haproxy/include/proto/proto_tcp.h

51 lines
1.7 KiB
C
Raw Normal View History

/*
* include/proto/proto_tcp.h
* This file contains TCP socket protocol definitions.
*
* Copyright (C) 2000-2013 Willy Tarreau - w@1wt.eu
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation, version 2.1
* exclusively.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef _PROTO_PROTO_TCP_H
#define _PROTO_PROTO_TCP_H
#include <common/config.h>
#include <types/action.h>
#include <types/task.h>
#include <proto/stick_table.h>
int tcp_bind_socket(int fd, int flags, struct sockaddr_storage *local, struct sockaddr_storage *remote);
void tcpv4_add_listener(struct listener *listener);
void tcpv6_add_listener(struct listener *listener);
int tcp_pause_listener(struct listener *l);
int tcp_connect_server(struct connection *conn, int data, int delack);
int tcp_connect_probe(struct connection *conn);
int tcp_get_src(int fd, struct sockaddr *sa, socklen_t salen, int dir);
int tcp_get_dst(int fd, struct sockaddr *sa, socklen_t salen, int dir);
MEDIUM: protocol: implement a "drain" function in protocol layers Since commit cfd97c6f was merged into 1.5-dev14 (BUG/MEDIUM: checks: prevent TIME_WAITs from appearing also on timeouts), some valid health checks sometimes used to show some TCP resets. For example, this HTTP health check sent to a local server : 19:55:15.742818 IP 127.0.0.1.16568 > 127.0.0.1.8000: S 3355859679:3355859679(0) win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7> 19:55:15.742841 IP 127.0.0.1.8000 > 127.0.0.1.16568: S 1060952566:1060952566(0) ack 3355859680 win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7> 19:55:15.742863 IP 127.0.0.1.16568 > 127.0.0.1.8000: . ack 1 win 257 19:55:15.745402 IP 127.0.0.1.16568 > 127.0.0.1.8000: P 1:23(22) ack 1 win 257 19:55:15.745488 IP 127.0.0.1.8000 > 127.0.0.1.16568: FP 1:146(145) ack 23 win 257 19:55:15.747109 IP 127.0.0.1.16568 > 127.0.0.1.8000: R 23:23(0) ack 147 win 257 After some discussion with Chris Huang-Leaver, it appeared clear that what we want is to only send the RST when we have no other choice, which means when the server has not closed. So we still keep SYN/SYN-ACK/RST for pure TCP checks, but don't want to see an RST emitted as above when the server has already sent the FIN. The solution against this consists in implementing a "drain" function at the protocol layer, which, when defined, causes as much as possible of the input socket buffer to be flushed to make recv() return zero so that we know that the server's FIN was received and ACKed. On Linux, we can make use of MSG_TRUNC on TCP sockets, which has the benefit of draining everything at once without even copying data. On other platforms, we read up to one buffer of data before the close. If recv() manages to get the final zero, we don't disable lingering. Same for hard errors. Otherwise we do. In practice, on HTTP health checks we generally find that the close was pending and is returned upon first recv() call. The network trace becomes cleaner : 19:55:23.650621 IP 127.0.0.1.16561 > 127.0.0.1.8000: S 3982804816:3982804816(0) win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7> 19:55:23.650644 IP 127.0.0.1.8000 > 127.0.0.1.16561: S 4082139313:4082139313(0) ack 3982804817 win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7> 19:55:23.650666 IP 127.0.0.1.16561 > 127.0.0.1.8000: . ack 1 win 257 19:55:23.651615 IP 127.0.0.1.16561 > 127.0.0.1.8000: P 1:23(22) ack 1 win 257 19:55:23.651696 IP 127.0.0.1.8000 > 127.0.0.1.16561: FP 1:146(145) ack 23 win 257 19:55:23.652628 IP 127.0.0.1.16561 > 127.0.0.1.8000: F 23:23(0) ack 147 win 257 19:55:23.652655 IP 127.0.0.1.8000 > 127.0.0.1.16561: . ack 24 win 257 This change should be backported to 1.4 which is where Chris encountered this issue. The code is different, so probably the tcp_drain() function will have to be put in the checks only.
2013-06-10 17:56:38 +00:00
int tcp_drain(int fd);
/* Export some samples. */
int smp_fetch_src(const struct arg *args, struct sample *smp, const char *kw, void *private);
#endif /* _PROTO_PROTO_TCP_H */
/*
* Local variables:
* c-indent-level: 8
* c-basic-offset: 8
* End:
*/