 79.8156 /boot/vmlinux-3.4.11-yocto-standard
2487 65108 11.1908 /usr/bin/oprofiled
2488 CPU_CLK_UNHALT...|
2489 samples| %|
2490 ------------------
2491 64416 98.9372 /usr/bin/oprofiled
2492 692 1.0628 /lib/libc-2.16.so
2493 36959 6.3526 /no-vmlinux
2494 4378 0.7525 /bin/busybox
2495 CPU_CLK_UNHALT...|
2496 samples| %|
2497 ------------------
2498 2844 64.9612 /lib/libc-2.16.so
2499 1337 30.5391 /bin/busybox
2500 193 4.4084 /lib/ld-2.16.so
2501 2 0.0457 /lib/libnss_compat-2.16.so
2502 1 0.0228 /lib/libnsl-2.16.so
2503 1 0.0228 /lib/libnss_files-2.16.so
2504 4344 0.7467 /bin/bash
2505 CPU_CLK_UNHALT...|
2506 samples| %|
2507 ------------------
2508 2657 61.1648 /bin/bash
2509 1665 38.3287 /lib/libc-2.16.so
2510 18 0.4144 /lib/ld-2.16.so
2511 3 0.0691 /lib/libtinfo.so.5.9
2512 1 0.0230 /lib/libdl-2.16.so
2513 .
2514 .
2515 .
2516 </literallayout>
2517 Using the paths shown in the above output and the -l option to
2518 opreport, we can see all the functions that have hits in the
2519 profile and their sample counts and percentages. Here's a
2520 portion of what we get for the kernel:
2521 <literallayout class='monospaced'>
2522 root@crownbay:~# opreport -l /boot/vmlinux-3.4.11-yocto-standard
2523
2524 CPU: Intel Architectural Perfmon, speed 1.3e+06 MHz (estimated)
2525 Counted CPU_CLK_UNHALTED events (Clock cycles when not halted) with a unit mask of 0x00 (No unit mask) count 100000
2526 samples % symbol name
2527 233981 50.3873 intel_idle
2528 15437 3.3243 rb_get_reader_page
2529 14503 3.1232 ring_buffer_consume
2530 14092 3.0347 mutex_spin_on_owner
2531 13024 2.8047 read_hpet
2532 8039 1.7312 sub_preempt_count
2533 7096 1.5281 ioread32
2534 6997 1.5068 add_preempt_count
2535 3985 0.8582 rb_advance_reader
2536 3488 0.7511 add_event_entry
2537 3303 0.7113 get_parent_ip
2538 3104 0.6684 rb_buffer_peek
2539 2960 0.6374 op_cpu_buffer_read_entry
2540 2614 0.5629 sync_buffer
2541 2545 0.5481 debug_smp_processor_id
2542 2456 0.5289 ohci_irq
2543 2397 0.5162 memset
2544 2349 0.5059 __copy_to_user_ll
2545 2185 0.4705 ring_buffer_event_length
2546 1918 0.4130 in_lock_functions
2547 1850 0.3984 __schedule
2548 1767 0.3805 __copy_from_user_ll_nozero
2549 1575 0.3392 rb_event_data_length
2550 1256 0.2705 memcpy
2551 1233 0.2655 system_call
2552 1213 0.2612 menu_select
2553 </literallayout>
2554 Notice that above we see an entry for the __copy_to_user_ll()
2555 function that we've looked at with other profilers as well.
2556 </para>
2557
2558 <para>
2559 Here's what we get when we do the same thing for the
2560 busybox executable:
2561 <literallayout class='monospaced'>
2562 CPU: Intel Architectural Perfmon, speed 1.3e+06 MHz (estimated)
2563 Counted CPU_CLK_UNHALTED events (Clock cycles when not halted) with a unit mask of 0x00 (No unit mask) count 100000
2564 samples % image name symbol name
2565 349 8.4198 busybox retrieve_file_data
2566 308 7.4306 libc-2.16.so _IO_file_xsgetn
2567 283 6.8275 libc-2.16.so __read_nocancel
2568 235 5.6695 libc-2.16.so syscall
2569 233 5.6212 libc-2.16.so clearerr
2570 215 5.1870 libc-2.16.so fread
2571 181 4.3667 libc-2.16.so __write_nocancel
2572 158 3.8118 libc-2.16.so __underflow
2573 151 3.6429 libc-2.16.so _dl_addr
2574 150 3.6188 busybox progress_meter
2575 150 3.6188 libc-2.16.so __poll_nocancel
2576 148 3.5706 libc-2.16.so _IO_file_underflow@@GLIBC_2.1
2577 137 3.3052 busybox safe_poll
2578 125 3.0157 busybox bb_progress_update
2579 122 2.9433 libc-2.16.so __x86.get_pc_thunk.bx
2580 95 2.2919 busybox full_write
2581 81 1.9542 busybox safe_write
2582 77 1.8577 busybox xwrite
2583 72 1.7370 libc-2.16.so _IO_file_read
2584 71 1.7129 libc-2.16.so _IO_sgetn
2585 67 1.6164 libc-2.16.so poll
2586 52 1.2545 libc-2.16.so _IO_switch_to_get_mode
2587 45 1.0856 libc-2.16.so read
2588 34 0.8203 libc-2.16.so write
2589 32 0.7720 busybox monotonic_sec
2590 25 0.6031 libc-2.16.so vfprintf
2591 22 0.5308 busybox get_mono
2592 14 0.3378 ld-2.16.so strcmp
2593 14 0.3378 libc-2.16.so __x86.get_pc_thunk.cx
2594 .
2595 .
2596 .
2597 </literallayout>
2598 Since we recorded the profile with a callchain depth of 6, we
2599 should be able to see our __copy_to_user_ll() callchains in
2600 the output, and indeed we can if we search around a bit in
2601 the 'opreport --callgraph' output:
2602 <literallayout class='monospaced'>
2603 root@crownbay:~# opreport --callgraph /boot/vmlinux-3.4.11-yocto-standard
2604
2605 392 6.9639 vmlinux-3.4.11-yocto-standard sock_aio_read
2606 736 13.0751 vmlinux-3.4.11-yocto-standard __generic_file_aio_write
2607 3255 57.8255 vmlinux-3.4.11-yocto-standard inet_recvmsg
2608 785 0.1690 vmlinux-3.4.11-yocto-standard tcp_recvmsg
2609 1790 31.7940 vmlinux-3.4.11-yocto-standard local_bh_enable
2610 1238 21.9893 vmlinux-3.4.11-yocto-standard __kfree_skb
2611 992 17.6199 vmlinux-3.4.11-yocto-standard lock_sock_nested
2612 785 13.9432 vmlinux-3.4.11-yocto-standard tcp_recvmsg [self]
2613 525 9.3250 vmlinux-3.4.11-yocto-standard release_sock
2614 112 1.9893 vmlinux-3.4.11-yocto-standard tcp_cleanup_rbuf
2615 72 1.2789 vmlinux-3.4.11-yocto-standard skb_copy_datagram_iovec
2616
2617 170 0.0366 vmlinux-3.4.11-yocto-standard skb_copy_datagram_iovec
2618 1491 73.3038 vmlinux-3.4.11-yocto-standard memcpy_toiovec
2619 327 16.0767 vmlinux-3.4.11-yocto-standard skb_copy_datagram_iovec
2620 170 8.3579 vmlinux-3.4.11-yocto-standard skb_copy_datagram_iovec [self]
2621 20 0.9833 vmlinux-3.4.11-yocto-standard copy_to_user
2622
2623 2588 98.2909 vmlinux-3.4.11-yocto-standard copy_to_user
2624 2349 0.5059 vmlinux-3.4.11-yocto-standard __copy_to_user_ll
2625 2349 89.2138 vmlinux-3.4.11-yocto-standard __copy_to_user_ll [self]
2626 166 6.3046 vmlinux-3.4.11-yocto-standard do_page_fault
2627 </literallayout>
2628 Remember that by default OProfile sessions are cumulative
2629 i.e. if you start and stop a profiling session, then start a
2630 new one, the new one will not erase the previous run(s) but
2631 will build on it. If you want to restart a profile from scratch,
2632 you need to reset:
2633 <literallayout class='monospaced'>
2634 root@crownbay:~# opcontrol --reset
2635 </literallayout>
2636 </para>
2637 </section>
2638
2639 <section id='oprofileui-a-gui-for-oprofile'>
2640 <title>OProfileUI - A GUI for OProfile</title>
2641
2642 <para>
2643 Yocto also supports a graphical UI for controlling and viewing
2644 OProfile traces, called OProfileUI. To use it, you first need
2645 to clone the oprofileui git repo, then configure, build, and
2646 install it:
2647 <literallayout class='monospaced'>
2648 [trz@empanada tmp]$ git clone git://git.yoctoproject.org/oprofileui
2649 [trz@empanada tmp]$ cd oprofileui
2650 [trz@empanada oprofileui]$ ./autogen.sh
2651 [trz@empanada oprofileui]$ sudo make install
2652 </literallayout>
2653 OprofileUI replaces the 'opreport' functionality with a GUI,
2654 and normally doesn't require the user to use 'opcontrol' either.
