perf tests: Do not rely on dso__data_read_offset() to open dso
authorNamhyung Kim <namhyung@kernel.org>
Fri, 30 Jan 2015 02:33:28 +0000 (11:33 +0900)
committerArnaldo Carvalho de Melo <acme@redhat.com>
Fri, 6 Feb 2015 10:46:35 +0000 (11:46 +0100)
commit63d3c6f3835d011c783c606c8a1583b041f579aa
tree265db940d9911b060c88e743ef1b86c6a103f77e
parent66af43d56345a7ca549ba1089fe11a6953072417
perf tests: Do not rely on dso__data_read_offset() to open dso

Do not rely on dso__data_read_offset() will always call dso__data_fd()
internally.  With multi-thread support, accessing a fd will be protected
by a lock and it'll cause a huge contention.  It can be avoided since we
can skip reading from file if there's a data in the dso cache.

If one needs to call the dso__data_read_offset(), [s]he also needs to
call dso__data_fd() (or set dso->binary_type at least) first like the
dwarf unwind code does.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1422585209-32742-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools/perf/tests/dso-data.c