Lines Matching refs:to
8 to be collected and sent to a host machine for analysis. At present the
9 main use for this is to profile boot time.
15 The trace feature uses GCC's instrument-functions feature to trace all
17 The memory buffer can be saved to the host over a network link using
18 tftpput or by writing to an attached memory device such as MMC.
33 Add the following to include/configs/sandbox.h (if not already there)
51 Run sandbox, wait for a bit of trace information to appear, and then capture
74 66,491 calls not traced due to depth
79 950,490 traced function calls (333217 dropped due to overflow)
82 1,275,767 calls not traced due to depth
84 Call list dumped to 00000000, size 0xae0a40
100 Then run proftool to convert the trace information to ftrace format
106 Finally run pytimechart to display it
127 Size of trace buffer to allocate for U-Boot. This buffer is
128 used after relocation, as a place to put function tracing
133 Define this to start tracing early, before relocation.
138 you can define an area of memory to use for the trace
140 relocation. The contents of this buffer are then copied to
150 Pass 'FTRACE=1' to the U-Boot Makefile to actually instrument the code.
151 This is kept as a separate option so that it is easy to enable/disable
152 instrumenting from the command line instead of having to change board
159 When you run U-Boot on your board it will collect trace data up to the
168 doing end-to-end timing.
170 The best time to start tracing is right at the beginning of U-Boot. The
171 best time to stop tracing is right at the end. In practice it is hard
172 to achieve these ideals.
181 command. Therefore this implementation provides a way to collect trace
182 data after bootm has finished processing, but just before it jumps to
238 These variables keep track of the amount of data written to the trace
240 to the output buffer can use these to specify the buffer to write to, and
241 update profoffset each time. This allows successive commands to append data
242 to the same buffer, for example::
247 (the latter command appends more data to the buffer).
251 Specifies commands to run just before booting the OS. This
252 is a useful time to write the trace data to the host for
260 to transmit it to the host. Notably you can use tftput to send the data
267 This starts up USB (to talk to an attached USB Ethernet dongle), writes
268 a trace log to address 10000000 and sends it to a host machine using
293 Write a text dump of the file in Linux ftrace format to stdout
300 your Debian-style machine, and use your favourite search engine to obtain
301 documentation). It expects the file to have a .txt extension. The program
309 The following suggestions may be helpful if you are trying to reduce boot
316 (it is common for tracing to add 10% to the time)
318 3. Collect the trace information as descibed above. Use this to find where
322 possible to speed up the initialisation of a device, or remove an unused
333 There are a few parameters in the code that you may want to consider.
334 There is a function call depth limit (set to 15 by default). When the
348 - Trace filter to select which functions are recorded