2655 If you want to profile the kernel, however, you need to either
2656 use the UI to specify a vmlinux or use 'opcontrol' to specify
2657 it on the target:
2658 </para>
2659
2660 <para>
2661 First, on the target, check if vmlinux file: is set:
2662 <literallayout class='monospaced'>
2663 root@crownbay:~# opcontrol --status
2664 </literallayout>
2665 If not:
2666 <literallayout class='monospaced'>
2667 root@crownbay:~# opcontrol --shutdown
2668 root@crownbay:~# opcontrol --vmlinux=/boot/vmlinux-`uname -r`
2669 root@crownbay:~# opcontrol --start-daemon
2670 </literallayout>
2671 Now, start the oprofile UI on the host system:
2672 <literallayout class='monospaced'>
2673 [trz@empanada oprofileui]$ oprofile-viewer
2674 </literallayout>
2675 To run a profile on the remote system, first connect to the
2676 remote system by pressing the 'Connect' button and supplying
2677 the IP address and port of the remote system (the default
2678 port is 4224).
2679 </para>
2680
2681 <para>
2682 The oprofile server should automatically be started already.
2683 If not, the connection will fail and you either typed in the
2684 wrong IP address and port (see below), or you need to start
2685 the server yourself:
2686 <literallayout class='monospaced'>
2687 root@crownbay:~# oprofile-server
2688 </literallayout>
2689 Or, to specify a specific port:
2690 <literallayout class='monospaced'>
2691 root@crownbay:~# oprofile-server --port 8888
2692 </literallayout>
2693 Once connected, press the 'Start' button and then run the
2694 wget workload on the remote system:
2695 <literallayout class='monospaced'>
2696 root@crownbay:~# rm linux-2.6.19.2.tar.bz2; wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>; sync
2697 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
2698 linux-2.6.19.2.tar.b 100% |*******************************| 41727k 0:00:00 ETA
2699 </literallayout>
2700 Once the workload completes, press the 'Stop' button. At that
2701 point the OProfile viewer will download the profile files it's
2702 collected (this may take some time, especially if the kernel
2703 was profiled). While it downloads the files, you should see
2704 something like the following:
2705 </para>
2706
2707 <para>
2708 <imagedata fileref="figures/oprofileui-downloading.png" width="6in" depth="7in" align="center" scalefit="1" />
2709 </para>
2710
2711 <para>
2712 Once the profile files have been retrieved, you should see a
2713 list of the processes that were profiled:
2714 </para>
2715
2716 <para>
2717 <imagedata fileref="figures/oprofileui-processes.png" width="6in" depth="7in" align="center" scalefit="1" />
2718 </para>
2719
2720 <para>
2721 If you select one of them, you should see all the symbols that
2722 were hit during the profile. Selecting one of them will show a
2723 list of callers and callees of the chosen function in two
2724 panes below the top pane. For example, here's what we see
2725 when we select __copy_to_user_ll():
2726 </para>
2727
2728 <para>
2729 <imagedata fileref="figures/oprofileui-copy-to-user.png" width="6in" depth="7in" align="center" scalefit="1" />
2730 </para>
2731
2732 <para>
2733 As another example, we can look at the busybox process and see
2734 that the progress meter made a system call:
2735 </para>
2736
2737 <para>
2738 <imagedata fileref="figures/oprofileui-busybox.png" width="6in" depth="7in" align="center" scalefit="1" />
2739 </para>
2740 </section>
2741
2742 <section id='oprofile-documentation'>
2743 <title>Documentation</title>
2744
2745 <para>
2746 Yocto already has some information on setting up and using
2747 OProfile and oprofileui. As this document doesn't cover
2748 everything in detail, it may be worth taking a look at the
2749 "<ulink url='&YOCTO_DOCS_DEV_URL;#platdev-oprofile'>Profiling with OProfile</ulink>"
2750 section in the Yocto Project Development Manual
2751 </para>
2752
2753 <para>
2754 The OProfile manual can be found here:
2755 <ulink url='http://oprofile.sourceforge.net/doc/index.html'>OProfile manual</ulink>
2756 </para>
2757
2758 <para>
2759 The OProfile website contains links to the above manual and
2760 bunch of other items including an extensive set of examples:
2761 <ulink url='http://oprofile.sourceforge.net/about/'>About OProfile</ulink>
2762 </para>
2763 </section>
2764</section>
2765
2766<section id='profile-manual-sysprof'>
2767 <title>Sysprof</title>
2768
2769 <para>
2770 Sysprof is a very easy to use system-wide profiler that consists
2771 of a single window with three panes and a few buttons which allow
2772 you to start, stop, and view the profile from one place.
2773 </para>
2774
2775 <section id='sysprof-setup'>
2776 <title>Setup</title>
2777
2778 <para>
2779 For this section, we'll assume you've already performed the
2780 basic setup outlined in the General Setup section.
2781 </para>
2782
2783 <para>
2784 Sysprof is a GUI-based application that runs on the target
2785 system. For the rest of this document we assume you've
2786 ssh'ed to the host and will be running Sysprof on the
2787 target (you can use the '-X' option to ssh and have the
2788 Sysprof GUI run on the target but display remotely on the
2789 host if you want).
2790 </para>
2791 </section>
2792
2793 <section id='sysprof-basic-usage'>
2794 <title>Basic Usage</title>
2795
2796 <para>
2797 To start profiling the system, you simply press the 'Start'
2798 button. To stop profiling and to start viewing the profile data
2799 in one easy step, press the 'Profile' button.
2800 </para>
2801
2802 <para>
2803 Once you've pressed the profile button, the three panes will
2804 fill up with profiling data:
2805 </para>
2806
2807 <para>
2808 <imagedata fileref="figures/sysprof-copy-to-user.png" width="6in" depth="4in" align="center" scalefit="1" />
2809 </para>
2810
2811 <para>
2812 The left pane shows a list of functions and processes.
2813 Selecting one of those expands that function in the right
2814 pane, showing all its callees. Note that this caller-oriented
2815 display is essentially the inverse of perf's default
2816 callee-oriented callchain display.
2817 </para>
2818
2819 <para>
2820 In the screenshot above, we're focusing on __copy_to_user_ll()
2821 and looking up the callchain we can see that one of the callers
2822 of __copy_to_user_ll is sys_read() and the complete callpath
2823 between them. Notice that this is essentially a portion of the
2824 same information we saw in the perf display shown in the perf
2825 section of this page.
