[PATCH v8 6/8] fs: only send IPI to invalidate LRU BH when needed

[Gilad Ben-Yossef]

In several code paths, such as when unmounting a file system (but
not only) we send an IPI to ask each cpu to invalidate its local
LRU BHs.

For multi-cores systems that have many cpus that may not have
any LRU BH because they are idle or because they have not performed
any file system accesses since last invalidation (e.g. CPU crunching
on high perfomance computing nodes that write results to shared
memory or only using filesystems that do not use the bh layer.)
This can lead to loss of performance each time someone switches
the KVM (the virtual keyboard and screen type, not the hypervisor)
if it has a USB storage stuck in.

This patch attempts to only send an IPI to cpus that have LRU BH.

Signed-off-by: Gilad Ben-Yossef <gilad@xxxxxxxxxxxxx>
Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
CC: Christoph Lameter <cl@xxxxxxxxx>
CC: Chris Metcalf <cmetcalf@xxxxxxxxxx>
CC: Frederic Weisbecker <fweisbec@xxxxxxxxx>
CC: Russell King <linux@xxxxxxxxxxxxxxxx>
CC: linux-mm@xxxxxxxxx
CC: Pekka Enberg <penberg@xxxxxxxxxx>
CC: Matt Mackall <mpm@xxxxxxxxxxx>
CC: Sasha Levin <levinsasha928@xxxxxxxxx>
CC: Rik van Riel <riel@xxxxxxxxxx>
CC: Andi Kleen <andi@xxxxxxxxxxxxxx>
CC: Mel Gorman <mel@xxxxxxxxx>
CC: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
CC: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
CC: linux-fsdevel@xxxxxxxxxxxxxxx
CC: Avi Kivity <avi@xxxxxxxxxx>
CC: Michal Nazarewicz <mina86@xxxxxxxxxx>
CC: Kosaki Motohiro <kosaki.motohiro@xxxxxxxxx>
CC: Milton Miller <miltonm@xxxxxxx>
---
 fs/buffer.c |   15 ++++++++++++++-
 1 files changed, 14 insertions(+), 1 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 1a30db7..baa075e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1384,10 +1384,23 @@ static void invalidate_bh_lru(void *arg)
 	}
 	put_cpu_var(bh_lrus);
 }
+
+static bool has_bh_in_lru(int cpu, void *dummy)
+{
+	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
+	int i;
 	
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		if (b->bhs[i])
+			return 1;
+	}
+
+	return 0;
+}
+
 void invalidate_bh_lrus(void)
 {
-	on_each_cpu(invalidate_bh_lru, NULL, 1);
+	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
-- 
1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/