haproxy/src/haproxy.c

2112 lines
58 KiB
C
Raw Normal View History

/*
* HA-Proxy : High Availability-enabled HTTP/TCP proxy
[RELEASE] Released version 1.7-dev3 Released version 1.7-dev3 with the following main changes : - MINOR: sample: Moves ARGS underlying type from 32 to 64 bits. - BUG/MINOR: log: Don't use strftime() which can clobber timezone if chrooted - BUILD: namespaces: fix a potential build warning in namespaces.c - MINOR: da: Using ARG12 macro for the sample fetch and the convertor. - DOC: add encoding to json converter example - BUG/MINOR: conf: "listener id" expects integer, but its not checked - DOC: Clarify tunes.vars.xxx-max-size settings - CLEANUP: chunk: adding NULL check to chunk_dup allocation. - CLEANUP: connection: fix double negation on memcmp() - BUG/MEDIUM: peers: fix incorrect age in frequency counters - BUG/MEDIUM: Fix RFC5077 resumption when more than TLS_TICKETS_NO are present - BUG/MAJOR: Fix crash in http_get_fhdr with exactly MAX_HDR_HISTORY headers - BUG/MINOR: lua: can't load external libraries - BUG/MINOR: prevent the dump of uninitialized vars - CLEANUP: map: it seems that the map were planed to be chained - MINOR: lua: move class registration facilities - MINOR: lua: remove some useless checks - CLEANUP: lua: Remove two same functions - MINOR: lua: refactor the Lua object registration - MINOR: lua: precise message when a critical error is catched - MINOR: lua: post initialization - MINOR: lua: Add internal function which strip spaces - MINOR: lua: convert field to lua type - DOC: "addr" parameter applies to both health and agent checks - DOC: timeout client: pointers to timeout http-request - DOC: typo on stick-store response - DOC: stick-table: amend paragraph blaming the loss of table upon reload - DOC: typo: ACL subdir match - DOC: typo: maxconn paragraph is wrong due to a wrong buffer size - DOC: regsub: parser limitation about the inability to use closing square brackets - DOC: typo: req.uri is now replaced by capture.req.uri - DOC: name set-gpt0 mismatch with the expected keyword - MINOR: http: sample fetch which returns unique-id - MINOR: dumpstats: extract stats fields enum and names - MINOR: dumpstats: split stats_dump_info_to_buffer() in two parts - MINOR: dumpstats: split stats_dump_fe_stats() in two parts - MINOR: dumpstats: split stats_dump_li_stats() in two parts - MINOR: dumpstats: split stats_dump_sv_stats() in two parts - MINOR: dumpstats: split stats_dump_be_stats() in two parts - MINOR: lua: dump general info - MINOR: lua: add class proxy - MINOR: lua: add class server - MINOR: lua: add class listener - BUG/MEDIUM: stick-tables: some sample-fetch doesn't work in the connection state. - MEDIUM: proxy: use dynamic allocation for error dumps - CLEANUP: remove unneeded casts - CLEANUP: uniformize last argument of malloc/calloc - DOC: fix "needed" typo - BUG/MINOR: dumpstats: fix write to global chunk - BUG/MINOR: dns: inapropriate way out after a resolution timeout - BUG/MINOR: dns: trigger a DNS query type change on resolution timeout - CLEANUP: proto_http: few corrections for gcc warnings. - BUG/MINOR: DNS: resolution structure change - BUG/MINOR : allow to log cookie for tarpit and denied request - BUG/MEDIUM: ssl: rewind the BIO when reading certificates - OPTIM/MINOR: session: abort if possible before connecting to the backend - DOC: http: rename the unique-id sample and add the documentation - BUG/MEDIUM: trace.c: rdtsc() is defined in two files - BUG/MEDIUM: channel: fix miscalculation of available buffer space (2nd try) - BUG/MINOR: server: risk of over reading the pref_net array. - BUG/MINOR: cfgparse: couple of small memory leaks. - BUG/MEDIUM: sample: initialize the pointer before parse_binary call. - DOC: fix discrepancy in the example for http-request redirect - MINOR: acl: Add predefined METH_DELETE, METH_PUT - CLEANUP: .gitignore cleanup - DOC: Clarify IPv4 address / mask notation rules - CLEANUP: fix inconsistency between fd->iocb, proto->accept and accept() - BUG/MEDIUM: fix maxaccept computation on per-process listeners - BUG/MINOR: listener: stop unbound listeners on startup - BUG/MINOR: fix maxaccept computation according to the frontend process range - TESTS: add blocksig.c to run tests with all signals blocked - MEDIUM: unblock signals on startup. - MINOR: filters: Print the list of existing filters during HA startup - MINOR: filters: Typo in an error message - MINOR: filters: Filters must define the callbacks struct during config parsing - DOC: filters: Add filters documentation - BUG/MEDIUM: channel: don't allow to overwrite the reserve until connected - BUG/MEDIUM: channel: incorrect polling condition may delay event delivery - BUG/MEDIUM: channel: fix miscalculation of available buffer space (3rd try) - BUG/MEDIUM: log: fix risk of segfault when logging HTTP fields in TCP mode - MINOR: Add ability for agent-check to set server maxconn - CLEANUP: Use server_parse_maxconn_change_request for maxconn CLI updates - MINOR: filters: add opaque data - BUG/MEDIUM: lua: protects the upper boundary of the argument list for converters/fetches. - MINOR: lua: migrate the argument mask to 64 bits type. - BUG/MINOR: dumpstats: Fix the "Total bytes saved" counter in backends stats - BUG/MINOR: log: fix a typo that would cause %HP to log <BADREQ> - BUG/MEDIUM: http: fix incorrect reporting of server errors - MINOR: channel: add new function channel_congested() - BUG/MEDIUM: http: fix risk of CPU spikes with pipelined requests from dead client - BUG/MAJOR: channel: fix miscalculation of available buffer space (4th try) - BUG/MEDIUM: stream: ensure the SI_FL_DONT_WAKE flag is properly cleared - BUG/MEDIUM: channel: fix inconsistent handling of 4GB-1 transfers - BUG/MEDIUM: stats: show servers state may show an empty or incomplete result - BUG/MEDIUM: stats: show backend may show an empty or incomplete result - MINOR: stats: fix typo in help messages - MINOR: stats: show stat resolvers missing in the help message - BUG/MINOR: dns: fix DNS header definition - BUG/MEDIUM: dns: fix alignment issue when building DNS queries - CLEANUP: don't ignore scripts in .gitignore - BUILD: add a few release and backport scripts in scripts/
2016-05-10 09:36:58 -04:00
* Copyright 2000-2016 Willy Tarreau <willy@haproxy.org>.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Please refer to RFC2068 or RFC2616 for informations about HTTP protocol, and
* RFC2965 for informations about cookies usage. More generally, the IETF HTTP
* Working Group's web site should be consulted for protocol related changes :
*
* http://ftp.ics.uci.edu/pub/ietf/http/
*
* Pending bugs (may be not fixed because never reproduced) :
* - solaris only : sometimes, an HTTP proxy with only a dispatch address causes
* the proxy to terminate (no core) if the client breaks the connection during
* the response. Seen on 1.1.8pre4, but never reproduced. May not be related to
* the snprintf() bug since requests were simple (GET / HTTP/1.0), but may be
* related to missing setsid() (fixed in 1.1.15)
* - a proxy with an invalid config will prevent the startup even if disabled.
*
* ChangeLog has moved to the CHANGELOG file.
*
*/
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
#include <ctype.h>
#include <dirent.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/tcp.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <netdb.h>
#include <fcntl.h>
#include <errno.h>
#include <signal.h>
#include <stdarg.h>
#include <sys/resource.h>
#include <sys/wait.h>
#include <time.h>
#include <syslog.h>
#include <grp.h>
#ifdef USE_CPU_AFFINITY
#include <sched.h>
#ifdef __FreeBSD__
#include <sys/param.h>
#include <sys/cpuset.h>
#endif
#endif
#ifdef DEBUG_FULL
#include <assert.h>
#endif
#include <common/base64.h>
#include <common/cfgparse.h>
#include <common/chunk.h>
#include <common/compat.h>
#include <common/config.h>
#include <common/defaults.h>
#include <common/errors.h>
#include <common/memory.h>
#include <common/mini-clist.h>
MAJOR: namespace: add Linux network namespace support This patch makes it possible to create binds and servers in separate namespaces. This can be used to proxy between multiple completely independent virtual networks (with possibly overlapping IP addresses) and a non-namespace-aware proxy implementation that supports the proxy protocol (v2). The setup is something like this: net1 on VLAN 1 (namespace 1) -\ net2 on VLAN 2 (namespace 2) -- haproxy ==== proxy (namespace 0) net3 on VLAN 3 (namespace 3) -/ The proxy is configured to make server connections through haproxy and sending the expected source/target addresses to haproxy using the proxy protocol. The network namespace setup on the haproxy node is something like this: = 8< = $ cat setup.sh ip netns add 1 ip link add link eth1 type vlan id 1 ip link set eth1.1 netns 1 ip netns exec 1 ip addr add 192.168.91.2/24 dev eth1.1 ip netns exec 1 ip link set eth1.$id up ... = 8< = = 8< = $ cat haproxy.cfg frontend clients bind 127.0.0.1:50022 namespace 1 transparent default_backend scb backend server mode tcp server server1 192.168.122.4:2222 namespace 2 send-proxy-v2 = 8< = A bind line creates the listener in the specified namespace, and connections originating from that listener also have their network namespace set to that of the listener. A server line either forces the connection to be made in a specified namespace or may use the namespace from the client-side connection if that was set. For more documentation please read the documentation included in the patch itself. Signed-off-by: KOVACS Tamas <ktamas@balabit.com> Signed-off-by: Sarkozi Laszlo <laszlo.sarkozi@balabit.com> Signed-off-by: KOVACS Krisztian <hidden@balabit.com>
2014-11-17 09:11:45 -05:00
#include <common/namespace.h>
#include <common/regex.h>
#include <common/standard.h>
#include <common/time.h>
#include <common/uri_auth.h>
#include <common/version.h>
#include <types/capture.h>
#include <types/compression.h>
MAJOR: filters: Add filters support This patch adds the support of filters in HAProxy. The main idea is to have a way to "easely" extend HAProxy by adding some "modules", called filters, that will be able to change HAProxy behavior in a programmatic way. To do so, many entry points has been added in code to let filters to hook up to different steps of the processing. A filter must define a flt_ops sutrctures (see include/types/filters.h for details). This structure contains all available callbacks that a filter can define: struct flt_ops { /* * Callbacks to manage the filter lifecycle */ int (*init) (struct proxy *p); void (*deinit)(struct proxy *p); int (*check) (struct proxy *p); /* * Stream callbacks */ void (*stream_start) (struct stream *s); void (*stream_accept) (struct stream *s); void (*session_establish)(struct stream *s); void (*stream_stop) (struct stream *s); /* * HTTP callbacks */ int (*http_start) (struct stream *s, struct http_msg *msg); int (*http_start_body) (struct stream *s, struct http_msg *msg); int (*http_start_chunk) (struct stream *s, struct http_msg *msg); int (*http_data) (struct stream *s, struct http_msg *msg); int (*http_last_chunk) (struct stream *s, struct http_msg *msg); int (*http_end_chunk) (struct stream *s, struct http_msg *msg); int (*http_chunk_trailers)(struct stream *s, struct http_msg *msg); int (*http_end_body) (struct stream *s, struct http_msg *msg); void (*http_end) (struct stream *s, struct http_msg *msg); void (*http_reset) (struct stream *s, struct http_msg *msg); int (*http_pre_process) (struct stream *s, struct http_msg *msg); int (*http_post_process) (struct stream *s, struct http_msg *msg); void (*http_reply) (struct stream *s, short status, const struct chunk *msg); }; To declare and use a filter, in the configuration, the "filter" keyword must be used in a listener/frontend section: frontend test ... filter <FILTER-NAME> [OPTIONS...] The filter referenced by the <FILTER-NAME> must declare a configuration parser on its own name to fill flt_ops and filter_conf field in the proxy's structure. An exemple will be provided later to make it perfectly clear. For now, filters cannot be used in backend section. But this is only a matter of time. Documentation will also be added later. This is the first commit of a long list about filters. It is possible to have several filters on the same listener/frontend. These filters are stored in an array of at most MAX_FILTERS elements (define in include/types/filters.h). Again, this will be replaced later by a list of filters. The filter API has been highly refactored. Main changes are: * Now, HA supports an infinite number of filters per proxy. To do so, filters are stored in list. * Because filters are stored in list, filters state has been moved from the channel structure to the filter structure. This is cleaner because there is no more info about filters in channel structure. * It is possible to defined filters on backends only. For such filters, stream_start/stream_stop callbacks are not called. Of course, it is possible to mix frontend and backend filters. * Now, TCP streams are also filtered. All callbacks without the 'http_' prefix are called for all kind of streams. In addition, 2 new callbacks were added to filter data exchanged through a TCP stream: - tcp_data: it is called when new data are available or when old unprocessed data are still waiting. - tcp_forward_data: it is called when some data can be consumed. * New callbacks attached to channel were added: - channel_start_analyze: it is called when a filter is ready to process data exchanged through a channel. 2 new analyzers (a frontend and a backend) are attached to channels to call this callback. For a frontend filter, it is called before any other analyzer. For a backend filter, it is called when a backend is attached to a stream. So some processing cannot be filtered in that case. - channel_analyze: it is called before each analyzer attached to a channel, expects analyzers responsible for data sending. - channel_end_analyze: it is called when all other analyzers have finished their processing. A new analyzers is attached to channels to call this callback. For a TCP stream, this is always the last one called. For a HTTP one, the callback is called when a request/response ends, so it is called one time for each request/response. * 'session_established' callback has been removed. Everything that is done in this callback can be handled by 'channel_start_analyze' on the response channel. * 'http_pre_process' and 'http_post_process' callbacks have been replaced by 'channel_analyze'. * 'http_start' callback has been replaced by 'http_headers'. This new one is called just before headers sending and parsing of the body. * 'http_end' callback has been replaced by 'channel_end_analyze'. * It is possible to set a forwarder for TCP channels. It was already possible to do it for HTTP ones. * Forwarders can partially consumed forwardable data. For this reason a new HTTP message state was added before HTTP_MSG_DONE : HTTP_MSG_ENDING. Now all filters can define corresponding callbacks (http_forward_data and tcp_forward_data). Each filter owns 2 offsets relative to buf->p, next and forward, to track, respectively, input data already parsed but not forwarded yet by the filter and parsed data considered as forwarded by the filter. A any time, we have the warranty that a filter cannot parse or forward more input than previous ones. And, of course, it cannot forward more input than it has parsed. 2 macros has been added to retrieve these offets: FLT_NXT and FLT_FWD. In addition, 2 functions has been added to change the 'next size' and the 'forward size' of a filter. When a filter parses input data, it can alter these data, so the size of these data can vary. This action has an effet on all previous filters that must be handled. To do so, the function 'filter_change_next_size' must be called, passing the size variation. In the same spirit, if a filter alter forwarded data, it must call the function 'filter_change_forward_size'. 'filter_change_next_size' can be called in 'http_data' and 'tcp_data' callbacks and only these ones. And 'filter_change_forward_size' can be called in 'http_forward_data' and 'tcp_forward_data' callbacks and only these ones. The data changes are the filter responsability, but with some limitation. It must not change already parsed/forwarded data or data that previous filters have not parsed/forwarded yet. Because filters can be used on backends, when we the backend is set for a stream, we add filters defined for this backend in the filter list of the stream. But we must only do that when the backend and the frontend of the stream are not the same. Else same filters are added a second time leading to undefined behavior. The HTTP compression code had to be moved. So it simplifies http_response_forward_body function. To do so, the way the data are forwarded has changed. Now, a filter (and only one) can forward data. In a commit to come, this limitation will be removed to let all filters take part to data forwarding. There are 2 new functions that filters should use to deal with this feature: * flt_set_http_data_forwarder: This function sets the filter (using its id) that will forward data for the specified HTTP message. It is possible if it was not already set by another filter _AND_ if no data was yet forwarded (msg->msg_state <= HTTP_MSG_BODY). It returns -1 if an error occurs. * flt_http_data_forwarder: This function returns the filter id that will forward data for the specified HTTP message. If there is no forwarder set, it returns -1. When an HTTP data forwarder is set for the response, the HTTP compression is disabled. Of course, this is not definitive.