2826 </para>
2827
2828 <para>
2829 <imagedata fileref="figures/sysprof-copy-from-user.png" width="6in" depth="4in" align="center" scalefit="1" />
2830 </para>
2831
2832 <para>
2833 Similarly, the above is a snapshot of the Sysprof display of a
2834 copy-from-user callchain.
2835 </para>
2836
2837 <para>
2838 Finally, looking at the third Sysprof pane in the lower left,
2839 we can see a list of all the callers of a particular function
2840 selected in the top left pane. In this case, the lower pane is
2841 showing all the callers of __mark_inode_dirty:
2842 </para>
2843
2844 <para>
2845 <imagedata fileref="figures/sysprof-callers.png" width="6in" depth="4in" align="center" scalefit="1" />
2846 </para>
2847
2848 <para>
2849 Double-clicking on one of those functions will in turn change the
2850 focus to the selected function, and so on.
2851 </para>
2852
2853 <informalexample>
2854 <emphasis>Tying it Together:</emphasis> If you like sysprof's 'caller-oriented'
2855 display, you may be able to approximate it in other tools as
2856 well. For example, 'perf report' has the -g (--call-graph)
2857 option that you can experiment with; one of the options is
2858 'caller' for an inverted caller-based callgraph display.
2859 </informalexample>
2860 </section>
2861
2862 <section id='sysprof-documentation'>
2863 <title>Documentation</title>
2864
2865 <para>
2866 There doesn't seem to be any documentation for Sysprof, but
2867 maybe that's because it's pretty self-explanatory.
2868 The Sysprof website, however, is here:
2869 <ulink url='http://sysprof.com/'>Sysprof, System-wide Performance Profiler for Linux</ulink>
2870 </para>
2871 </section>
2872</section>
2873
2874<section id='lttng-linux-trace-toolkit-next-generation'>
2875 <title>LTTng (Linux Trace Toolkit, next generation)</title>
2876
2877 <section id='lttng-setup'>
2878 <title>Setup</title>
2879
2880 <para>
2881 For this section, we'll assume you've already performed the
2882 basic setup outlined in the General Setup section.
2883 </para>
2884
2885 <para>
2886 LTTng is run on the target system by ssh'ing to it.
2887 However, if you want to see the traces graphically,
2888 install Eclipse as described in section
2889 "<link linkend='manually-copying-a-trace-to-the-host-and-viewing-it-in-eclipse'>Manually copying a trace to the host and viewing it in Eclipse (i.e. using Eclipse without network support)</link>"
2890 and follow the directions to manually copy traces to the host and
2891 view them in Eclipse (i.e. using Eclipse without network support).
2892 </para>
2893
2894 <note>
2895 Be sure to download and install/run the 'SR1' or later Juno release
2896 of eclipse e.g.:
2897 <ulink url='http://www.eclipse.org/downloads/download.php?file=/technology/epp/downloads/release/juno/SR1/eclipse-cpp-juno-SR1-linux-gtk-x86_64.tar.gz'>http://www.eclipse.org/downloads/download.php?file=/technology/epp/downloads/release/juno/SR1/eclipse-cpp-juno-SR1-linux-gtk-x86_64.tar.gz</ulink>
2898 </note>
2899 </section>
2900
2901 <section id='collecting-and-viewing-traces'>
2902 <title>Collecting and Viewing Traces</title>
2903
2904 <para>
2905 Once you've applied the above commits and built and booted your
2906 image (you need to build the core-image-sato-sdk image or use one of the
2907 other methods described in the General Setup section), you're
2908 ready to start tracing.
2909 </para>
2910
2911 <section id='collecting-and-viewing-a-trace-on-the-target-inside-a-shell'>
2912 <title>Collecting and viewing a trace on the target (inside a shell)</title>
2913
2914 <para>
2915 First, from the host, ssh to the target:
2916 <literallayout class='monospaced'>
2917 $ ssh -l root 192.168.1.47
2918 The authenticity of host '192.168.1.47 (192.168.1.47)' can't be established.
2919 RSA key fingerprint is 23:bd:c8:b1:a8:71:52:00:ee:00:4f:64:9e:10:b9:7e.
2920 Are you sure you want to continue connecting (yes/no)? yes
2921 Warning: Permanently added '192.168.1.47' (RSA) to the list of known hosts.
2922 root@192.168.1.47's password:
2923 </literallayout>
2924 Once on the target, use these steps to create a trace:
2925 <literallayout class='monospaced'>
2926 root@crownbay:~# lttng create
2927 Spawning a session daemon
2928 Session auto-20121015-232120 created.
2929 Traces will be written in /home/root/lttng-traces/auto-20121015-232120
2930 </literallayout>
2931 Enable the events you want to trace (in this case all
2932 kernel events):
2933 <literallayout class='monospaced'>
2934 root@crownbay:~# lttng enable-event --kernel --all
2935 All kernel events are enabled in channel channel0
2936 </literallayout>
2937 Start the trace:
2938 <literallayout class='monospaced'>
2939 root@crownbay:~# lttng start
2940 Tracing started for session auto-20121015-232120
2941 </literallayout>
2942 And then stop the trace after awhile or after running
2943 a particular workload that you want to trace:
2944 <literallayout class='monospaced'>
2945 root@crownbay:~# lttng stop
2946 Tracing stopped for session auto-20121015-232120
2947 </literallayout>
2948 You can now view the trace in text form on the target:
2949 <literallayout class='monospaced'>
2950 root@crownbay:~# lttng view
2951 [23:21:56.989270399] (+?.?????????) sys_geteuid: { 1 }, { }
2952 [23:21:56.989278081] (+0.000007682) exit_syscall: { 1 }, { ret = 0 }
2953 [23:21:56.989286043] (+0.000007962) sys_pipe: { 1 }, { fildes = 0xB77B9E8C }
2954 [23:21:56.989321802] (+0.000035759) exit_syscall: { 1 }, { ret = 0 }
2955 [23:21:56.989329345] (+0.000007543) sys_mmap_pgoff: { 1 }, { addr = 0x0, len = 10485760, prot = 3, flags = 131362, fd = 4294967295, pgoff = 0 }
2956 [23:21:56.989351694] (+0.000022349) exit_syscall: { 1 }, { ret = -1247805440 }
2957 [23:21:56.989432989] (+0.000081295) sys_clone: { 1 }, { clone_flags = 0x411, newsp = 0xB5EFFFE4, parent_tid = 0xFFFFFFFF, child_tid = 0x0 }
2958 [23:21:56.989477129] (+0.000044140) sched_stat_runtime: { 1 }, { comm = "lttng-consumerd", tid = 1193, runtime = 681660, vruntime = 43367983388 }
2959 [23:21:56.989486697] (+0.000009568) sched_migrate_task: { 1 }, { comm = "lttng-consumerd", tid = 1193, prio = 20, orig_cpu = 1, dest_cpu = 1 }
2960 [23:21:56.989508418] (+0.000021721) hrtimer_init: { 1 }, { hrtimer = 3970832076, clockid = 1, mode = 1 }
2961 [23:21:56.989770462] (+0.000262044) hrtimer_cancel: { 1 }, { hrtimer = 3993865440 }
2962 [23:21:56.989771580] (+0.000001118) hrtimer_cancel: { 0 }, { hrtimer = 3993812192 }
2963 [23:21:56.989776957] (+0.000005377) hrtimer_expire_entry: { 1 }, { hrtimer = 3993865440, now = 79815980007057, function = 3238465232 }
2964 [23:21:56.989778145] (+0.000001188) hrtimer_expire_entry: { 0 }, { hrtimer = 3993812192, now = 79815980008174, function = 3238465232 }
2965 [23:21:56.989791695] (+0.000013550) softirq_raise: { 1 }, { vec = 1 }
2966 [23:21:56.989795396] (+0.000003701) softirq_raise: { 0 }, { vec = 1 }
2967 [23:21:56.989800635] (+0.000005239) softirq_raise: { 0 }, { vec = 9 }
2968 [23:21:56.989807130] (+0.000006495) sched_stat_runtime: { 1 }, { comm = "lttng-consumerd", tid = 1193, runtime = 330710, vruntime = 43368314098 }
