haproxy/include/types/protocol.h

78 lines
3.2 KiB
C
Raw Normal View History

/*
* include/types/protocol.h
* This file defines the structures used by generic network protocols.
*
* Copyright (C) 2000-2012 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 _TYPES_PROTOCOL_H
#define _TYPES_PROTOCOL_H
#include <sys/types.h>
#include <sys/socket.h>
#include <common/config.h>
#include <common/mini-clist.h>
#include <eb32tree.h>
/* some pointer types referenced below */
struct listener;
struct connection;
/* max length of a protcol name, including trailing zero */
#define PROTO_NAME_LEN 16
/* This structure contains all information needed to easily handle a protocol.
* Its primary goal is to ease listeners maintenance. Specifically, the
* bind_all() primitive must be used before any fork(), and the enable_all()
* primitive must be called after the fork() to enable all fds. Last, the
* unbind_all() primitive closes all listeners.
*/
struct protocol {
char name[PROTO_NAME_LEN]; /* protocol name, zero-terminated */
int sock_domain; /* socket domain, as passed to socket() */
int sock_type; /* socket type, as passed to socket() */
int sock_prot; /* socket protocol, as passed to socket() */
sa_family_t sock_family; /* socket family, for sockaddr */
socklen_t sock_addrlen; /* socket address length, used by bind() */
int l3_addrlen; /* layer3 address length, used by hashes */
void (*accept)(int fd); /* generic accept function */
int (*bind)(struct listener *l, char *errmsg, int errlen); /* bind a listener */
int (*bind_all)(struct protocol *proto, char *errmsg, int errlen); /* bind all unbound listeners */
int (*unbind_all)(struct protocol *proto); /* unbind all bound listeners */
int (*enable_all)(struct protocol *proto); /* enable all bound listeners */
int (*disable_all)(struct protocol *proto); /* disable all bound listeners */
int (*connect)(struct connection *, int data, int delack); /* connect function if any */
int (*get_src)(int fd, struct sockaddr *, socklen_t, int dir); /* syscall used to retrieve src addr */
int (*get_dst)(int fd, struct sockaddr *, socklen_t, int dir); /* syscall used to retrieve dst addr */
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 13:56:38 -04:00
int (*drain)(int fd); /* indicates whether we can safely close the fd */
int (*pause)(struct listener *l); /* temporarily pause this listener for a soft restart */
struct list listeners; /* list of listeners using this protocol */
int nb_listeners; /* number of listeners */
struct list list; /* list of registered protocols */
};
#endif /* _TYPES_PROTOCOL_H */
/*
* Local variables:
* c-indent-level: 8
* c-basic-offset: 8
* End:
*/