2015-04-30 05:48:27 -04:00
#include <types/filters.h>
#include <types/global.h>
#include <types/acl.h>
#include <types/peers.h>
#include <proto/acl.h>
#include <proto/applet.h>
#include <proto/arg.h>
#include <proto/auth.h>
#include <proto/backend.h>
#include <proto/channel.h>
#include <proto/checks.h>
#include <proto/connection.h>
#include <proto/fd.h>
MAJOR: filters: Add filters support This patch adds the support of filters in HAProxy. The main idea is to have a way to "easely" extend HAProxy by adding some "modules", called filters, that will be able to change HAProxy behavior in a programmatic way. To do so, many entry points has been added in code to let filters to hook up to different steps of the processing. A filter must define a flt_ops sutrctures (see include/types/filters.h for details). This structure contains all available callbacks that a filter can define: struct flt_ops { /* * Callbacks to manage the filter lifecycle */ int (*init) (struct proxy *p); void (*deinit)(struct proxy *p); int (*check) (struct proxy *p); /* * Stream callbacks */ void (*stream_start) (struct stream *s); void (*stream_accept) (struct stream *s); void (*session_establish)(struct stream *s); void (*stream_stop) (struct stream *s); /* * HTTP callbacks */ int (*http_start) (struct stream *s, struct http_msg *msg); int (*http_start_body) (struct stream *s, struct http_msg *msg); int (*http_start_chunk) (struct stream *s, struct http_msg *msg); int (*http_data) (struct stream *s, struct http_msg *msg); int (*http_last_chunk) (struct stream *s, struct http_msg *msg); int (*http_end_chunk) (struct stream *s, struct http_msg *msg); int (*http_chunk_trailers)(struct stream *s, struct http_msg *msg); int (*http_end_body) (struct stream *s, struct http_msg *msg); void (*http_end) (struct stream *s, struct http_msg *msg); void (*http_reset) (struct stream *s, struct http_msg *msg); int (*http_pre_process) (struct stream *s, struct http_msg *msg); int (*http_post_process) (struct stream *s, struct http_msg *msg); void (*http_reply) (struct stream *s, short status, const struct chunk *msg); }; To declare and use a filter, in the configuration, the "filter" keyword must be used in a listener/frontend section: frontend test ... filter <FILTER-NAME> [OPTIONS...] The filter referenced by the <FILTER-NAME> must declare a configuration parser on its own name to fill flt_ops and filter_conf field in the proxy's structure. An exemple will be provided later to make it perfectly clear. For now, filters cannot be used in backend section. But this is only a matter of time. Documentation will also be added later. This is the first commit of a long list about filters. It is possible to have several filters on the same listener/frontend. These filters are stored in an array of at most MAX_FILTERS elements (define in include/types/filters.h). Again, this will be replaced later by a list of filters. The filter API has been highly refactored. Main changes are: * Now, HA supports an infinite number of filters per proxy. To do so, filters are stored in list. * Because filters are stored in list, filters state has been moved from the channel structure to the filter structure. This is cleaner because there is no more info about filters in channel structure. * It is possible to defined filters on backends only. For such filters, stream_start/stream_stop callbacks are not called. Of course, it is possible to mix frontend and backend filters. * Now, TCP streams are also filtered. All callbacks without the 'http_' prefix are called for all kind of streams. In addition, 2 new callbacks were added to filter data exchanged through a TCP stream: - tcp_data: it is called when new data are available or when old unprocessed data are still waiting. - tcp_forward_data: it is called when some data can be consumed. * New callbacks attached to channel were added: - channel_start_analyze: it is called when a filter is ready to process data exchanged through a channel. 2 new analyzers (a frontend and a backend) are attached to channels to call this callback. For a frontend filter, it is called before any other analyzer. For a backend filter, it is called when a backend is attached to a stream. So some processing cannot be filtered in that case. - channel_analyze: it is called before each analyzer attached to a channel, expects analyzers responsible for data sending. - channel_end_analyze: it is called when all other analyzers have finished their processing. A new analyzers is attached to channels to call this callback. For a TCP stream, this is always the last one called. For a HTTP one, the callback is called when a request/response ends, so it is called one time for each request/response. * 'session_established' callback has been removed. Everything that is done in this callback can be handled by 'channel_start_analyze' on the response channel. * 'http_pre_process' and 'http_post_process' callbacks have been replaced by 'channel_analyze'. * 'http_start' callback has been replaced by 'http_headers'. This new one is called just before headers sending and parsing of the body. * 'http_end' callback has been replaced by 'channel_end_analyze'. * It is possible to set a forwarder for TCP channels. It was already possible to do it for HTTP ones. * Forwarders can partially consumed forwardable data. For this reason a new HTTP message state was added before HTTP_MSG_DONE : HTTP_MSG_ENDING. Now all filters can define corresponding callbacks (http_forward_data and tcp_forward_data). Each filter owns 2 offsets relative to buf->p, next and forward, to track, respectively, input data already parsed but not forwarded yet by the filter and parsed data considered as forwarded by the filter. A any time, we have the warranty that a filter cannot parse or forward more input than previous ones. And, of course, it cannot forward more input than it has parsed. 2 macros has been added to retrieve these offets: FLT_NXT and FLT_FWD. In addition, 2 functions has been added to change the 'next size' and the 'forward size' of a filter. When a filter parses input data, it can alter these data, so the size of these data can vary. This action has an effet on all previous filters that must be handled. To do so, the function 'filter_change_next_size' must be called, passing the size variation. In the same spirit, if a filter alter forwarded data, it must call the function 'filter_change_forward_size'. 'filter_change_next_size' can be called in 'http_data' and 'tcp_data' callbacks and only these ones. And 'filter_change_forward_size' can be called in 'http_forward_data' and 'tcp_forward_data' callbacks and only these ones. The data changes are the filter responsability, but with some limitation. It must not change already parsed/forwarded data or data that previous filters have not parsed/forwarded yet. Because filters can be used on backends, when we the backend is set for a stream, we add filters defined for this backend in the filter list of the stream. But we must only do that when the backend and the frontend of the stream are not the same. Else same filters are added a second time leading to undefined behavior. The HTTP compression code had to be moved. So it simplifies http_response_forward_body function. To do so, the way the data are forwarded has changed. Now, a filter (and only one) can forward data. In a commit to come, this limitation will be removed to let all filters take part to data forwarding. There are 2 new functions that filters should use to deal with this feature: * flt_set_http_data_forwarder: This function sets the filter (using its id) that will forward data for the specified HTTP message. It is possible if it was not already set by another filter _AND_ if no data was yet forwarded (msg->msg_state <= HTTP_MSG_BODY). It returns -1 if an error occurs. * flt_http_data_forwarder: This function returns the filter id that will forward data for the specified HTTP message. If there is no forwarder set, it returns -1. When an HTTP data forwarder is set for the response, the HTTP compression is disabled. Of course, this is not definitive.
2015-04-30 05:48:27 -04:00
#include <proto/filters.h>
#include <proto/hdr_idx.h>
#include <proto/hlua.h>
#include <proto/listener.h>
#include <proto/log.h>
#include <proto/pattern.h>
#include <proto/protocol.h>
#include <proto/proto_http.h>
#include <proto/proxy.h>
#include <proto/queue.h>
#include <proto/server.h>
#include <proto/session.h>
REORG/MAJOR: session: rename the "session" entity to "stream" With HTTP/2, we'll have to support multiplexed streams. A stream is in fact the largest part of what we currently call a session, it has buffers, logs, etc. In order to catch any error, this commit removes any reference to the struct session and tries to rename most "session" occurrences in function names to "stream" and "sess" to "strm" when that's related to a session. The files stream.{c,h} were added and session.{c,h} removed. The session will be reintroduced later and a few parts of the stream will progressively be moved overthere. It will more or less contain only what we need in an embryonic session. Sample fetch functions and converters will have to change a bit so that they'll use an L5 (session) instead of what's currently called "L4" which is in fact L6 for now. Once all changes are completed, we should see approximately this : L7 - http_txn L6 - stream L5 - session L4 - connection | applet There will be at most one http_txn per stream, and a same session will possibly be referenced by multiple streams. A connection will point to a session and to a stream. The session will hold all the information we need to keep even when we don't yet have a stream. Some more cleanup is needed because some code was already far from being clean. The server queue management still refers to sessions at many places while comments talk about connections. This will have to be cleaned up once we have a server-side connection pool manager. Stream flags "SN_*" still need to be renamed, it doesn't seem like any of them will need to move to the session.
2015-04-02 18:22:06 -04:00
#include <proto/stream.h>
#include <proto/signal.h>
#include <proto/task.h>
#include <proto/dns.h>
#include <proto/vars.h>
#ifdef USE_OPENSSL
#include <proto/ssl_sock.h>
#endif
#ifdef USE_WURFL
#include <proto/wurfl.h>
#endif
#ifdef USE_DEVICEATLAS
#include <import/da.h>
#endif
#ifdef USE_51DEGREES
#include <import/51d.h>
#endif
/*********************************************************************/
extern const struct comp_algo comp_algos[];
/*********************************************************************/
/* list of config files */
static struct list cfg_cfgfiles = LIST_HEAD_INIT(cfg_cfgfiles);
int pid; /* current process id */
2007-11-26 10:13:36 -05:00
int relative_pid = 1; /* process id starting at 1 */
/* global options */
struct global global = {
.nbproc = 1,
.req_count = 0,
.logsrvs = LIST_HEAD_INIT(global.logsrvs),
#if defined(USE_ZLIB) && defined(DEFAULT_MAXZLIBMEM)
.maxzlibmem = DEFAULT_MAXZLIBMEM * 1024U * 1024U,
#else
.maxzlibmem = 0,
#endif
.comp_rate_lim = 0,
.ssl_server_verify = SSL_SERVER_VERIFY_REQUIRED,
.unix_bind = {
.ux = {
.uid = -1,
.gid = -1,
.mode = 0,
}
},
.tune = {
.bufsize = BUFSIZE,
.maxrewrite = -1,
.chksize = BUFSIZE,
MAJOR: session: only wake up as many sessions as available buffers permit We've already experimented with three wake up algorithms when releasing buffers : the first naive one used to wake up far too many sessions, causing many of them not to get any buffer. The second approach which was still in use prior to this patch consisted in waking up either 1 or 2 sessions depending on the number of FDs we had released. And this was still inaccurate. The third one tried to cover the accuracy issues of the second and took into consideration the number of FDs the sessions would be willing to use, but most of the time we ended up waking up too many of them for nothing, or deadlocking by lack of buffers. This patch completely removes the need to allocate two buffers at once. Instead it splits allocations into critical and non-critical ones and implements a reserve in the pool for this. The deadlock situation happens when all buffers are be allocated for requests pending in a maxconn-limited server queue, because then there's no more way to allocate buffers for responses, and these responses are critical to release the servers's connection in order to release the pending requests. In fact maxconn on a server creates a dependence between sessions and particularly between oldest session's responses and latest session's requests. Thus, it is mandatory to get a free buffer for a response in order to release a server connection which will permit to release a request buffer. Since we definitely have non-symmetrical buffers, we need to implement this logic in the buffer allocation mechanism. What this commit does is implement a reserve of buffers which can only be allocated for responses and that will never be allocated for requests. This is made possible by the requester indicating how much margin it wants to leave after the allocation succeeds. Thus it is a cooperative allocation mechanism : the requester (process_session() in general) prefers not to get a buffer in order to respect other's need for response buffers. The session management code always knows if a buffer will be used for requests or responses, so that is not difficult : - either there's an applet on the initiator side and we really need the request buffer (since currently the applet is called in the context of the session) - or we have a connection and we really need the response buffer (in order to support building and sending an error message back) This reserve ensures that we don't take all allocatable buffers for requests waiting in a queue. The downside is that all the extra buffers are really allocated to ensure they can be allocated. But with small values it is not an issue. With this change, we don't observe any more deadlocks even when running with maxconn 1 on a server under severely constrained memory conditions. The code becomes a bit tricky, it relies on the scheduler's run queue to estimate how many sessions are already expected to run so that it doesn't wake up everyone with too few resources. A better solution would probably consist in having two queues, one for urgent requests and one for normal requests. A failed allocation for a session dealing with an error, a connection event, or the need for a response (or request when there's an applet on the left) would go to the urgent request queue, while other requests would go to the other queue. Urgent requests would be served from 1 entry in the pool, while the regular ones would be served only according to the reserve. Despite not yet having this, it works remarkably well. This mechanism is quite efficient, we don't perform too many wake up calls anymore. For 1 million sessions elapsed during massive memory contention, we observe about 4.5M calls to process_session() compared to 4.0M without memory constraints. Previously we used to observe up to 16M calls, which rougly means 12M failures. During a test run under high memory constraints (limit enforced to 27 MB instead of the 58 MB normally needed), performance used to drop by 53% prior to this patch. Now with this patch instead it *increases* by about 1.5%. The best effect of this change is that by limiting the memory usage to about 2/3 to 3/4 of what is needed by default, it's possible to increase performance by up to about 18% mainly due to the fact that pools are reused more often and remain hot in the CPU cache (observed on regular HTTP traffic with 20k objects, buffers.limit = maxconn/10, buffers.reserve = limit/2). Below is an example of scenario which used to cause a deadlock previously : - connection is received - two buffers are allocated in process_session() then released - one is allocated when receiving an HTTP request - the second buffer is allocated then released in process_session() for request parsing then connection establishment. - poll() says we can send, so the request buffer is sent and released - process session gets notified that the connection is now established and allocates two buffers then releases them - all other sessions do the same till one cannot get the request buffer without hitting the margin - and now the server responds. stream_interface allocates the response buffer and manages to get it since it's higher priority being for a response. - but process_session() cannot allocate the request buffer anymore => We could end up with all buffers used by responses so that none may be allocated for a request in process_session(). When the applet processing leaves the session context, the test will have to be changed so that we always allocate a response buffer regardless of the left side (eg: H2->H1 gateway). A final improvement would consists in being able to only retry the failed I/O operation without waking up a task, but to date all experiments to achieve this have proven not to be reliable enough.
2014-11-26 19:11:56 -05:00
.reserved_bufs = RESERVED_BUFS,
.pattern_cache = DEFAULT_PAT_LRU_SIZE,
#ifdef USE_OPENSSL
.sslcachesize = SSLCACHESIZE,
.ssl_default_dh_param = SSL_DEFAULT_DH_PARAM,
#ifdef DEFAULT_SSL_MAX_RECORD
.ssl_max_record = DEFAULT_SSL_MAX_RECORD,
#endif
.ssl_ctx_cache = DEFAULT_SSL_CTX_CACHE,
#endif
#ifdef USE_ZLIB
.zlibmemlevel = 8,
.zlibwindowsize = MAX_WBITS,
#endif
.comp_maxlevel = 1,
#ifdef DEFAULT_IDLE_TIMER
.idle_timer = DEFAULT_IDLE_TIMER,
#else
.idle_timer = 1000, /* 1 second */
#endif
},
#ifdef USE_OPENSSL
#ifdef DEFAULT_MAXSSLCONN
.maxsslconn = DEFAULT_MAXSSLCONN,
#endif
#endif
#ifdef USE_DEVICEATLAS
.deviceatlas = {
.loglevel = 0,
.jsonpath = 0,
.cookiename = 0,
.cookienamelen = 0,
.useragentid = 0,
.daset = 0,
.separator = '|',
},
#endif
#ifdef USE_51DEGREES
._51degrees = {
.property_separator = ',',
.property_names = LIST_HEAD_INIT(global._51degrees.property_names),
.data_file_path = NULL,
#ifdef FIFTYONEDEGREES_H_PATTERN_INCLUDED
.data_set = { },
#endif
.cache_size = 0,
},
#endif
#ifdef USE_WURFL
.wurfl = {
.data_file = NULL,
.cache_size = NULL,
.engine_mode = -1,
.useragent_priority = -1,
.information_list_separator = ',',
.information_list = LIST_HEAD_INIT(global.wurfl.information_list),
.patch_file_list = LIST_HEAD_INIT(global.wurfl.patch_file_list),
.handle = NULL,
},
#endif
/* others NULL OK */
};
/*********************************************************************/
int stopping; /* non zero means stopping in progress */
int jobs = 0; /* number of active jobs (conns, listeners, active tasks, ...) */
/* Here we store informations about the pids of the processes we may pause
* or kill. We will send them a signal every 10 ms until we can bind to all
* our ports. With 200 retries, that's about 2 seconds.
*/
#define MAX_START_RETRIES 200
static int *oldpids = NULL;
static int oldpids_sig; /* use USR1 or TERM */
/* this is used to drain data, and as a temporary buffer for sprintf()... */
struct chunk trash = { };
/* this buffer is always the same size as standard buffers and is used for
* swapping data inside a buffer.
*/
char *swap_buffer = NULL;
int nb_oldpids = 0;
const int zero = 0;
const int one = 1;
const struct linger nolinger = { .l_onoff = 1, .l_linger = 0 };
char hostname[MAX_HOSTNAME_LEN];
char localpeer[MAX_HOSTNAME_LEN];
/* used from everywhere just to drain results we don't want to read and which
* recent versions of gcc increasingly and annoyingly complain about.
