From fec5e652e58fa6017b2c9e06466cb2a6538de5b4 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 16 Apr 2010 16:01:27 -0700 Subject: rfs: Receive Flow Steering This patch implements receive flow steering (RFS). RFS steers received packets for layer 3 and 4 processing to the CPU where the application for the corresponding flow is running. RFS is an extension of Receive Packet Steering (RPS). The basic idea of RFS is that when an application calls recvmsg (or sendmsg) the application's running CPU is stored in a hash table that is indexed by the connection's rxhash which is stored in the socket structure. The rxhash is passed in skb's received on the connection from netif_receive_skb. For each received packet, the associated rxhash is used to look up the CPU in the hash table, if a valid CPU is set then the packet is steered to that CPU using the RPS mechanisms. The convolution of the simple approach is that it would potentially allow OOO packets. If threads are thrashing around CPUs or multiple threads are trying to read from the same sockets, a quickly changing CPU value in the hash table could cause rampant OOO packets-- we consider this a non-starter. To avoid OOO packets, this solution implements two types of hash tables: rps_sock_flow_table and rps_dev_flow_table. rps_sock_table is a global hash table. Each entry is just a CPU number and it is populated in recvmsg and sendmsg as described above. This table contains the "desired" CPUs for flows. rps_dev_flow_table is specific to each device queue. Each entry contains a CPU and a tail queue counter. The CPU is the "current" CPU for a matching flow. The tail queue counter holds the value of a tail queue counter for the associated CPU's backlog queue at the time of last enqueue for a flow matching the entry. Each backlog queue has a queue head counter which is incremented on dequeue, and so a queue tail counter is computed as queue head count + queue length. When a packet is enqueued on a backlog queue, the current value of the queue tail counter is saved in the hash entry of the rps_dev_flow_table. And now the trick: when selecting the CPU for RPS (get_rps_cpu) the rps_sock_flow table and the rps_dev_flow table for the RX queue are consulted. When the desired CPU for the flow (found in the rps_sock_flow table) does not match the current CPU (found in the rps_dev_flow table), the current CPU is changed to the desired CPU if one of the following is true: - The current CPU is unset (equal to RPS_NO_CPU) - Current CPU is offline - The current CPU's queue head counter >= queue tail counter in the rps_dev_flow table. This checks if the queue tail has advanced beyond the last packet that was enqueued using this table entry. This guarantees that all packets queued using this entry have been dequeued, thus preserving in order delivery. Making each queue have its own rps_dev_flow table has two advantages: 1) the tail queue counters will be written on each receive, so keeping the table local to interrupting CPU s good for locality. 2) this allows lockless access to the table-- the CPU number and queue tail counter need to be accessed together under mutual exclusion from netif_receive_skb, we assume that this is only called from device napi_poll which is non-reentrant. This patch implements RFS for TCP and connected UDP sockets. It should be usable for other flow oriented protocols. There are two configuration parameters for RFS. The "rps_flow_entries" kernel init parameter sets the number of entries in the rps_sock_flow_table, the per rxqueue sysfs entry "rps_flow_cnt" contains the number of entries in the rps_dev_flow table for the rxqueue. Both are rounded to power of two. The obvious benefit of RFS (over just RPS) is that it achieves CPU locality between the receive processing for a flow and the applications processing; this can result in increased performance (higher pps, lower latency). The benefits of RFS are dependent on cache hierarchy, application load, and other factors. On simple benchmarks, we don't necessarily see improvement and sometimes see degradation. However, for more complex benchmarks and for applications where cache pressure is much higher this technique seems to perform very well. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. The RPC test is an request/response test similar in structure to netperf RR test ith 100 threads on each host, but does more work in userspace that netperf. e1000e on 8 core Intel No RFS or RPS 104K tps at 30% CPU No RFS (best RPS config): 290K tps at 63% CPU RFS 303K tps at 61% CPU RPC test tps CPU% 50/90/99% usec latency Latency StdDev No RFS/RPS 103K 48% 757/900/3185 4472.35 RPS only: 174K 73% 415/993/2468 491.66 RFS 223K 73% 379/651/1382 315.61 Signed-off-by: Tom Herbert Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 111 +++++++++++++++++++++++++++++++++++++-------- net/core/net-sysfs.c | 94 ++++++++++++++++++++++++++++++++++++-- net/core/sysctl_net_core.c | 68 +++++++++++++++++++++++++++ 