haproxy/src/backend.c

1858 lines
53 KiB
C
Raw Normal View History

/*
* Backend variables and functions.
*
* Copyright 2000-2013 Willy Tarreau <w@1wt.eu>
*
* 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.
*
*/
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <syslog.h>
#include <string.h>
#include <ctype.h>
#include <sys/types.h>
#include <common/buffer.h>
#include <common/compat.h>
#include <common/config.h>
#include <common/debug.h>
#include <common/hash.h>
#include <common/ticks.h>
#include <common/time.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 14:11:45 +00:00
#include <common/namespace.h>
#include <types/global.h>
#include <proto/acl.h>
#include <proto/arg.h>
#include <proto/backend.h>
#include <proto/channel.h>
#include <proto/frontend.h>
#include <proto/lb_chash.h>
#include <proto/lb_fas.h>
#include <proto/lb_fwlc.h>
#include <proto/lb_fwrr.h>
#include <proto/lb_map.h>
#include <proto/log.h>
#include <proto/obj_type.h>
#include <proto/payload.h>
#include <proto/protocol.h>
#include <proto/proto_http.h>
#include <proto/proto_tcp.h>
#include <proto/proxy.h>
#include <proto/queue.h>
#include <proto/sample.h>
#include <proto/server.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 22:22:06 +00:00
#include <proto/stream.h>
#include <proto/raw_sock.h>
#include <proto/stream_interface.h>
#include <proto/task.h>
#ifdef USE_OPENSSL
#include <proto/ssl_sock.h>
#endif /* USE_OPENSSL */
int be_lastsession(const struct proxy *be)
{
if (be->be_counters.last_sess)
return now.tv_sec - be->be_counters.last_sess;
return -1;
}
/* helper function to invoke the correct hash method */
static unsigned int gen_hash(const struct proxy* px, const char* key, unsigned long len)
{
unsigned int hash;
switch (px->lbprm.algo & BE_LB_HASH_FUNC) {
case BE_LB_HFCN_DJB2:
hash = hash_djb2(key, len);
break;
case BE_LB_HFCN_WT6:
hash = hash_wt6(key, len);
break;
case BE_LB_HFCN_CRC32:
hash = hash_crc32(key, len);
break;
case BE_LB_HFCN_SDBM:
/* this is the default hash function */
default:
hash = hash_sdbm(key, len);
break;
}
return hash;
}
/*
* This function recounts the number of usable active and backup servers for
* proxy <p>. These numbers are returned into the p->srv_act and p->srv_bck.
* This function also recomputes the total active and backup weights. However,
* it does not update tot_weight nor tot_used. Use update_backend_weight() for
* this.
*/
void recount_servers(struct proxy *px)
{
struct server *srv;
px->srv_act = px->srv_bck = 0;
px->lbprm.tot_wact = px->lbprm.tot_wbck = 0;
px->lbprm.fbck = NULL;
for (srv = px->srv; srv != NULL; srv = srv->next) {
if (!srv_is_usable(srv))
continue;
if (srv->flags & SRV_F_BACKUP) {
if (!px->srv_bck &&
!(px->options & PR_O_USE_ALL_BK))
px->lbprm.fbck = srv;
px->srv_bck++;
srv->cumulative_weight = px->lbprm.tot_wbck;
px->lbprm.tot_wbck += srv->eweight;
} else {
px->srv_act++;
srv->cumulative_weight = px->lbprm.tot_wact;
px->lbprm.tot_wact += srv->eweight;
}
}
}
/* This function simply updates the backend's tot_weight and tot_used values
* after servers weights have been updated. It is designed to be used after
* recount_servers() or equivalent.
*/
void update_backend_weight(struct proxy *px)
{
if (px->srv_act) {
px->lbprm.tot_weight = px->lbprm.tot_wact;
px->lbprm.tot_used = px->srv_act;
}
else if (px->lbprm.fbck) {
/* use only the first backup server */
px->lbprm.tot_weight = px->lbprm.fbck->eweight;
px->lbprm.tot_used = 1;
}
else {
px->lbprm.tot_weight = px->lbprm.tot_wbck;
px->lbprm.tot_used = px->srv_bck;
}
}
/*
* This function tries to find a running server for the proxy <px> following
* the source hash method. Depending on the number of active/backup servers,
* it will either look for active servers, or for backup servers.
* If any server is found, it will be returned. If no valid server is found,
* NULL is returned.