*/
int shut_your_big_mouth_gcc_int = 0;
/* list of the temporarily limited listeners because of lack of resource */
struct list global_listener_queue = LIST_HEAD_INIT(global_listener_queue);
struct task *global_listener_queue_task;
static struct task *manage_global_listener_queue(struct task *t);
/* bitfield of a few warnings to emit just once (WARN_*) */
unsigned int warned = 0;
/*********************************************************************/
/* general purpose functions ***************************************/
/*********************************************************************/
void display_version()
{
printf("HA-Proxy version " HAPROXY_VERSION " " HAPROXY_DATE"\n");
[RELEASE] Released version 1.7-dev2 Released version 1.7-dev2 with the following main changes : - DOC: lua: fix lua API - DOC: mailers: typo in 'hostname' description - DOC: compression: missing mention of libslz for compression algorithm - BUILD/MINOR: regex: missing header - BUG/MINOR: stream: bad return code - DOC: lua: fix somme errors and add implicit types - MINOR: lua: add set/get priv for applets - BUG/MINOR: http: fix several off-by-one errors in the url_param parser - BUG/MINOR: http: Be sure to process all the data received from a server - MINOR: filters/http: Use a wrapper function instead of stream_int_retnclose - BUG/MINOR: chunk: make chunk_dup() always check and set dst->size - DOC: ssl: fixed some formatting errors in crt tag - MINOR: chunks: ensure that chunk_strcpy() adds a trailing zero - MINOR: chunks: add chunk_strcat() and chunk_newstr() - MINOR: chunk: make chunk_initstr() take a const string - MEDIUM: tools: add csv_enc_append() to preserve the original chunk - MINOR: tools: make csv_enc_append() always start at the first byte of the chunk - MINOR: lru: new function to delete <nb> least recently used keys - DOC: add Ben Shillito as the maintainer of 51d - BUG/MINOR: 51d: Ensures a unique domain for each configuration - BUG/MINOR: 51d: Aligns Pattern cache implementation with HAProxy best practices. - BUG/MINOR: 51d: Releases workset back to pool. - BUG/MINOR: 51d: Aligned const pointers to changes in 51Degrees. - CLEANUP: 51d: Aligned if statements with HAProxy best practices and removed casts from malloc. - MINOR: rename master process name in -Ds (systemd mode) - DOC: fix a few spelling mistakes - DOC: fix "workaround" spelling - BUG/MINOR: examples: Fixing haproxy.spec to remove references to .cfg files - MINOR: fix the return type for dns_response_get_query_id() function - MINOR: server state: missing LF (\n) on error message printed when parsing server state file - BUG/MEDIUM: dns: no DNS resolution happens if no ports provided to the nameserver - BUG/MAJOR: servers state: server port is erased when dns resolution is enabled on a server - BUG/MEDIUM: servers state: server port is used uninitialized - BUG/MEDIUM: config: Adding validation to stick-table expire value. - BUG/MEDIUM: sample: http_date() doesn't provide the right day of the week - BUG/MEDIUM: channel: fix miscalculation of available buffer space. - MEDIUM: pools: add a new flag to avoid rounding pool size up - BUG/MEDIUM: buffers: do not round up buffer size during allocation - BUG/MINOR: stream: don't force retries if the server is DOWN - BUG/MINOR: counters: make the sc-inc-gpc0 and sc-set-gpt0 touch the table - MINOR: unix: don't mention free ports on EAGAIN - BUG/CLEANUP: CLI: report the proper field states in "show sess" - MINOR: stats: send content-length with the redirect to allow keep-alive - BUG: stream_interface: Reuse connection even if the output channel is empty - DOC: remove old tunnel mode assumptions - BUG/MAJOR: http-reuse: fix risk of orphaned connections - BUG/MEDIUM: http-reuse: do not share private connections across backends - BUG/MINOR: ssl: Be sure to use unique serial for regenerated certificates - BUG/MINOR: stats: fix missing comma in stats on agent drain - MAJOR: filters: Add filters support - MINOR: filters: Do not reset stream analyzers if the client is gone - REORG: filters: Prepare creation of the HTTP compression filter - MAJOR: filters/http: Rewrite the HTTP compression as a filter - MEDIUM: filters: Use macros to call filters callbacks to speed-up processing - MEDIUM: filters: remove http_start_chunk, http_last_chunk and http_chunk_end - MEDIUM: filters: Replace filter_http_headers callback by an analyzer - MEDIUM: filters/http: Move body parsing of HTTP messages in dedicated functions - MINOR: filters: Add stream_filters structure to hide filters info - MAJOR: filters: Require explicit registration to filter HTTP body and TCP data - MINOR: filters: Remove unused or useless stuff and do small optimizations - MEDIUM: filters: Optimize the HTTP compression for chunk encoded response - MINOR: filters/http: Slightly update the parsing of chunks - MINOR: filters/http: Forward remaining data when a channel has no "data" filters - MINOR: filters: Add an filter example - MINOR: filters: Extract proxy stuff from the struct filter - MINOR: map: Add regex matching replacement - BUG/MINOR: lua: unsafe initialization - DOC: lua: fix somme errors - MINOR: lua: file dedicated to unsafe functions - MINOR: lua: add "now" time function - MINOR: standard: add RFC HTTP date parser - MINOR: lua: Add date functions - MINOR: lua: move common function - MINOR: lua: merge function - MINOR: lua: Add concat class - MINOR: standard: add function "escape_chunk" - MEDIUM: log: add a new log format flag "E" - DOC: add server name at rate-limit sessions example - BUG/MEDIUM: ssl: fix off-by-one in ALPN list allocation - BUG/MEDIUM: ssl: fix off-by-one in NPN list allocation - DOC: LUA: fix some typos and syntax errors - MINOR: cli: add a new "show env" command - MEDIUM: config: allow to manipulate environment variables in the global section - MEDIUM: cfgparse: reject incorrect 'timeout retry' keyword spelling in resolvers - MINOR: mailers: increase default timeout to 10 seconds - MINOR: mailers: use <CRLF> for all line endings - BUG/MAJOR: lua: segfault using Concat object - DOC: lua: copyrights - MINOR: common: mask conversion - MEDIUM: dns: extract options - MEDIUM: dns: add a "resolve-net" option which allow to prefer an ip in a network - MINOR: mailers: make it possible to configure the connection timeout - BUG/MAJOR: lua: applets can't sleep. - BUG/MINOR: server: some prototypes are renamed - BUG/MINOR: lua: Useless copy - BUG/MEDIUM: stats: stats bind-process doesn't propagate the process mask correctly - BUG/MINOR: server: fix the format of the warning on address change - CLEANUP: server: add "const" to some message strings - MINOR: server: generalize the "updater" source - BUG/MEDIUM: chunks: always reject negative-length chunks - BUG/MINOR: systemd: ensure we don't miss signals - BUG/MINOR: systemd: report the correct signal in debug message output - BUG/MINOR: systemd: propagate the correct signal to haproxy - MINOR: systemd: ensure a reload doesn't mask a stop - BUG/MEDIUM: cfgparse: wrong argument offset after parsing server "sni" keyword - CLEANUP: stats: Avoid computation with uninitialized bits. - CLEANUP: pattern: Ignore unknown samples in pat_match_ip(). - CLEANUP: map: Avoid memory leak in out-of-memory condition. - BUG/MINOR: tcpcheck: fix incorrect list usage resulting in failure to load certain configs - BUG/MAJOR: samples: check smp->strm before using it - MINOR: sample: add a new helper to initialize the owner of a sample - MINOR: sample: always set a new sample's owner before evaluating it - BUG/MAJOR: vars: always retrieve the stream and session from the sample - CLEANUP: payload: remove useless and confusing nullity checks for channel buffer - BUG/MINOR: ssl: fix usage of the various sample fetch functions - MINOR: stats: create fields types suitable for all CSV output data - MINOR: stats: add all the "show info" fields in a table - MEDIUM: stats: fill all the show info elements prior to displaying them - MINOR: stats: add a function to emit fields into a chunk - MINOR: stats: add stats_dump_info_fields() to dump one field per line - MEDIUM: stats: make use of stats_dump_info_fields() for "show info" - MINOR: stats: add a declaration of all stats fields - MINOR: stats: don't hard-code the CSV fields list anymore - MINOR: stats: create stats fields storage and CSV dump function - MEDIUM: stats: convert stats_dump_fe_stats() to use stats_dump_fields_csv() - MEDIUM: stats: make stats_dump_fe_stats() use stats fields for HTML dump - MEDIUM: stats: convert stats_dump_li_stats() to use stats_dump_fields_csv() - MEDIUM: stats: make stats_dump_li_stats() use stats fields for HTML dump - MEDIUM: stats: convert stats_dump_be_stats() to use stats_dump_fields_csv() - MEDIUM: stats: make stats_dump_be_stats() use stats fields for HTML dump - MEDIUM: stats: convert stats_dump_sv_stats() to use stats_dump_fields_csv() - MEDIUM: stats: make stats_dump_sv_stats() use the stats field for HTML - MEDIUM: stats: move the server state coloring logic to the server dump function - MINOR: stats: do not use srv->admin & STATS_ADMF_MAINT in HTML dumps - MINOR: stats: do not check srv->state for SRV_ST_STOPPED in HTML dumps - MINOR: stats: make CSV report server check status only when enabled - MINOR: stats: only report backend's down time if it has servers - MINOR: stats: prepend '*' in front of the check status when in progress - MINOR: stats: make HTML stats dump rely on the table for the check status - MINOR: stats: add agent_status, agent_code, agent_duration to output - MINOR: stats: add check_desc and agent_desc to the output fields - MINOR: stats: add check and agent's health values in the output - MEDIUM: stats: make the HTML server state dump use the CSV states - MEDIUM: stats: only report observe errors when observe is set - MEDIUM: stats: expose the same flags for CLI and HTTP accesses - MEDIUM: stats: report server's address in the CSV output - MEDIUM: stats: report the cookie value in the server & backend CSV dumps - MEDIUM: stats: compute the color code only in the HTML form - MEDIUM: stats: report the listeners' address in the CSV output - MEDIUM: stats: make it possible to report the WAITING state for listeners - REORG: stats: dump the frontend's HTML stats via a generic function - REORG: stats: dump the socket stats via the generic function - REORG: stats: dump the server stats via the generic function - REORG: stats: dump the backend stats via the generic function - MEDIUM: stats: add a new "mode" column to report the proxy mode - MINOR: stats: report the load balancing algorithm in CSV output - MINOR: stats: add 3 fields to report the frontend-specific connection stats - MINOR: stats: report number of intercepted requests for frontend and backends - MINOR: stats: introduce stats_dump_one_line() to dump one stats line - CLEANUP: stats: make stats_dump_fields_html() not rely on proxy anymore - MINOR: stats: add ST_SHOWADMIN to pass the admin info in the regular flags - MINOR: stats: make stats_dump_fields_html() not use &trash by default - MINOR: stats: add functions to emit typed fields into a chunk - MEDIUM: stats: support "show info typed" on the CLI - MEDIUM: stats: implement a typed output format for stats - DOC: document the "show info typed" and "show stat typed" output formats - MINOR: cfgparse: warn when uid parameter is not a number - MINOR: cfgparse: warn when gid parameter is not a number - BUG/MINOR: standard: Avoid free of non-allocated pointer - BUG/MINOR: pattern: Avoid memory leak on out-of-memory condition - CLEANUP: http: fix a build warning introduced by a recent fix - BUG/MINOR: log: GMT offset not updated when entering/leaving DST
2016-03-13 19:10:05 -04:00
printf("Copyright 2000-2016 Willy Tarreau <willy@haproxy.org>\n\n");
}
void display_build_opts()
{
printf("Build options :"
#ifdef BUILD_TARGET
"\n TARGET = " BUILD_TARGET
#endif
#ifdef BUILD_CPU
"\n CPU = " BUILD_CPU
#endif
#ifdef BUILD_CC
"\n CC = " BUILD_CC
#endif
#ifdef BUILD_CFLAGS
"\n CFLAGS = " BUILD_CFLAGS
#endif
#ifdef BUILD_OPTIONS
"\n OPTIONS = " BUILD_OPTIONS
#endif
"\n\nDefault settings :"
"\n maxconn = %d, bufsize = %d, maxrewrite = %d, maxpollevents = %d"
"\n\n",
DEFAULT_MAXCONN, BUFSIZE, MAXREWRITE, MAX_POLL_EVENTS);
printf("Encrypted password support via crypt(3): "
#ifdef CONFIG_HAP_CRYPT
"yes"
#else
"no"
#endif
"\n");
#ifdef USE_ZLIB
printf("Built with zlib version : " ZLIB_VERSION "\n");
2016-09-12 17:42:14 -04:00
printf("Running on zlib version : %s\n", zlibVersion());
#elif defined(USE_SLZ)
printf("Built with libslz for stateless compression.\n");
#else /* USE_ZLIB */
printf("Built without compression support (neither USE_ZLIB nor USE_SLZ are set)\n");
#endif
printf("Compression algorithms supported :");
{
int i;
for (i = 0; comp_algos[i].cfg_name; i++) {
printf("%s %s(\"%s\")", (i == 0 ? "" : ","), comp_algos[i].cfg_name, comp_algos[i].ua_name);
}
if (i == 0) {
printf("none");
}
}
printf("\n");
#ifdef USE_OPENSSL
printf("Built with OpenSSL version : "
#ifdef OPENSSL_IS_BORINGSSL
"BoringSSL\n");
#else /* OPENSSL_IS_BORINGSSL */
OPENSSL_VERSION_TEXT "\n");
printf("Running on OpenSSL version : %s%s\n",
SSLeay_version(SSLEAY_VERSION),
((OPENSSL_VERSION_NUMBER ^ SSLeay()) >> 8) ? " (VERSIONS DIFFER!)" : "");
#endif
printf("OpenSSL library supports TLS extensions : "
#if OPENSSL_VERSION_NUMBER < 0x00907000L
"no (library version too old)"
#elif defined(OPENSSL_NO_TLSEXT)
"no (disabled via OPENSSL_NO_TLSEXT)"
#else
"yes"
#endif
"\n");
printf("OpenSSL library supports SNI : "
#ifdef SSL_CTRL_SET_TLSEXT_HOSTNAME
"yes"
#else
#ifdef OPENSSL_NO_TLSEXT
"no (because of OPENSSL_NO_TLSEXT)"
#else
"no (version might be too old, 0.9.8f min needed)"
#endif
#endif
"\n");
printf("OpenSSL library supports prefer-server-ciphers : "
#ifdef SSL_OP_CIPHER_SERVER_PREFERENCE
"yes"
#else
"no (0.9.7 or later needed)"
#endif
"\n");
#else /* USE_OPENSSL */
printf("Built without OpenSSL support (USE_OPENSSL not set)\n");
#endif
#ifdef USE_PCRE
printf("Built with PCRE version : %s\n", (HAP_XSTRING(Z PCRE_PRERELEASE)[1] == 0)?
HAP_XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) :
HAP_XSTRING(PCRE_MAJOR.PCRE_MINOR) HAP_XSTRING(PCRE_PRERELEASE PCRE_DATE));
printf("Running on PCRE version : %s", pcre_version());
printf("\nPCRE library supports JIT : ");
#ifdef USE_PCRE_JIT
{
int r;
pcre_config(PCRE_CONFIG_JIT, &r);
if (r)
printf("yes");
else
printf("no (libpcre build without JIT?)");
}
#else
printf("no (USE_PCRE_JIT not set)");
#endif
printf("\n");
#else
printf("Built without PCRE support (using libc's regex instead)\n");
#endif
#ifdef USE_LUA
printf("Built with Lua version : %s\n", LUA_RELEASE);
#else
printf("Built without Lua support\n");
#endif
#if defined(CONFIG_HAP_TRANSPARENT)
printf("Built with transparent proxy support using:"
#if defined(IP_TRANSPARENT)
" IP_TRANSPARENT"
#endif
#if defined(IPV6_TRANSPARENT)
" IPV6_TRANSPARENT"
#endif
#if defined(IP_FREEBIND)
" IP_FREEBIND"
#endif
#if defined(IP_BINDANY)
" IP_BINDANY"
#endif
#if defined(IPV6_BINDANY)
" IPV6_BINDANY"
#endif
#if defined(SO_BINDANY)
" SO_BINDANY"
#endif
"\n");
#endif
MAJOR: namespace: add Linux network namespace support This patch makes it possible to create binds and servers in separate namespaces. This can be used to proxy between multiple completely independent virtual networks (with possibly overlapping IP addresses) and a non-namespace-aware proxy implementation that supports the proxy protocol (v2). The setup is something like this: net1 on VLAN 1 (namespace 1) -\ net2 on VLAN 2 (namespace 2) -- haproxy ==== proxy (namespace 0) net3 on VLAN 3 (namespace 3) -/ The proxy is configured to make server connections through haproxy and sending the expected source/target addresses to haproxy using the proxy protocol. The network namespace setup on the haproxy node is something like this: = 8< = $ cat setup.sh ip netns add 1 ip link add link eth1 type vlan id 1 ip link set eth1.1 netns 1 ip netns exec 1 ip addr add 192.168.91.2/24 dev eth1.1 ip netns exec 1 ip link set eth1.$id up ... = 8< = = 8< = $ cat haproxy.cfg frontend clients bind 127.0.0.1:50022 namespace 1 transparent default_backend scb backend server mode tcp server server1 192.168.122.4:2222 namespace 2 send-proxy-v2 = 8< = A bind line creates the listener in the specified namespace, and connections originating from that listener also have their network namespace set to that of the listener. A server line either forces the connection to be made in a specified namespace or may use the namespace from the client-side connection if that was set. For more documentation please read the documentation included in the patch itself. Signed-off-by: KOVACS Tamas <ktamas@balabit.com> Signed-off-by: Sarkozi Laszlo <laszlo.sarkozi@balabit.com> Signed-off-by: KOVACS Krisztian <hidden@balabit.com>
2014-11-17 09:11:45 -05:00
#if defined(CONFIG_HAP_NS)
printf("Built with network namespace support\n");
#endif
#ifdef USE_DEVICEATLAS
printf("Built with DeviceAtlas support\n");
#endif
#ifdef USE_51DEGREES
printf("Built with 51Degrees support\n");
#endif
#ifdef USE_WURFL
printf("Built with WURFL support\n");
#endif
putchar('\n');
list_pollers(stdout);
putchar('\n');
list_filters(stdout);
putchar('\n');
}
/*
* This function prints the command line usage and exits
*/
void usage(char *name)
{
display_version();
fprintf(stderr,
"Usage : %s [-f <cfgfile|cfgdir>]* [ -vdV"
"D ] [ -n <maxconn> ] [ -N <maxpconn> ]\n"
" [ -p <pidfile> ] [ -m <max megs> ] [ -C <dir> ] [-- <cfgfile>*]\n"
" -v displays version ; -vv shows known build options.\n"
" -d enters debug mode ; -db only disables background mode.\n"
" -dM[<byte>] poisons memory with <byte> (defaults to 0x50)\n"
" -V enters verbose mode (disables quiet mode)\n"
" -D goes daemon ; -C changes to <dir> before loading files.\n"
" -q quiet mode : don't display messages\n"
" -c check mode : only check config files and exit\n"
" -n sets the maximum total # of connections (%d)\n"
" -m limits the usable amount of memory (in MB)\n"
" -N sets the default, per-proxy maximum # of connections (%d)\n"
" -L set local peer name (default to hostname)\n"
" -p writes pids of all children to this file\n"
#if defined(ENABLE_EPOLL)
" -de disables epoll() usage even when available\n"
#endif
#if defined(ENABLE_KQUEUE)
" -dk disables kqueue() usage even when available\n"
#endif
#if defined(ENABLE_POLL)
" -dp disables poll() usage even when available\n"
#endif
#if defined(CONFIG_HAP_LINUX_SPLICE)
" -dS disables splice usage (broken on old kernels)\n"
#endif
#if defined(USE_GETADDRINFO)
" -dG disables getaddrinfo() usage\n"
#endif
#if defined(SO_REUSEPORT)
" -dR disables SO_REUSEPORT usage\n"
#endif
" -dr ignores server address resolution failures\n"
" -dV disables SSL verify on servers side\n"
" -sf/-st [pid ]* finishes/terminates old pids.\n"
"\n",
name, DEFAULT_MAXCONN, cfg_maxpconn);
exit(1);
}
/*********************************************************************/
/* more specific functions ***************************************/
/*********************************************************************/
/*
* upon SIGUSR1, let's have a soft stop. Note that soft_stop() broadcasts
* a signal zero to all subscribers. This means that it's as easy as
* subscribing to signal 0 to get informed about an imminent shutdown.
