683043e200
If net.core.rmem_max and net.core.wmem_max sysctls have low values, we can get bigger buffers by not trying to set them high -- the kernel would lock their values to what we get. Try, instead, to get bigger buffers by queueing as much as possible, and if maximum values in tcp_wmem and tcp_rmem are bigger than this, that will work. While at it, drop QUICKACK option for non-spliced sockets, I set that earlier by mistake. Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
74 lines
2.5 KiB
C
74 lines
2.5 KiB
C
#ifndef TCP_H
|
|
#define TCP_H
|
|
|
|
#define TCP_TIMER_INTERVAL 20 /* ms */
|
|
|
|
#define TCP_MAX_CONNS (128 * 1024)
|
|
#define TCP_MAX_SOCKS (TCP_MAX_CONNS + USHRT_MAX * 2)
|
|
|
|
struct ctx;
|
|
|
|
void tcp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
|
|
struct timespec *now);
|
|
int tcp_tap_handler(struct ctx *c, int af, void *addr,
|
|
struct tap_l4_msg *msg, int count, struct timespec *now);
|
|
int tcp_sock_init(struct ctx *c, struct timespec *now);
|
|
void tcp_timer(struct ctx *c, struct timespec *ts);
|
|
void tcp_update_l2_buf(unsigned char *eth_d, unsigned char *eth_s,
|
|
uint32_t *ip_da);
|
|
void tcp_remap_to_tap(in_port_t port, in_port_t delta);
|
|
void tcp_remap_to_init(in_port_t port, in_port_t delta);
|
|
|
|
/**
|
|
* union tcp_epoll_ref - epoll reference portion for TCP connections
|
|
* @listen: Set if this file descriptor is a listening socket
|
|
* @splice: Set if descriptor is associated to a spliced connection
|
|
* @v6: Set for IPv6 sockets or connections
|
|
* @index: Index of connection in table, or port for bound sockets
|
|
* @u32: Opaque u32 value of reference
|
|
*/
|
|
union tcp_epoll_ref {
|
|
struct {
|
|
uint32_t listen:1,
|
|
splice:1,
|
|
v6:1,
|
|
index:20;
|
|
};
|
|
uint32_t u32;
|
|
};
|
|
|
|
/**
|
|
* struct tcp_ctx - Execution context for TCP routines
|
|
* @hash_secret: 128-bit secret for hash functions, ISN and hash table
|
|
* @tap_conn_count: Count of tap connections in connection table
|
|
* @splice_conn_count: Count of spliced connections in connection table
|
|
* @port_to_tap: Ports bound host-side, packets to tap or spliced
|
|
* @init_detect_ports: If set, periodically detect ports bound in init
|
|
* @port_to_init: Ports bound namespace-side, spliced to init
|
|
* @ns_detect_ports: If set, periodically detect ports bound in namespace
|
|
* @timer_run: Timestamp of most recent timer run
|
|
* @kernel_snd_wnd: Kernel reports sending window (with commit 8f7baad7f035)
|
|
* @pipe_size: Size of pipes for spliced connections
|
|
* @refill_ts: Time of last refill operation for pools of sockets/pipes
|
|
* @port_detect_ts: Time of last TCP port detection/rebind, if enabled
|
|
* @low_wmem: Low probed net.core.wmem_max
|
|
* @low_rmem: Low probed net.core.rmem_max
|
|
*/
|
|
struct tcp_ctx {
|
|
uint64_t hash_secret[2];
|
|
int tap_conn_count;
|
|
int splice_conn_count;
|
|
uint8_t port_to_tap [USHRT_MAX / 8];
|
|
int init_detect_ports;
|
|
uint8_t port_to_init [USHRT_MAX / 8];
|
|
int ns_detect_ports;
|
|
struct timespec timer_run;
|
|
int kernel_snd_wnd;
|
|
size_t pipe_size;
|
|
struct timespec refill_ts;
|
|
struct timespec port_detect_ts;
|
|
int low_wmem;
|
|
int low_rmem;
|
|
};
|
|
|
|
#endif /* TCP_H */
|