*/
struct server *get_server_sh(struct proxy *px, const char *addr, int len)
{
unsigned int h, l;
if (px->lbprm.tot_weight == 0)
return NULL;
l = h = 0;
/* note: we won't hash if there's only one server left */
if (px->lbprm.tot_used == 1)
goto hash_done;
while ((l + sizeof (int)) <= len) {
h ^= ntohl(*(unsigned int *)(&addr[l]));
l += sizeof (int);
}
2013-11-05 16:54:02 +00:00
if ((px->lbprm.algo & BE_LB_HASH_MOD) == BE_LB_HMOD_AVAL)
h = full_hash(h);
hash_done:
if (px->lbprm.algo & BE_LB_LKUP_CHTREE)
return chash_get_server_hash(px, h);
else
return map_get_server_hash(px, h);
}
/*
* This function tries to find a running server for the proxy <px> following
* the URI hash method. In order to optimize cache hits, the hash computation
* ends at the question mark. Depending on the number of active/backup servers,
* it will either look for active servers, or for backup servers.
* If any server is found, it will be returned. If no valid server is found,
* NULL is returned.
*
* This code was contributed by Guillaume Dallaire, who also selected this hash
* algorithm out of a tens because it gave him the best results.
*
*/
struct server *get_server_uh(struct proxy *px, char *uri, int uri_len)
{
unsigned int hash = 0;
int c;
int slashes = 0;
const char *start, *end;
if (px->lbprm.tot_weight == 0)
return NULL;
/* note: we won't hash if there's only one server left */
if (px->lbprm.tot_used == 1)
goto hash_done;
if (px->uri_len_limit)
uri_len = MIN(uri_len, px->uri_len_limit);
start = end = uri;
while (uri_len--) {
c = *end;
if (c == '/') {
slashes++;
if (slashes == px->uri_dirs_depth1) /* depth+1 */
break;
}
MINOR: balance uri: added 'whole' parameter to include query string in hash calculation This patch brings a new "whole" parameter to "balance uri" which makes the hash work over the whole uri, not just the part before the query string. Len and depth parameter are still honnored. The reason for this new feature is explained below. I have 3 backend servers, each accepting different form of HTTP queries: http://backend1.server.tld/service1.php?q=... http://backend1.server.tld/service2.php?q=... http://backend2.server.tld/index.php?query=...&subquery=... http://backend3.server.tld/image/49b8c0d9ff Each backend server returns a different response based on either: - the URI path (the left part of the URI before the question mark) - the query string (the right part of the URI after the question mark) - or the combination of both I wanted to set up a common caching cluster (using 6 Squid servers, each configured as reverse proxy for those 3 backends) and have HAProxy balance the queries among the Squid servers based on URL. I also wanted to achieve hight cache hit ration on each Squid server and send the same queries to the same Squid servers. Initially I was considering using the 'balance uri' algorithm, but that would not work as in case of backend2 all queries would go to only one Squid server. The 'balance url_param' would not work either as it would send the backend3 queries to only one Squid server. So I thought the simplest solution would be to use 'balance uri', but to calculate the hash based on the whole URI (URI path + query string), instead of just the URI path.
2012-05-19 09:19:54 +00:00
else if (c == '?' && !px->uri_whole)
break;
end++;
}
hash = gen_hash(px, start, (end - start));
2013-11-05 16:54:02 +00:00
if ((px->lbprm.algo & BE_LB_HASH_MOD) == BE_LB_HMOD_AVAL)
hash = full_hash(hash);
hash_done:
if (px->lbprm.algo & BE_LB_LKUP_CHTREE)
return chash_get_server_hash(px, hash);
else
return map_get_server_hash(px, hash);
}
/*
* This function tries to find a running server for the proxy <px> following
* the URL parameter hash method. It looks for a specific parameter in the
* URL and hashes it to compute the server ID. This is useful to optimize
* performance by avoiding bounces between servers in contexts where sessions
* are shared but cookies are not usable. If the parameter is not found, NULL
* is returned. If any server is found, it will be returned. If no valid server
* is found, NULL is returned.