*/
void sig_soft_stop(struct sig_handler *sh)
{
soft_stop();
signal_unregister_handler(sh);
pool_gc2();
}
/*
* upon SIGTTOU, we pause everything
*/
void sig_pause(struct sig_handler *sh)
{
pause_proxies();
pool_gc2();
}
/*
* upon SIGTTIN, let's have a soft stop.
*/
void sig_listen(struct sig_handler *sh)
{
resume_proxies();
}
/*
* this function dumps every server's state when the process receives SIGHUP.
*/
void sig_dump_state(struct sig_handler *sh)
{
struct proxy *p = proxy;
Warning("SIGHUP received, dumping servers states.\n");
while (p) {
struct server *s = p->srv;
send_log(p, LOG_NOTICE, "SIGHUP received, dumping servers states for proxy %s.\n", p->id);
while (s) {
chunk_printf(&trash,
"SIGHUP: Server %s/%s is %s. Conn: %d act, %d pend, %lld tot.",
p->id, s->id,
(s->state != SRV_ST_STOPPED) ? "UP" : "DOWN",
s->cur_sess, s->nbpend, s->counters.cum_sess);
Warning("%s\n", trash.str);
send_log(p, LOG_NOTICE, "%s\n", trash.str);
s = s->next;
}
/* FIXME: those info are a bit outdated. We should be able to distinguish between FE and BE. */
if (!p->srv) {
chunk_printf(&trash,
"SIGHUP: Proxy %s has no servers. Conn: act(FE+BE): %d+%d, %d pend (%d unass), tot(FE+BE): %lld+%lld.",
p->id,
p->feconn, p->beconn, p->totpend, p->nbpend, p->fe_counters.cum_conn, p->be_counters.cum_conn);
} else if (p->srv_act == 0) {
chunk_printf(&trash,
"SIGHUP: Proxy %s %s ! Conn: act(FE+BE): %d+%d, %d pend (%d unass), tot(FE+BE): %lld+%lld.",
p->id,
(p->srv_bck) ? "is running on backup servers" : "has no server available",
p->feconn, p->beconn, p->totpend, p->nbpend, p->fe_counters.cum_conn, p->be_counters.cum_conn);
} else {
chunk_printf(&trash,
"SIGHUP: Proxy %s has %d active servers and %d backup servers available."
" Conn: act(FE+BE): %d+%d, %d pend (%d unass), tot(FE+BE): %lld+%lld.",
p->id, p->srv_act, p->srv_bck,
p->feconn, p->beconn, p->totpend, p->nbpend, p->fe_counters.cum_conn, p->be_counters.cum_conn);
}
Warning("%s\n", trash.str);
send_log(p, LOG_NOTICE, "%s\n", trash.str);
p = p->next;
}
}
void dump(struct sig_handler *sh)
{
/* dump memory usage then free everything possible */
dump_pools();
pool_gc2();
}
/* This function check if cfg_cfgfiles containes directories.
* If it find one, it add all the files (and only files) it containes
* in cfg_cfgfiles in place of the directory (and remove the directory).
* It add the files in lexical order.
* It add only files with .cfg extension.
* It doesn't add files with name starting with '.'
*/
void cfgfiles_expand_directories(void)
{
struct wordlist *wl, *wlb;
char *err = NULL;
list_for_each_entry_safe(wl, wlb, &cfg_cfgfiles, list) {
struct stat file_stat;
struct dirent **dir_entries = NULL;
int dir_entries_nb;
int dir_entries_it;
if (stat(wl->s, &file_stat)) {
Alert("Cannot open configuration file/directory %s : %s\n",
wl->s,
strerror(errno));
exit(1);
}
if (!S_ISDIR(file_stat.st_mode))
continue;
/* from this point wl->s is a directory */
dir_entries_nb = scandir(wl->s, &dir_entries, NULL, alphasort);
if (dir_entries_nb < 0) {
Alert("Cannot open configuration directory %s : %s\n",
wl->s,
strerror(errno));
exit(1);
}
/* for each element in the directory wl->s */
for (dir_entries_it = 0; dir_entries_it < dir_entries_nb; dir_entries_it++) {
struct dirent *dir_entry = dir_entries[dir_entries_it];
char *filename = NULL;
char *d_name_cfgext = strstr(dir_entry->d_name, ".cfg");
/* don't add filename that begin with .
* only add filename with .cfg extention
*/
if (dir_entry->d_name[0] == '.' ||
!(d_name_cfgext && d_name_cfgext[4] == '\0'))
goto next_dir_entry;
if (!memprintf(&filename, "%s/%s", wl->s, dir_entry->d_name)) {
Alert("Cannot load configuration files %s : out of memory.\n",
filename);
exit(1);
}
if (stat(filename, &file_stat)) {
Alert("Cannot open configuration file %s : %s\n",
wl->s,
strerror(errno));
exit(1);
}
/* don't add anything else than regular file in cfg_cfgfiles
* this way we avoid loops
*/
if (!S_ISREG(file_stat.st_mode))
goto next_dir_entry;
if (!list_append_word(&wl->list, filename, &err)) {
Alert("Cannot load configuration files %s : %s\n",
filename,
err);
exit(1);
}
next_dir_entry:
free(filename);
free(dir_entry);
}
free(dir_entries);
/* remove the current directory (wl) from cfg_cfgfiles */
free(wl->s);
LIST_DEL(&wl->list);
free(wl);
}
free(err);
}
/*
* This function initializes all the necessary variables. It only returns
* if everything is OK. If something fails, it exits.
*/
void init(int argc, char **argv)
{
int arg_mode = 0; /* MODE_DEBUG, ... */
char *tmp;
char *cfg_pidfile = NULL;
int err_code = 0;
char *err_msg = NULL;
struct wordlist *wl;
char *progname;
char *change_dir = NULL;
MAJOR: filters: Add filters support This patch adds the support of filters in HAProxy. The main idea is to have a way to "easely" extend HAProxy by adding some "modules", called filters, that will be able to change HAProxy behavior in a programmatic way. To do so, many entry points has been added in code to let filters to hook up to different steps of the processing. A filter must define a flt_ops sutrctures (see include/types/filters.h for details). This structure contains all available callbacks that a filter can define: struct flt_ops { /* * Callbacks to manage the filter lifecycle */ int (*init) (struct proxy *p); void (*deinit)(struct proxy *p); int (*check) (struct proxy *p); /* * Stream callbacks */ void (*stream_start) (struct stream *s); void (*stream_accept) (struct stream *s); void (*session_establish)(struct stream *s); void (*stream_stop) (struct stream *s); /* * HTTP callbacks */ int (*http_start) (struct stream *s, struct http_msg *msg); int (*http_start_body) (struct stream *s, struct http_msg *msg); int (*http_start_chunk) (struct stream *s, struct http_msg *msg); int (*http_data) (struct stream *s, struct http_msg *msg); int (*http_last_chunk) (struct stream *s, struct http_msg *msg); int (*http_end_chunk) (struct stream *s, struct http_msg *msg); int (*http_chunk_trailers)(struct stream *s, struct http_msg *msg); int (*http_end_body) (struct stream *s, struct http_msg *msg); void (*http_end) (struct stream *s, struct http_msg *msg); void (*http_reset) (struct stream *s, struct http_msg *msg); int (*http_pre_process) (struct stream *s, struct http_msg *msg); int (*http_post_process) (struct stream *s, struct http_msg *msg); void (*http_reply) (struct stream *s, short status, const struct chunk *msg); }; To declare and use a filter, in the configuration, the "filter" keyword must be used in a listener/frontend section: frontend test ... filter <FILTER-NAME> [OPTIONS...] The filter referenced by the <FILTER-NAME> must declare a configuration parser on its own name to fill flt_ops and filter_conf field in the proxy's structure. An exemple will be provided later to make it perfectly clear. For now, filters cannot be used in backend section. But this is only a matter of time. Documentation will also be added later. This is the first commit of a long list about filters. It is possible to have several filters on the same listener/frontend. These filters are stored in an array of at most MAX_FILTERS elements (define in include/types/filters.h). Again, this will be replaced later by a list of filters. The filter API has been highly refactored. Main changes are: * Now, HA supports an infinite number of filters per proxy. To do so, filters are stored in list. * Because filters are stored in list, filters state has been moved from the channel structure to the filter structure. This is cleaner because there is no more info about filters in channel structure. * It is possible to defined filters on backends only. For such filters, stream_start/stream_stop callbacks are not called. Of course, it is possible to mix frontend and backend filters. * Now, TCP streams are also filtered. All callbacks without the 'http_' prefix are called for all kind of streams. In addition, 2 new callbacks were added to filter data exchanged through a TCP stream: - tcp_data: it is called when new data are available or when old unprocessed data are still waiting. - tcp_forward_data: it is called when some data can be consumed. * New callbacks attached to channel were added: - channel_start_analyze: it is called when a filter is ready to process data exchanged through a channel. 2 new analyzers (a frontend and a backend) are attached to channels to call this callback. For a frontend filter, it is called before any other analyzer. For a backend filter, it is called when a backend is attached to a stream. So some processing cannot be filtered in that case. - channel_analyze: it is called before each analyzer attached to a channel, expects analyzers responsible for data sending. - channel_end_analyze: it is called when all other analyzers have finished their processing. A new analyzers is attached to channels to call this callback. For a TCP stream, this is always the last one called. For a HTTP one, the callback is called when a request/response ends, so it is called one time for each request/response. * 'session_established' callback has been removed. Everything that is done in this callback can be handled by 'channel_start_analyze' on the response channel. * 'http_pre_process' and 'http_post_process' callbacks have been replaced by 'channel_analyze'. * 'http_start' callback has been replaced by 'http_headers'. This new one is called just before headers sending and parsing of the body. * 'http_end' callback has been replaced by 'channel_end_analyze'. * It is possible to set a forwarder for TCP channels. It was already possible to do it for HTTP ones. * Forwarders can partially consumed forwardable data. For this reason a new HTTP message state was added before HTTP_MSG_DONE : HTTP_MSG_ENDING. Now all filters can define corresponding callbacks (http_forward_data and tcp_forward_data). Each filter owns 2 offsets relative to buf->p, next and forward, to track, respectively, input data already parsed but not forwarded yet by the filter and parsed data considered as forwarded by the filter. A any time, we have the warranty that a filter cannot parse or forward more input than previous ones. And, of course, it cannot forward more input than it has parsed. 2 macros has been added to retrieve these offets: FLT_NXT and FLT_FWD. In addition, 2 functions has been added to change the 'next size' and the 'forward size' of a filter. When a filter parses input data, it can alter these data, so the size of these data can vary. This action has an effet on all previous filters that must be handled. To do so, the function 'filter_change_next_size' must be called, passing the size variation. In the same spirit, if a filter alter forwarded data, it must call the function 'filter_change_forward_size'. 'filter_change_next_size' can be called in 'http_data' and 'tcp_data' callbacks and only these ones. And 'filter_change_forward_size' can be called in 'http_forward_data' and 'tcp_forward_data' callbacks and only these ones. The data changes are the filter responsability, but with some limitation. It must not change already parsed/forwarded data or data that previous filters have not parsed/forwarded yet. Because filters can be used on backends, when we the backend is set for a stream, we add filters defined for this backend in the filter list of the stream. But we must only do that when the backend and the frontend of the stream are not the same. Else same filters are added a second time leading to undefined behavior. The HTTP compression code had to be moved. So it simplifies http_response_forward_body function. To do so, the way the data are forwarded has changed. Now, a filter (and only one) can forward data. In a commit to come, this limitation will be removed to let all filters take part to data forwarding. There are 2 new functions that filters should use to deal with this feature: * flt_set_http_data_forwarder: This function sets the filter (using its id) that will forward data for the specified HTTP message. It is possible if it was not already set by another filter _AND_ if no data was yet forwarded (msg->msg_state <= HTTP_MSG_BODY). It returns -1 if an error occurs. * flt_http_data_forwarder: This function returns the filter id that will forward data for the specified HTTP message. If there is no forwarder set, it returns -1. When an HTTP data forwarder is set for the response, the HTTP compression is disabled. Of course, this is not definitive.
2015-04-30 05:48:27 -04:00
struct proxy *px;
chunk_init(&trash, malloc(global.tune.bufsize), global.tune.bufsize);
alloc_trash_buffers(global.tune.bufsize);
/* NB: POSIX does not make it mandatory for gethostname() to NULL-terminate
* the string in case of truncation, and at least FreeBSD appears not to do
* it.
*/
memset(hostname, 0, sizeof(hostname));
gethostname(hostname, sizeof(hostname) - 1);
memset(localpeer, 0, sizeof(localpeer));
memcpy(localpeer, hostname, (sizeof(hostname) > sizeof(localpeer) ? sizeof(localpeer) : sizeof(hostname)) - 1);
/*
* Initialize the previously static variables.
*/
totalconn = actconn = maxfd = listeners = stopping = 0;
#ifdef HAPROXY_MEMMAX
global.rlimit_memmax_all = HAPROXY_MEMMAX;
#endif
tzset();
tv_update_date(-1,-1);
start_date = now;
srandom(now_ms - getpid());
init_log();
signal_init();
if (init_acl() != 0)
exit(1);
init_task();
REORG/MAJOR: session: rename the "session" entity to "stream" With HTTP/2, we'll have to support multiplexed streams. A stream is in fact the largest part of what we currently call a session, it has buffers, logs, etc. In order to catch any error, this commit removes any reference to the struct session and tries to rename most "session" occurrences in function names to "stream" and "sess" to "strm" when that's related to a session. The files stream.{c,h} were added and session.{c,h} removed. The session will be reintroduced later and a few parts of the stream will progressively be moved overthere. It will more or less contain only what we need in an embryonic session. Sample fetch functions and converters will have to change a bit so that they'll use an L5 (session) instead of what's currently called "L4" which is in fact L6 for now. Once all changes are completed, we should see approximately this : L7 - http_txn L6 - stream L5 - session L4 - connection | applet There will be at most one http_txn per stream, and a same session will possibly be referenced by multiple streams. A connection will point to a session and to a stream. The session will hold all the information we need to keep even when we don't yet have a stream. Some more cleanup is needed because some code was already far from being clean. The server queue management still refers to sessions at many places while comments talk about connections. This will have to be cleaned up once we have a server-side connection pool manager. Stream flags "SN_*" still need to be renamed, it doesn't seem like any of them will need to move to the session.