3 files changed, 250 insertions(+), 23 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index e8041eb76ac..d7107ac835f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2203,19 +2203,28 @@ int weight_p __read_mostly = 64; /* old backlog weight */ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; #ifdef CONFIG_RPS + +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table *rps_sock_flow_table; +EXPORT_SYMBOL(rps_sock_flow_table); + /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ -static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow **rflowp) { struct ipv6hdr *ip6; struct iphdr *ip; struct netdev_rx_queue *rxqueue; struct rps_map *map; + struct rps_dev_flow_table *flow_table; + struct rps_sock_flow_table *sock_flow_table; int cpu = -1; u8 ip_proto; + u16 tcpu; u32 addr1, addr2, ports, ihl; if (skb_rx_queue_recorded(skb)) { @@ -2232,7 +2241,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) } else rxqueue = dev->_rx; - if (!rxqueue->rps_map) + if (!rxqueue->rps_map && !rxqueue->rps_flow_table) goto done; if (skb->rxhash) @@ -2284,9 +2293,48 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) skb->rxhash = 1; got_hash: + flow_table = rcu_dereference(rxqueue->rps_flow_table); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + if (flow_table && sock_flow_table) { + u16 next_cpu; + struct rps_dev_flow *rflow; + + rflow = &flow_table->flows[skb->rxhash & flow_table->mask]; + tcpu = rflow->cpu; + + next_cpu = sock_flow_table->ents[skb->rxhash & + sock_flow_table->mask]; + + /* + * If the desired CPU (where last recvmsg was done) is + * different from current CPU (one in the rx-queue flow + * table entry), switch if one of the following holds: + * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is offline. + * - The current CPU's queue tail has advanced beyond the + * last packet that was enqueued using this table entry. + * This guarantees that all previous packets for the flow + * have been dequeued, thus preserving in order delivery. + */ + if (unlikely(tcpu != next_cpu) && + (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + ((int)(per_cpu(softnet_data, tcpu).input_queue_head - + rflow->last_qtail)) >= 0)) { + tcpu = rflow->cpu = next_cpu; + if (tcpu != RPS_NO_CPU) + rflow->last_qtail = per_cpu(softnet_data, + tcpu).input_queue_head; + } + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + *rflowp = rflow; + cpu = tcpu; + goto done; + } + } + map = rcu_dereference(rxqueue->rps_map); if (map) { - u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; if (cpu_online(tcpu)) { cpu = tcpu; @@ -2320,13 +2368,14 @@ static void trigger_softirq(void *data) __napi_schedule(&queue->backlog); __get_cpu_var(netdev_rx_stat).received_rps++; } -#endif /* CONFIG_SMP */ +#endif /* CONFIG_RPS */ /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ -static int enqueue_to_backlog(struct sk_buff *skb, int cpu) +static int enqueue_to_backlog(struct sk_buff *skb, int cpu, + unsigned int *qtail) { struct softnet_data *queue; unsigned long flags; @@ -2341,6 +2390,10 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu) if (queue->input_pkt_queue.qlen) { enqueue: __skb_queue_tail(&queue->input_pkt_queue, skb); +#ifdef CONFIG_RPS + *qtail = queue->input_queue_head + + queue->input_pkt_queue.qlen; +#endif rps_unlock(queue); local_irq_restore(flags); return NET_RX_SUCCESS; @@ -2355,11 +2408,10 @@ enqueue: cpu_set(cpu, rcpus->mask[rcpus->select]); __raise_softirq_irqoff(NET_RX_SOFTIRQ); - } else - __napi_schedule(&queue->backlog); -#else - __napi_schedule(&queue->backlog); + goto enqueue; + } #endif + __napi_schedule(&queue->backlog); } goto enqueue; } @@ -2401,18 +2453,25 @@ int netif_rx(struct sk_buff *skb) #ifdef CONFIG_RPS { + struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); - cpu = get_rps_cpu(skb->dev, skb); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); - ret = enqueue_to_backlog(skb, cpu); + + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); } #else - ret = enqueue_to_backlog(skb, get_cpu()); - put_cpu(); + { + unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); + } #endif return ret; } @@ -2830,14 +2889,22 @@ out: int netif_receive_skb(struct sk_buff *skb) { #ifdef CONFIG_RPS - int cpu; + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu, ret; + + rcu_read_lock(); - cpu = get_rps_cpu(skb->dev, skb); + cpu = get_rps_cpu(skb->dev, skb, &rflow); - if (cpu < 0) - return __netif_receive_skb(skb); - else - return enqueue_to_backlog(skb, cpu); + if (cpu >= 0) { + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); + } else { + rcu_read_unlock(); + ret = __netif_receive_skb(skb); + } + + return ret; #else return __netif_receive_skb(skb); #endif @@ -2856,6 +2923,7 @@ static void flush_backlog(void *arg) if (skb->dev == dev) { __skb_unlink(skb, &queue->input_pkt_queue); kfree_skb(skb); + incr_input_queue_head(queue); } rps_unlock(queue); } @@ -3179,6 +3247,7 @@ static int process_backlog(struct napi_struct *napi, int