*/
struct server *get_server_ph(struct proxy *px, const char *uri, int uri_len)
{
unsigned int hash = 0;
const char *start, *end;
const char *p;
const char *params;
int plen;
/* when tot_weight is 0 then so is srv_count */
if (px->lbprm.tot_weight == 0)
return NULL;
if ((p = memchr(uri, '?', uri_len)) == NULL)
return NULL;
p++;
uri_len -= (p - uri);
plen = px->url_param_len;
params = p;
while (uri_len > plen) {
/* Look for the parameter name followed by an equal symbol */
if (params[plen] == '=') {
if (memcmp(params, px->url_param_name, plen) == 0) {
/* OK, we have the parameter here at <params>, and
* the value after the equal sign, at <p>
* skip the equal symbol
*/
p += plen + 1;
start = end = p;
uri_len -= plen + 1;
while (uri_len && *end != '&') {
uri_len--;
end++;
}
hash = gen_hash(px, start, (end - start));
2013-11-05 16:54:02 +00:00
if ((px->lbprm.algo & BE_LB_HASH_MOD) == BE_LB_HMOD_AVAL)
hash = full_hash(hash);
if (px->lbprm.algo & BE_LB_LKUP_CHTREE)
return chash_get_server_hash(px, hash);
else
return map_get_server_hash(px, hash);
}
}
/* skip to next parameter */
p = memchr(params, '&', uri_len);
if (!p)
return NULL;
p++;
uri_len -= (p - params);
params = p;
}
return NULL;
}
/*
* this does the same as the previous server_ph, but check the body contents
*/
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 22:22:06 +00:00
struct server *get_server_ph_post(struct stream *s)
{
unsigned int hash = 0;
struct http_txn *txn = s->txn;
struct channel *req = &s->req;
struct http_msg *msg = &txn->req;
struct proxy *px = s->be;
unsigned int plen = px->url_param_len;
unsigned long len = http_body_bytes(msg);
const char *params = b_ptr(req->buf, -http_data_rewind(msg));
const char *p = params;
const char *start, *end;
if (len == 0)
return NULL;
if (len > req->buf->data + req->buf->size - p)
len = req->buf->data + req->buf->size - p;
if (px->lbprm.tot_weight == 0)
return NULL;
while (len > plen) {
/* Look for the parameter name followed by an equal symbol */
if (params[plen] == '=') {
if (memcmp(params, px->url_param_name, plen) == 0) {
/* OK, we have the parameter here at <params>, and
* the value after the equal sign, at <p>
* skip the equal symbol
*/
p += plen + 1;
start = end = p;
len -= plen + 1;
while (len && *end != '&') {
if (unlikely(!HTTP_IS_TOKEN(*p))) {
/* if in a POST, body must be URI encoded or it's not a URI.
* Do not interpret any possible binary data as a parameter.
*/
if (likely(HTTP_IS_LWS(*p))) /* eol, uncertain uri len */
break;
return NULL; /* oh, no; this is not uri-encoded.
* This body does not contain parameters.
*/
}
len--;
end++;
/* should we break if vlen exceeds limit? */
}
hash = gen_hash(px, start, (end - start));
2013-11-05 16:54:02 +00:00
if ((px->lbprm.algo & BE_LB_HASH_MOD) == BE_LB_HMOD_AVAL)
hash = full_hash(hash);
if (px->lbprm.algo & BE_LB_LKUP_CHTREE)
return chash_get_server_hash(px, hash);
else
return map_get_server_hash(px, hash);
}
}
/* skip to next parameter */
p = memchr(params, '&', len);
if (!p)
return NULL;
p++;
len -= (p - params);
params = p;
}
return NULL;
}
/*
* This function tries to find a running server for the proxy <px> following
* the Header parameter hash method. It looks for a specific parameter in the
* URL and hashes it to compute the server ID. This is useful to optimize
* performance by avoiding bounces between servers in contexts where sessions
* are shared but cookies are not usable. If the parameter is not found, NULL
* is returned. If any server is found, it will be returned. If no valid server
* is found, NULL is returned.
*/
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 22:22:06 +00:00
struct server *get_server_hh(struct stream *s)
{
unsigned int hash = 0;
struct http_txn *txn = s->txn;
struct proxy *px = s->be;
unsigned int plen = px->hh_len;
unsigned long len;
struct hdr_ctx ctx;
const char *p;
const char *start, *end;
/* tot_weight appears to mean srv_count */
if (px->lbprm.tot_weight == 0)
return NULL;
ctx.idx = 0;
/* if the message is chunked, we skip the chunk size, but use the value as len */
http_find_header2(px->hh_name, plen, b_ptr(s->req.buf, -http_hdr_rewind(&txn->req)), &txn->hdr_idx, &ctx);
/* if the header is not found or empty, let's fallback to round robin */
if (!ctx.idx || !ctx.vlen)
return NULL;
/* note: we won't hash if there's only one server left */
if (px->lbprm.tot_used == 1)
goto hash_done;
/* Found a the hh_name in the headers.
* we will compute the hash based on this value ctx.val.
*/
len = ctx.vlen;
p = (char *)ctx.line + ctx.val;
if (!px->hh_match_domain) {
hash = gen_hash(px, p, len);
} else {
int dohash = 0;
p += len;
/* special computation, use only main domain name, not tld/host
* going back from the end of string, start hashing at first
* dot stop at next.
* This is designed to work with the 'Host' header, and requires
* a special option to activate this.