2015-04-02 18:22:06 -04:00
init_stream();
init_session();
init_connection();
/* warning, we init buffers later */
init_pendconn();
init_proto_http();
/* Initialise lua. */
hlua_init();
/* Initialize process vars */
vars_init(&global.vars, SCOPE_PROC);
global.tune.options |= GTUNE_USE_SELECT; /* select() is always available */
#if defined(ENABLE_POLL)
global.tune.options |= GTUNE_USE_POLL;
#endif
#if defined(ENABLE_EPOLL)
global.tune.options |= GTUNE_USE_EPOLL;
#endif
#if defined(ENABLE_KQUEUE)
global.tune.options |= GTUNE_USE_KQUEUE;
#endif
#if defined(CONFIG_HAP_LINUX_SPLICE)
global.tune.options |= GTUNE_USE_SPLICE;
#endif
#if defined(USE_GETADDRINFO)
global.tune.options |= GTUNE_USE_GAI;
#endif
#if defined(SO_REUSEPORT)
global.tune.options |= GTUNE_USE_REUSEPORT;
#endif
pid = getpid();
progname = *argv;
while ((tmp = strchr(progname, '/')) != NULL)
progname = tmp + 1;
/* the process name is used for the logs only */
chunk_initstr(&global.log_tag, strdup(progname));
argc--; argv++;
while (argc > 0) {
char *flag;
if (**argv == '-') {
flag = *argv+1;
/* 1 arg */
if (*flag == 'v') {
display_version();
if (flag[1] == 'v') /* -vv */
display_build_opts();
exit(0);
}
#if defined(ENABLE_EPOLL)
else if (*flag == 'd' && flag[1] == 'e')
global.tune.options &= ~GTUNE_USE_EPOLL;
#endif
#if defined(ENABLE_POLL)
else if (*flag == 'd' && flag[1] == 'p')
global.tune.options &= ~GTUNE_USE_POLL;
#endif
#if defined(ENABLE_KQUEUE)
else if (*flag == 'd' && flag[1] == 'k')
global.tune.options &= ~GTUNE_USE_KQUEUE;
#endif
#if defined(CONFIG_HAP_LINUX_SPLICE)
else if (*flag == 'd' && flag[1] == 'S')
global.tune.options &= ~GTUNE_USE_SPLICE;
#endif
#if defined(USE_GETADDRINFO)
else if (*flag == 'd' && flag[1] == 'G')
global.tune.options &= ~GTUNE_USE_GAI;
#endif
#if defined(SO_REUSEPORT)
else if (*flag == 'd' && flag[1] == 'R')
global.tune.options &= ~GTUNE_USE_REUSEPORT;
#endif
else if (*flag == 'd' && flag[1] == 'V')
global.ssl_server_verify = SSL_SERVER_VERIFY_NONE;
else if (*flag == 'V')
arg_mode |= MODE_VERBOSE;
else if (*flag == 'd' && flag[1] == 'b')
arg_mode |= MODE_FOREGROUND;
else if (*flag == 'd' && flag[1] == 'M')
mem_poison_byte = flag[2] ? strtol(flag + 2, NULL, 0) : 'P';
else if (*flag == 'd' && flag[1] == 'r')
global.tune.options |= GTUNE_RESOLVE_DONTFAIL;
else if (*flag == 'd')
arg_mode |= MODE_DEBUG;
else if (*flag == 'c')
arg_mode |= MODE_CHECK;
else if (*flag == 'D') {
arg_mode |= MODE_DAEMON;
if (flag[1] == 's') /* -Ds */
arg_mode |= MODE_SYSTEMD;
}
else if (*flag == 'q')
arg_mode |= MODE_QUIET;
else if (*flag == 's' && (flag[1] == 'f' || flag[1] == 't')) {
/* list of pids to finish ('f') or terminate ('t') */
if (flag[1] == 'f')
oldpids_sig = SIGUSR1; /* finish then exit */
else
oldpids_sig = SIGTERM; /* terminate immediately */
while (argc > 1 && argv[1][0] != '-') {
oldpids = realloc(oldpids, (nb_oldpids + 1) * sizeof(int));
if (!oldpids) {
Alert("Cannot allocate old pid : out of memory.\n");
exit(1);
}
argc--; argv++;
oldpids[nb_oldpids] = atol(*argv);
if (oldpids[nb_oldpids] <= 0)
usage(progname);
nb_oldpids++;
}
}
else if (flag[0] == '-' && flag[1] == 0) { /* "--" */
/* now that's a cfgfile list */
argv++; argc--;
while (argc > 0) {
if (!list_append_word(&cfg_cfgfiles, *argv, &err_msg)) {
Alert("Cannot load configuration file/directory %s : %s\n",
*argv,
err_msg);
exit(1);
}
argv++; argc--;
}
break;
}
else { /* >=2 args */
argv++; argc--;
if (argc == 0)
usage(progname);
switch (*flag) {
case 'C' : change_dir = *argv; break;
case 'n' : cfg_maxconn = atol(*argv); break;
case 'm' : global.rlimit_memmax_all = atol(*argv); break;
case 'N' : cfg_maxpconn = atol(*argv); break;
case 'L' : strncpy(localpeer, *argv, sizeof(localpeer) - 1); break;
case 'f' :
if (!list_append_word(&cfg_cfgfiles, *argv, &err_msg)) {
Alert("Cannot load configuration file/directory %s : %s\n",
*argv,
err_msg);
exit(1);
}
break;
case 'p' : cfg_pidfile = *argv; break;
default: usage(progname);
}
}
}
else
usage(progname);
argv++; argc--;
}
global.mode = MODE_STARTING | /* during startup, we want most of the alerts */
(arg_mode & (MODE_DAEMON | MODE_SYSTEMD | MODE_FOREGROUND | MODE_VERBOSE
| MODE_QUIET | MODE_CHECK | MODE_DEBUG));
if (change_dir && chdir(change_dir) < 0) {
Alert("Could not change to directory %s : %s\n", change_dir, strerror(errno));
exit(1);
}
/* handle cfgfiles that are actualy directories */
cfgfiles_expand_directories();
if (LIST_ISEMPTY(&cfg_cfgfiles))
usage(progname);
global.maxsock = 10; /* reserve 10 fds ; will be incremented by socket eaters */
init_default_instance();
list_for_each_entry(wl, &cfg_cfgfiles, list) {
int ret;
ret = readcfgfile(wl->s);
if (ret == -1) {
Alert("Could not open configuration file %s : %s\n",
wl->s, strerror(errno));
exit(1);
}
if (ret & (ERR_ABORT|ERR_FATAL))
Alert("Error(s) found in configuration file : %s\n", wl->s);
err_code |= ret;
if (err_code & ERR_ABORT)
exit(1);
}
pattern_finalize_config();
#if (defined SSL_CTRL_SET_TLSEXT_TICKET_KEY_CB && TLS_TICKETS_NO > 0)
tlskeys_finalize_config();
#endif
err_code |= check_config_validity();
if (err_code & (ERR_ABORT|ERR_FATAL)) {
Alert("Fatal errors found in configuration.\n");
exit(1);
}
/* recompute the amount of per-process memory depending on nbproc and
* the shared SSL cache size (allowed to exist in all processes).
*/
if (global.rlimit_memmax_all) {
#if defined (USE_OPENSSL) && !defined(USE_PRIVATE_CACHE)
int64_t ssl_cache_bytes = global.tune.sslcachesize * 200LL;
global.rlimit_memmax =
((((int64_t)global.rlimit_memmax_all * 1048576LL) -
ssl_cache_bytes) / global.nbproc +
ssl_cache_bytes + 1048575LL) / 1048576LL;
#else
global.rlimit_memmax = global.rlimit_memmax_all / global.nbproc;
#endif
}
MAJOR: namespace: add Linux network namespace support This patch makes it possible to create binds and servers in separate namespaces. This can be used to proxy between multiple completely independent virtual networks (with possibly overlapping IP addresses) and a non-namespace-aware proxy implementation that supports the proxy protocol (v2). The setup is something like this: net1 on VLAN 1 (namespace 1) -\ net2 on VLAN 2 (namespace 2) -- haproxy ==== proxy (namespace 0) net3 on VLAN 3 (namespace 3) -/ The proxy is configured to make server connections through haproxy and sending the expected source/target addresses to haproxy using the proxy protocol. The network namespace setup on the haproxy node is something like this: = 8< = $ cat setup.sh ip netns add 1 ip link add link eth1 type vlan id 1 ip link set eth1.1 netns 1 ip netns exec 1 ip addr add 192.168.91.2/24 dev eth1.1 ip netns exec 1 ip link set eth1.$id up ... = 8< = = 8< = $ cat haproxy.cfg frontend clients bind 127.0.0.1:50022 namespace 1 transparent default_backend scb backend server mode tcp server server1 192.168.122.4:2222 namespace 2 send-proxy-v2 = 8< = A bind line creates the listener in the specified namespace, and connections originating from that listener also have their network namespace set to that of the listener. A server line either forces the connection to be made in a specified namespace or may use the namespace from the client-side connection if that was set. For more documentation please read the documentation included in the patch itself. Signed-off-by: KOVACS Tamas <ktamas@balabit.com> Signed-off-by: Sarkozi Laszlo <laszlo.sarkozi@balabit.com> Signed-off-by: KOVACS Krisztian <hidden@balabit.com>
2014-11-17 09:11:45 -05:00
#ifdef CONFIG_HAP_NS
err_code |= netns_init();
if (err_code & (ERR_ABORT|ERR_FATAL)) {
Alert("Failed to initialize namespace support.\n");
exit(1);
}
#endif
/* Apply server states */
apply_server_state();
for (px = proxy; px; px = px->next)
srv_compute_all_admin_states(px);
/* Apply servers' configured address */
err_code |= srv_init_addr();
if (err_code & (ERR_ABORT|ERR_FATAL)) {
Alert("Failed to initialize server(s) addr.\n");
exit(1);
}
if (global.mode & MODE_CHECK) {
struct peers *pr;
struct proxy *px;
for (pr = peers; pr; pr = pr->next)
if (pr->peers_fe)
break;
for (px = proxy; px; px = px->next)
if (px->state == PR_STNEW && !LIST_ISEMPTY(&px->conf.listeners))
break;
if (pr || px) {
/* At least one peer or one listener has been found */
qfprintf(stdout, "Configuration file is valid\n");
exit(0);
}
qfprintf(stdout, "Configuration file has no error but will not start (no listener) => exit(2).\n");
exit(2);
}
global_listener_queue_task = task_new();
if (!global_listener_queue_task) {
Alert("Out of memory when initializing global task\n");
exit(1);
}
/* very simple initialization, users will queue the task if needed */
global_listener_queue_task->context = NULL; /* not even a context! */
global_listener_queue_task->process = manage_global_listener_queue;
global_listener_queue_task->expire = TICK_ETERNITY;
CLEANUP: channel: use "channel" instead of "buffer" in function names This is a massive rename of most functions which should make use of the word "channel" instead of the word "buffer" in their names. In concerns the following ones (new names) : unsigned long long channel_forward(struct channel *buf, unsigned long long bytes); static inline void channel_init(struct channel *buf) static inline int channel_input_closed(struct channel *buf) static inline int channel_output_closed(struct channel *buf) static inline void channel_check_timeouts(struct channel *b) static inline void channel_erase(struct channel *buf) static inline void channel_shutr_now(struct channel *buf) static inline void channel_shutw_now(struct channel *buf) static inline void channel_abort(struct channel *buf) static inline void channel_stop_hijacker(struct channel *buf) static inline void channel_auto_connect(struct channel *buf) static inline void channel_dont_connect(struct channel *buf) static inline void channel_auto_close(struct channel *buf) static inline void channel_dont_close(struct channel *buf) static inline void channel_auto_read(struct channel *buf) static inline void channel_dont_read(struct channel *buf) unsigned long long channel_forward(struct channel *buf, unsigned long long bytes) Some functions provided by channel.[ch] have kept their "buffer" name because they are really designed to act on the buffer according to some information gathered from the channel. They have been moved together to the same place in the file for better readability but they were not changed at all. The "buffer" memory pool was also renamed "channel".
2012-08-27 18:06:31 -04:00
/* now we know the buffer size, we can initialize the channels and buffers */
init_buffer();
#if defined(USE_DEVICEATLAS)
init_deviceatlas();
#endif
#ifdef USE_51DEGREES
init_51degrees();
#endif
#ifdef USE_WURFL
ha_wurfl_init();
#endif
MAJOR: filters: Add filters support This patch adds the support of filters in HAProxy. The main idea is to have a way to "easely" extend HAProxy by adding some "modules", called filters, that will be able to change HAProxy behavior in a programmatic way. To do so, many entry points has been added in code to let filters to hook up to different steps of the processing. A filter must define a flt_ops sutrctures (see include/types/filters.h for details). This structure contains all available callbacks that a filter can define: struct flt_ops { /* * Callbacks to manage the filter lifecycle */ int (*init) (struct proxy *p); void (*deinit)(struct proxy *p); int (*check) (struct proxy *p); /* * Stream callbacks */ void (*stream_start) (struct stream *s); void (*stream_accept) (struct stream *s); void (*session_establish)(struct stream *s); void (*stream_stop) (struct stream *s); /* * HTTP callbacks */ int (*http_start) (struct stream *s, struct http_msg *msg); int (*http_start_body) (struct stream *s, struct http_msg *msg); int (*http_start_chunk) (struct stream *s, struct http_msg *msg); int (*http_data) (struct stream *s, struct http_msg *msg); int (*http_last_chunk) (struct stream *s, struct http_msg *msg); int (*http_end_chunk) (struct stream *s, struct http_msg *msg); int (*http_chunk_trailers)(struct stream *s, struct http_msg *msg); int (*http_end_body) (struct stream *s, struct http_msg *msg); void (*http_end) (struct stream *s, struct http_msg *msg); void (*http_reset) (struct stream *s, struct http_msg *msg); int (*http_pre_process) (struct stream *s, struct http_msg *msg); int (*http_post_process) (struct stream *s, struct http_msg *msg); void (*http_reply) (struct stream *s, short status, const struct chunk *msg); }; To declare and use a filter, in the configuration, the "filter" keyword must be used in a listener/frontend section: frontend test ... filter <FILTER-NAME> [OPTIONS...] The filter referenced by the <FILTER-NAME> must declare a configuration parser on its own name to fill flt_ops and filter_conf field in the proxy's structure. An exemple will be provided later to make it perfectly clear. For now, filters cannot be used in backend section. But this is only a matter of time. Documentation will also be added later. This is the first commit of a long list about filters. It is possible to have several filters on the same listener/frontend. These filters are stored in an array of at most MAX_FILTERS elements (define in include/types/filters.h). Again, this will be replaced later by a list of filters. The filter API has been highly refactored. Main changes are: * Now, HA supports an infinite number of filters per proxy. To do so, filters are stored in list. * Because filters are stored in list, filters state has been moved from the channel structure to the filter structure. This is cleaner because there is no more info about filters in channel structure. * It is possible to defined filters on backends only. For such filters, stream_start/stream_stop callbacks are not called. Of course, it is possible to mix frontend and backend filters. * Now, TCP streams are also filtered. All callbacks without the 'http_' prefix are called for all kind of streams. In addition, 2 new callbacks were added to filter data exchanged through a TCP stream: - tcp_data: it is called when new data are available or when old unprocessed data are still waiting. - tcp_forward_data: it is called when some data can be consumed. * New callbacks attached to channel were added: - channel_start_analyze: it is called when a filter is ready to process data exchanged through a channel. 2 new analyzers (a frontend and a backend) are attached to channels to call this callback. For a frontend filter, it is called before any other analyzer. For a backend filter, it is called when a backend is attached to a stream. So some processing cannot be filtered in that case. - channel_analyze: it is called before each analyzer attached to a channel, expects analyzers responsible for data sending. - channel_end_analyze: it is called when all other analyzers have finished their processing. A new analyzers is attached to channels to call this callback. For a TCP stream, this is always the last one called. For a HTTP one, the callback is called when a request/response ends, so it is called one time for each request/response. * 'session_established' callback has been removed. Everything that is done in this callback can be handled by 'channel_start_analyze' on the response channel. * 'http_pre_process' and 'http_post_process' callbacks have been replaced by 'channel_analyze'. * 'http_start' callback has been replaced by 'http_headers'. This new one is called just before headers sending and parsing of the body. * 'http_end' callback has been replaced by 'channel_end_analyze'. * It is possible to set a forwarder for TCP channels. It was already possible to do it for HTTP ones. * Forwarders can partially consumed forwardable data. For this reason a new HTTP message state was added before HTTP_MSG_DONE : HTTP_MSG_ENDING. Now all filters can define corresponding callbacks (http_forward_data and tcp_forward_data). Each filter owns 2 offsets relative to buf->p, next and forward, to track, respectively, input data already parsed but not forwarded yet by the filter and parsed data considered as forwarded by the filter. A any time, we have the warranty that a filter cannot parse or forward more input than previous ones. And, of course, it cannot forward more input than it has parsed. 2 macros has been added to retrieve these offets: FLT_NXT and FLT_FWD. In addition, 2 functions has been added to change the 'next size' and the 'forward size' of a filter. When a filter parses input data, it can alter these data, so the size of these data can vary. This action has an effet on all previous filters that must be handled. To do so, the function 'filter_change_next_size' must be called, passing the size variation. In the same spirit, if a filter alter forwarded data, it must call the function 'filter_change_forward_size'. 'filter_change_next_size' can be called in 'http_data' and 'tcp_data' callbacks and only these ones. And 'filter_change_forward_size' can be called in 'http_forward_data' and 'tcp_forward_data' callbacks and only these ones. The data changes are the filter responsability, but with some limitation. It must not change already parsed/forwarded data or data that previous filters have not parsed/forwarded yet. Because filters can be used on backends, when we the backend is set for a stream, we add filters defined for this backend in the filter list of the stream. But we must only do that when the backend and the frontend of the stream are not the same. Else same filters are added a second time leading to undefined behavior. The HTTP compression code had to be moved. So it simplifies http_response_forward_body function. To do so, the way the data are forwarded has changed. Now, a filter (and only one) can forward data. In a commit to come, this limitation will be removed to let all filters take part to data forwarding. There are 2 new functions that filters should use to deal with this feature: * flt_set_http_data_forwarder: This function sets the filter (using its id) that will forward data for the specified HTTP message. It is possible if it was not already set by another filter _AND_ if no data was yet forwarded (msg->msg_state <= HTTP_MSG_BODY). It returns -1 if an error occurs. * flt_http_data_forwarder: This function returns the filter id that will forward data for the specified HTTP message. If there is no forwarder set, it returns -1. When an HTTP data forwarder is set for the response, the HTTP compression is disabled. Of course, this is not definitive.
2015-04-30 05:48:27 -04:00
for (px = proxy; px; px = px->next) {
err_code |= flt_init(px);
if (err_code & (ERR_ABORT|ERR_FATAL)) {
Alert("Failed to initialize filters for proxy '%s'.\n",
px->id);
exit(1);
}
}
if (start_checks() < 0)
exit(1);
if (cfg_maxconn > 0)
global.maxconn = cfg_maxconn;
if (cfg_pidfile) {
free(global.pidfile);
global.pidfile = strdup(cfg_pidfile);
}
/* Now we want to compute the maxconn and possibly maxsslconn values.
* It's a bit tricky. If memmax is not set, maxconn defaults to
* DEFAULT_MAXCONN and maxsslconn defaults to DEFAULT_MAXSSLCONN.
*
* If memmax is set, then it depends on which values are set. If
* maxsslconn is set, we use memmax to determine how many cleartext
* connections may be added, and set maxconn to the sum of the two.
* If maxconn is set and not maxsslconn, maxsslconn is computed from
* the remaining amount of memory between memmax and the cleartext
* connections. If neither are set, then it is considered that all
* connections are SSL-capable, and maxconn is computed based on this,
* then maxsslconn accordingly. We need to know if SSL is used on the
* frontends, backends, or both, because when it's used on both sides,
* we need twice the value for maxsslconn, but we only count the
* handshake once since it is not performed on the two sides at the
* same time (frontend-side is terminated before backend-side begins).
* The SSL stack is supposed to have filled ssl_session_cost and
* ssl_handshake_cost during its initialization. In any case, if
* SYSTEM_MAXCONN is set, we still enforce it as an upper limit for
* maxconn in order to protect the system.
*/
if (!global.rlimit_memmax) {
if (global.maxconn == 0) {
global.maxconn = DEFAULT_MAXCONN;
if (global.mode & (MODE_VERBOSE|MODE_DEBUG))
fprintf(stderr, "Note: setting global.maxconn to %d.\n", global.maxconn);
}
}
#ifdef USE_OPENSSL
else if (!global.maxconn && !global.maxsslconn &&
(global.ssl_used_frontend || global.ssl_used_backend)) {
/* memmax is set, compute everything automatically. Here we want
* to ensure that all SSL connections will be served. We take
* care of the number of sides where SSL is used, and consider
* the worst case : SSL used on both sides and doing a handshake
* simultaneously. Note that we can't have more than maxconn
* handshakes at a time by definition, so for the worst case of
* two SSL conns per connection, we count a single handshake.
