inetpeer: remove unused list

Andi Kleen and Tim Chen reported huge contention on inetpeer
unused_peers.lock, on memcached workload on a 40 core machine, with
disabled route cache.

It appears we constantly flip peers refcnt between 0 and 1 values, and
we must insert/remove peers from unused_peers.list, holding a contended
spinlock.

Remove this list completely and perform a garbage collection on-the-fly,
at lookup time, using the expired nodes we met during the tree
traversal.

This removes a lot of code, makes locking more standard, and obsoletes
two sysctls (inet_peer_gc_mintime and inet_peer_gc_maxtime). This also
removes two pointers in inet_peer structure.

There is still a false sharing effect because refcnt is in first cache
line of object [were the links and keys used by lookups are located], we
might move it at the end of inet_peer structure to let this first cache
line mostly read by cpus.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Andi Kleen <andi@firstfloor.org>
CC: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/ip-sysctl.txt

@@ -106,16 +106,6 @@ inet_peer_maxttl - INTEGER
 	when the number of entries in the pool is very small).
 	Measured in seconds.
 
-inet_peer_gc_mintime - INTEGER
-	Minimum interval between garbage collection passes.  This interval is
-	in effect under high memory pressure on the pool.
-	Measured in seconds.
-
-inet_peer_gc_maxtime - INTEGER
-	Minimum interval between garbage collection passes.  This interval is
-	in effect under low (or absent) memory pressure on the pool.
-	Measured in seconds.
-
 TCP variables:
 
 somaxconn - INTEGER

include/net/inetpeer.h

@@ -32,7 +32,6 @@ struct inet_peer {
 	struct inet_peer __rcu	*avl_left, *avl_right;
 	struct inetpeer_addr	daddr;
 	__u32			avl_height;
-	struct list_head	unused;
 	__u32			dtime;		/* the time of last use of not
 						 * referenced entries */
 	atomic_t		refcnt;
@@ -56,6 +55,7 @@ struct inet_peer {
 			struct inetpeer_addr_base	redirect_learned;
 		};
 		struct rcu_head         rcu;
+		struct inet_peer	*gc_next;
 	};
 };
 

include/net/ip.h

@@ -228,8 +228,6 @@ extern struct ctl_path net_ipv4_ctl_path[];
 extern int inet_peer_threshold;
 extern int inet_peer_minttl;
 extern int inet_peer_maxttl;
-extern int inet_peer_gc_mintime;
-extern int inet_peer_gc_maxtime;
 
 /* From ip_output.c */
 extern int sysctl_ip_dynaddr;

net/ipv4/sysctl_net_ipv4.c

@@ -397,20 +397,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{
-		.procname	= "inet_peer_gc_mintime",
-		.data		= &inet_peer_gc_mintime,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "inet_peer_gc_maxtime",
-		.data		= &inet_peer_gc_maxtime,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
 	{
 		.procname	= "tcp_orphan_retries",
 		.data		= &sysctl_tcp_orphan_retries,