Okay, attached is a change that might give you what you want. I tried my
pipe-bench program (see cover note) with perf. The output of the program with
the patch applied was:
- pipe 305127298 36262221772 302185181 7887690
The output of perf with the patch applied:
239,943.92 msec task-clock # 1.997 CPUs utilized
17,728 context-switches # 73.884 M/sec
124 cpu-migrations # 0.517 M/sec
9,330 page-faults # 38.884 M/sec
885,107,207,365 cycles # 3688822.793 GHz
1,386,873,499,490 instructions # 1.57 insn per cycle
311,037,372,339 branches # 1296296921.931 M/sec
33,467,827 branch-misses # 0.01% of all branches
And without:
239,891.87 msec task-clock # 1.997 CPUs utilized
22,187 context-switches # 92.488 M/sec
133 cpu-migrations # 0.554 M/sec
9,334 page-faults # 38.909 M/sec
884,906,976,128 cycles # 3688787.725 GHz
1,391,986,932,265 instructions # 1.57 insn per cycle
311,394,686,857 branches # 1298067400.849 M/sec
30,242,823 branch-misses # 0.01% of all branches
So it did make something like a 20% reduction in context switches.
David
---
diff --git a/fs/pipe.c b/fs/pipe.c
index e3d5f7a39123..5167921edd73 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -276,7 +276,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
size_t total_len = iov_iter_count(to);
struct file *filp = iocb->ki_filp;
struct pipe_inode_info *pipe = filp->private_data;
- int do_wakeup;
+ int do_wakeup, wake;
ssize_t ret;
/* Null read succeeds. */
@@ -329,11 +329,12 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
tail++;
pipe->tail = tail;
do_wakeup = 1;
- if (head - (tail - 1) == pipe->max_usage)
+ wake = head - (tail - 1) == pipe->max_usage / 2;
+ if (wake)
wake_up_interruptible_sync_poll_locked(
&pipe->wait, EPOLLOUT | EPOLLWRNORM);
spin_unlock_irq(&pipe->wait.lock);
- if (head - (tail - 1) == pipe->max_usage)
+ if (wake)
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
total_len -= chars;
