net: introduce SO_MAX_PACING_RATE
As mentioned in commit afe4fd0624
("pkt_sched: fq: Fair Queue packet
scheduler"), this patch adds a new socket option.
SO_MAX_PACING_RATE offers the application the ability to cap the
rate computed by transport layer. Value is in bytes per second.
u32 val = 1000000;
setsockopt(sockfd, SOL_SOCKET, SO_MAX_PACING_RATE, &val, sizeof(val));
To be effectively paced, a flow must use FQ packet scheduler.
Note that a packet scheduler takes into account the headers for its
computations. The effective payload rate depends on MSS and retransmits
if any.
I chose to make this pacing rate a SOL_SOCKET option instead of a
TCP one because this can be used by other protocols.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
parent
4aa0a03f51
commit
62748f32d5
|
@ -81,6 +81,8 @@
|
|||
|
||||
#define SO_SELECT_ERR_QUEUE 45
|
||||
|
||||
#define SO_BUSY_POLL 46
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _UAPI_ASM_SOCKET_H */
|
||||
|
|
|
@ -76,4 +76,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* __ASM_AVR32_SOCKET_H */
|
||||
|
|
|
@ -78,6 +78,8 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_SOCKET_H */
|
||||
|
||||
|
||||
|
|
|
@ -76,5 +76,7 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_SOCKET_H */
|
||||
|
||||
|
|
|
@ -76,4 +76,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_SOCKET_H */
|
||||
|
|
|
@ -85,4 +85,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_IA64_SOCKET_H */
|
||||
|
|
|
@ -76,4 +76,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_M32R_SOCKET_H */
|
||||
|
|
|
@ -94,4 +94,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _UAPI_ASM_SOCKET_H */
|
||||
|
|
|
@ -76,4 +76,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_SOCKET_H */
|
||||
|
|
|
@ -75,6 +75,8 @@
|
|||
|
||||
#define SO_BUSY_POLL 0x4027
|
||||
|
||||
#define SO_MAX_PACING_RATE 0x4048
|
||||
|
||||
/* O_NONBLOCK clashes with the bits used for socket types. Therefore we
|
||||
* have to define SOCK_NONBLOCK to a different value here.
|
||||
*/
|
||||
|
|
|
@ -83,4 +83,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_POWERPC_SOCKET_H */
|
||||
|
|
|
@ -82,4 +82,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _ASM_SOCKET_H */
|
||||
|
|
|
@ -72,6 +72,8 @@
|
|||
|
||||
#define SO_BUSY_POLL 0x0030
|
||||
|
||||
#define SO_MAX_PACING_RATE 0x0031
|
||||
|
||||
/* Security levels - as per NRL IPv6 - don't actually do anything */
|
||||
#define SO_SECURITY_AUTHENTICATION 0x5001
|
||||
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
|
||||
|
|
|
@ -87,4 +87,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* _XTENSA_SOCKET_H */
|
||||
|
|
|
@ -363,6 +363,7 @@ struct sock {
|
|||
int sk_wmem_queued;
|
||||
gfp_t sk_allocation;
|
||||
u32 sk_pacing_rate; /* bytes per second */
|
||||
u32 sk_max_pacing_rate;
|
||||
netdev_features_t sk_route_caps;
|
||||
netdev_features_t sk_route_nocaps;
|
||||
int sk_gso_type;
|
||||
|
|
|
@ -78,4 +78,6 @@
|
|||
|
||||
#define SO_BUSY_POLL 46
|
||||
|
||||
#define SO_MAX_PACING_RATE 47
|
||||
|
||||
#endif /* __ASM_GENERIC_SOCKET_H */
|
||||
|
|
|
@ -914,6 +914,13 @@ set_rcvbuf:
|
|||
}
|
||||
break;
|
||||
#endif
|
||||
|
||||
case SO_MAX_PACING_RATE:
|
||||
sk->sk_max_pacing_rate = val;
|
||||
sk->sk_pacing_rate = min(sk->sk_pacing_rate,
|
||||
sk->sk_max_pacing_rate);
|
||||
break;
|
||||
|
||||
default:
|
||||
ret = -ENOPROTOOPT;
|
||||
break;
|
||||
|
@ -1177,6 +1184,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
|
|||
break;
|
||||
#endif
|
||||
|
||||
case SO_MAX_PACING_RATE:
|
||||
v.val = sk->sk_max_pacing_rate;
|
||||
break;
|
||||
|
||||
default:
|
||||
return -ENOPROTOOPT;
|
||||
}
|
||||
|
@ -2319,6 +2330,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
|
|||
sk->sk_ll_usec = sysctl_net_busy_read;
|
||||
#endif
|
||||
|
||||
sk->sk_max_pacing_rate = ~0U;
|
||||
/*
|
||||
* Before updating sk_refcnt, we must commit prior changes to memory
|
||||
* (Documentation/RCU/rculist_nulls.txt for details)
|
||||
|
|
|
@ -735,7 +735,7 @@ static void tcp_update_pacing_rate(struct sock *sk)
|
|||
if (tp->srtt > 8 + 2)
|
||||
do_div(rate, tp->srtt);
|
||||
|
||||
sk->sk_pacing_rate = min_t(u64, rate, ~0U);
|
||||
sk->sk_pacing_rate = min_t(u64, rate, sk->sk_max_pacing_rate);
|
||||
}
|
||||
|
||||
/* Calculate rto without backoff. This is the second half of Van Jacobson's
|
||||
|
|
Loading…
Reference in New Issue