[NET]: Eliminate netif_rx massive packet drops.

Eliminate the throttling behaviour when the netif receive queue fills
because it behaves badly when using high speed networks under load.
The throttling cause multiple packet drops that cause TCP to go into
slow start mode. The same effective patch has been part of BIC TCP and
H-TCP as well as part of Web100.

The existing code drops 100's of packets when the queue fills;
this changes it to individual packet drop-tail.

Signed-off-by: Stephen Hemmminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 718ad579c65ca8018e8e26a95810bd3513812c8c..3a0ed7f9e8015bb3165fb1e55eaf44493d9521e2 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -164,7 +164,6 @@ struct netif_rx_stats
        unsigned total;
        unsigned dropped;
        unsigned time_squeeze;
-       unsigned throttled;
        unsigned cpu_collision;
 };
 
@@ -557,10 +556,9 @@ static inline int unregister_gifconf(unsigned int family)
 
 struct softnet_data
 {
-       int                     throttle;
+       struct net_device       *output_queue;
        struct sk_buff_head     input_pkt_queue;
        struct list_head        poll_list;
-       struct net_device       *output_queue;
        struct sk_buff          *completion_queue;
 
        struct net_device       backlog_dev;    /* Sorry. 8) */

diff --git a/net/core/dev.c b/net/core/dev.c
index 3156df699f014569e208785901ab36d335f3b795..1a64508e527ffe8ea235302211c6c638d36fdcbb 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -198,7 +198,7 @@ static struct notifier_block *netdev_chain;
  *     Device drivers call our routines to queue packets here. We empty the
  *     queue in the local softnet handler.
  */
-DEFINE_PER_CPU(struct softnet_data, softnet_data) = { 0, };
+DEFINE_PER_CPU(struct softnet_data, softnet_data) = { NULL };
 
 #ifdef CONFIG_SYSFS
 extern int netdev_sysfs_init(void);
@@ -1372,7 +1372,6 @@ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
 
 int netif_rx(struct sk_buff *skb)
 {
-       int this_cpu;
        struct softnet_data *queue;
        unsigned long flags;
 
@@ -1388,15 +1387,11 @@ int netif_rx(struct sk_buff *skb)
         * short when CPU is congested, but is still operating.
         */
        local_irq_save(flags);
-       this_cpu = smp_processor_id();
        queue = &__get_cpu_var(softnet_data);
 
        __get_cpu_var(netdev_rx_stat).total++;
        if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
                if (queue->input_pkt_queue.qlen) {
-                       if (queue->throttle)
-                               goto drop;
-
 enqueue:
                        dev_hold(skb->dev);
                        __skb_queue_tail(&queue->input_pkt_queue, skb);
@@ -1404,19 +1399,10 @@ enqueue:
                        return NET_RX_SUCCESS;
                }
 
-               if (queue->throttle)
-                       queue->throttle = 0;
-
                netif_rx_schedule(&queue->backlog_dev);
                goto enqueue;
        }
 
-       if (!queue->throttle) {
-               queue->throttle = 1;
-               __get_cpu_var(netdev_rx_stat).throttled++;
-       }
-
-drop:
        __get_cpu_var(netdev_rx_stat).dropped++;
        local_irq_restore(flags);
 
@@ -1701,8 +1687,6 @@ job_done:
        smp_mb__before_clear_bit();
        netif_poll_enable(backlog_dev);
 
-       if (queue->throttle)
-               queue->throttle = 0;
        local_irq_enable();
        return 0;
 }
@@ -1976,7 +1960,7 @@ static int softnet_seq_show(struct seq_file *seq, void *v)
        struct netif_rx_stats *s = v;
 
        seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
-                  s->total, s->dropped, s->time_squeeze, s->throttled,
+                  s->total, s->dropped, s->time_squeeze, 0,
                   0, 0, 0, 0, /* was fastroute */
                   s->cpu_collision );
        return 0;
@@ -3220,7 +3204,6 @@ static int __init net_dev_init(void)
 
                queue = &per_cpu(softnet_data, i);
                skb_queue_head_init(&queue->input_pkt_queue);
-               queue->throttle = 0;
                queue->completion_queue = NULL;
                INIT_LIST_HEAD(&queue->poll_list);
                set_bit(__LINK_STATE_START, &queue->backlog_dev.state);