taskstats: fix sub-threads accounting
PATCH 1/1 taskstats: fix sub-threads accounting
If there are no listeners, taskstats_exit_send() just returns because taskstats_exit_alloc() didn't allocate *tidstats. This is wrong, each sub-thread should do fill_tgid_exit() on exit, otherwise its ->delays is not recorded in ->signal->stats and lost.
Q: We don't send TASKSTATS_TYPE_AGGR_TGID when single-threaded process exits. Is it good? How can the listener figure out that it was actually a process exit, not sub-thread?
kernel/taskstats.c renamed from kernel/taskstats.c~2_send +10 -7
@@ -446,10 +446,9 @@ void taskstats_exit_send(struct task_strint is_thread_group;struct nlattr *na; -if (!family_registered || !tidstats) +if (!family_registered)return ; - rc =0 ;/* * Size includes space for nested attributes */
@@ -457,8 +456,15 @@ void taskstats_exit_send(struct task_strnla_total_size (sizeof (struct taskstats )) +nla_total_size (0 ); is_thread_group = (tsk->signal->stats !=NULL ); -if (is_thread_group) - size =2 * size;/* PID + STATS + TGID + STATS */ +if (is_thread_group) { +/* PID + STATS + TGID + STATS */ + size =2 * size; +/* fill the tsk->signal->stats structure */ +fill_tgid_exit (tsk); + } + +if (!tidstats) +return ; rc =prepare_reply (NULL ,TASKSTATS_CMD_NEW , &rep_skb, &reply, size);if (rc <0 )
@@ -478,11 +484,8 @@ void taskstats_exit_send(struct task_str goto send;/* -* tsk has/had a thread group so fill the tsk->signal->stats structure * Doesn't matter if tsk is the leader or the last group member leaving */ - -fill_tgid_exit (tsk);if (!group_dead) goto send;
Quoted 4 lines · Oleg Nesterov
If there are no listeners,
taskstats_exit_send()just returns becausetaskstats_exit_alloc()didn't allocate *tidstats. This is wrong, each sub-thread should dofill_tgid_exit()on exit, otherwise its ->delays is not recorded in ->signal->stats and lost.
Good catch. Thanks for the detailed look at the delay accounting code.
Quoted 4 lines
Q: We don't send
TASKSTATS_TYPE_AGGR_TGIDwhen single-threaded process exits. Is it good? How can the listener figure out that it was actually a process exit, not sub-thread?
We had a detailed discussion on this on lkml earlier. The overhead of sending essentially the same data twice (once as AGGR_TGID and once as PID) was deemed too heavy esp. as the taskstats structure size grew. Also, single threaded exit is a common case.
Using process events, its possible for user space to distinguish single threaded process exits.
Quoted 2 lines
Signed-off-by Oleg Nesterov <[email protected]>
Quoted 46 lines
kernel/taskstats.c renamed from kernel/taskstats.c~2_send +10
-7@@ -446,10 +446,9 @@ void taskstats_exit_send(struct task_strint is_thread_group;struct nlattr *na; -if (!family_registered || !tidstats) +if (!family_registered)return ; - rc =0 ;/* * Size includes space for nested attributes */ @@ -457,8 +456,15 @@ void taskstats_exit_send(struct task_strnla_total_size (sizeof (struct taskstats )) +nla_total_size (0 ); is_thread_group = (tsk->signal->stats !=NULL ); -if (is_thread_group) - size =2 * size;/* PID + STATS + TGID + STATS */ +if (is_thread_group) { +/* PID + STATS + TGID + STATS */ + size =2 * size; +/* fill the tsk->signal->stats structure */ +fill_tgid_exit (tsk); + } + +if (!tidstats) +return ; rc =prepare_reply (NULL ,TASKSTATS_CMD_NEW , &rep_skb, &reply, size);if (rc <0 )@@ -478,11 +484,8 @@ void taskstats_exit_send(struct task_str goto send;/* -* tsk has/had a thread group so fill the tsk->signal->stats structure * Doesn't matter if tsk is the leader or the last group member leaving */ - -fill_tgid_exit (tsk);if (!group_dead) goto send;
Quoted 7 lines · Shailabh Nagar
Quoted 4 lines · Oleg Nesterov
Q: We don't send
TASKSTATS_TYPE_AGGR_TGIDwhen single-threaded process exits. Is it good? How can the listener figure out that it was actually a process exit, not sub-thread?
Quoted 7 lines
We had a detailed discussion on this on lkml earlier. The overhead of sending essentially the same data twice (once as
AGGR_TGIDand once as PID) was deemed too heavy esp. as the taskstats structure size grew. Also, single threaded exit is a common case.Using process events, its possible for user space to distinguish single threaded process exits.
Ok, I see.
The taskstats's code is very clean and understandable, the only thing I can't get is: why these listeners are per-cpu? It is very easy to add 'int exited_on_this_cpu' to struct taskstats.
Probaly this was done to filter out unneeded events (cpusets) ? In that case it seems better to add cpumask_t to 'struct listener' but have a single listener_array list.
Thanks!
Oleg.