[PATCH] per-task-delay-accounting: sync block I/O and swapin delay collection

Unlike earlier iterations of the delay accounting patches, now delays are only
collected for the actual I/O waits rather than try and cover the delays seen
in I/O submission paths.

Account separately for block I/O delays incurred as a result of swapin page
faults whose frequency can be affected by the task/process' rss limit.  Hence
swapin delays can act as feedback for rss limit changes independent of I/O
priority changes.

Signed-off-by: Shailabh Nagar <nagar@watson.ibm.com>
Signed-off-by: Balbir Singh <balbir@in.ibm.com>
Cc: Jes Sorensen <jes@sgi.com>
Cc: Peter Chubb <peterc@gelato.unsw.edu.au>
Cc: Erich Focht <efocht@ess.nec.de>
Cc: Levent Serinol <lserinol@gmail.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, 24 insertions, 0 deletions

diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index fbf7f2284952..3546b0800f9f 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -85,3 +85,22 @@ static void delayacct_end(struct timespec *start, struct timespec *end,
         spin_unlock(&current->delays->lock);
 }
 
+void __delayacct_blkio_start(void)
+{
+        delayacct_start(&current->delays->blkio_start);
+}
+
+void __delayacct_blkio_end(void)
+{
+        if (current->delays->flags & DELAYACCT_PF_SWAPIN)
+                /* Swapin block I/O */
+                delayacct_end(&current->delays->blkio_start,
+                        &current->delays->blkio_end,
+                        &current->delays->swapin_delay,
+                        &current->delays->swapin_count);
+        else    /* Other block I/O */
+                delayacct_end(&current->delays->blkio_start,
+                        &current->delays->blkio_end,
+                        &current->delays->blkio_delay,
+                        &current->delays->blkio_count);
+}
diff --git a/kernel/sched.c b/kernel/sched.c
index e9a0b61f12ab..9d42cbfc4f8b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -51,6 +51,7 @@
 #include <linux/times.h>
 #include <linux/acct.h>
 #include <linux/kprobes.h>
+#include <linux/delayacct.h>
 #include <asm/tlb.h>
 
 #include <asm/unistd.h>
@@ -4534,9 +4535,11 @@ void __sched io_schedule(void)
 {
         struct rq *rq = &__raw_get_cpu_var(runqueues);
 
+        delayacct_blkio_start();
         atomic_inc(&rq->nr_iowait);
         schedule();
         atomic_dec(&rq->nr_iowait);
+        delayacct_blkio_end();
 }
 EXPORT_SYMBOL(io_schedule);
 
@@ -4545,9 +4548,11 @@ long __sched io_schedule_timeout(long timeout)
         struct rq *rq = &__raw_get_cpu_var(runqueues);
         long ret;
 
+        delayacct_blkio_start();
         atomic_inc(&rq->nr_iowait);
         ret = schedule_timeout(timeout);
         atomic_dec(&rq->nr_iowait);
+        delayacct_blkio_end();
         return ret;
 }