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>
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 8a159cc..1f0966f 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -32,7 +32,6 @@
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 inetpeer_addr_base redirect_learned;
};
struct rcu_head rcu;
+ struct inet_peer *gc_next;
};
};