1.TH SLEEPGRAPH 8
  2.SH NAME
  3sleepgraph \- Suspend/Resume timing analysis
  4.SH SYNOPSIS
  5.ft B
  6.B sleepgraph
  7.RB [ OPTIONS ]
  8.RB [ COMMAND ]
  9.SH DESCRIPTION
 10\fBsleepgraph \fP is designed to assist kernel and OS developers
 11in optimizing their linux stack's suspend/resume time. Using a kernel
 12image built with a few extra options enabled, the tool will execute a
 13suspend and capture dmesg and ftrace data until resume is complete.
 14This data is transformed into a device timeline and an optional
 15callgraph to give a detailed view of which devices/subsystems are
 16taking the most time in suspend/resume.
 17.PP
 18If no specific command is given, the default behavior is to initiate
 19a suspend/resume.
 20.PP
 21Generates output files in subdirectory: suspend-yymmdd-HHMMSS
 22   html timeline   :     <hostname>_<mode>.html
 23   raw dmesg file  :     <hostname>_<mode>_dmesg.txt
 24   raw ftrace file :     <hostname>_<mode>_ftrace.txt
 25.SH OPTIONS
 26.TP
 27\fB-h\fR
 28Print the help text.
 29.TP
 30\fB-v\fR
 31Print the current tool version.
 32.TP
 33\fB-verbose\fR
 34Print extra information during execution and analysis.
 35.TP
 36\fB-config \fIfile\fR
 37Pull arguments and config options from a file.
 38.TP
 39\fB-m \fImode\fR
 40Mode to initiate for suspend e.g. standby, freeze, mem (default: mem).
 41.TP
 42\fB-o \fIname\fR
 43Overrides the output subdirectory name when running a new test.
 44Use {date}, {time}, {hostname} for current values.
 45.sp
 46e.g. suspend-{hostname}-{date}-{time}
 47.TP
 48\fB-rtcwake \fIt\fR | off
 49Use rtcwake to autoresume after \fIt\fR seconds (default: 15). Set t to "off" to
 50disable rtcwake and require a user keypress to resume.
 51.TP
 52\fB-addlogs\fR
 53Add the dmesg and ftrace logs to the html output. They will be viewable by
 54clicking buttons in the timeline.
 55.TP
 56\fB-noturbostat\fR
 57By default, if turbostat is found and the requested mode is freeze, sleepgraph
 58will execute the suspend via turbostat and collect data in the timeline log.
 59This option disables the use of turbostat.
 60.TP
 61\fB-result \fIfile\fR
 62Export a results table to a text file for parsing.
 63.TP
 64\fB-sync\fR
 65Sync the filesystems before starting the test. This reduces the size of
 66the sys_sync call which happens in the suspend_prepare phase.
 67.TP
 68\fB-rs \fIenable/disable\fR
 69During test, enable/disable runtime suspend for all devices. The test is delayed
 70by 5 seconds to allow runtime suspend changes to occur. The settings are restored
 71after the test is complete.
 72.TP
 73\fB-display \fIon/off/standby/suspend\fR
 74Switch the display to the requested mode for the test using the xset command.
 75This helps maintain the consistency of test data for better comparison.
 76.TP
 77\fB-wifi\fR
 78If a wifi connection is available, check that it reconnects after resume. Include
 79the reconnect time in the total resume time calculation and treat wifi timeouts
 80as resume failures.
 81.TP
 82\fB-wifitrace\fR
 83Trace through the wifi reconnect time and include it in the timeline.
 84
 85.SS "advanced"
 86.TP
 87\fB-gzip\fR
 88Gzip the trace and dmesg logs to save space. The tool can also read in gzipped
 89logs for processing.
 90.TP
 91\fB-cmd \fIstr\fR
 92Run the timeline over a custom suspend command, e.g. pm-suspend. By default
 93the tool forces suspend via /sys/power/state so this allows testing over
 94an OS's official suspend method. The output file will change to
 95hostname_command.html and will autodetect which suspend mode was triggered.
 96.TP
 97\fB-filter \fI"d1,d2,..."\fR
 98Filter out all but these device callbacks. These strings can be device names
 99or module names. e.g. 0000:00:02.0, ata5, i915, usb, etc.
100.TP
101\fB-mindev \fIt\fR
102Discard all device callbacks shorter than \fIt\fR milliseconds (default: 0.0).
103This reduces the html file size as there can be many tiny callbacks which are barely
104visible. The value is a float: e.g. 0.001 represents 1 us.
105.TP
106\fB-proc\fR
107Add usermode process info into the timeline (default: disabled).
108.TP
109\fB-dev\fR
110Add kernel source calls and threads to the timeline (default: disabled).
111.TP
112\fB-x2\fR
113Run two suspend/resumes back to back (default: disabled).