*/
int sides = !!global.ssl_used_frontend + !!global.ssl_used_backend;
int64_t mem = global.rlimit_memmax * 1048576ULL;
mem -= global.tune.sslcachesize * 200; // about 200 bytes per SSL cache entry
mem -= global.maxzlibmem;
mem = mem * MEM_USABLE_RATIO;
global.maxconn = mem /
REORG/MAJOR: session: rename the "session" entity to "stream" With HTTP/2, we'll have to support multiplexed streams. A stream is in fact the largest part of what we currently call a session, it has buffers, logs, etc. In order to catch any error, this commit removes any reference to the struct session and tries to rename most "session" occurrences in function names to "stream" and "sess" to "strm" when that's related to a session. The files stream.{c,h} were added and session.{c,h} removed. The session will be reintroduced later and a few parts of the stream will progressively be moved overthere. It will more or less contain only what we need in an embryonic session. Sample fetch functions and converters will have to change a bit so that they'll use an L5 (session) instead of what's currently called "L4" which is in fact L6 for now. Once all changes are completed, we should see approximately this : L7 - http_txn L6 - stream L5 - session L4 - connection | applet There will be at most one http_txn per stream, and a same session will possibly be referenced by multiple streams. A connection will point to a session and to a stream. The session will hold all the information we need to keep even when we don't yet have a stream. Some more cleanup is needed because some code was already far from being clean. The server queue management still refers to sessions at many places while comments talk about connections. This will have to be cleaned up once we have a server-side connection pool manager. Stream flags "SN_*" still need to be renamed, it doesn't seem like any of them will need to move to the session.
2015-04-02 18:22:06 -04:00
((STREAM_MAX_COST + 2 * global.tune.bufsize) + // stream + 2 buffers per stream
sides * global.ssl_session_max_cost + // SSL buffers, one per side
global.ssl_handshake_max_cost); // 1 handshake per connection max
global.maxconn = round_2dig(global.maxconn);
#ifdef SYSTEM_MAXCONN
if (global.maxconn > DEFAULT_MAXCONN)
global.maxconn = DEFAULT_MAXCONN;
#endif /* SYSTEM_MAXCONN */
global.maxsslconn = sides * global.maxconn;
if (global.mode & (MODE_VERBOSE|MODE_DEBUG))
fprintf(stderr, "Note: setting global.maxconn to %d and global.maxsslconn to %d.\n",
global.maxconn, global.maxsslconn);
}
else if (!global.maxsslconn &&
(global.ssl_used_frontend || global.ssl_used_backend)) {
/* memmax and maxconn are known, compute maxsslconn automatically.
* maxsslconn being forced, we don't know how many of it will be
* on each side if both sides are being used. The worst case is
* when all connections use only one SSL instance because
* handshakes may be on two sides at the same time.
*/
int sides = !!global.ssl_used_frontend + !!global.ssl_used_backend;
int64_t mem = global.rlimit_memmax * 1048576ULL;
int64_t sslmem;
mem -= global.tune.sslcachesize * 200; // about 200 bytes per SSL cache entry
mem -= global.maxzlibmem;
mem = mem * MEM_USABLE_RATIO;
REORG/MAJOR: session: rename the "session" entity to "stream" With HTTP/2, we'll have to support multiplexed streams. A stream is in fact the largest part of what we currently call a session, it has buffers, logs, etc. In order to catch any error, this commit removes any reference to the struct session and tries to rename most "session" occurrences in function names to "stream" and "sess" to "strm" when that's related to a session. The files stream.{c,h} were added and session.{c,h} removed. The session will be reintroduced later and a few parts of the stream will progressively be moved overthere. It will more or less contain only what we need in an embryonic session. Sample fetch functions and converters will have to change a bit so that they'll use an L5 (session) instead of what's currently called "L4" which is in fact L6 for now. Once all changes are completed, we should see approximately this : L7 - http_txn L6 - stream L5 - session L4 - connection | applet There will be at most one http_txn per stream, and a same session will possibly be referenced by multiple streams. A connection will point to a session and to a stream. The session will hold all the information we need to keep even when we don't yet have a stream. Some more cleanup is needed because some code was already far from being clean. The server queue management still refers to sessions at many places while comments talk about connections. This will have to be cleaned up once we have a server-side connection pool manager. Stream flags "SN_*" still need to be renamed, it doesn't seem like any of them will need to move to the session.
2015-04-02 18:22:06 -04:00
sslmem = mem - global.maxconn * (int64_t)(STREAM_MAX_COST + 2 * global.tune.bufsize);
global.maxsslconn = sslmem / (global.ssl_session_max_cost + global.ssl_handshake_max_cost);
global.maxsslconn = round_2dig(global.maxsslconn);
if (sslmem <= 0 || global.maxsslconn < sides) {
Alert("Cannot compute the automatic maxsslconn because global.maxconn is already too "
"high for the global.memmax value (%d MB). The absolute maximum possible value "
"without SSL is %d, but %d was found and SSL is in use.\n",
global.rlimit_memmax,
REORG/MAJOR: session: rename the "session" entity to "stream" With HTTP/2, we'll have to support multiplexed streams. A stream is in fact the largest part of what we currently call a session, it has buffers, logs, etc. In order to catch any error, this commit removes any reference to the struct session and tries to rename most "session" occurrences in function names to "stream" and "sess" to "strm" when that's related to a session. The files stream.{c,h} were added and session.{c,h} removed. The session will be reintroduced later and a few parts of the stream will progressively be moved overthere. It will more or less contain only what we need in an embryonic session. Sample fetch functions and converters will have to change a bit so that they'll use an L5 (session) instead of what's currently called "L4" which is in fact L6 for now. Once all changes are completed, we should see approximately this : L7 - http_txn L6 - stream L5 - session L4 - connection | applet There will be at most one http_txn per stream, and a same session will possibly be referenced by multiple streams. A connection will point to a session and to a stream. The session will hold all the information we need to keep even when we don't yet have a stream. Some more cleanup is needed because some code was already far from being clean. The server queue management still refers to sessions at many places while comments talk about connections. This will have to be cleaned up once we have a server-side connection pool manager. Stream flags "SN_*" still need to be renamed, it doesn't seem like any of them will need to move to the session.
2015-04-02 18:22:06 -04:00
(int)(mem / (STREAM_MAX_COST + 2 * global.tune.bufsize)),
global.maxconn);
exit(1);
}
if (global.maxsslconn > sides * global.maxconn)
global.maxsslconn = sides * global.maxconn;
if (global.mode & (MODE_VERBOSE|MODE_DEBUG))
fprintf(stderr, "Note: setting global.maxsslconn to %d\n", global.maxsslconn);
}
#endif
else if (!global.maxconn) {
/* memmax and maxsslconn are known/unused, compute maxconn automatically */
int sides = !!global.ssl_used_frontend + !!global.ssl_used_backend;
int64_t mem = global.rlimit_memmax * 1048576ULL;
int64_t clearmem;
if (global.ssl_used_frontend || global.ssl_used_backend)
mem -= global.tune.sslcachesize * 200; // about 200 bytes per SSL cache entry
mem -= global.maxzlibmem;
mem = mem * MEM_USABLE_RATIO;
clearmem = mem;
if (sides)
clearmem -= (global.ssl_session_max_cost + global.ssl_handshake_max_cost) * (int64_t)global.maxsslconn;
REORG/MAJOR: session: rename the "session" entity to "stream" With HTTP/2, we'll have to support multiplexed streams. A stream is in fact the largest part of what we currently call a session, it has buffers, logs, etc. In order to catch any error, this commit removes any reference to the struct session and tries to rename most "session" occurrences in function names to "stream" and "sess" to "strm" when that's related to a session. The files stream.{c,h} were added and session.{c,h} removed. The session will be reintroduced later and a few parts of the stream will progressively be moved overthere. It will more or less contain only what we need in an embryonic session. Sample fetch functions and converters will have to change a bit so that they'll use an L5 (session) instead of what's currently called "L4" which is in fact L6 for now. Once all changes are completed, we should see approximately this : L7 - http_txn L6 - stream L5 - session L4 - connection | applet There will be at most one http_txn per stream, and a same session will possibly be referenced by multiple streams. A connection will point to a session and to a stream. The session will hold all the information we need to keep even when we don't yet have a stream. Some more cleanup is needed because some code was already far from being clean. The server queue management still refers to sessions at many places while comments talk about connections. This will have to be cleaned up once we have a server-side connection pool manager. Stream flags "SN_*" still need to be renamed, it doesn't seem like any of them will need to move to the session.
2015-04-02 18:22:06 -04:00
global.maxconn = clearmem / (STREAM_MAX_COST + 2 * global.tune.bufsize);
global.maxconn = round_2dig(global.maxconn);
#ifdef SYSTEM_MAXCONN
if (global.maxconn > DEFAULT_MAXCONN)
global.maxconn = DEFAULT_MAXCONN;
#endif /* SYSTEM_MAXCONN */
if (clearmem <= 0 || !global.maxconn) {
Alert("Cannot compute the automatic maxconn because global.maxsslconn is already too "
"high for the global.memmax value (%d MB). The absolute maximum possible value "
"is %d, but %d was found.\n",
global.rlimit_memmax,
(int)(mem / (global.ssl_session_max_cost + global.ssl_handshake_max_cost)),
global.maxsslconn);
exit(1);
}
if (global.mode & (MODE_VERBOSE|MODE_DEBUG)) {
if (sides && global.maxsslconn > sides * global.maxconn) {
fprintf(stderr, "Note: global.maxsslconn is forced to %d which causes global.maxconn "
"to be limited to %d. Better reduce global.maxsslconn to get more "
"room for extra connections.\n", global.maxsslconn, global.maxconn);
}
fprintf(stderr, "Note: setting global.maxconn to %d\n", global.maxconn);
}
}
if (!global.maxpipes) {
/* maxpipes not specified. Count how many frontends and backends
* may be using splicing, and bound that to maxconn.
*/
struct proxy *cur;
int nbfe = 0, nbbe = 0;
for (cur = proxy; cur; cur = cur->next) {
if (cur->options2 & (PR_O2_SPLIC_ANY)) {
if (cur->cap & PR_CAP_FE)
nbfe += cur->maxconn;
if (cur->cap & PR_CAP_BE)
nbbe += cur->fullconn ? cur->fullconn : global.maxconn;
}
}
global.maxpipes = MAX(nbfe, nbbe);
if (global.maxpipes > global.maxconn)
global.maxpipes = global.maxconn;
global.maxpipes /= 4;
}
global.hardmaxconn = global.maxconn; /* keep this max value */
global.maxsock += global.maxconn * 2; /* each connection needs two sockets */
global.maxsock += global.maxpipes * 2; /* each pipe needs two FDs */
if (global.stats_fe)
global.maxsock += global.stats_fe->maxconn;
if (peers) {
/* peers also need to bypass global maxconn */
struct peers *p = peers;
for (p = peers; p; p = p->next)
if (p->peers_fe)
global.maxsock += p->peers_fe->maxconn;
}
if (global.tune.maxpollevents <= 0)
global.tune.maxpollevents = MAX_POLL_EVENTS;
if (global.tune.recv_enough == 0)
global.tune.recv_enough = MIN_RECV_AT_ONCE_ENOUGH;
if (global.tune.maxrewrite < 0)
global.tune.maxrewrite = MAXREWRITE;
if (global.tune.maxrewrite >= global.tune.bufsize / 2)
global.tune.maxrewrite = global.tune.bufsize / 2;
if (arg_mode & (MODE_DEBUG | MODE_FOREGROUND)) {
/* command line debug mode inhibits configuration mode */
global.mode &= ~(MODE_DAEMON | MODE_SYSTEMD | MODE_QUIET);
global.mode |= (arg_mode & (MODE_DEBUG | MODE_FOREGROUND));
}
if (arg_mode & (MODE_DAEMON | MODE_SYSTEMD)) {
/* command line daemon mode inhibits foreground and debug modes mode */
global.mode &= ~(MODE_DEBUG | MODE_FOREGROUND);
global.mode |= (arg_mode & (MODE_DAEMON | MODE_SYSTEMD));
}
global.mode |= (arg_mode & (MODE_QUIET | MODE_VERBOSE));
if ((global.mode & MODE_DEBUG) && (global.mode & (MODE_DAEMON | MODE_SYSTEMD | MODE_QUIET))) {
Warning("<debug> mode incompatible with <quiet>, <daemon> and <systemd>. Keeping <debug> only.\n");
global.mode &= ~(MODE_DAEMON | MODE_SYSTEMD | MODE_QUIET);
}
if ((global.nbproc > 1) && !(global.mode & (MODE_DAEMON | MODE_SYSTEMD))) {
if (!(global.mode & (MODE_FOREGROUND | MODE_DEBUG)))
Warning("<nbproc> is only meaningful in daemon mode. Setting limit to 1 process.\n");
global.nbproc = 1;
}
if (global.nbproc < 1)
global.nbproc = 1;
swap_buffer = calloc(1, global.tune.bufsize);
get_http_auth_buff = calloc(1, global.tune.bufsize);
static_table_key = calloc(1, sizeof(*static_table_key));
fdinfo = calloc(1, sizeof(struct fdinfo) * (global.maxsock));
fdtab = calloc(1, sizeof(struct fdtab) * (global.maxsock));
/*
* Note: we could register external pollers here.
* Built-in pollers have been registered before main().
