Hi Jiri,
On Mon, Mar 30, 2015 at 01:49:07PM +0200, Jiri Olsa wrote:
> On Mon, Mar 30, 2015 at 01:21:08PM +0200, Jiri Olsa wrote:
> > On Mon, Mar 30, 2015 at 12:22:20PM +0200, Jiri Olsa wrote:
> > > On Mon, Mar 30, 2015 at 10:07:37AM +0200, Jiri Olsa wrote:
> > >
> > > SNIP
> > >
> > > > >
> > > > > 2 things:
> > > > > 1. let run for a long time. go about using the server. do lots of
> > > > > builds,
> > > > > etc. it takes time
> > > > >
> > > > > 2. use a box with a LOT of cpus (1024 in my case)
> > > > >
> > > > > Make sure ulimit is set to get the core.
> > > >
> > > > reproduced under 24 cpu box with kernel build (make -j25)
> > > > running on background.. will try to look closer
> > > >
> > > > perf: Segmentation fault
> > > > -------- backtrace --------
> > > > ./perf[0x4fd79b]
> > > > /lib64/libc.so.6(+0x358f0)[0x7f9cbff528f0]
> > > > ./perf(thread__put+0x5b)[0x4b1a7b]
> > > > ./perf(hists__delete_entries+0x70)[0x4c8670]
> > > > ./perf[0x436a88]
> > > > ./perf[0x4fa73d]
> > > > ./perf(perf_evlist__tui_browse_hists+0x97)[0x4fc437]
> > > > ./perf[0x4381d0]
> > > > /lib64/libpthread.so.0(+0x7ee5)[0x7f9cc1ff2ee5]
> > > > /lib64/libc.so.6(clone+0x6d)[0x7f9cc0011b8d]
> > > > [0x0]
> > >
> > > looks like race among __machine__findnew_thread and thread__put
> > > over the machine->threads rb_tree insert/removal
> > >
> > > is there a reason why thread__put does not erase itself from
> > > machine->threads?
>
> that was the reason.. we do this separately.. not in thread__put..
> is there a reason for this? ;-)
>
> testing attached patch..
>
> jirka
>
>
> ---
> diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
> index f7fb258..966564a 100644
> --- a/tools/perf/util/build-id.c
> +++ b/tools/perf/util/build-id.c
> @@ -60,7 +60,6 @@ static int perf_event__exit_del_thread(struct perf_tool
> *tool __maybe_unused,
> event->fork.ppid, event->fork.ptid);
>
> if (thread) {
> - rb_erase(&thread->rb_node, &machine->threads);
> if (machine->last_match == thread)
> thread__zput(machine->last_match);
> thread__put(thread);
> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> index e335330..a8443ef 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -30,6 +30,7 @@ int machine__init(struct machine *machine, const char
> *root_dir, pid_t pid)
> dsos__init(&machine->kernel_dsos);
>
> machine->threads = RB_ROOT;
> + pthread_mutex_init(&machine->threads_lock, NULL);
> INIT_LIST_HEAD(&machine->dead_threads);
> machine->last_match = NULL;
>
> @@ -380,10 +381,13 @@ static struct thread *__machine__findnew_thread(struct
> machine *machine,
> if (!create)
> return NULL;
>
> - th = thread__new(pid, tid);
> + th = thread__new(machine, pid, tid);
> if (th != NULL) {
> +
> + pthread_mutex_lock(&machine->threads_lock);
> rb_link_node(&th->rb_node, parent, p);
> rb_insert_color(&th->rb_node, &machine->threads);
> + pthread_mutex_unlock(&machine->threads_lock);
I think you also need to protect the rb tree traversal above.
But this makes every sample processing grabs and releases the lock so
might cause high overhead. It can be a problem if such processing is
done parallelly like my multi-thread work. :-/
Thanks,
Namhyung
>
> /*
> * We have to initialize map_groups separately
> @@ -394,7 +398,9 @@ static struct thread *__machine__findnew_thread(struct
> machine *machine,
> * leader and that would screwed the rb tree.
> */
> if (thread__init_map_groups(th, machine)) {
> + pthread_mutex_lock(&machine->threads_lock);
> rb_erase(&th->rb_node, &machine->threads);
> + pthread_mutex_unlock(&machine->threads_lock);
> thread__delete(th);
> return NULL;
> }
> @@ -1258,7 +1264,6 @@ static void machine__remove_thread(struct machine
> *machine, struct thread *th)
> if (machine->last_match == th)
> thread__zput(machine->last_match);
>
> - rb_erase(&th->rb_node, &machine->threads);
> /*
> * Move it first to the dead_threads list, then drop the reference,
> * if this is the last reference, then the thread__delete destructor
> diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
> index e2faf3b..e3468d6 100644
> --- a/tools/perf/util/machine.h
> +++ b/tools/perf/util/machine.h
> @@ -30,6 +30,7 @@ struct machine {
> bool comm_exec;
> char *root_dir;
> struct rb_root threads;
> + pthread_mutex_t threads_lock;
> struct list_head dead_threads;
> struct thread *last_match;
> struct vdso_info *vdso_info;
> diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
> index 1c8fbc9..4592fc4 100644
> --- a/tools/perf/util/thread.c
> +++ b/tools/perf/util/thread.c
> @@ -26,7 +26,7 @@ int thread__init_map_groups(struct thread *thread, struct
> machine *machine)
> return thread->mg ? 0 : -1;
> }
>
> -struct thread *thread__new(pid_t pid, pid_t tid)
> +struct thread *thread__new(struct machine *machine, pid_t pid, pid_t tid)
> {
> char *comm_str;
> struct comm *comm;
> @@ -38,6 +38,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
> thread->ppid = -1;
> thread->cpu = -1;
> INIT_LIST_HEAD(&thread->comm_list);
> + thread->machine = machine;
>
> if (unwind__prepare_access(thread) < 0)
> goto err_thread;
> @@ -91,7 +92,14 @@ struct thread *thread__get(struct thread *thread)
> void thread__put(struct thread *thread)
> {
> if (thread && --thread->refcnt == 0) {
> + struct machine *machine = thread->machine;
> +
> list_del_init(&thread->node);
> +
> + pthread_mutex_lock(&machine->threads_lock);
> + rb_erase(&thread->rb_node, &machine->threads);
> + pthread_mutex_unlock(&machine->threads_lock);
> +
> thread__delete(thread);
> }
> }
> diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
> index 9b8a54d..df6fb69 100644
> --- a/tools/perf/util/thread.h
> +++ b/tools/perf/util/thread.h
> @@ -31,12 +31,13 @@ struct thread {
>
> void *priv;
> struct thread_stack *ts;
> + struct machine *machine;
> };
>
> struct machine;
> struct comm;
>
> -struct thread *thread__new(pid_t pid, pid_t tid);
> +struct thread *thread__new(struct machine *machine, pid_t pid, pid_t tid);
> int thread__init_map_groups(struct thread *thread, struct machine *machine);
> void thread__delete(struct thread *thread);
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
