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 <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _UAPI_ASM_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _UAPI__ASM_AVR32_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _ASM_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _ASM_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _ASM_IA64_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _ASM_M32R_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _UAPI_ASM_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _ASM_SOCKET_H */
#define SO_BPF_EXTENSIONS 0x4029
+#define SO_INCOMING_CPU 0x402A
+
#endif /* _UAPI_ASM_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _ASM_POWERPC_SOCKET_H */
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _ASM_SOCKET_H */
#define SO_BPF_EXTENSIONS 0x0032
+#define SO_INCOMING_CPU 0x0033
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* _XTENSA_SOCKET_H */
* @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
#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;
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
#define SO_BPF_EXTENSIONS 48
+#define SO_INCOMING_CPU 49
+
#endif /* __ASM_GENERIC_SOCKET_H */
v.val = sk->sk_max_pacing_rate;
break;
+ case SO_INCOMING_CPU:
+ v.val = sk->sk_incoming_cpu;
+ break;
+
default:
return -ENOPROTOOPT;
}
newsk->sk_err = 0;
newsk->sk_priority = 0;
+ newsk->sk_incoming_cpu = raw_smp_processor_id();
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
if (sk_filter(sk, skb))
goto discard_and_relse;
+ sk_incoming_cpu_update(sk);
skb->dev = NULL;
bh_lock_sock_nested(sk);
if (inet_sk(sk)->inet_daddr) {
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
+ sk_incoming_cpu_update(sk);
}
rc = sock_queue_rcv_skb(sk, skb);
if (sk_filter(sk, skb))
goto discard_and_relse;
+ sk_incoming_cpu_update(sk);
skb->dev = NULL;
bh_lock_sock_nested(sk);
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
+ sk_incoming_cpu_update(sk);
}
rc = sock_queue_rcv_skb(sk, skb);
if (sock_flag(sk, SOCK_DEAD) || (sk->sk_shutdown & RCV_SHUTDOWN))
goto out_free;
- if (!sctp_ulpevent_is_notification(event))
+ if (!sctp_ulpevent_is_notification(event)) {
sk_mark_napi_id(sk, skb);
-
+ sk_incoming_cpu_update(sk);
+ }
/* Check if the user wishes to receive this event. */
if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
goto out_free;