diff options
Diffstat (limited to 'Documentation/tracers')
| -rw-r--r-- | Documentation/tracers/mmiotrace.txt | 27 |
1 files changed, 19 insertions, 8 deletions
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt index 84246f703875..a4afb560a45b 100644 --- a/Documentation/tracers/mmiotrace.txt +++ b/Documentation/tracers/mmiotrace.txt | |||
| @@ -25,7 +25,8 @@ Mmiotrace feature is compiled in by the CONFIG_MMIOTRACE option. Tracing is | |||
| 25 | disabled by default, so it is safe to have this set to yes. SMP systems are | 25 | disabled by default, so it is safe to have this set to yes. SMP systems are |
| 26 | supported, but tracing is unreliable and may miss events if more than one CPU | 26 | supported, but tracing is unreliable and may miss events if more than one CPU |
| 27 | is on-line, therefore mmiotrace takes all but one CPU off-line during run-time | 27 | is on-line, therefore mmiotrace takes all but one CPU off-line during run-time |
| 28 | activation [not implemented]. | 28 | activation. You can re-enable CPUs by hand, but you have been warned, there |
| 29 | is no way to automatically detect if you are losing events due to CPUs racing. | ||
| 29 | 30 | ||
| 30 | 31 | ||
| 31 | Usage Quick Reference | 32 | Usage Quick Reference |
| @@ -37,7 +38,7 @@ $ cat /debug/tracing/trace_pipe > mydump.txt & | |||
| 37 | Start X or whatever. | 38 | Start X or whatever. |
| 38 | $ echo "X is up" > /debug/tracing/marker | 39 | $ echo "X is up" > /debug/tracing/marker |
| 39 | $ echo none > /debug/tracing/current_tracer | 40 | $ echo none > /debug/tracing/current_tracer |
| 40 | Check kernel log. | 41 | Check for lost events. |
| 41 | 42 | ||
| 42 | 43 | ||
| 43 | Usage | 44 | Usage |
| @@ -67,12 +68,22 @@ do. | |||
| 67 | 68 | ||
| 68 | Shut down mmiotrace (requires root privileges): | 69 | Shut down mmiotrace (requires root privileges): |
| 69 | $ echo none > /debug/tracing/current_tracer | 70 | $ echo none > /debug/tracing/current_tracer |
| 70 | The 'cat' process exits. If it does not, kill it by 'fg' and pressing ctrl+c. | 71 | The 'cat' process exits. If it does not, kill it by issuing 'fg' command and |
| 71 | 72 | pressing ctrl+c. | |
| 72 | [This feature is not implemented yet!] | 73 | |
| 73 | Check your kernel log. If there are messages about mmiotrace losing events, | 74 | Check that mmiotrace did not lose events due to a buffer filling up. Either |
| 74 | this is due to buffer overrun, and the trace is incomplete. You should enlarge | 75 | $ grep -i lost mydump.txt |
| 75 | the buffers and try again. [How?] | 76 | which tells you exactly how many events were lost, or use |
| 77 | $ dmesg | ||
| 78 | to view your kernel log and look for "mmiotrace has lost events" warning. If | ||
| 79 | events were lost, the trace is incomplete. You should enlarge the buffers and | ||
| 80 | try again. Buffers are enlarged by first seeing how large the current buffers | ||
| 81 | are: | ||
| 82 | $ cat /debug/tracing/trace_entries | ||
| 83 | gives you a number. Approximately double this number and write it back, for | ||
| 84 | instance: | ||
| 85 | $ echo 128000 > /debug/tracing/trace_entries | ||
| 86 | Then start again from the top. | ||
| 76 | 87 | ||
| 77 | If you are doing a trace for a driver project, e.g. Nouveau, you should also | 88 | If you are doing a trace for a driver project, e.g. Nouveau, you should also |
| 78 | do the following before sending your results: | 89 | do the following before sending your results: |