2969 [23:21:56.989809993] (+0.000002863) sched_stat_runtime: { 0 }, { comm = "lttng-sessiond", tid = 1181, runtime = 1015313, vruntime = 36976733240 }
2970 [23:21:56.989818514] (+0.000008521) hrtimer_expire_exit: { 0 }, { hrtimer = 3993812192 }
2971 [23:21:56.989819631] (+0.000001117) hrtimer_expire_exit: { 1 }, { hrtimer = 3993865440 }
2972 [23:21:56.989821866] (+0.000002235) hrtimer_start: { 0 }, { hrtimer = 3993812192, function = 3238465232, expires = 79815981000000, softexpires = 79815981000000 }
2973 [23:21:56.989822984] (+0.000001118) hrtimer_start: { 1 }, { hrtimer = 3993865440, function = 3238465232, expires = 79815981000000, softexpires = 79815981000000 }
2974 [23:21:56.989832762] (+0.000009778) softirq_entry: { 1 }, { vec = 1 }
2975 [23:21:56.989833879] (+0.000001117) softirq_entry: { 0 }, { vec = 1 }
2976 [23:21:56.989838069] (+0.000004190) timer_cancel: { 1 }, { timer = 3993871956 }
2977 [23:21:56.989839187] (+0.000001118) timer_cancel: { 0 }, { timer = 3993818708 }
2978 [23:21:56.989841492] (+0.000002305) timer_expire_entry: { 1 }, { timer = 3993871956, now = 79515980, function = 3238277552 }
2979 [23:21:56.989842819] (+0.000001327) timer_expire_entry: { 0 }, { timer = 3993818708, now = 79515980, function = 3238277552 }
2980 [23:21:56.989854831] (+0.000012012) sched_stat_runtime: { 1 }, { comm = "lttng-consumerd", tid = 1193, runtime = 49237, vruntime = 43368363335 }
2981 [23:21:56.989855949] (+0.000001118) sched_stat_runtime: { 0 }, { comm = "lttng-sessiond", tid = 1181, runtime = 45121, vruntime = 36976778361 }
2982 [23:21:56.989861257] (+0.000005308) sched_stat_sleep: { 1 }, { comm = "kworker/1:1", tid = 21, delay = 9451318 }
2983 [23:21:56.989862374] (+0.000001117) sched_stat_sleep: { 0 }, { comm = "kworker/0:0", tid = 4, delay = 9958820 }
2984 [23:21:56.989868241] (+0.000005867) sched_wakeup: { 0 }, { comm = "kworker/0:0", tid = 4, prio = 120, success = 1, target_cpu = 0 }
2985 [23:21:56.989869358] (+0.000001117) sched_wakeup: { 1 }, { comm = "kworker/1:1", tid = 21, prio = 120, success = 1, target_cpu = 1 }
2986 [23:21:56.989877460] (+0.000008102) timer_expire_exit: { 1 }, { timer = 3993871956 }
2987 [23:21:56.989878577] (+0.000001117) timer_expire_exit: { 0 }, { timer = 3993818708 }
2988 .
2989 .
2990 .
2991 </literallayout>
2992 You can now safely destroy the trace session (note that
2993 this doesn't delete the trace - it's still there
2994 in ~/lttng-traces):
2995 <literallayout class='monospaced'>
2996 root@crownbay:~# lttng destroy
2997 Session auto-20121015-232120 destroyed at /home/root
2998 </literallayout>
2999 Note that the trace is saved in a directory of the same
3000 name as returned by 'lttng create', under the ~/lttng-traces
3001 directory (note that you can change this by supplying your
3002 own name to 'lttng create'):
3003 <literallayout class='monospaced'>
3004 root@crownbay:~# ls -al ~/lttng-traces
3005 drwxrwx--- 3 root root 1024 Oct 15 23:21 .
3006 drwxr-xr-x 5 root root 1024 Oct 15 23:57 ..
3007 drwxrwx--- 3 root root 1024 Oct 15 23:21 auto-20121015-232120
3008 </literallayout>
3009 </para>
3010 </section>
3011
3012 <section id='collecting-and-viewing-a-userspace-trace-on-the-target-inside-a-shell'>
3013 <title>Collecting and viewing a userspace trace on the target (inside a shell)</title>
3014
3015 <para>
3016 For LTTng userspace tracing, you need to have a properly
3017 instrumented userspace program. For this example, we'll use
3018 the 'hello' test program generated by the lttng-ust build.
3019 </para>
3020
3021 <para>
3022 The 'hello' test program isn't installed on the rootfs by
3023 the lttng-ust build, so we need to copy it over manually.
3024 First cd into the build directory that contains the hello
3025 executable:
3026 <literallayout class='monospaced'>
3027 $ cd build/tmp/work/core2_32-poky-linux/lttng-ust/2.0.5-r0/git/tests/hello/.libs
3028 </literallayout>
3029 Copy that over to the target machine:
3030 <literallayout class='monospaced'>
3031 $ scp hello root@192.168.1.20:
3032 </literallayout>
3033 You now have the instrumented lttng 'hello world' test
3034 program on the target, ready to test.
3035 </para>
3036
3037 <para>
3038 First, from the host, ssh to the target:
3039 <literallayout class='monospaced'>
3040 $ ssh -l root 192.168.1.47
3041 The authenticity of host '192.168.1.47 (192.168.1.47)' can't be established.
3042 RSA key fingerprint is 23:bd:c8:b1:a8:71:52:00:ee:00:4f:64:9e:10:b9:7e.
3043 Are you sure you want to continue connecting (yes/no)? yes
3044 Warning: Permanently added '192.168.1.47' (RSA) to the list of known hosts.
3045 root@192.168.1.47's password:
3046 </literallayout>
3047 Once on the target, use these steps to create a trace:
3048 <literallayout class='monospaced'>
3049 root@crownbay:~# lttng create
3050 Session auto-20190303-021943 created.
3051 Traces will be written in /home/root/lttng-traces/auto-20190303-021943
3052 </literallayout>
3053 Enable the events you want to trace (in this case all
3054 userspace events):
3055 <literallayout class='monospaced'>
3056 root@crownbay:~# lttng enable-event --userspace --all
3057 All UST events are enabled in channel channel0
3058 </literallayout>
3059 Start the trace:
3060 <literallayout class='monospaced'>
3061 root@crownbay:~# lttng start
3062 Tracing started for session auto-20190303-021943
3063 </literallayout>
3064 Run the instrumented hello world program:
3065 <literallayout class='monospaced'>
3066 root@crownbay:~# ./hello
3067 Hello, World!
3068 Tracing... done.
3069 </literallayout>
3070 And then stop the trace after awhile or after running a
3071 particular workload that you want to trace:
3072 <literallayout class='monospaced'>
3073 root@crownbay:~# lttng stop
3074 Tracing stopped for session auto-20190303-021943
3075 </literallayout>
3076 You can now view the trace in text form on the target:
3077 <literallayout class='monospaced'>
3078 root@crownbay:~# lttng view
3079 [02:31:14.906146544] (+?.?????????) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 0, intfield2 = 0x0, longfield = 0, netintfield = 0, netintfieldhex = 0x0, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4, seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
3080 [02:31:14.906170360] (+0.000023816) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 1, intfield2 = 0x1, longfield = 1, netintfield = 1, netintfieldhex = 0x1, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4, seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
3081 [02:31:14.906183140] (+0.000012780) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 2, intfield2 = 0x2, longfield = 2, netintfield = 2, netintfieldhex = 0x2, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4, seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
3082 [02:31:14.906194385] (+0.000011245) hello:1424 ust_tests_hello:tptest: { cpu_id = 1 }, { intfield = 3, intfield2 = 0x3, longfield = 3, netintfield = 3, netintfieldhex = 0x3, arrfield1 = [ [0] = 1, [1] = 2, [2] = 3 ], arrfield2 = "test", _seqfield1_length = 4, seqfield1 = [ [0] = 116, [1] = 101, [2] = 115, [3] = 116 ], _seqfield2_length = 4, seqfield2 = "test", stringfield = "test", floatfield = 2222, doublefield = 2, boolfield = 1 }
3083 .