114.TP
115\fB-x2delay \fIt\fR
116Include \fIt\fR ms delay between multiple test runs (default: 0 ms).
117.TP
118\fB-predelay \fIt\fR
119Include \fIt\fR ms delay before 1st suspend (default: 0 ms).
120.TP
121\fB-postdelay \fIt\fR
122Include \fIt\fR ms delay after last resume (default: 0 ms).
123.TP
124\fB-multi \fIn d\fR
125Used for endurance testing. If \fIn\fR is entirely numeric, it's treated as a count:
126Execute \fIn\fR consecutive tests at \fId\fR second intervals.
127If \fIn\fR is an integer followed by a "d", "h", or "m", it's treated as a duration:
128Execute tests continuously over \fIn\fR days, hours, or minutes at \fId\fR second intervals.
129The outputs will be created in a new subdirectory, for count: suspend-{date}-{time}-xN,
130for duration: suspend-{date}-{time}-Nm. When the multitest run is done, the \fI-summary\fR
131command is called automatically to create summary html files for all the data (unless you
132use \fI-skiphtml\fR). \fI-skiphtml\fR will speed up the testing by not creating timelines
133or summary html files. You can then run the tool again at a later time with \fI-summary\fR
134and \fI-genhtml\fR to create the timelines.
135.TP
136\fB-maxfail \fIn\fR
137Abort a -multi run after \fIn\fR consecutive fails. 0 means never abort (default = 0).
138.TP
139\fB-skiphtml\fR
140Run the test and capture the trace logs, but skip the timeline generation.
141You can generate the html timelines later with \fI-dmesg\fR & \fI-ftrace\fR, or
142by running \fI-summary\fR and \fI-genhtml\fR.
143
144.SS "ftrace debug"
145.TP
146\fB-f\fR
147Use ftrace to create device callgraphs (default: disabled). This can produce
148very large outputs, i.e. 10MB - 100MB.
149.TP
150\fB-ftop\fR
151Use ftrace on the top level call: "suspend_devices_and_enter" only (default: disabled).
152This option implies -f and creates a single callgraph covering all of suspend/resume.
153.TP
154\fB-maxdepth \fIlevel\fR
155limit the callgraph trace depth to \fIlevel\fR (default: 0=all). This is
156the best way to limit the output size when using callgraphs via -f.
157.TP
158\fB-expandcg\fR
159pre-expand the callgraph data in the html output (default: disabled)
160.TP
161\fB-fadd \fIfile\fR
162Add functions to be graphed in the timeline from a list in a text file
163.TP
164\fB-mincg \fIt\fR
165Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0.0).
166This reduces the html file size as there can be many tiny callgraphs
167which are barely visible in the timeline.
168The value is a float: e.g. 0.001 represents 1 us.
169.TP
170\fB-cgfilter \fI"func1,func2,..."\fR
171Reduce callgraph output in the timeline by limiting it certain devices. The
172argument can be a single device name or a comma delimited list.
173(default: none)
174.TP
175\fB-cgskip \fIfile\fR
176Reduce callgraph timeline size by skipping over uninteresting functions
177in the trace, e.g. printk or console_unlock. The functions listed
178in this file will show up as empty leaves in the callgraph with only the start/end
179times displayed. cgskip.txt is used automatically if found in the path, so
180use "off" to disable completely (default: cgskip.txt)
181.TP
182\fB-cgphase \fIp\fR
183Only show callgraph data for phase \fIp\fR (e.g. suspend_late).
184.TP
185\fB-cgtest \fIn\fR
186In an x2 run, only show callgraph data for test \fIn\fR (e.g. 0 or 1).
187.TP
188\fB-timeprec \fIn\fR
189Number of significant digits in timestamps (0:S, [3:ms], 6:us).
190.TP
191\fB-bufsize \fIN\fR
192Set trace buffer size to N kilo-bytes (default: all of free memory up to 3GB)
193
194.SH COMMANDS
195.TP
196\fB-summary \fIindir\fR
197Create a set of summary pages for all tests in \fIindir\fR recursively.
198Creates summary.html, summary-issues.html, and summary-devices.html in the current folder.
199summary.html is a table of tests with relevant info sorted by kernel/host/mode,
200and links to the test html files. It identifies the minimum, maximum, and median
201suspend and resume times for you with highlights and links in the header.
202summary-issues.html is a list of kernel issues found in dmesg from all the tests.
203summary-devices.html is a list of devices and times from all the tests.
204
205Use \fI-genhtml\fR to regenerate any tests with missing html.
206.TP
207\fB-genhtml\fR
208Used with \fI-summary\fR to regenerate any missing html timelines from their
209dmesg and ftrace logs. This will require a significant amount of time if there
210are thousands of tests.
211.TP
212\fB-modes\fR
213List available suspend modes.
