[PATCH] delay accounting taskstats interface send tgid once

Send per-tgid data only once during exit of a thread group instead of once
with each member thread exit.

Currently, when a thread exits, besides its per-tid data, the per-tgid data
of its thread group is also sent out, if its thread group is non-empty.
The per-tgid data sent consists of the sum of per-tid stats for all
*remaining* threads of the thread group.

This patch modifies this sending in two ways:

- the per-tgid data is sent only when the last thread of a thread group
  exits.  This cuts down heavily on the overhead of sending/receiving
  per-tgid data, especially when other exploiters of the taskstats
  interface aren't interested in per-tgid stats

- the semantics of the per-tgid data sent are changed.  Instead of being
  the sum of per-tid data for remaining threads, the value now sent is the
  true total accumalated statistics for all threads that are/were part of
  the thread group.

The patch also addresses a minor issue where failure of one accounting
subsystem to fill in the taskstats structure was causing the send of
taskstats to not be sent at all.

The patch has been tested for stability and run cerberus for over 4 hours
on an SMP.

[akpm@osdl.org: bugfixes]
Signed-off-by: Shailabh Nagar <nagar@watson.ibm.com>
Signed-off-by: Balbir Singh <balbir@in.ibm.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 59 insertions, 16 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3c5610ca0c92..6afa72e080cb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -463,6 +463,10 @@ struct signal_struct {
 #ifdef CONFIG_BSD_PROCESS_ACCT
         struct pacct_struct pacct;      /* per-process accounting information */
 #endif
+#ifdef CONFIG_TASKSTATS
+        spinlock_t stats_lock;
+        struct taskstats *stats;
+#endif
 };
 
 /* Context switch must be unlocked if interrupts are to be enabled */
diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h
index fc9da2e26443..0ae8f67af1fd 100644
--- a/include/linux/taskstats_kern.h
+++ b/include/linux/taskstats_kern.h
@@ -19,36 +19,75 @@ enum {
 extern kmem_cache_t *taskstats_cache;
 extern struct mutex taskstats_exit_mutex;
 
-static inline void taskstats_exit_alloc(struct taskstats **ptidstats,
-                                        struct taskstats **ptgidstats)
+static inline void taskstats_exit_alloc(struct taskstats **ptidstats)
 {
         *ptidstats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL);
-        *ptgidstats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL);
 }
 
-static inline void taskstats_exit_free(struct taskstats *tidstats,
-                                        struct taskstats *tgidstats)
+static inline void taskstats_exit_free(struct taskstats *tidstats)
 {
         if (tidstats)
                 kmem_cache_free(taskstats_cache, tidstats);
-        if (tgidstats)
-                kmem_cache_free(taskstats_cache, tgidstats);
 }
 
-extern void taskstats_exit_send(struct task_struct *, struct taskstats *,
-                                struct taskstats *);
-extern void taskstats_init_early(void);
+static inline void taskstats_tgid_init(struct signal_struct *sig)
+{
+        spin_lock_init(&sig->stats_lock);
+        sig->stats = NULL;
+}
+
+static inline void taskstats_tgid_alloc(struct signal_struct *sig)
+{
+        struct taskstats *stats;
+        unsigned long flags;
+
+        stats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL);
+        if (!stats)
+                return;
+
+        spin_lock_irqsave(&sig->stats_lock, flags);
+        if (!sig->stats) {
+                sig->stats = stats;
+                stats = NULL;
+        }
+        spin_unlock_irqrestore(&sig->stats_lock, flags);
+
+        if (stats)
+                kmem_cache_free(taskstats_cache, stats);
+}
 
+static inline void taskstats_tgid_free(struct signal_struct *sig)
+{
+        struct taskstats *stats = NULL;
+        unsigned long flags;
+
+        spin_lock_irqsave(&sig->stats_lock, flags);
+        if (sig->stats) {
+                stats = sig->stats;
+                sig->stats = NULL;
+        }
+        spin_unlock_irqrestore(&sig->stats_lock, flags);
+        if (stats)
+                kmem_cache_free(taskstats_cache, stats);
+}
+
+extern void taskstats_exit_send(struct task_struct *, struct taskstats *, int);
+extern void taskstats_init_early(void);
+extern void taskstats_tgid_alloc(struct signal_struct *);
 #else
-static inline void taskstats_exit_alloc(struct taskstats **ptidstats,
-                                        struct taskstats **ptgidstats)
+static inline void taskstats_exit_alloc(struct taskstats **ptidstats)
 {}
-static inline void taskstats_exit_free(struct taskstats *ptidstats,
-                                        struct taskstats *ptgidstats)
+static inline void taskstats_exit_free(struct taskstats *ptidstats)
 {}
 static inline void taskstats_exit_send(struct task_struct *tsk,
-                                        struct taskstats *tidstats,
-                                        struct taskstats *tgidstats)
+                                       struct taskstats *tidstats,
+                                       int group_dead)
+{}
+static inline void taskstats_tgid_init(struct signal_struct *sig)
+{}
+static inline void taskstats_tgid_alloc(struct signal_struct *sig)
+{}
+static inline void taskstats_tgid_free(struct signal_struct *sig)
 {}
 static inline void taskstats_init_early(void)
 {}