*/
if (!(global.tune.options & GTUNE_USE_KQUEUE))
disable_poller("kqueue");
if (!(global.tune.options & GTUNE_USE_EPOLL))
disable_poller("epoll");
if (!(global.tune.options & GTUNE_USE_POLL))
disable_poller("poll");
if (!(global.tune.options & GTUNE_USE_SELECT))
disable_poller("select");
/* Note: we could disable any poller by name here */
if (global.mode & (MODE_VERBOSE|MODE_DEBUG)) {
list_pollers(stderr);
fprintf(stderr, "\n");
list_filters(stderr);
}
if (!init_pollers()) {
Alert("No polling mechanism available.\n"
" It is likely that haproxy was built with TARGET=generic and that FD_SETSIZE\n"
" is too low on this platform to support maxconn and the number of listeners\n"
" and servers. You should rebuild haproxy specifying your system using TARGET=\n"
" in order to support other polling systems (poll, epoll, kqueue) or reduce the\n"
" global maxconn setting to accommodate the system's limitation. For reference,\n"
" FD_SETSIZE=%d on this system, global.maxconn=%d resulting in a maximum of\n"
" %d file descriptors. You should thus reduce global.maxconn by %d. Also,\n"
" check build settings using 'haproxy -vv'.\n\n",
FD_SETSIZE, global.maxconn, global.maxsock, (global.maxsock + 1 - FD_SETSIZE) / 2);
exit(1);
}
if (global.mode & (MODE_VERBOSE|MODE_DEBUG)) {
printf("Using %s() as the polling mechanism.\n", cur_poller.name);
}
if (!global.node)
global.node = strdup(hostname);
if (!hlua_post_init())
exit(1);
/* initialize structures for name resolution */
if (!dns_init_resolvers())
exit(1);
free(err_msg);
}
static void deinit_acl_cond(struct acl_cond *cond)
{
struct acl_term_suite *suite, *suiteb;
struct acl_term *term, *termb;
if (!cond)
return;
list_for_each_entry_safe(suite, suiteb, &cond->suites, list) {
list_for_each_entry_safe(term, termb, &suite->terms, list) {
LIST_DEL(&term->list);
free(term);
}
LIST_DEL(&suite->list);
free(suite);
}
free(cond);
}
static void deinit_tcp_rules(struct list *rules)
{
struct act_rule *trule, *truleb;
list_for_each_entry_safe(trule, truleb, rules, list) {
LIST_DEL(&trule->list);
deinit_acl_cond(trule->cond);
free(trule);
}
}
static void deinit_stick_rules(struct list *rules)
{
struct sticking_rule *rule, *ruleb;
list_for_each_entry_safe(rule, ruleb, rules, list) {
LIST_DEL(&rule->list);
deinit_acl_cond(rule->cond);
release_sample_expr(rule->expr);
free(rule);
}
}
void deinit(void)
{
struct proxy *p = proxy, *p0;
struct cap_hdr *h,*h_next;
struct server *s,*s_next;
struct listener *l,*l_next;
struct acl_cond *cond, *condb;
struct hdr_exp *exp, *expb;
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
struct acl *acl, *aclb;
struct switching_rule *rule, *ruleb;
struct server_rule *srule, *sruleb;
struct redirect_rule *rdr, *rdrb;
struct wordlist *wl, *wlb;
struct cond_wordlist *cwl, *cwlb;
struct uri_auth *uap, *ua = NULL;
struct logsrv *log, *logb;
struct logformat_node *lf, *lfb;
struct bind_conf *bind_conf, *bind_back;
int i;
deinit_signals();
while (p) {
free(p->conf.file);
free(p->id);
free(p->check_req);
free(p->cookie_name);
free(p->cookie_domain);
free(p->url_param_name);
free(p->capture_name);
free(p->monitor_uri);
free(p->rdp_cookie_name);
if (p->conf.logformat_string != default_http_log_format &&
p->conf.logformat_string != default_tcp_log_format &&
p->conf.logformat_string != clf_http_log_format)
free(p->conf.logformat_string);
free(p->conf.lfs_file);
free(p->conf.uniqueid_format_string);
free(p->conf.uif_file);
free(p->lbprm.map.srv);
if (p->conf.logformat_sd_string != default_rfc5424_sd_log_format)
free(p->conf.logformat_sd_string);
free(p->conf.lfsd_file);
for (i = 0; i < HTTP_ERR_SIZE; i++)
chunk_destroy(&p->errmsg[i]);
list_for_each_entry_safe(cwl, cwlb, &p->req_add, list) {
LIST_DEL(&cwl->list);
free(cwl->s);
free(cwl);
}
list_for_each_entry_safe(cwl, cwlb, &p->rsp_add, list) {
LIST_DEL(&cwl->list);
free(cwl->s);
free(cwl);
}
list_for_each_entry_safe(cond, condb, &p->mon_fail_cond, list) {
LIST_DEL(&cond->list);
prune_acl_cond(cond);
free(cond);
}
for (exp = p->req_exp; exp != NULL; ) {
if (exp->preg) {
regex_free(exp->preg);
free(exp->preg);
}
free((char *)exp->replace);
expb = exp;
exp = exp->next;
free(expb);
}
for (exp = p->rsp_exp; exp != NULL; ) {
if (exp->preg) {
regex_free(exp->preg);
free(exp->preg);
}
free((char *)exp->replace);
expb = exp;
exp = exp->next;
free(expb);
}
/* build a list of unique uri_auths */
if (!ua)
ua = p->uri_auth;
else {
/* check if p->uri_auth is unique */
for (uap = ua; uap; uap=uap->next)
if (uap == p->uri_auth)
break;
if (!uap && p->uri_auth) {
/* add it, if it is */
p->uri_auth->next = ua;
ua = p->uri_auth;
}
}
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
list_for_each_entry_safe(acl, aclb, &p->acl, list) {
LIST_DEL(&acl->list);
prune_acl(acl);
free(acl);
}
list_for_each_entry_safe(srule, sruleb, &p->server_rules, list) {
LIST_DEL(&srule->list);
prune_acl_cond(srule->cond);
free(srule->cond);
free(srule);
}
list_for_each_entry_safe(rule, ruleb, &p->switching_rules, list) {
LIST_DEL(&rule->list);
if (rule->cond) {
prune_acl_cond(rule->cond);
free(rule->cond);
free(rule->file);
}
free(rule);
}
list_for_each_entry_safe(rdr, rdrb, &p->redirect_rules, list) {
LIST_DEL(&rdr->list);
if (rdr->cond) {
prune_acl_cond(rdr->cond);
free(rdr->cond);
}
free(rdr->rdr_str);
list_for_each_entry_safe(lf, lfb, &rdr->rdr_fmt, list) {
LIST_DEL(&lf->list);
free(lf);
}
free(rdr);
}
list_for_each_entry_safe(log, logb, &p->logsrvs, list) {
LIST_DEL(&log->list);
free(log);
}
list_for_each_entry_safe(lf, lfb, &p->logformat, list) {
LIST_DEL(&lf->list);
free(lf);
}
list_for_each_entry_safe(lf, lfb, &p->logformat_sd, list) {
LIST_DEL(&lf->list);
free(lf);
}
deinit_tcp_rules(&p->tcp_req.inspect_rules);
deinit_tcp_rules(&p->tcp_req.l4_rules);
deinit_stick_rules(&p->storersp_rules);
deinit_stick_rules(&p->sticking_rules);
h = p->req_cap;
while (h) {
h_next = h->next;
free(h->name);
pool_destroy2(h->pool);
free(h);
h = h_next;
}/* end while(h) */
h = p->rsp_cap;
while (h) {
h_next = h->next;
free(h->name);
pool_destroy2(h->pool);
free(h);
h = h_next;
}/* end while(h) */
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
s = p->srv;
while (s) {
s_next = s->next;
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
if (s->check.task) {
task_delete(s->check.task);
task_free(s->check.task);
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
}
MEDIUM: checks: Add supplementary agent checks Allow an auxiliary agent check to be run independently of the regular a regular health check. This is enabled by the agent-check server setting. The agent-port, which specifies the TCP port to use for the agent's connections, is required. The agent-inter, which specifies the interval between agent checks and timeout of agent checks, is optional. If not set the value for regular checks is used. e.g. server web1_1 127.0.0.1:80 check agent-port 10000 If either the health or agent check determines that a server is down then it is marked as being down, otherwise it is marked as being up. An agent health check performed by opening a TCP socket and reading an ASCII string. The string should have one of the following forms: * An ASCII representation of an positive integer percentage. e.g. "75%" Values in this format will set the weight proportional to the initial weight of a server as configured when haproxy starts. * The string "drain". This will cause the weight of a server to be set to 0, and thus it will not accept any new connections other than those that are accepted via persistence. * The string "down", optionally followed by a description string. Mark the server as down and log the description string as the reason. * The string "stopped", optionally followed by a description string. This currently has the same behaviour as "down". * The string "fail", optionally followed by a description string. This currently has the same behaviour as "down". Signed-off-by: Simon Horman <horms@verge.net.au>
2013-11-24 20:46:36 -05:00
if (s->agent.task) {
task_delete(s->agent.task);
task_free(s->agent.task);
}
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
if (s->warmup) {
task_delete(s->warmup);
task_free(s->warmup);
}
free(s->id);
free(s->cookie);
free(s->check.bi);
free(s->check.bo);
MEDIUM: checks: Add supplementary agent checks Allow an auxiliary agent check to be run independently of the regular a regular health check. This is enabled by the agent-check server setting. The agent-port, which specifies the TCP port to use for the agent's connections, is required. The agent-inter, which specifies the interval between agent checks and timeout of agent checks, is optional. If not set the value for regular checks is used. e.g. server web1_1 127.0.0.1:80 check agent-port 10000 If either the health or agent check determines that a server is down then it is marked as being down, otherwise it is marked as being up. An agent health check performed by opening a TCP socket and reading an ASCII string. The string should have one of the following forms: * An ASCII representation of an positive integer percentage. e.g. "75%" Values in this format will set the weight proportional to the initial weight of a server as configured when haproxy starts. * The string "drain". This will cause the weight of a server to be set to 0, and thus it will not accept any new connections other than those that are accepted via persistence. * The string "down", optionally followed by a description string. Mark the server as down and log the description string as the reason. * The string "stopped", optionally followed by a description string. This currently has the same behaviour as "down". * The string "fail", optionally followed by a description string. This currently has the same behaviour as "down". Signed-off-by: Simon Horman <horms@verge.net.au>
2013-11-24 20:46:36 -05:00
free(s->agent.bi);
free(s->agent.bo);
free(s->agent.send_string);
free((char*)s->conf.file);
#ifdef USE_OPENSSL
if (s->use_ssl || s->check.use_ssl)
ssl_sock_free_srv_ctx(s);
#endif
free(s);
s = s_next;
}/* end while(s) */
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
list_for_each_entry_safe(l, l_next, &p->conf.listeners, by_fe) {
unbind_listener(l);
delete_listener(l);
LIST_DEL(&l->by_fe);
LIST_DEL(&l->by_bind);
free(l->name);
free(l->counters);
free(l);
}
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
/* Release unused SSL configs. */
list_for_each_entry_safe(bind_conf, bind_back, &p->conf.bind, by_fe) {
#ifdef USE_OPENSSL
ssl_sock_free_ca(bind_conf);
ssl_sock_free_all_ctx(bind_conf);
free(bind_conf->ca_file);
free(bind_conf->ca_sign_file);
free(bind_conf->ca_sign_pass);
free(bind_conf->ciphers);
free(bind_conf->ecdhe);
free(bind_conf->crl_file);
#endif /* USE_OPENSSL */
free(bind_conf->file);
free(bind_conf->arg);
LIST_DEL(&bind_conf->by_fe);
free(bind_conf);
}
MAJOR: filters: Add filters support This patch adds the support of filters in HAProxy. The main idea is to have a way to "easely" extend HAProxy by adding some "modules", called filters, that will be able to change HAProxy behavior in a programmatic way. To do so, many entry points has been added in code to let filters to hook up to different steps of the processing. A filter must define a flt_ops sutrctures (see include/types/filters.h for details). This structure contains all available callbacks that a filter can define: struct flt_ops { /* * Callbacks to manage the filter lifecycle */ int (*init) (struct proxy *p); void (*deinit)(struct proxy *p); int (*check) (struct proxy *p); /* * Stream callbacks */ void (*stream_start) (struct stream *s); void (*stream_accept) (struct stream *s); void (*session_establish)(struct stream *s); void (*stream_stop) (struct stream *s); /* * HTTP callbacks */ int (*http_start) (struct stream *s, struct http_msg *msg); int (*http_start_body) (struct stream *s, struct http_msg *msg); int (*http_start_chunk) (struct stream *s, struct http_msg *msg); int (*http_data) (struct stream *s, struct http_msg *msg); int (*http_last_chunk) (struct stream *s, struct http_msg *msg); int (*http_end_chunk) (struct stream *s, struct http_msg *msg); int (*http_chunk_trailers)(struct stream *s, struct http_msg *msg); int (*http_end_body) (struct stream *s, struct http_msg *msg); void (*http_end) (struct stream *s, struct http_msg *msg); void (*http_reset) (struct stream *s, struct http_msg *msg); int (*http_pre_process) (struct stream *s, struct http_msg *msg); int (*http_post_process) (struct stream *s, struct http_msg *msg); void (*http_reply) (struct stream *s, short status, const struct chunk *msg); }; To declare and use a filter, in the configuration, the "filter" keyword must be used in a listener/frontend section: frontend test ... filter <FILTER-NAME> [OPTIONS...] The filter referenced by the <FILTER-NAME> must declare a configuration parser on its own name to fill flt_ops and filter_conf field in the proxy's structure. An exemple will be provided later to make it perfectly clear. For now, filters cannot be used in backend section. But this is only a matter of time. Documentation will also be added later. This is the first commit of a long list about filters. It is possible to have several filters on the same listener/frontend. These filters are stored in an array of at most MAX_FILTERS elements (define in include/types/filters.h). Again, this will be replaced later by a list of filters. The filter API has been highly refactored. Main changes are: * Now, HA supports an infinite number of filters per proxy. To do so, filters are stored in list. * Because filters are stored in list, filters state has been moved from the channel structure to the filter structure. This is cleaner because there is no more info about filters in channel structure. * It is possible to defined filters on backends only. For such filters, stream_start/stream_stop callbacks are not called. Of course, it is possible to mix frontend and backend filters. * Now, TCP streams are also filtered. All callbacks without the 'http_' prefix are called for all kind of streams. In addition, 2 new callbacks were added to filter data exchanged through a TCP stream: - tcp_data: it is called when new data are available or when old unprocessed data are still waiting. - tcp_forward_data: it is called when some data can be consumed. * New callbacks attached to channel were added: - channel_start_analyze: it is called when a filter is ready to process data exchanged through a channel. 2 new analyzers (a frontend and a backend) are attached to channels to call this callback. For a frontend filter, it is called before any other analyzer. For a backend filter, it is called when a backend is attached to a stream. So some processing cannot be filtered in that case. - channel_analyze: it is called before each analyzer attached to a channel, expects analyzers responsible for data sending. - channel_end_analyze: it is called when all other analyzers have finished their processing. A new analyzers is attached to channels to call this callback. For a TCP stream, this is always the last one called. For a HTTP one, the callback is called when a request/response ends, so it is called one time for each request/response. * 'session_established' callback has been removed. Everything that is done in this callback can be handled by 'channel_start_analyze' on the response channel. * 'http_pre_process' and 'http_post_process' callbacks have been replaced by 'channel_analyze'. * 'http_start' callback has been replaced by 'http_headers'. This new one is called just before headers sending and parsing of the body. * 'http_end' callback has been replaced by 'channel_end_analyze'. * It is possible to set a forwarder for TCP channels. It was already possible to do it for HTTP ones. * Forwarders can partially consumed forwardable data. For this reason a new HTTP message state was added before HTTP_MSG_DONE : HTTP_MSG_ENDING. Now all filters can define corresponding callbacks (http_forward_data and tcp_forward_data). Each filter owns 2 offsets relative to buf->p, next and forward, to track, respectively, input data already parsed but not forwarded yet by the filter and parsed data considered as forwarded by the filter. A any time, we have the warranty that a filter cannot parse or forward more input than previous ones. And, of course, it cannot forward more input than it has parsed. 2 macros has been added to retrieve these offets: FLT_NXT and FLT_FWD. In addition, 2 functions has been added to change the 'next size' and the 'forward size' of a filter. When a filter parses input data, it can alter these data, so the size of these data can vary. This action has an effet on all previous filters that must be handled. To do so, the function 'filter_change_next_size' must be called, passing the size variation. In the same spirit, if a filter alter forwarded data, it must call the function 'filter_change_forward_size'. 'filter_change_next_size' can be called in 'http_data' and 'tcp_data' callbacks and only these ones. And 'filter_change_forward_size' can be called in 'http_forward_data' and 'tcp_forward_data' callbacks and only these ones. The data changes are the filter responsability, but with some limitation. It must not change already parsed/forwarded data or data that previous filters have not parsed/forwarded yet. Because filters can be used on backends, when we the backend is set for a stream, we add filters defined for this backend in the filter list of the stream. But we must only do that when the backend and the frontend of the stream are not the same. Else same filters are added a second time leading to undefined behavior. The HTTP compression code had to be moved. So it simplifies http_response_forward_body function. To do so, the way the data are forwarded has changed. Now, a filter (and only one) can forward data. In a commit to come, this limitation will be removed to let all filters take part to data forwarding. There are 2 new functions that filters should use to deal with this feature: * flt_set_http_data_forwarder: This function sets the filter (using its id) that will forward data for the specified HTTP message. It is possible if it was not already set by another filter _AND_ if no data was yet forwarded (msg->msg_state <= HTTP_MSG_BODY). It returns -1 if an error occurs. * flt_http_data_forwarder: This function returns the filter id that will forward data for the specified HTTP message. If there is no forwarder set, it returns -1. When an HTTP data forwarder is set for the response, the HTTP compression is disabled. Of course, this is not definitive.
2015-04-30 05:48:27 -04:00
flt_deinit(p);
free(p->desc);
free(p->fwdfor_hdr_name);
free_http_req_rules(&p->http_req_rules);
free_http_res_rules(&p->http_res_rules);
free(p->task);
pool_destroy2(p->req_cap_pool);
pool_destroy2(p->rsp_cap_pool);
pool_destroy2(p->table.pool);
p0 = p;
p = p->next;
free(p0);
}/* end while(p) */
while (ua) {
uap = ua;
ua = ua->next;
free(uap->uri_prefix);
free(uap->auth_realm);
free(uap->node);
free(uap->desc);
userlist_free(uap->userlist);
free_http_req_rules(&uap->http_req_rules);
free(uap);
}
userlist_free(userlist);
cfg_unregister_sections();
free_trash_buffers();
chunk_destroy(&trash);
protocol_unbind_all();
#if defined(USE_DEVICEATLAS)
deinit_deviceatlas();
#endif
#ifdef USE_51DEGREES
deinit_51degrees();
#endif
#ifdef USE_WURFL
ha_wurfl_deinit();
#endif
free(global.log_send_hostname); global.log_send_hostname = NULL;
chunk_destroy(&global.log_tag);
free(global.chroot); global.chroot = NULL;
free(global.pidfile); global.pidfile = NULL;
free(global.node); global.node = NULL;
free(global.desc); global.desc = NULL;
free(fdinfo); fdinfo = NULL;
free(fdtab); fdtab = NULL;
free(oldpids); oldpids = NULL;
free(static_table_key); static_table_key = NULL;
free(get_http_auth_buff); get_http_auth_buff = NULL;
free(swap_buffer); swap_buffer = NULL;
free(global_listener_queue_task); global_listener_queue_task = NULL;
list_for_each_entry_safe(log, logb, &global.logsrvs, list) {
LIST_DEL(&log->list);
free(log);
}
list_for_each_entry_safe(wl, wlb, &cfg_cfgfiles, list) {
free(wl->s);
LIST_DEL(&wl->list);
free(wl);
}
vars_prune(&global.vars, NULL, NULL);
REORG/MAJOR: session: rename the "session" entity to "stream" With HTTP/2, we'll have to support multiplexed streams. A stream is in fact the largest part of what we currently call a session, it has buffers, logs, etc. In order to catch any error, this commit removes any reference to the struct session and tries to rename most "session" occurrences in function names to "stream" and "sess" to "strm" when that's related to a session. The files stream.{c,h} were added and session.{c,h} removed. The session will be reintroduced later and a few parts of the stream will progressively be moved overthere. It will more or less contain only what we need in an embryonic session. Sample fetch functions and converters will have to change a bit so that they'll use an L5 (session) instead of what's currently called "L4" which is in fact L6 for now. Once all changes are completed, we should see approximately this : L7 - http_txn L6 - stream L5 - session L4 - connection | applet There will be at most one http_txn per stream, and a same session will possibly be referenced by multiple streams. A connection will point to a session and to a stream. The session will hold all the information we need to keep even when we don't yet have a stream. Some more cleanup is needed because some code was already far from being clean. The server queue management still refers to sessions at many places while comments talk about connections. This will have to be cleaned up once we have a server-side connection pool manager. Stream flags "SN_*" still need to be renamed, it doesn't seem like any of them will need to move to the session.
