Lines Matching refs:to
11 to be collected and sent to a host machine for analysis. At present the
12 main use for this is to profile boot time.
18 The trace feature uses GCC's instrument-functions feature to trace all
20 The memory buffer can be saved to the host over a network link using
21 tftpput or by writing to an attached memory device such as MMC.
36 Add the following to include/configs/sandbox.h (if not already there)
50 Run sandbox, wait for a bit of trace information to appear, and then capture
72 66,491 calls not traced due to depth
77 950,490 traced function calls (333217 dropped due to overflow)
80 1,275,767 calls not traced due to depth
82 Call list dumped to 00000000, size 0xae0a40
98 Then run proftool to convert the trace information to ftrace format.
102 Finally run pytimechart to display it:
121 Size of trace buffer to allocate for U-Boot. This buffer is
122 used after relocation, as a place to put function tracing
127 Define this to start tracing early, before relocation.
132 you can define an area of memory to use for the trace
134 relocation. The contents of this buffer are then copied to
144 Pass 'FTRACE=1' to the U-Boot Makefile to actually instrument the code.
145 This is kept as a separate option so that it is easy to enable/disable
146 instrumenting from the command line instead of having to change board
153 When you run U-Boot on your board it will collect trace data up to the
162 doing end-to-end timing.
164 The best time to start tracing is right at the beginning of U-Boot. The
165 best time to stop tracing is right at the end. In practice it is hard
166 to achieve these ideals.
175 command. Therefore this implementation provides a way to collect trace
176 data after bootm has finished processing, but just before it jumps to
232 These variables keep track of the amount of data written to the trace
234 to the output buffer can use these to specify the buffer to write to, and
235 update profoffset each time. This allows successive commands to append data
236 to the same buffer, for example:
241 (the latter command appends more data to the buffer).
245 Specifies commands to run just before booting the OS. This
246 is a useful time to write the trace data to the host for
254 to transmit it to the host. Notably you can use tftput to send the data
261 This starts up USB (to talk to an attached USB Ethernet dongle), writes
262 a trace log to address 10000000 and sends it to a host machine using
286 Write a text dump of the file in Linux ftrace format to stdout
293 your Debian-style machine, and use your favourite search engine to obtain
294 documentation). It expects the file to have a .txt extension. The program
302 The following suggestions may be helpful if you are trying to reduce boot
309 (it is common for tracing to add 10% to the time)
311 3. Collect the trace information as descibed above. Use this to find where
315 possible to speed up the initialisation of a device, or remove an unused
326 There are a few parameters in the code that you may want to consider.
327 There is a function call depth limit (set to 15 by default). When the
341 - Trace filter to select which functions are recorded