3084 .
3085 .
3086 </literallayout>
3087 You can now safely destroy the trace session (note that
3088 this doesn't delete the trace - it's still
3089 there in ~/lttng-traces):
3090 <literallayout class='monospaced'>
3091 root@crownbay:~# lttng destroy
3092 Session auto-20190303-021943 destroyed at /home/root
3093 </literallayout>
3094 </para>
3095 </section>
3096
3097 <section id='manually-copying-a-trace-to-the-host-and-viewing-it-in-eclipse'>
3098 <title>Manually copying a trace to the host and viewing it in Eclipse (i.e. using Eclipse without network support)</title>
3099
3100 <para>
3101 If you already have an LTTng trace on a remote target and
3102 would like to view it in Eclipse on the host, you can easily
3103 copy it from the target to the host and import it into
3104 Eclipse to view it using the LTTng Eclipse plug-in already
3105 bundled in the Eclipse (Juno SR1 or greater).
3106 </para>
3107
3108 <para>
3109 Using the trace we created in the previous section, archive
3110 it and copy it to your host system:
3111 <literallayout class='monospaced'>
3112 root@crownbay:~/lttng-traces# tar zcvf auto-20121015-232120.tar.gz auto-20121015-232120
3113 auto-20121015-232120/
3114 auto-20121015-232120/kernel/
3115 auto-20121015-232120/kernel/metadata
3116 auto-20121015-232120/kernel/channel0_1
3117 auto-20121015-232120/kernel/channel0_0
3118
3119 $ scp root@192.168.1.47:lttng-traces/auto-20121015-232120.tar.gz .
3120 root@192.168.1.47's password:
3121 auto-20121015-232120.tar.gz 100% 1566KB 1.5MB/s 00:01
3122 </literallayout>
3123 Unarchive it on the host:
3124 <literallayout class='monospaced'>
3125 $ gunzip -c auto-20121015-232120.tar.gz | tar xvf -
3126 auto-20121015-232120/
3127 auto-20121015-232120/kernel/
3128 auto-20121015-232120/kernel/metadata
3129 auto-20121015-232120/kernel/channel0_1
3130 auto-20121015-232120/kernel/channel0_0
3131 </literallayout>
3132 We can now import the trace into Eclipse and view it:
3133 <orderedlist>
3134 <listitem><para>First, start eclipse and open the
3135 'LTTng Kernel' perspective by selecting the following
3136 menu item:
3137 <literallayout class='monospaced'>
3138 Window | Open Perspective | Other...
3139 </literallayout></para></listitem>
3140 <listitem><para>In the dialog box that opens, select
3141 'LTTng Kernel' from the list.</para></listitem>
3142 <listitem><para>Back at the main menu, select the
3143 following menu item:
3144 <literallayout class='monospaced'>
3145 File | New | Project...
3146 </literallayout></para></listitem>
3147 <listitem><para>In the dialog box that opens, select
3148 the 'Tracing | Tracing Project' wizard and press
3149 'Next>'.</para></listitem>
3150 <listitem><para>Give the project a name and press
3151 'Finish'.</para></listitem>
3152 <listitem><para>In the 'Project Explorer' pane under
3153 the project you created, right click on the
3154 'Traces' item.</para></listitem>
3155 <listitem><para>Select 'Import..." and in the dialog
3156 that's displayed:</para></listitem>
3157 <listitem><para>Browse the filesystem and find the
3158 select the 'kernel' directory containing the trace
3159 you copied from the target
3160 e.g. auto-20121015-232120/kernel</para></listitem>
3161 <listitem><para>'Checkmark' the directory in the tree
3162 that's displayed for the trace</para></listitem>
3163 <listitem><para>Below that, select 'Common Trace Format:
3164 Kernel Trace' for the 'Trace Type'</para></listitem>
3165 <listitem><para>Press 'Finish' to close the dialog
3166 </para></listitem>
3167 <listitem><para>Back in the 'Project Explorer' pane,
3168 double-click on the 'kernel' item for the
3169 trace you just imported under 'Traces'
3170 </para></listitem>
3171 </orderedlist>
3172 You should now see your trace data displayed graphically
3173 in several different views in Eclipse:
3174 </para>
3175
3176 <para>
3177 <imagedata fileref="figures/lttngmain0.png" width="6in" depth="6in" align="center" scalefit="1" />
3178 </para>
3179
3180 <para>
3181 You can access extensive help information on how to use
3182 the LTTng plug-in to search and analyze captured traces via
3183 the Eclipse help system:
3184 <literallayout class='monospaced'>
3185 Help | Help Contents | LTTng Plug-in User Guide
3186 </literallayout>
3187 </para>
3188 </section>
3189
3190 <section id='collecting-and-viewing-a-trace-in-eclipse'>
3191 <title>Collecting and viewing a trace in Eclipse</title>
3192
3193 <note>
3194 This section on collecting traces remotely doesn't currently
3195 work because of Eclipse 'RSE' connectivity problems. Manually
3196 tracing on the target, copying the trace files to the host,
3197 and viewing the trace in Eclipse on the host as outlined in
3198 previous steps does work however - please use the manual
3199 steps outlined above to view traces in Eclipse.
3200 </note>
3201
3202 <para>
3203 In order to trace a remote target, you also need to add
3204 a 'tracing' group on the target and connect as a user
3205 who's part of that group e.g:
3206 <literallayout class='monospaced'>
3207 # adduser tomz
3208 # groupadd -r tracing
3209 # usermod -a -G tracing tomz
3210 </literallayout>
3211 <orderedlist>
3212 <listitem><para>First, start eclipse and open the
3213 'LTTng Kernel' perspective by selecting the following
3214 menu item:
3215 <literallayout class='monospaced'>
3216 Window | Open Perspective | Other...
3217 </literallayout></para></listitem>
3218 <listitem><para>In the dialog box that opens, select
3219 'LTTng Kernel' from the list.</para></listitem>
3220 <listitem><para>Back at the main menu, select the
3221 following menu item:
3222 <literallayout class='monospaced'>
3223 File | New | Project...
3224 </literallayout></para></listitem>
3225 <listitem><para>In the dialog box that opens, select
3226 the 'Tracing | Tracing Project' wizard and
3227 press 'Next>'.</para></listitem>
3228 <listitem><para>Give the project a name and press
3229 'Finish'. That should result in an entry in the
3230 'Project' subwindow.</para></listitem>
3231 <listitem><para>In the 'Control' subwindow just below
3232 it, press 'New Connection'.</para></listitem>
3233 <listitem><para>Add a new connection, giving it the
3234 hostname or IP address of the target system.
3235 </para></listitem>
3236 <listitem><para>Provide the username and password
3237 of a qualified user (a member of the 'tracing' group)
3238 or root account on the target system.
3239 </para></listitem>
3240 <listitem><para>Provide appropriate answers to whatever
3241 else is asked for e.g. 'secure storage password'
3242 can be anything you want.
