Messages in this thread | | | Date | Tue, 12 Nov 2013 08:36:03 -0700 | From | David Ahern <> | Subject | Re: [PATCH 4/5] perf record: mmap output file - v5 |
| |
On 11/12/13, 8:19 AM, Peter Zijlstra wrote: > On Tue, Nov 12, 2013 at 12:07:51PM -0300, Arnaldo Carvalho de Melo wrote: >> Em Tue, Nov 12, 2013 at 03:57:07PM +0100, Peter Zijlstra escreveu: >>> On Tue, Nov 12, 2013 at 07:46:56AM -0700, David Ahern wrote: >>>> When recording raw_syscalls for the entire system, e.g., >>>> perf record -e raw_syscalls:*,sched:sched_switch -a -- sleep 1 >>>> >>>> you end up with a negative feedback loop as perf itself calls write() fairly >>>> often. This patch handles the problem by mmap'ing the file in chunks of 64M at >>>> a time and copies events from the event buffers to the file avoiding write >>>> system calls. >>> >>> You know this completely fails the moment you trace faults, because >>> every new access to one of those pages (to mark it dirty) will trigger a >>> fault. And we'll take a bunch more faults -- one for each page -- than >>> we ever did write() syscalls. >> >> So we should provide a neon lettered warning when doing that, no? :-) > > Dunno.. it _should_ all work. Try it and see what it does.. Once the > events are bigger than a page things might get 'interesting' though. >
one option here is not allow page faults and system wide system calls. system wide tracing needs mmap; page faults for a task can use write(). I left that option in case something like this came up.
David
| |