[PATCH] knfsd: split svc_serv into pools

Split out the list of idle threads and pending sockets from svc_serv into a
new svc_pool structure, and allocate a fixed number (in this patch, 1) of
pools per svc_serv.  The new structure contains a lock which takes over
several of the duties of svc_serv->sv_lock, which is now relegated to
protecting only sv_tempsocks, sv_permsocks, and sv_tmpcnt in svc_serv.

The point is to move the hottest fields out of svc_serv and into svc_pool,
allowing a following patch to arrange for a svc_pool per NUMA node or per CPU.
 This is a major step towards making the NFS server NUMA-friendly.

Signed-off-by: Greg Banks <gnb@melbourne.sgi.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 24 insertions, 2 deletions

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 5eabded11061..c27d806af310 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -17,6 +17,25 @@
 #include <linux/wait.h>
 #include <linux/mm.h>
 
+
+/*
+ *
+ * RPC service thread pool.
+ *
+ * Pool of threads and temporary sockets.  Generally there is only
+ * a single one of these per RPC service, but on NUMA machines those
+ * services that can benefit from it (i.e. nfs but not lockd) will
+ * have one pool per NUMA node.  This optimisation reduces cross-
+ * node traffic on multi-node NUMA NFS servers.
+ */
+struct svc_pool {
+        unsigned int            sp_id;          /* pool id; also node id on NUMA */
+        spinlock_t              sp_lock;        /* protects all fields */
+        struct list_head        sp_threads;     /* idle server threads */
+        struct list_head        sp_sockets;     /* pending sockets */
+        unsigned int            sp_nrthreads;   /* # of threads in pool */
+} ____cacheline_aligned_in_smp;
+
 /*
  * RPC service.
  *
@@ -28,8 +47,6 @@
  * We currently do not support more than one RPC program per daemon.
  */
 struct svc_serv {
-        struct list_head        sv_threads;     /* idle server threads */
-        struct list_head        sv_sockets;     /* pending sockets */
         struct svc_program *    sv_program;     /* RPC program */
         struct svc_stat *       sv_stats;       /* RPC statistics */
         spinlock_t              sv_lock;
@@ -44,6 +61,9 @@ struct svc_serv {
 
         char *                  sv_name;        /* service name */
 
+        unsigned int            sv_nrpools;     /* number of thread pools */
+        struct svc_pool *       sv_pools;       /* array of thread pools */
+
         void                    (*sv_shutdown)(struct svc_serv *serv);
                                                 /* Callback to use when last thread
                                                  * exits.
@@ -138,6 +158,7 @@ struct svc_rqst {
         int                     rq_addrlen;
 
         struct svc_serv *       rq_server;      /* RPC service definition */
+        struct svc_pool *       rq_pool;        /* thread pool */
         struct svc_procedure *  rq_procinfo;    /* procedure info */
         struct auth_ops *       rq_authop;      /* authentication flavour */
         struct svc_cred         rq_cred;        /* auth info */
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 7154e71c6d1f..4c296152cbfa 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -20,6 +20,7 @@ struct svc_sock {
         struct socket *         sk_sock;        /* berkeley socket layer */
         struct sock *           sk_sk;          /* INET layer */
 
+        struct svc_pool *       sk_pool;        /* current pool iff queued */
         struct svc_serv *       sk_server;      /* service for this socket */
         atomic_t                sk_inuse;       /* use count */
         unsigned long           sk_flags;