3243 If you get an 'RSE Error' it may be due to proxies.
3244 It may be possible to get around the problem by
3245 changing the following setting:
3246 <literallayout class='monospaced'>
3247 Window | Preferences | Network Connections
3248 </literallayout>
3249 Switch 'Active Provider' to 'Direct'
3250 </para></listitem>
3251 </orderedlist>
3252 </para>
3253 </section>
3254 </section>
3255
3256 <section id='lltng-documentation'>
3257 <title>Documentation</title>
3258
3259 <para>
3260 There doesn't seem to be any current documentation covering
3261 LTTng 2.0, but maybe that's because the project is in transition.
3262 The LTTng 2.0 website, however, is here:
3263 <ulink url='http://lttng.org/lttng2.0'>LTTng Project</ulink>
3264 </para>
3265
3266 <para>
3267 You can access extensive help information on how to use the
3268 LTTng plug-in to search and analyze captured traces via the
3269 Eclipse help system:
3270 <literallayout class='monospaced'>
3271 Help | Help Contents | LTTng Plug-in User Guide
3272 </literallayout>
3273 </para>
3274 </section>
3275</section>
3276
3277<section id='profile-manual-blktrace'>
3278 <title>blktrace</title>
3279
3280 <para>
3281 blktrace is a tool for tracing and reporting low-level disk I/O.
3282 blktrace provides the tracing half of the equation; its output can
3283 be piped into the blkparse program, which renders the data in a
3284 human-readable form and does some basic analysis:
3285 </para>
3286
3287 <section id='blktrace-setup'>
3288 <title>Setup</title>
3289
3290 <para>
3291 For this section, we'll assume you've already performed the
3292 basic setup outlined in the
3293 "<link linkend='profile-manual-general-setup'>General Setup</link>"
3294 section.
3295 </para>
3296
3297 <para>
3298 blktrace is an application that runs on the target system.
3299 You can run the entire blktrace and blkparse pipeline on the
3300 target, or you can run blktrace in 'listen' mode on the target
3301 and have blktrace and blkparse collect and analyze the data on
3302 the host (see the
3303 "<link linkend='using-blktrace-remotely'>Using blktrace Remotely</link>"
3304 section below).
3305 For the rest of this section we assume you've ssh'ed to the
3306 host and will be running blkrace on the target.
3307 </para>
3308 </section>
3309
3310 <section id='blktrace-basic-usage'>
3311 <title>Basic Usage</title>
3312
3313 <para>
3314 To record a trace, simply run the 'blktrace' command, giving it
3315 the name of the block device you want to trace activity on:
3316 <literallayout class='monospaced'>
3317 root@crownbay:~# blktrace /dev/sdc
3318 </literallayout>
3319 In another shell, execute a workload you want to trace.
3320 <literallayout class='monospaced'>
3321 root@crownbay:/media/sdc# rm linux-2.6.19.2.tar.bz2; wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>; sync
3322 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
3323 linux-2.6.19.2.tar.b 100% |*******************************| 41727k 0:00:00 ETA
3324 </literallayout>
3325 Press Ctrl-C in the blktrace shell to stop the trace. It will
3326 display how many events were logged, along with the per-cpu file
3327 sizes (blktrace records traces in per-cpu kernel buffers and
3328 simply dumps them to userspace for blkparse to merge and sort
3329 later).
3330 <literallayout class='monospaced'>
3331 ^C=== sdc ===
3332 CPU 0: 7082 events, 332 KiB data
3333 CPU 1: 1578 events, 74 KiB data
3334 Total: 8660 events (dropped 0), 406 KiB data
3335 </literallayout>
3336 If you examine the files saved to disk, you see multiple files,
3337 one per CPU and with the device name as the first part of the
3338 filename:
3339 <literallayout class='monospaced'>
3340 root@crownbay:~# ls -al
3341 drwxr-xr-x 6 root root 1024 Oct 27 22:39 .
3342 drwxr-sr-x 4 root root 1024 Oct 26 18:24 ..
3343 -rw-r--r-- 1 root root 339938 Oct 27 22:40 sdc.blktrace.0
3344 -rw-r--r-- 1 root root 75753 Oct 27 22:40 sdc.blktrace.1
3345 </literallayout>
3346 To view the trace events, simply invoke 'blkparse' in the
3347 directory containing the trace files, giving it the device name
3348 that forms the first part of the filenames:
3349 <literallayout class='monospaced'>
3350 root@crownbay:~# blkparse sdc
3351
3352 8,32 1 1 0.000000000 1225 Q WS 3417048 + 8 [jbd2/sdc-8]
3353 8,32 1 2 0.000025213 1225 G WS 3417048 + 8 [jbd2/sdc-8]
3354 8,32 1 3 0.000033384 1225 P N [jbd2/sdc-8]
3355 8,32 1 4 0.000043301 1225 I WS 3417048 + 8 [jbd2/sdc-8]
3356 8,32 1 0 0.000057270 0 m N cfq1225 insert_request
3357 8,32 1 0 0.000064813 0 m N cfq1225 add_to_rr
3358 8,32 1 5 0.000076336 1225 U N [jbd2/sdc-8] 1
3359 8,32 1 0 0.000088559 0 m N cfq workload slice:150
3360 8,32 1 0 0.000097359 0 m N cfq1225 set_active wl_prio:0 wl_type:1
3361 8,32 1 0 0.000104063 0 m N cfq1225 Not idling. st->count:1
3362 8,32 1 0 0.000112584 0 m N cfq1225 fifo= (null)
3363 8,32 1 0 0.000118730 0 m N cfq1225 dispatch_insert
3364 8,32 1 0 0.000127390 0 m N cfq1225 dispatched a request
3365 8,32 1 0 0.000133536 0 m N cfq1225 activate rq, drv=1
3366 8,32 1 6 0.000136889 1225 D WS 3417048 + 8 [jbd2/sdc-8]
3367 8,32 1 7 0.000360381 1225 Q WS 3417056 + 8 [jbd2/sdc-8]
3368 8,32 1 8 0.000377422 1225 G WS 3417056 + 8 [jbd2/sdc-8]
3369 8,32 1 9 0.000388876 1225 P N [jbd2/sdc-8]
3370 8,32 1 10 0.000397886 1225 Q WS 3417064 + 8 [jbd2/sdc-8]
3371 8,32 1 11 0.000404800 1225 M WS 3417064 + 8 [jbd2/sdc-8]
3372 8,32 1 12 0.000412343 1225 Q WS 3417072 + 8 [jbd2/sdc-8]
3373 8,32 1 13 0.000416533 1225 M WS 3417072 + 8 [jbd2/sdc-8]
3374 8,32 1 14 0.000422121 1225 Q WS 3417080 + 8 [jbd2/sdc-8]
3375 8,32 1 15 0.000425194 1225 M WS 3417080 + 8 [jbd2/sdc-8]
3376 8,32 1 16 0.000431968 1225 Q WS 3417088 + 8 [jbd2/sdc-8]
3377 8,32 1 17 0.000435251 1225 M WS 3417088 + 8 [jbd2/sdc-8]
3378 8,32 1 18 0.000440279 1225 Q WS 3417096 + 8 [jbd2/sdc-8]
3379 8,32 1 19 0.000443911 1225 M WS 3417096 + 8 [jbd2/sdc-8]
3380 8,32 1 20 0.000450336 1225 Q WS 3417104 + 8 [jbd2/sdc-8]
3381 8,32 1 21 0.000454038 1225 M WS 3417104 + 8 [jbd2/sdc-8]
3382 8,32 1 22 0.000462070 1225 Q WS 3417112 + 8 [jbd2/sdc-8]
3383 8,32 1 23 0.000465422 1225 M WS 3417112 + 8 [jbd2/sdc-8]
3384 8,32 1 24 0.000474222 1225 I WS 3417056 + 64 [jbd2/sdc-8]
3385 8,32 1 0 0.000483022 0 m N cfq1225 insert_request
3386 8,32 1 25 0.000489727 1225 U N [jbd2/sdc-8] 1
3387 8,32 1 0 0.000498457 0 m N cfq1225 Not idling. st->count:1
3388 8,32 1 0 0.000503765 0 m N cfq1225 dispatch_insert
3389 8,32 1 0 0.000512914 0 m N cfq1225 dispatched a request
3390 8,32 1 0 0.000518851 0 m N cfq1225 activate rq, drv=2
3391 .
