NFSD: Optimize DRC bucket pruning

DRC bucket pruning is done by nfsd_cache_lookup(), which is part of
every NFSv2 and NFSv3 dispatch (ie, it's done while the client is
waiting).

I added a trace_printk() in prune_bucket() to see just how long
it takes to prune. Here are two ends of the spectrum:

 prune_bucket: Scanned 1 and freed 0 in 90 ns, 62 entries remaining
 prune_bucket: Scanned 2 and freed 1 in 716 ns, 63 entries remaining
...
 prune_bucket: Scanned 75 and freed 74 in 34149 ns, 1 entries remaining

Pruning latency is noticeable on fast transports with fast storage.
By noticeable, I mean that the latency measured here in the worst
case is the same order of magnitude as the round trip time for
cached server operations.

We could do something like moving expired entries to an expired list
and then free them later instead of freeing them right in
prune_bucket(). But simply limiting the number of entries that can
be pruned by a lookup is simple and retains more entries in the
cache, making the DRC somewhat more effective.

Comparison with a 70/30 fio 8KB 12 thread direct I/O test:

Before:

  write: IOPS=61.6k, BW=481MiB/s (505MB/s)(14.1GiB/30001msec); 0 zone resets

WRITE:
	1848726 ops (30%)
	avg bytes sent per op: 8340 avg bytes received per op: 136
	backlog wait: 0.635158 	RTT: 0.128525 	total execute time: 0.827242 (milliseconds)

After:

  write: IOPS=63.0k, BW=492MiB/s (516MB/s)(14.4GiB/30001msec); 0 zone resets

WRITE:
	1891144 ops (30%)
	avg bytes sent per op: 8340 avg bytes received per op: 136
	backlog wait: 0.616114 	RTT: 0.126842 	total execute time: 0.805348 (milliseconds)

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

fs/nfsd/nfscache.c

@@ -241,8 +241,8 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
 	list_move_tail(&rp->c_lru, &b->lru_head);
 }
 
-static long
-prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
+static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn,
+			 unsigned int max)
 {
 	struct svc_cacherep *rp, *tmp;
 	long freed = 0;
@@ -258,11 +258,17 @@ prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
 		    time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
 			break;
 		nfsd_reply_cache_free_locked(b, rp, nn);
-		freed++;
+		if (max && freed++ > max)
+			break;
 	}
 	return freed;
 }
 
+static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
+{
+	return prune_bucket(b, nn, 3);
+}
+
 /*
  * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
  * Also prune the oldest ones when the total exceeds the max number of entries.
@@ -279,7 +285,7 @@ prune_cache_entries(struct nfsd_net *nn)
 		if (list_empty(&b->lru_head))
 			continue;
 		spin_lock(&b->cache_lock);
-		freed += prune_bucket(b, nn);
+		freed += prune_bucket(b, nn, 0);
 		spin_unlock(&b->cache_lock);
 	}
 	return freed;
@@ -453,8 +459,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp)
 	atomic_inc(&nn->num_drc_entries);
 	nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp));
 
-	/* go ahead and prune the cache */
-	prune_bucket(b, nn);
+	nfsd_prune_bucket(b, nn);
 
 out_unlock:
 	spin_unlock(&b->cache_lock);