taskstats: add context-switch counters

Make available to the user the following task and process performance
statistics:

	* Involuntary Context Switches (task_struct->nivcsw)
	* Voluntary Context Switches (task_struct->nvcsw)

Statistics information is available from:
	1. taskstats interface (Documentation/accounting/)
	2. /proc/PID/status (task only).

This data is useful for detecting hyperactivity patterns between processes.

[akpm@linux-foundation.org: cleanup]
Signed-off-by: Maxim Uvarov <muvarov@ru.mvista.com>
Cc: Shailabh Nagar <nagar@watson.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Cc: Jonathan Lim <jlim@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 41 insertions, 3 deletions

diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index 71acc28ed0d1..24c5aade8998 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -49,6 +49,7 @@ char name[100];
 int dbg;
 int print_delays;
 int print_io_accounting;
+int print_task_context_switch_counts;
 __u64 stime, utime;
 
 #define PRINTF(fmt, arg...) {                   \
@@ -195,7 +196,7 @@ void print_delayacct(struct taskstats *t)
                "IO    %15s%15s\n"
                "      %15llu%15llu\n"
                "MEM   %15s%15s\n"
-               "      %15llu%15llu\n\n",
+               "      %15llu%15llu\n"
                "count", "real total", "virtual total", "delay total",
                t->cpu_count, t->cpu_run_real_total, t->cpu_run_virtual_total,
                t->cpu_delay_total,
@@ -204,6 +205,14 @@ void print_delayacct(struct taskstats *t)
                "count", "delay total", t->swapin_count, t->swapin_delay_total);
 }
 
+void task_context_switch_counts(struct taskstats *t)
+{
+        printf("\n\nTask   %15s%15s\n"
+               "       %15lu%15lu\n",
+               "voluntary", "nonvoluntary",
+               t->nvcsw, t->nivcsw);
+}
+
 void print_ioacct(struct taskstats *t)
 {
         printf("%s: read=%llu, write=%llu, cancelled_write=%llu\n",
@@ -235,7 +244,7 @@ int main(int argc, char *argv[])
         struct msgtemplate msg;
 
         while (1) {
-                c = getopt(argc, argv, "diw:r:m:t:p:vl");
+                c = getopt(argc, argv, "qdiw:r:m:t:p:vl");
                 if (c < 0)
                         break;
 
@@ -248,6 +257,10 @@ int main(int argc, char *argv[])
                         printf("printing IO accounting\n");
                         print_io_accounting = 1;
                         break;
+                case 'q':
+                        printf("printing task/process context switch rates\n");
+                        print_task_context_switch_counts = 1;
+                        break;
                 case 'w':
                         logfile = strdup(optarg);
                         printf("write to file %s\n", logfile);
@@ -389,6 +402,8 @@ int main(int argc, char *argv[])
                                                         print_delayacct((struct taskstats *) NLA_DATA(na));
                                                 if (print_io_accounting)
                                                         print_ioacct((struct taskstats *) NLA_DATA(na));
+                                                if (print_task_context_switch_counts)
+                                                        task_context_switch_counts((struct taskstats *) NLA_DATA(na));
                                                 if (fd) {
                                                         if (write(fd, NLA_DATA(na), na->nla_len) < 0) {
                                                                 err(1,"write error\n");
diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt
index 661c797eaf79..8aa7529f8258 100644
--- a/Documentation/accounting/taskstats-struct.txt
+++ b/Documentation/accounting/taskstats-struct.txt
@@ -22,6 +22,8 @@ There are three different groups of fields in the struct taskstats:
     /* Extended accounting fields end */
     Their values are collected if CONFIG_TASK_XACCT is set.
 
+4) Per-task and per-thread context switch count statistics
+
 Future extension should add fields to the end of the taskstats struct, and
 should not change the relative position of each field within the struct.
 
@@ -158,4 +160,8 @@ struct taskstats {
 
         /* Extended accounting fields end */
 
+4) Per-task and per-thread statistics
+        __u64   nvcsw;                  /* Context voluntary switch counter */
+        __u64   nivcsw;                 /* Context involuntary switch counter */
+
 }
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 680c913575f0..9cbab7e93557 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -289,6 +289,15 @@ static inline char *task_cap(struct task_struct *p, char *buffer)
                             cap_t(p->cap_effective));
 }
 
+static inline char *task_context_switch_counts(struct task_struct *p,
+                                                char *buffer)
+{
+        return buffer + sprintf(buffer, "voluntary_ctxt_switches:\t%lu\n"
+                            "nonvoluntary_ctxt_switches:\t%lu\n",
+                            p->nvcsw,
+                            p->nivcsw);
+}
+
 int proc_pid_status(struct task_struct *task, char * buffer)
 {
         char * orig = buffer;
@@ -307,6 +316,7 @@ int proc_pid_status(struct task_struct *task, char * buffer)
 #if defined(CONFIG_S390)
         buffer = task_show_regs(task, buffer);
 #endif
+        buffer = task_context_switch_counts(task, buffer);
         return buffer - orig;
 }
 
diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h
index a46104a28f66..dce1ed204972 100644
--- a/include/linux/taskstats.h
+++ b/include/linux/taskstats.h
@@ -31,7 +31,7 @@
  */
 
 
-#define TASKSTATS_VERSION       4
+#define TASKSTATS_VERSION       5
 #define TS_COMM_LEN             32      /* should be >= TASK_COMM_LEN
                                          * in linux/sched.h */
 
@@ -149,6 +149,9 @@ struct taskstats {
         __u64   read_bytes;             /* bytes of read I/O */
         __u64   write_bytes;            /* bytes of write I/O */
         __u64   cancelled_write_bytes;  /* bytes of cancelled write I/O */
+
+        __u64  nvcsw;                   /* voluntary_ctxt_switches */
+        __u64  nivcsw;                  /* nonvoluntary_ctxt_switches */
 };
 
 
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 906cae771585..059431ed67db 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -196,6 +196,8 @@ static int fill_pid(pid_t pid, struct task_struct *tsk,
 
         /* fill in basic acct fields */
         stats->version = TASKSTATS_VERSION;
+        stats->nvcsw = tsk->nvcsw;
+        stats->nivcsw = tsk->nivcsw;
         bacct_add_tsk(stats, tsk);
 
         /* fill in extended acct fields */
@@ -242,6 +244,8 @@ static int fill_tgid(pid_t tgid, struct task_struct *first,
                  */
                 delayacct_add_tsk(stats, tsk);
 
+                stats->nvcsw += tsk->nvcsw;
+                stats->nivcsw += tsk->nivcsw;
         } while_each_thread(first, tsk);
 
         unlock_task_sighand(first, &flags);