214.TP
215\fB-status\fR
216Test to see if the system is able to run this tool. Use this along
217with any options you intend to use to see if they will work.
218.TP
219\fB-fpdt\fR
220Print out the contents of the ACPI Firmware Performance Data Table.
221.TP
222\fB-wificheck\fR
223Print out wifi status and connection details.
224.TP
225\fB-xon/-xoff/-xstandby/-xsuspend\fR
226Test xset by attempting to switch the display to the given mode. This
227is the same command which will be issued by \fB-display \fImode\fR.
228.TP
229\fB-xstat\fR
230Get the current DPMS display mode.
231.TP
232\fB-sysinfo\fR
233Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode.
234.TP
235\fB-devinfo\fR
236Print out the pm settings of all devices which support runtime suspend.
237.TP
238\fB-cmdinfo\fR
239Print out all the platform data collected from the system that makes it into the logs.
240.TP
241\fB-flist\fR
242Print the list of ftrace functions currently being captured. Functions
243that are not available as symbols in the current kernel are shown in red.
244By default, the tool traces a list of important suspend/resume functions
245in order to better fill out the timeline. If the user has added their own
246with -fadd they will also be checked.
247.TP
248\fB-flistall\fR
249Print all ftrace functions capable of being captured. These are all the
250possible values you can add to trace via the -fadd argument.
251.SS "rebuild"
252.TP
253\fB-ftrace \fIfile\fR
254Create HTML output from an existing ftrace file.
255.TP
256\fB-dmesg \fIfile\fR
257Create HTML output from an existing dmesg file.
258
259.SH EXAMPLES
260.SS "simple commands"
261Check which suspend modes are currently supported.
262.IP
263\f(CW$ sleepgraph -modes\fR
264.PP
265Read the Firmware Performance Data Table (FPDT)
266.IP
267\f(CW$ sudo sleepgraph -fpdt\fR
268.PP
269Print out the current USB power topology
270.IP
271\f(CW$ sleepgraph -usbtopo
272.PP
273Verify that you can run a command with a set of arguments
274.IP
275\f(CW$ sudo sleepgraph -f -rtcwake 30 -status
276.PP
277Generate a summary of all timelines in a particular folder.
278.IP
279\f(CW$ sleepgraph -summary ~/workspace/myresults/\fR
280.PP
281
282.SS "capturing basic timelines"
283Execute a mem suspend with a 15 second wakeup. Include the logs in the html.
284.IP
285\f(CW$ sudo sleepgraph -rtcwake 15 -addlogs\fR
286.PP
287Execute a standby with a 15 second wakeup. Change the output folder name.
288.IP
289\f(CW$ sudo sleepgraph -m standby -rtcwake 15 -o "standby-{host}-{date}-{time}"\fR
290.PP
291Execute a freeze with no wakeup (require keypress). Change output folder name.
292.IP
293\f(CW$ sudo sleepgraph -m freeze -rtcwake off -o "freeze-{hostname}-{date}-{time}"\fR
294.PP
295
296.SS "capturing advanced timelines"
297Execute a suspend & include dev mode source calls, limit callbacks to 5ms or larger.
298.IP
299\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -dev -mindev 5\fR
300.PP
301Run two suspends back to back, include a 500ms delay before, after, and in between runs.
302.IP
303\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -x2 -predelay 500 -x2delay 500 -postdelay 500\fR
304.PP
305Execute a suspend using a custom command.
306.IP
307\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR
308.PP
309
310.SS "endurance testing using -multi"
311.PP
312Do a batch run of 10 freezes with 30 seconds delay between runs.
313.IP
314\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 10 30\fR
315.PP
316Do a batch run of freezes for 24 hours.
317.IP
318\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 24h 0\fR
319
320.SS "adding callgraph data"
321Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger.
322.IP
323\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f -maxdepth 5 -mincg 10\fR
324.PP
325Capture a full callgraph across all suspend, then filter the html by a single phase.
326.IP
327\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f\fR
328.IP
329\f(CW$ sleepgraph -dmesg host_mem_dmesg.txt -ftrace host_mem_ftrace.txt -f -cgphase resume
330.PP
331
332.SS "rebuild timeline from logs"
333.PP
334Rebuild the html from a previous run's logs, using the same options.
335.IP
336\f(CW$ sleepgraph -dmesg dmesg.txt -ftrace ftrace.txt -callgraph\fR
337.PP
338Rebuild the html with different options.
339.IP
340\f(CW$ sleepgraph -dmesg dmesg.txt -ftrace ftrace.txt -addlogs -srgap\fR
341
342.SH "SEE ALSO"
343dmesg(1)
344.PP
345.SH AUTHOR
346.nf
347Written by Todd Brandt <todd.e.brandt@linux.intel.com>