2015-04-02 18:22:06 -04:00
pool_destroy2(pool2_stream);
pool_destroy2(pool2_session);
pool_destroy2(pool2_connection);
pool_destroy2(pool2_buffer);
pool_destroy2(pool2_requri);
pool_destroy2(pool2_task);
pool_destroy2(pool2_capture);
pool_destroy2(pool2_pendconn);
pool_destroy2(pool2_sig_handlers);
pool_destroy2(pool2_hdr_idx);
pool_destroy2(pool2_http_txn);
[MEDIUM] Fix memory freeing at exit New functions implemented: - deinit_pollers: called at the end of deinit()) - prune_acl: called via list_for_each_entry_safe Add missing pool_destroy2 calls: - p->hdr_idx_pool - pool2_tree64 Implement all task stopping: - health-check: needs new "struct task" in the struct server - queue processing: queue_mgt - appsess_refresh: appsession_refresh before (idle system): ==6079== LEAK SUMMARY: ==6079== definitely lost: 1,112 bytes in 75 blocks. ==6079== indirectly lost: 53,356 bytes in 2,090 blocks. ==6079== possibly lost: 52 bytes in 1 blocks. ==6079== still reachable: 150,996 bytes in 504 blocks. ==6079== suppressed: 0 bytes in 0 blocks. after (idle system): ==6945== LEAK SUMMARY: ==6945== definitely lost: 7,644 bytes in 137 blocks. ==6945== indirectly lost: 9,913 bytes in 587 blocks. ==6945== possibly lost: 0 bytes in 0 blocks. ==6945== still reachable: 0 bytes in 0 blocks. ==6945== suppressed: 0 bytes in 0 blocks. before (running system for ~2m): ==9343== LEAK SUMMARY: ==9343== definitely lost: 1,112 bytes in 75 blocks. ==9343== indirectly lost: 54,199 bytes in 2,122 blocks. ==9343== possibly lost: 52 bytes in 1 blocks. ==9343== still reachable: 151,128 bytes in 509 blocks. ==9343== suppressed: 0 bytes in 0 blocks. after (running system for ~2m): ==11616== LEAK SUMMARY: ==11616== definitely lost: 7,644 bytes in 137 blocks. ==11616== indirectly lost: 9,981 bytes in 591 blocks. ==11616== possibly lost: 0 bytes in 0 blocks. ==11616== still reachable: 4 bytes in 1 blocks. ==11616== suppressed: 0 bytes in 0 blocks. Still not perfect but significant improvement.
2008-05-29 17:53:44 -04:00
deinit_pollers();
} /* end deinit() */
/* sends the signal <sig> to all pids found in <oldpids>. Returns the number of
* pids the signal was correctly delivered to.
*/
static int tell_old_pids(int sig)
{
int p;
int ret = 0;
for (p = 0; p < nb_oldpids; p++)
if (kill(oldpids[p], sig) == 0)
ret++;
return ret;
}
/* Runs the polling loop */
void run_poll_loop()
{
int next;
tv_update_date(0,1);
while (1) {
/* Process a few tasks */
process_runnable_tasks();
/* check if we caught some signals and process them */
signal_process_queue();
/* Check if we can expire some tasks */
next = wake_expired_tasks();
/* stop when there's nothing left to do */
if (jobs == 0)
break;
/* expire immediately if events are pending */
if (fd_cache_num || tasks_run_queue || signal_queue_len || applets_active_queue)
next = now_ms;
/* The poller will ensure it returns around <next> */
cur_poller.poll(&cur_poller, next);
fd_process_cached_events();
applet_run_active();
}
}
/* This is the global management task for listeners. It enables listeners waiting
* for global resources when there are enough free resource, or at least once in
* a while. It is designed to be called as a task.
*/
static struct task *manage_global_listener_queue(struct task *t)
{
int next = TICK_ETERNITY;
/* queue is empty, nothing to do */
if (LIST_ISEMPTY(&global_listener_queue))
goto out;
/* If there are still too many concurrent connections, let's wait for
* some of them to go away. We don't need to re-arm the timer because
* each of them will scan the queue anyway.
*/
if (unlikely(actconn >= global.maxconn))
goto out;
/* We should periodically try to enable listeners waiting for a global
* resource here, because it is possible, though very unlikely, that
* they have been blocked by a temporary lack of global resource such
* as a file descriptor or memory and that the temporary condition has
* disappeared.
*/
dequeue_all_listeners(&global_listener_queue);
out:
t->expire = next;
task_queue(t);
return t;
}
int main(int argc, char **argv)
{
int err, retry;
struct rlimit limit;
char errmsg[100];
int pidfd = -1;
init(argc, argv);
signal_register_fct(SIGQUIT, dump, SIGQUIT);
signal_register_fct(SIGUSR1, sig_soft_stop, SIGUSR1);
signal_register_fct(SIGHUP, sig_dump_state, SIGHUP);
/* Always catch SIGPIPE even on platforms which define MSG_NOSIGNAL.
* Some recent FreeBSD setups report broken pipes, and MSG_NOSIGNAL
* was defined there, so let's stay on the safe side.
*/
signal_register_fct(SIGPIPE, NULL, 0);
/* ulimits */
if (!global.rlimit_nofile)
global.rlimit_nofile = global.maxsock;
if (global.rlimit_nofile) {
limit.rlim_cur = limit.rlim_max = global.rlimit_nofile;
if (setrlimit(RLIMIT_NOFILE, &limit) == -1) {
/* try to set it to the max possible at least */
getrlimit(RLIMIT_NOFILE, &limit);
limit.rlim_cur = limit.rlim_max;
if (setrlimit(RLIMIT_NOFILE, &limit) != -1)
getrlimit(RLIMIT_NOFILE, &limit);
Warning("[%s.main()] Cannot raise FD limit to %d, limit is %d.\n", argv[0], global.rlimit_nofile, (int)limit.rlim_cur);
global.rlimit_nofile = limit.rlim_cur;
}
}
if (global.rlimit_memmax) {
limit.rlim_cur = limit.rlim_max =
global.rlimit_memmax * 1048576ULL;
#ifdef RLIMIT_AS
if (setrlimit(RLIMIT_AS, &limit) == -1) {
Warning("[%s.main()] Cannot fix MEM limit to %d megs.\n",
argv[0], global.rlimit_memmax);
}
#else
if (setrlimit(RLIMIT_DATA, &limit) == -1) {
Warning("[%s.main()] Cannot fix MEM limit to %d megs.\n",
argv[0], global.rlimit_memmax);
}
#endif
}
/* We will loop at most 100 times with 10 ms delay each time.
* That's at most 1 second. We only send a signal to old pids
* if we cannot grab at least one port.
*/
retry = MAX_START_RETRIES;
err = ERR_NONE;
while (retry >= 0) {
struct timeval w;
err = start_proxies(retry == 0 || nb_oldpids == 0);
/* exit the loop on no error or fatal error */
if ((err & (ERR_RETRYABLE|ERR_FATAL)) != ERR_RETRYABLE)
break;
if (nb_oldpids == 0 || retry == 0)
break;
/* FIXME-20060514: Solaris and OpenBSD do not support shutdown() on
* listening sockets. So on those platforms, it would be wiser to
* simply send SIGUSR1, which will not be undoable.
*/
if (tell_old_pids(SIGTTOU) == 0) {
/* no need to wait if we can't contact old pids */
retry = 0;
continue;
}
/* give some time to old processes to stop listening */
w.tv_sec = 0;
w.tv_usec = 10*1000;
select(0, NULL, NULL, NULL, &w);
retry--;
}
/* Note: start_proxies() sends an alert when it fails. */
if ((err & ~ERR_WARN) != ERR_NONE) {
if (retry != MAX_START_RETRIES && nb_oldpids) {
protocol_unbind_all(); /* cleanup everything we can */
tell_old_pids(SIGTTIN);
}
exit(1);
}
if (listeners == 0) {
Alert("[%s.main()] No enabled listener found (check for 'bind' directives) ! Exiting.\n", argv[0]);
/* Note: we don't have to send anything to the old pids because we
* never stopped them. */
exit(1);
}
err = protocol_bind_all(errmsg, sizeof(errmsg));
if ((err & ~ERR_WARN) != ERR_NONE) {
if ((err & ERR_ALERT) || (err & ERR_WARN))
Alert("[%s.main()] %s.\n", argv[0], errmsg);
Alert("[%s.main()] Some protocols failed to start their listeners! Exiting.\n", argv[0]);
protocol_unbind_all(); /* cleanup everything we can */
if (nb_oldpids)
tell_old_pids(SIGTTIN);
exit(1);
} else if (err & ERR_WARN) {
Alert("[%s.main()] %s.\n", argv[0], errmsg);
}
/* prepare pause/play signals */
signal_register_fct(SIGTTOU, sig_pause, SIGTTOU);
signal_register_fct(SIGTTIN, sig_listen, SIGTTIN);
/* MODE_QUIET can inhibit alerts and warnings below this line */
global.mode &= ~MODE_STARTING;
if ((global.mode & MODE_QUIET) && !(global.mode & MODE_VERBOSE)) {
/* detach from the tty */
fclose(stdin); fclose(stdout); fclose(stderr);
}
/* open log & pid files before the chroot */
if (global.mode & (MODE_DAEMON | MODE_SYSTEMD) && global.pidfile != NULL) {
unlink(global.pidfile);
pidfd = open(global.pidfile, O_CREAT | O_WRONLY | O_TRUNC, 0644);
if (pidfd < 0) {
Alert("[%s.main()] Cannot create pidfile %s\n", argv[0], global.pidfile);
if (nb_oldpids)
tell_old_pids(SIGTTIN);
protocol_unbind_all();
exit(1);
}
}
if ((global.last_checks & LSTCHK_NETADM) && global.uid) {
Alert("[%s.main()] Some configuration options require full privileges, so global.uid cannot be changed.\n"
"", argv[0]);
protocol_unbind_all();
exit(1);
}
/* If the user is not root, we'll still let him try the configuration
* but we inform him that unexpected behaviour may occur.
*/
if ((global.last_checks & LSTCHK_NETADM) && getuid())
Warning("[%s.main()] Some options which require full privileges"
" might not work well.\n"
"", argv[0]);
/* chroot if needed */
if (global.chroot != NULL) {
if (chroot(global.chroot) == -1 || chdir("/") == -1) {
Alert("[%s.main()] Cannot chroot(%s).\n", argv[0], global.chroot);
if (nb_oldpids)
tell_old_pids(SIGTTIN);
protocol_unbind_all();
exit(1);
}
}
if (nb_oldpids)
nb_oldpids = tell_old_pids(oldpids_sig);
/* Note that any error at this stage will be fatal because we will not
* be able to restart the old pids.
*/
/* setgid / setuid */
if (global.gid) {
if (getgroups(0, NULL) > 0 && setgroups(0, NULL) == -1)
Warning("[%s.main()] Failed to drop supplementary groups. Using 'gid'/'group'"
" without 'uid'/'user' is generally useless.\n", argv[0]);
if (setgid(global.gid) == -1) {
Alert("[%s.main()] Cannot set gid %d.\n", argv[0], global.gid);
protocol_unbind_all();
exit(1);
}
}
if (global.uid && setuid(global.uid) == -1) {
Alert("[%s.main()] Cannot set uid %d.\n", argv[0], global.uid);
protocol_unbind_all();
exit(1);
}
/* check ulimits */
limit.rlim_cur = limit.rlim_max = 0;
getrlimit(RLIMIT_NOFILE, &limit);
if (limit.rlim_cur < global.maxsock) {
Warning("[%s.main()] FD limit (%d) too low for maxconn=%d/maxsock=%d. Please raise 'ulimit-n' to %d or more to avoid any trouble.\n",
argv[0], (int)limit.rlim_cur, global.maxconn, global.maxsock, global.maxsock);
}
if (global.mode & (MODE_DAEMON | MODE_SYSTEMD)) {
struct proxy *px;
struct peers *curpeers;
int ret = 0;
int *children = calloc(global.nbproc, sizeof(int));
int proc;
BUG/MEDIUM: systemd: let the wrapper know that haproxy has completed or failed Pierre Cheynier found that there's a persistent issue with the systemd wrapper. Too fast reloads can lead to certain old processes not being signaled at all and continuing to run. The problem was tracked down as a race between the startup and the signal processing : nothing prevents the wrapper from starting new processes while others are still starting, and the resulting pid file will only contain the latest pids in this case. This can happen with large configs and/or when a lot of SSL certificates are involved. In order to solve this we want the wrapper to wait for the new processes to complete their startup. But we also want to ensure it doesn't wait for nothing in case of error. The solution found here is to create a pipe between the wrapper and the sub-processes. The wrapper waits on the pipe and the sub-processes are expected to close this pipe once they completed their startup. That way we don't queue up new processes until the previous ones have registered their pids to the pid file. And if anything goes wrong, the wrapper is immediately released. The only thing is that we need the sub-processes to know the pipe's file descriptor. We pass it in an environment variable called HAPROXY_WRAPPER_FD. It was confirmed both by Pierre and myself that this completely solves the "zombie" process issue so that only the new processes continue to listen on the sockets. It seems that in the future this stuff could be moved to the haproxy master process, also getting rid of an environment variable. This fix needs to be backported to 1.6 and 1.5.
2016-10-25 11:20:24 -04:00
char *wrapper_fd;
/* the father launches the required number of processes */
for (proc = 0; proc < global.nbproc; proc++) {
ret = fork();
if (ret < 0) {
Alert("[%s.main()] Cannot fork.\n", argv[0]);
protocol_unbind_all();
exit(1); /* there has been an error */
}
else if (ret == 0) /* child breaks here */
break;
children[proc] = ret;
if (pidfd >= 0) {
char pidstr[100];
snprintf(pidstr, sizeof(pidstr), "%d\n", ret);
shut_your_big_mouth_gcc(write(pidfd, pidstr, strlen(pidstr)));
}
relative_pid++; /* each child will get a different one */
}
#ifdef USE_CPU_AFFINITY
if (proc < global.nbproc && /* child */
proc < LONGBITS && /* only the first 32/64 processes may be pinned */
global.cpu_map[proc]) /* only do this if the process has a CPU map */
#ifdef __FreeBSD__
cpuset_setaffinity(CPU_LEVEL_WHICH, CPU_WHICH_PID, -1, sizeof(unsigned long), (void *)&global.cpu_map[proc]);
#else
sched_setaffinity(0, sizeof(unsigned long), (void *)&global.cpu_map[proc]);
#endif
#endif
/* close the pidfile both in children and father */
if (pidfd >= 0) {
//lseek(pidfd, 0, SEEK_SET); /* debug: emulate eglibc bug */
close(pidfd);
}
BUG/MEDIUM: systemd: let the wrapper know that haproxy has completed or failed Pierre Cheynier found that there's a persistent issue with the systemd wrapper. Too fast reloads can lead to certain old processes not being signaled at all and continuing to run. The problem was tracked down as a race between the startup and the signal processing : nothing prevents the wrapper from starting new processes while others are still starting, and the resulting pid file will only contain the latest pids in this case. This can happen with large configs and/or when a lot of SSL certificates are involved. In order to solve this we want the wrapper to wait for the new processes to complete their startup. But we also want to ensure it doesn't wait for nothing in case of error. The solution found here is to create a pipe between the wrapper and the sub-processes. The wrapper waits on the pipe and the sub-processes are expected to close this pipe once they completed their startup. That way we don't queue up new processes until the previous ones have registered their pids to the pid file. And if anything goes wrong, the wrapper is immediately released. The only thing is that we need the sub-processes to know the pipe's file descriptor. We pass it in an environment variable called HAPROXY_WRAPPER_FD. It was confirmed both by Pierre and myself that this completely solves the "zombie" process issue so that only the new processes continue to listen on the sockets. It seems that in the future this stuff could be moved to the haproxy master process, also getting rid of an environment variable. This fix needs to be backported to 1.6 and 1.5.
2016-10-25 11:20:24 -04:00
/* each child must notify the wrapper that it's ready by closing the requested fd */
wrapper_fd = getenv("HAPROXY_WRAPPER_FD");
if (wrapper_fd) {
int pipe_fd = atoi(wrapper_fd);
if (pipe_fd >= 0)
close(pipe_fd);
}
/* We won't ever use this anymore */
free(oldpids); oldpids = NULL;
free(global.chroot); global.chroot = NULL;
free(global.pidfile); global.pidfile = NULL;
if (proc == global.nbproc) {
if (global.mode & MODE_SYSTEMD) {
int i;
protocol_unbind_all();
for (i = 1; i < argc; i++) {
memset(argv[i], '\0', strlen(argv[i]));
}
/* it's OK because "-Ds -f x" is the shortest form going here */
memcpy(argv[0] + strlen(argv[0]), "-master", 8);
for (proc = 0; proc < global.nbproc; proc++)
while (waitpid(children[proc], NULL, 0) == -1 && errno == EINTR);
}
exit(0); /* parent must leave */
}
/* we might have to unbind some proxies from some processes */
px = proxy;
while (px != NULL) {
if (px->bind_proc && px->state != PR_STSTOPPED) {
if (!(px->bind_proc & (1UL << proc)))
stop_proxy(px);
}
px = px->next;
}
/* we might have to unbind some peers sections from some processes */
for (curpeers = peers; curpeers; curpeers = curpeers->next) {
if (!curpeers->peers_fe)
continue;
if (curpeers->peers_fe->bind_proc & (1UL << proc))
continue;
stop_proxy(curpeers->peers_fe);
/* disable this peer section so that it kills itself */
signal_unregister_handler(curpeers->sighandler);
task_delete(curpeers->sync_task);
task_free(curpeers->sync_task);
curpeers->sync_task = NULL;
task_free(curpeers->peers_fe->task);
curpeers->peers_fe->task = NULL;
curpeers->peers_fe = NULL;
}
free(children);
children = NULL;
/* if we're NOT in QUIET mode, we should now close the 3 first FDs to ensure
* that we can detach from the TTY. We MUST NOT do it in other cases since
* it would have already be done, and 0-2 would have been affected to listening
* sockets
*/
if (!(global.mode & MODE_QUIET) || (global.mode & MODE_VERBOSE)) {
/* detach from the tty */
fclose(stdin); fclose(stdout); fclose(stderr);
global.mode &= ~MODE_VERBOSE;
global.mode |= MODE_QUIET; /* ensure that we won't say anything from now */
}
pid = getpid(); /* update child's pid */
setsid();
fork_poller();
}
protocol_enable_all();
/*
* That's it : the central polling loop. Run until we stop.
*/
run_poll_loop();
/* Do some cleanup */
deinit();
exit(0);
}
/*
* Local variables:
* c-indent-level: 8
* c-basic-offset: 8
* End:
*/