[PATCH v2 0/2] NFSD duplicate reply cache optimizations

[PATCH v2 0/2] NFSD duplicate reply cache optimizations

[Chuck Lever]

From: Chuck Lever <chuck.lever@oracle.com>

Two minor optimizations for the NFSD duplicate reply cache. These
showed slight improvement in WRITE throughput on exported fast
file systems.

Changes since v1:
- Remove RC_INPROG check from nfsd_prune_bucket_locked()

Chuck Lever (2):
  NFSD: Delay adding new entries to LRU
  NFSD: Reduce DRC bucket size

 fs/nfsd/nfscache.c | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

-- 
2.50.0

[PATCH v2 1/2] NFSD: Delay adding new entries to LRU

[Chuck Lever]

From: Chuck Lever <chuck.lever@oracle.com>

Neil Brown observes:
> I would not include RC_INPROG entries in the lru at all - they are
> always ignored, and will be added when they are switched to
> RCU_DONE.

I also removed a stale comment.

Suggested-by: NeilBrown <neil@brown.name>
Reviewed-by: NeilBrown <neil@brown.name>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfscache.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index ba9d326b3de6..d929c8c63bd9 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -237,10 +237,6 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn)
 
 }
 
-/*
- * Move cache entry to end of LRU list, and queue the cleaner to run if it's
- * not already scheduled.
- */
 static void
 lru_put_end(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp)
 {
@@ -272,13 +268,6 @@ nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b,
 
 	/* The bucket LRU is ordered oldest-first. */
 	list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) {
-		/*
-		 * Don't free entries attached to calls that are still
-		 * in-progress, but do keep scanning the list.
-		 */
-		if (rp->c_state == RC_INPROG)
-			continue;
-
 		if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries &&
 		    time_before(expiry, rp->c_timestamp))
 			break;
@@ -453,8 +442,6 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct nfsd_cacherep *key,
 				nn->longest_chain_cachesize,
 				atomic_read(&nn->num_drc_entries));
 	}
-
-	lru_put_end(b, ret);
 	return ret;
 }
 
-- 
2.50.0

[PATCH v2 2/2] NFSD: Reduce DRC bucket size

[Chuck Lever]

From: Chuck Lever <chuck.lever@oracle.com>

The common case is that a DRC lookup will not find the XID in the
bucket. Reduce the amount of pointer chasing during the lookup by
keeping fewer entries in each hash bucket.

Changing the bucket size constant forces the size of the DRC hash
table to increase, and the height of each bucket r-b tree to be
reduced.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfscache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index d929c8c63bd9..ab13ee9c7fd8 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -27,7 +27,7 @@
  * cache size, the idea being that when the cache is at its maximum number
  * of entries, then this should be the average number of entries per bucket.
  */
-#define TARGET_BUCKET_SIZE	64
+#define TARGET_BUCKET_SIZE	8
 
 struct nfsd_drc_bucket {
 	struct rb_root rb_head;
-- 
2.50.0