summaryrefslogtreecommitdiffstats
path: root/include/net/sock.h
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2014-11-11 05:54:28 -0800
committerDavid S. Miller <davem@davemloft.net>2014-11-11 13:00:06 -0500
commit2c8c56e15df3d4c2af3d656e44feb18789f75837 (patch)
treee3c81c868a7c14ca2bac7efd69b6b21e25c355d4 /include/net/sock.h
parent3d97379a67486bc481ab5b8f7aa5b7ceb6154a95 (diff)
downloadop-kernel-dev-2c8c56e15df3d4c2af3d656e44feb18789f75837.zip
op-kernel-dev-2c8c56e15df3d4c2af3d656e44feb18789f75837.tar.gz
net: introduce SO_INCOMING_CPU
Alternative to RPS/RFS is to use hardware support for multiple queues. Then split a set of million of sockets into worker threads, each one using epoll() to manage events on its own socket pool. Ideally, we want one thread per RX/TX queue/cpu, but we have no way to know after accept() or connect() on which queue/cpu a socket is managed. We normally use one cpu per RX queue (IRQ smp_affinity being properly set), so remembering on socket structure which cpu delivered last packet is enough to solve the problem. After accept(), connect(), or even file descriptor passing around processes, applications can use : int cpu; socklen_t len = sizeof(cpu); getsockopt(fd, SOL_SOCKET, SO_INCOMING_CPU, &cpu, &len); And use this information to put the socket into the right silo for optimal performance, as all networking stack should run on the appropriate cpu, without need to send IPI (RPS/RFS). Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net/sock.h')
-rw-r--r--include/net/sock.h12
1 files changed, 12 insertions, 0 deletions
diff --git a/include/net/sock.h b/include/net/sock.h
index 6767d75..7789b59 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -273,6 +273,7 @@ struct cg_proto;
* @sk_rcvtimeo: %SO_RCVTIMEO setting
* @sk_sndtimeo: %SO_SNDTIMEO setting
* @sk_rxhash: flow hash received from netif layer
+ * @sk_incoming_cpu: record cpu processing incoming packets
* @sk_txhash: computed flow hash for use on transmit
* @sk_filter: socket filtering instructions
* @sk_protinfo: private area, net family specific, when not using slab
@@ -350,6 +351,12 @@ struct sock {
#ifdef CONFIG_RPS
__u32 sk_rxhash;
#endif
+ u16 sk_incoming_cpu;
+ /* 16bit hole
+ * Warned : sk_incoming_cpu can be set from softirq,
+ * Do not use this hole without fully understanding possible issues.
+ */
+
__u32 sk_txhash;
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sk_napi_id;
@@ -833,6 +840,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
return sk->sk_backlog_rcv(sk, skb);
}
+static inline void sk_incoming_cpu_update(struct sock *sk)
+{
+ sk->sk_incoming_cpu = raw_smp_processor_id();
+}
+
static inline void sock_rps_record_flow_hash(__u32 hash)
{
#ifdef CONFIG_RPS
OpenPOWER on IntegriCloud