From 564824b0c52c34692d804bb6ea214451615b0b50 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Oct 2010 19:05:25 +0000 Subject: [PATCH] net: allocate skbs on local node commit b30973f877 (node-aware skb allocation) spread a wrong habit of allocating net drivers skbs on a given memory node : The one closest to the NIC hardware. This is wrong because as soon as we try to scale network stack, we need to use many cpus to handle traffic and hit slub/slab management on cross-node allocations/frees when these cpus have to alloc/free skbs bound to a central node. skb allocated in RX path are ephemeral, they have a very short lifetime : Extra cost to maintain NUMA affinity is too expensive. What appeared as a nice idea four years ago is in fact a bad one. In 2010, NIC hardwares are multiqueue, or we use RPS to spread the load, and two 10Gb NIC might deliver more than 28 million packets per second, needing all the available cpus. Cost of cross-node handling in network and vm stacks outperforms the small benefit hardware had when doing its DMA transfert in its 'local' memory node at RX time. Even trying to differentiate the two allocations done for one skb (the sk_buff on local node, the data part on NIC hardware node) is not enough to bring good performance. Signed-off-by: Eric Dumazet Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 20 ++++++++++++++++---- net/core/skbuff.c | 13 +------------ 2 files changed, 17 insertions(+), 16 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0b53c43ac92e..05a358f1ba11 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -496,13 +496,13 @@ extern struct sk_buff *__alloc_skb(unsigned int size, static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { - return __alloc_skb(size, priority, 0, -1); + return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { - return __alloc_skb(size, priority, 1, -1); + return __alloc_skb(size, priority, 1, NUMA_NO_NODE); } extern bool skb_recycle_check(struct sk_buff *skb, int skb_size); @@ -1563,13 +1563,25 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, return skb; } -extern struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask); +/** + * __netdev_alloc_page - allocate a page for ps-rx on a specific device + * @dev: network device to receive on + * @gfp_mask: alloc_pages_node mask + * + * Allocate a new page. dev currently unused. + * + * %NULL is returned if there is no free memory. + */ +static inline struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask) +{ + return alloc_pages_node(NUMA_NO_NODE, gfp_mask, 0); +} /** * netdev_alloc_page - allocate a page for ps-rx on a specific device * @dev: network device to receive on * - * Allocate a new page node local to the specified device. + * Allocate a new page. dev currently unused. * * %NULL is returned if there is no free memory. */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 752c1972b3a7..4e8b82e167d8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -247,10 +247,9 @@ EXPORT_SYMBOL(__alloc_skb); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask) { - int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1; struct sk_buff *skb; - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node); + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; @@ -259,16 +258,6 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, } EXPORT_SYMBOL(__netdev_alloc_skb); -struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask) -{ - int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1; - struct page *page; - - page = alloc_pages_node(node, gfp_mask, 0); - return page; -} -EXPORT_SYMBOL(__netdev_alloc_page); - void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size) {