3392 .
3393 .
3394 8,32 0 0 58.515006138 0 m N cfq3551 complete rqnoidle 1
3395 8,32 0 2024 58.516603269 3 C WS 3156992 + 16 [0]
3396 8,32 0 0 58.516626736 0 m N cfq3551 complete rqnoidle 1
3397 8,32 0 0 58.516634558 0 m N cfq3551 arm_idle: 8 group_idle: 0
3398 8,32 0 0 58.516636933 0 m N cfq schedule dispatch
3399 8,32 1 0 58.516971613 0 m N cfq3551 slice expired t=0
3400 8,32 1 0 58.516982089 0 m N cfq3551 sl_used=13 disp=6 charge=13 iops=0 sect=80
3401 8,32 1 0 58.516985511 0 m N cfq3551 del_from_rr
3402 8,32 1 0 58.516990819 0 m N cfq3551 put_queue
3403
3404 CPU0 (sdc):
3405 Reads Queued: 0, 0KiB Writes Queued: 331, 26,284KiB
3406 Read Dispatches: 0, 0KiB Write Dispatches: 485, 40,484KiB
3407 Reads Requeued: 0 Writes Requeued: 0
3408 Reads Completed: 0, 0KiB Writes Completed: 511, 41,000KiB
3409 Read Merges: 0, 0KiB Write Merges: 13, 160KiB
3410 Read depth: 0 Write depth: 2
3411 IO unplugs: 23 Timer unplugs: 0
3412 CPU1 (sdc):
3413 Reads Queued: 0, 0KiB Writes Queued: 249, 15,800KiB
3414 Read Dispatches: 0, 0KiB Write Dispatches: 42, 1,600KiB
3415 Reads Requeued: 0 Writes Requeued: 0
3416 Reads Completed: 0, 0KiB Writes Completed: 16, 1,084KiB
3417 Read Merges: 0, 0KiB Write Merges: 40, 276KiB
3418 Read depth: 0 Write depth: 2
3419 IO unplugs: 30 Timer unplugs: 1
3420
3421 Total (sdc):
3422 Reads Queued: 0, 0KiB Writes Queued: 580, 42,084KiB
3423 Read Dispatches: 0, 0KiB Write Dispatches: 527, 42,084KiB
3424 Reads Requeued: 0 Writes Requeued: 0
3425 Reads Completed: 0, 0KiB Writes Completed: 527, 42,084KiB
3426 Read Merges: 0, 0KiB Write Merges: 53, 436KiB
3427 IO unplugs: 53 Timer unplugs: 1
3428
3429 Throughput (R/W): 0KiB/s / 719KiB/s
3430 Events (sdc): 6,592 entries
3431 Skips: 0 forward (0 - 0.0%)
3432 Input file sdc.blktrace.0 added
3433 Input file sdc.blktrace.1 added
3434 </literallayout>
3435 The report shows each event that was found in the blktrace data,
3436 along with a summary of the overall block I/O traffic during
3437 the run. You can look at the
3438 <ulink url='http://linux.die.net/man/1/blkparse'>blkparse</ulink>
3439 manpage to learn the
3440 meaning of each field displayed in the trace listing.
3441 </para>
3442
3443 <section id='blktrace-live-mode'>
3444 <title>Live Mode</title>
3445
3446 <para>
3447 blktrace and blkparse are designed from the ground up to
3448 be able to operate together in a 'pipe mode' where the
3449 stdout of blktrace can be fed directly into the stdin of
3450 blkparse:
3451 <literallayout class='monospaced'>
3452 root@crownbay:~# blktrace /dev/sdc -o - | blkparse -i -
3453 </literallayout>
3454 This enables long-lived tracing sessions to run without
3455 writing anything to disk, and allows the user to look for
3456 certain conditions in the trace data in 'real-time' by
3457 viewing the trace output as it scrolls by on the screen or
3458 by passing it along to yet another program in the pipeline
3459 such as grep which can be used to identify and capture
3460 conditions of interest.
3461 </para>
3462
3463 <para>
3464 There's actually another blktrace command that implements
3465 the above pipeline as a single command, so the user doesn't
3466 have to bother typing in the above command sequence:
3467 <literallayout class='monospaced'>
3468 root@crownbay:~# btrace /dev/sdc
3469 </literallayout>
3470 </para>
3471 </section>
3472
3473 <section id='using-blktrace-remotely'>
3474 <title>Using blktrace Remotely</title>
3475
3476 <para>
3477 Because blktrace traces block I/O and at the same time
3478 normally writes its trace data to a block device, and
3479 in general because it's not really a great idea to make
3480 the device being traced the same as the device the tracer
3481 writes to, blktrace provides a way to trace without
3482 perturbing the traced device at all by providing native
3483 support for sending all trace data over the network.
3484 </para>
3485
3486 <para>
3487 To have blktrace operate in this mode, start blktrace on
3488 the target system being traced with the -l option, along with
3489 the device to trace:
3490 <literallayout class='monospaced'>
3491 root@crownbay:~# blktrace -l /dev/sdc
3492 server: waiting for connections...
3493 </literallayout>
3494 On the host system, use the -h option to connect to the
3495 target system, also passing it the device to trace:
3496 <literallayout class='monospaced'>
3497 $ blktrace -d /dev/sdc -h 192.168.1.43
3498 blktrace: connecting to 192.168.1.43
3499 blktrace: connected!
3500 </literallayout>
3501 On the target system, you should see this:
3502 <literallayout class='monospaced'>
3503 server: connection from 192.168.1.43
3504 </literallayout>
3505 In another shell, execute a workload you want to trace.
3506 <literallayout class='monospaced'>
3507 root@crownbay:/media/sdc# rm linux-2.6.19.2.tar.bz2; wget <ulink url='http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2'>http://downloads.yoctoproject.org/mirror/sources/linux-2.6.19.2.tar.bz2</ulink>; sync
3508 Connecting to downloads.yoctoproject.org (140.211.169.59:80)
3509 linux-2.6.19.2.tar.b 100% |*******************************| 41727k 0:00:00 ETA
3510 </literallayout>
3511 When it's done, do a Ctrl-C on the host system to
3512 stop the trace:
3513 <literallayout class='monospaced'>
3514 ^C=== sdc ===
3515 CPU 0: 7691 events, 361 KiB data
3516 CPU 1: 4109 events, 193 KiB data
3517 Total: 11800 events (dropped 0), 554 KiB data
3518 </literallayout>
3519 On the target system, you should also see a trace
3520 summary for the trace just ended:
3521 <literallayout class='monospaced'>
3522 server: end of run for 192.168.1.43:sdc
3523 === sdc ===
3524 CPU 0: 7691 events, 361 KiB data
3525 CPU 1: 4109 events, 193 KiB data
3526 Total: 11800 events (dropped 0), 554 KiB data
3527 </literallayout>
3528 The blktrace instance on the host will save the target
3529 output inside a hostname-timestamp directory:
3530 <literallayout class='monospaced'>
3531 $ ls -al
3532 drwxr-xr-x 10 root root 1024 Oct 28 02:40 .
3533 drwxr-sr-x 4 root root 1024 Oct 26 18:24 ..
3534 drwxr-xr-x 2 root root 1024 Oct 28 02:40 192.168.1.43-2012-10-28-02:40:56
3535 </literallayout>
3536 cd into that directory to see the output files:
3537 <literallayout class='monospaced'>
3538 $ ls -l
3539 -rw-r--r-- 1 root root 369193 Oct 28 02:44 sdc.blktrace.0
3540 -rw-r--r-- 1 root root 197278 Oct 28 02:44 sdc.blktrace.1
3541 </literallayout>
3542 And run blkparse on the host system using the device name:
3543 <literallayout class='monospaced'>
3544 $ blkparse sdc
3545
3546 8,32 1 1 0.000000000 1263 Q RM 6016 + 8 [ls]
3547 8,32 1 0 0.000036038 0 m N cfq1263 alloced
3548 8,32 1 2 0.000039390 1263 G RM 6016 + 8 [ls]
3549 8,32 1 3 0.000049168 1263 I RM 6016 + 8 [ls]
3550 8,32 1 0 0.000056152 0 m N cfq1263 insert_request
3551 8,32 1 0 0.000061600 0 m N cfq1263 add_to_rr
3552 8,32 1 0 0.000075498 0 m N cfq workload slice:300
3553 .
