Messages in this thread | | | Date | Mon, 30 Mar 2015 16:51:34 -0600 | From | David Ahern <> | Subject | [BUG] perf script segfault |
| |
Surprised Stephane has not hit this one yet:
$ perf record -e <any-event> -a | perf script Segmentation fault (core dumped)
It's the second one that core dumps.
$ gdb perf core.16704 ... [New LWP 16704] [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib64/libthread_db.so.1". Core was generated by `/tmp/perf/perf script'. Program terminated with signal SIGSEGV, Segmentation fault. #0 perf_tool__fill_defaults (tool=tool@entry=0x0) at util/session.c:259 259 if (tool->sample == NULL) ... (gdb) bt #0 perf_tool__fill_defaults (tool=tool@entry=0x0) at util/session.c:259 #1 0x00000000004a5baa in __perf_session__process_pipe_events (session=0x2178b80) at util/session.c:1178 #2 perf_session__process_events (session=0x2178b80) at util/session.c:1416 #3 0x000000000043c5dc in __cmd_script (script=0x7fffc7a4d840) at builtin-script.c:803 #4 cmd_script (argc=<optimized out>, argv=<optimized out>, prefix=<optimized out>) at builtin-script.c:1840 ...
tool was moved to ordered_events and is not initialized for pipe mode. I don't have time to look into it more than that before PTO on Wednesday.
David
| |