quota) local_irq_enable(); break; } + incr_input_queue_head(queue); rps_unlock(queue); local_irq_enable(); @@ -5542,8 +5611,10 @@ static int dev_cpu_callback(struct notifier_block *nfb, local_irq_enable(); /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); + incr_input_queue_head(oldsd); + } return NOTIFY_OK; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 96ed6905b82..143052a22b9 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "net-sysfs.h" @@ -601,22 +602,109 @@ ssize_t store_rps_map(struct netdev_rx_queue *queue, return len; } +static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + char *buf) +{ + struct rps_dev_flow_table *flow_table; + unsigned int val = 0; + + rcu_read_lock(); + flow_table = rcu_dereference(queue->rps_flow_table); + if (flow_table) + val = flow_table->mask + 1; + rcu_read_unlock(); + + return sprintf(buf, "%u\n", val); +} + +static void rps_dev_flow_table_release_work(struct work_struct *work) +{ + struct rps_dev_flow_table *table = container_of(work, + struct rps_dev_flow_table, free_work); + + vfree(table); +} + +static void rps_dev_flow_table_release(struct rcu_head *rcu) +{ + struct rps_dev_flow_table *table = container_of(rcu, + struct rps_dev_flow_table, rcu); + + INIT_WORK(&table->free_work, rps_dev_flow_table_release_work); + schedule_work(&table->free_work); +} + +ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + const char *buf, size_t len) +{ + unsigned int count; + char *endp; + struct rps_dev_flow_table *table, *old_table; + static DEFINE_SPINLOCK(rps_dev_flow_lock); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + count = simple_strtoul(buf, &endp, 0); + if (endp == buf) + return -EINVAL; + + if (count) { + int i; + + if (count > 1<<30) { + /* Enforce a limit to prevent overflow */ + return -EINVAL; + } + count = roundup_pow_of_two(count); + table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); + if (!table) + return -ENOMEM; + + table->mask = count - 1; + for (i = 0; i < count; i++) + table->flows[i].cpu = RPS_NO_CPU; + } else + table = NULL; + + spin_lock(&rps_dev_flow_lock); + old_table = queue->rps_flow_table; + rcu_assign_pointer(queue->rps_flow_table, table); + spin_unlock(&rps_dev_flow_lock); + + if (old_table) + call_rcu(&old_table->rcu, rps_dev_flow_table_release); + + return len; +} + static struct rx_queue_attribute rps_cpus_attribute = __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); + +static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = + __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, + show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); + static struct attribute *rx_queue_default_attrs[] = { &rps_cpus_attribute.attr, + &rps_dev_flow_table_cnt_attribute.attr, NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); - struct rps_map *map = queue->rps_map; struct netdev_rx_queue *first = queue->first; - if (map) - call_rcu(&map->rcu, rps_map_release); + if (queue->rps_map) + call_rcu(&queue->rps_map->rcu, rps_map_release); + + if (queue->rps_flow_table) + call_rcu(&queue->rps_flow_table->rcu, + rps_dev_flow_table_release); if (atomic_dec_and_test(&first->count)) kfree(first); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b7b6b8208f7..dcc7d25996a 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -11,12 +11,72 @@ #include #include #include +#include #include #include #include #include +#ifdef CONFIG_RPS +static int rps_sock_flow_sysctl(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned int orig_size, size; + int ret, i; + ctl_table tmp = { + .data = &size, + .maxlen = sizeof(size), + .mode = table->mode + }; + struct rps_sock_flow_table *orig_sock_table, *sock_table; + static DEFINE_MUTEX(sock_flow_mutex); + + mutex_lock(&sock_flow_mutex); + + orig_sock_table = rps_sock_flow_table; + size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; + + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + + if (write) { + if (size) { + if (size > 1<<30) { + /* Enforce limit to prevent overflow */ + mutex_unlock(&sock_flow_mutex); + return -EINVAL; + } + size = roundup_pow_of_two(size); + if (size != orig_size) { + sock_table = + vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size)); + if (!sock_table) { + mutex_unlock(&sock_flow_mutex); + return -ENOMEM; + } + + sock_table->mask = size - 1; + } else + sock_table = orig_sock_table; + + for (i = 0; i < size; i++) + sock_table->ents[i] = RPS_NO_CPU; + } else + sock_table = NULL; + + if (sock_table != orig_sock_table) { + rcu_assign_pointer(rps_sock_flow_table, sock_table); + synchronize_rcu(); + vfree(orig_sock_table); + } + } + + mutex_unlock(&sock_flow_mutex); + + return ret; +} +#endif /* CONFIG_RPS */ + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -82,6 +142,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_RPS + { + .procname = "rps_sock_flow_entries", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = rps_sock_flow_sysctl + }, +#endif #endif /* CONFIG_NET */ { .procname = "netdev_budget", -- cgit v1.2.3-70-g09d2