3554 .
3555 .
3556 8,32 0 0 177.266385696 0 m N cfq1267 arm_idle: 8 group_idle: 0
3557 8,32 0 0 177.266388140 0 m N cfq schedule dispatch
3558 8,32 1 0 177.266679239 0 m N cfq1267 slice expired t=0
3559 8,32 1 0 177.266689297 0 m N cfq1267 sl_used=9 disp=6 charge=9 iops=0 sect=56
3560 8,32 1 0 177.266692649 0 m N cfq1267 del_from_rr
3561 8,32 1 0 177.266696560 0 m N cfq1267 put_queue
3562
3563 CPU0 (sdc):
3564 Reads Queued: 0, 0KiB Writes Queued: 270, 21,708KiB
3565 Read Dispatches: 59, 2,628KiB Write Dispatches: 495, 39,964KiB
3566 Reads Requeued: 0 Writes Requeued: 0
3567 Reads Completed: 90, 2,752KiB Writes Completed: 543, 41,596KiB
3568 Read Merges: 0, 0KiB Write Merges: 9, 344KiB
3569 Read depth: 2 Write depth: 2
3570 IO unplugs: 20 Timer unplugs: 1
3571 CPU1 (sdc):
3572 Reads Queued: 688, 2,752KiB Writes Queued: 381, 20,652KiB
3573 Read Dispatches: 31, 124KiB Write Dispatches: 59, 2,396KiB
3574 Reads Requeued: 0 Writes Requeued: 0
3575 Reads Completed: 0, 0KiB Writes Completed: 11, 764KiB
3576 Read Merges: 598, 2,392KiB Write Merges: 88, 448KiB
3577 Read depth: 2 Write depth: 2
3578 IO unplugs: 52 Timer unplugs: 0
3579
3580 Total (sdc):
3581 Reads Queued: 688, 2,752KiB Writes Queued: 651, 42,360KiB
3582 Read Dispatches: 90, 2,752KiB Write Dispatches: 554, 42,360KiB
3583 Reads Requeued: 0 Writes Requeued: 0
3584 Reads Completed: 90, 2,752KiB Writes Completed: 554, 42,360KiB
3585 Read Merges: 598, 2,392KiB Write Merges: 97, 792KiB
3586 IO unplugs: 72 Timer unplugs: 1
3587
3588 Throughput (R/W): 15KiB/s / 238KiB/s
3589 Events (sdc): 9,301 entries
3590 Skips: 0 forward (0 - 0.0%)
3591 </literallayout>
3592 You should see the trace events and summary just as
3593 you would have if you'd run the same command on the target.
3594 </para>
3595 </section>
3596
3597 <section id='tracing-block-io-via-ftrace'>
3598 <title>Tracing Block I/O via 'ftrace'</title>
3599
3600 <para>
3601 It's also possible to trace block I/O using only
3602 <link linkend='the-trace-events-subsystem'>trace events subsystem</link>,
3603 which can be useful for casual tracing
3604 if you don't want to bother dealing with the userspace tools.
3605 </para>
3606
3607 <para>
3608 To enable tracing for a given device, use
3609 /sys/block/xxx/trace/enable, where xxx is the device name.
3610 This for example enables tracing for /dev/sdc:
3611 <literallayout class='monospaced'>
3612 root@crownbay:/sys/kernel/debug/tracing# echo 1 > /sys/block/sdc/trace/enable
3613 </literallayout>
3614 Once you've selected the device(s) you want to trace,
3615 selecting the 'blk' tracer will turn the blk tracer on:
3616 <literallayout class='monospaced'>
3617 root@crownbay:/sys/kernel/debug/tracing# cat available_tracers
3618 blk function_graph function nop
3619
3620 root@crownbay:/sys/kernel/debug/tracing# echo blk > current_tracer
3621 </literallayout>
3622 Execute the workload you're interested in:
3623 <literallayout class='monospaced'>
3624 root@crownbay:/sys/kernel/debug/tracing# cat /media/sdc/testfile.txt
3625 </literallayout>
3626 And look at the output (note here that we're using
3627 'trace_pipe' instead of trace to capture this trace -
3628 this allows us to wait around on the pipe for data to
3629 appear):
3630 <literallayout class='monospaced'>
3631 root@crownbay:/sys/kernel/debug/tracing# cat trace_pipe
3632 cat-3587 [001] d..1 3023.276361: 8,32 Q R 1699848 + 8 [cat]
3633 cat-3587 [001] d..1 3023.276410: 8,32 m N cfq3587 alloced
3634 cat-3587 [001] d..1 3023.276415: 8,32 G R 1699848 + 8 [cat]
3635 cat-3587 [001] d..1 3023.276424: 8,32 P N [cat]
3636 cat-3587 [001] d..2 3023.276432: 8,32 I R 1699848 + 8 [cat]
3637 cat-3587 [001] d..1 3023.276439: 8,32 m N cfq3587 insert_request
3638 cat-3587 [001] d..1 3023.276445: 8,32 m N cfq3587 add_to_rr
3639 cat-3587 [001] d..2 3023.276454: 8,32 U N [cat] 1
3640 cat-3587 [001] d..1 3023.276464: 8,32 m N cfq workload slice:150
3641 cat-3587 [001] d..1 3023.276471: 8,32 m N cfq3587 set_active wl_prio:0 wl_type:2
3642 cat-3587 [001] d..1 3023.276478: 8,32 m N cfq3587 fifo= (null)
3643 cat-3587 [001] d..1 3023.276483: 8,32 m N cfq3587 dispatch_insert
3644 cat-3587 [001] d..1 3023.276490: 8,32 m N cfq3587 dispatched a request
3645 cat-3587 [001] d..1 3023.276497: 8,32 m N cfq3587 activate rq, drv=1
3646 cat-3587 [001] d..2 3023.276500: 8,32 D R 1699848 + 8 [cat]
3647 </literallayout>
3648 And this turns off tracing for the specified device:
3649 <literallayout class='monospaced'>
3650 root@crownbay:/sys/kernel/debug/tracing# echo 0 > /sys/block/sdc/trace/enable
3651 </literallayout>
3652 </para>
3653 </section>
3654 </section>
3655
3656 <section id='blktrace-documentation'>
3657 <title>Documentation</title>
3658
3659 <para>
3660 Online versions of the man pages for the commands discussed
3661 in this section can be found here:
3662 <itemizedlist>
3663 <listitem><para><ulink url='http://linux.die.net/man/8/blktrace'>http://linux.die.net/man/8/blktrace</ulink>
3664 </para></listitem>
3665 <listitem><para><ulink url='http://linux.die.net/man/1/blkparse'>http://linux.die.net/man/1/blkparse</ulink>
3666 </para></listitem>
3667 <listitem><para><ulink url='http://linux.die.net/man/8/btrace'>http://linux.die.net/man/8/btrace</ulink>
3668 </para></listitem>
3669 </itemizedlist>
3670 </para>
3671
3672 <para>
3673 The above manpages, along with manpages for the other
3674 blktrace utilities (btt, blkiomon, etc) can be found in the
3675 /doc directory of the blktrace tools git repo:
3676 <literallayout class='monospaced'>
3677 $ git clone git://git.kernel.dk/blktrace.git
3678 </literallayout>
3679 </para>
3680 </section>
3681</section>
3682</chapter>
3683<!--
3684vim: expandtab tw=80 ts=4
3685-->