Re: [PATCH] sunrpc: use better NUMA affinities

["J. Bruce Fields" <bfields@fieldses.org>]

On Thu, Jul 28, 2011 at 08:04:09PM +0200, Eric Dumazet wrote:
> Use NUMA aware allocations to reduce latencies and increase throughput.
> 
> sunrpc kthreads can use kthread_create_on_node() if pool_mode is
> "percpu" or "pernode", and svc_prepare_thread()/svc_init_buffer() can
> also take into account NUMA node affinity for memory allocations.

By the way, thanks, applying for 3.2 with one minor fixup below.--b.

diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index ce620b5..516f337 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -199,7 +199,7 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 	INIT_LIST_HEAD(&serv->sv_cb_list);
 	spin_lock_init(&serv->sv_cb_lock);
 	init_waitqueue_head(&serv->sv_cb_waitq);
-	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]);
+	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
 	if (IS_ERR(rqstp)) {
 		svc_xprt_put(serv->sv_bc_xprt);
 		serv->sv_bc_xprt = NULL;

> 
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> CC: "J. Bruce Fields" <bfields@fieldses.org>
> CC: Neil Brown <neilb@suse.de>
> CC: David Miller <davem@davemloft.net>
> ---
>  fs/lockd/svc.c             |    2 +-
>  fs/nfs/callback.c          |    2 +-
>  include/linux/sunrpc/svc.h |    2 +-
>  net/sunrpc/svc.c           |   33 ++++++++++++++++++++++++---------
>  4 files changed, 27 insertions(+), 12 deletions(-)
> 
> diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
> index abfff9d..c061b9a 100644
> --- a/fs/lockd/svc.c
> +++ b/fs/lockd/svc.c
> @@ -282,7 +282,7 @@ int lockd_up(void)
>  	/*
>  	 * Create the kernel thread and wait for it to start.
>  	 */
> -	nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
> +	nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
>  	if (IS_ERR(nlmsvc_rqst)) {
>  		error = PTR_ERR(nlmsvc_rqst);
>  		nlmsvc_rqst = NULL;
> diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
> index e3d2942..ce620b5 100644
> --- a/fs/nfs/callback.c
> +++ b/fs/nfs/callback.c
> @@ -125,7 +125,7 @@ nfs4_callback_up(struct svc_serv *serv)
>  	else
>  		goto out_err;
>  
> -	return svc_prepare_thread(serv, &serv->sv_pools[0]);
> +	return svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
>  
>  out_err:
>  	if (ret == 0)
> diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
> index 223588a..a78a51e 100644
> --- a/include/linux/sunrpc/svc.h
> +++ b/include/linux/sunrpc/svc.h
> @@ -404,7 +404,7 @@ struct svc_procedure {
>  struct svc_serv *svc_create(struct svc_program *, unsigned int,
>  			    void (*shutdown)(struct svc_serv *));
>  struct svc_rqst *svc_prepare_thread(struct svc_serv *serv,
> -					struct svc_pool *pool);
> +					struct svc_pool *pool, int node);
>  void		   svc_exit_thread(struct svc_rqst *);
>  struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
>  			void (*shutdown)(struct svc_serv *),
> diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
> index 6a69a11..30d70ab 100644
> --- a/net/sunrpc/svc.c
> +++ b/net/sunrpc/svc.c
> @@ -295,6 +295,18 @@ svc_pool_map_put(void)
>  }
>  
>  
> +static int svc_pool_map_get_node(unsigned int pidx)
> +{
> +	const struct svc_pool_map *m = &svc_pool_map;
> +
> +	if (m->count) {
> +		if (m->mode == SVC_POOL_PERCPU)
> +			return cpu_to_node(m->pool_to[pidx]);
> +		if (m->mode == SVC_POOL_PERNODE)
> +			return m->pool_to[pidx];
> +	}
> +	return NUMA_NO_NODE;
> +}
>  /*
>   * Set the given thread's cpus_allowed mask so that it
>   * will only run on cpus in the given pool.
> @@ -499,7 +511,7 @@ EXPORT_SYMBOL_GPL(svc_destroy);
>   * We allocate pages and place them in rq_argpages.
>   */
>  static int
> -svc_init_buffer(struct svc_rqst *rqstp, unsigned int size)
> +svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node)
>  {
>  	unsigned int pages, arghi;
>  
> @@ -513,7 +525,7 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size)
>  	arghi = 0;
>  	BUG_ON(pages > RPCSVC_MAXPAGES);
>  	while (pages) {
> -		struct page *p = alloc_page(GFP_KERNEL);
> +		struct page *p = alloc_pages_node(node, GFP_KERNEL, 0);
>  		if (!p)
>  			break;
>  		rqstp->rq_pages[arghi++] = p;
> @@ -536,11 +548,11 @@ svc_release_buffer(struct svc_rqst *rqstp)
>  }
>  
>  struct svc_rqst *
> -svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool)
> +svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
>  {
>  	struct svc_rqst	*rqstp;
>  
> -	rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
> +	rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node);
>  	if (!rqstp)
>  		goto out_enomem;
>  
> @@ -554,15 +566,15 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool)
>  	rqstp->rq_server = serv;
>  	rqstp->rq_pool = pool;
>  
> -	rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
> +	rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
>  	if (!rqstp->rq_argp)
>  		goto out_thread;
>  
> -	rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
> +	rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
>  	if (!rqstp->rq_resp)
>  		goto out_thread;
>  
> -	if (!svc_init_buffer(rqstp, serv->sv_max_mesg))
> +	if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node))
>  		goto out_thread;
>  
>  	return rqstp;
> @@ -647,6 +659,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
>  	struct svc_pool *chosen_pool;
>  	int error = 0;
>  	unsigned int state = serv->sv_nrthreads-1;
> +	int node;
>  
>  	if (pool == NULL) {
>  		/* The -1 assumes caller has done a svc_get() */
> @@ -662,14 +675,16 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
>  		nrservs--;
>  		chosen_pool = choose_pool(serv, pool, &state);
>  
> -		rqstp = svc_prepare_thread(serv, chosen_pool);
> +		node = svc_pool_map_get_node(chosen_pool->sp_id);
> +		rqstp = svc_prepare_thread(serv, chosen_pool, node);
>  		if (IS_ERR(rqstp)) {
>  			error = PTR_ERR(rqstp);
>  			break;
>  		}
>  
>  		__module_get(serv->sv_module);
> -		task = kthread_create(serv->sv_function, rqstp, serv->sv_name);
> +		task = kthread_create_on_node(serv->sv_function, rqstp,
> +					      node, serv->sv_name);
>  		if (IS_ERR(task)) {
>  			error = PTR_ERR(task);
>  			module_put(serv->sv_module);
> 
>