*/
end = p;
while (len) {
if (dohash) {
/* Rewind the pointer until the previous char
* is a dot, this will allow to set the start
* position of the domain. */
if (*(p - 1) == '.')
break;
}
else if (*p == '.') {
/* The pointer is rewinded to the dot before the
* tld, we memorize the end of the domain and
* can enter the domain processing. */
end = p;
dohash = 1;
}
p--;
len--;
}
start = p;
hash = gen_hash(px, start, (end - start));
}
2013-11-05 16:54:02 +00:00
if ((px->lbprm.algo & BE_LB_HASH_MOD) == BE_LB_HMOD_AVAL)
hash = full_hash(hash);
hash_done:
if (px->lbprm.algo & BE_LB_LKUP_CHTREE)
return chash_get_server_hash(px, hash);
else
return map_get_server_hash(px, hash);
}
/* RDP Cookie HASH. */
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 22:22:06 +00:00
struct server *get_server_rch(struct stream *s)
{
unsigned int hash = 0;
struct proxy *px = s->be;
unsigned long len;
int ret;
struct sample smp;
BUG/MAJOR: fix regression on content-based hashing and http-send-name-header The recent split between the buffers and HTTP messages in 1.5-dev9 caused a major trouble : in the past, we used to keep a pointer to HTTP data in the buffer struct itself, which was the cause of most of the pain we had to deal with buffers. Now the two are split but we lost the information about the beginning of the HTTP message once it's being forwarded. While it seems normal, it happens that several parts of the code currently rely on this ability to inspect a buffer containing old contents : - balance uri - balance url_param - balance url_param check_post - balance hdr() - balance rdp-cookie() - http-send-name-header All these happen after the data are scheduled for being forwarded, which also causes a server to be selected. So for a long time we've been relying on supposedly sent data that we still had a pointer to. Now that we don't have such a pointer anymore, we only have one possibility : when we need to inspect such data, we have to rewind the buffer so that ->p points to where it previously was. We're lucky, no data can leave the buffer before it's being connecting outside, and since no inspection can begin until it's empty, we know that the skipped data are exactly ->o. So we rewind the buffer by ->o to get headers and advance it back by the same amount. Proceeding this way is particularly important when dealing with chunked- encoded requests, because the ->som and ->sov fields may be reused by the chunk parser before the connection attempt is made, so we cannot rely on them. Also, we need to be able to come back after retries and redispatches, which might change the size of the request if http-send-name-header is set. All of this is accounted for by the output queue so in the end it does not look like a bad solution. No backport is needed.
2012-05-18 20:12:14 +00:00
int rewind;
/* tot_weight appears to mean srv_count */
if (px->lbprm.tot_weight == 0)
return NULL;
memset(&smp, 0, sizeof(smp));
b_rew(s->req.buf, rewind = s->req.buf->o);
BUG/MAJOR: fix regression on content-based hashing and http-send-name-header The recent split between the buffers and HTTP messages in 1.5-dev9 caused a major trouble : in the past, we used to keep a pointer to HTTP data in the buffer struct itself, which was the cause of most of the pain we had to deal with buffers. Now the two are split but we lost the information about the beginning of the HTTP message once it's being forwarded. While it seems normal, it happens that several parts of the code currently rely on this ability to inspect a buffer containing old contents : - balance uri - balance url_param - balance url_param check_post - balance hdr() - balance rdp-cookie() - http-send-name-header All these happen after the data are scheduled for being forwarded, which also causes a server to be selected. So for a long time we've been relying on supposedly sent data that we still had a pointer to. Now that we don't have such a pointer anymore, we only have one possibility : when we need to inspect such data, we have to rewind the buffer so that ->p points to where it previously was. We're lucky, no data can leave the buffer before it's being connecting outside, and since no inspection can begin until it's empty, we know that the skipped data are exactly ->o. So we rewind the buffer by ->o to get headers and advance it back by the same amount. Proceeding this way is particularly important when dealing with chunked- encoded requests, because the ->som and ->sov fields may be reused by the chunk parser before the connection attempt is made, so we cannot rely on them. Also, we need to be able to come back after retries and redispatches, which might change the size of the request if http-send-name-header is set. All of this is accounted for by the output queue so in the end it does not look like a bad solution. No backport is needed.
2012-05-18 20:12:14 +00:00
ret = fetch_rdp_cookie_name(s, &smp, px->hh_name, px->hh_len);
len = smp.data.u.str.len;
b_adv(s->req.buf, rewind);
BUG/MAJOR: fix regression on content-based hashing and http-send-name-header The recent split between the buffers and HTTP messages in 1.5-dev9 caused a major trouble : in the past, we used to keep a pointer to HTTP data in the buffer struct itself, which was the cause of most of the pain we had to deal with buffers. Now the two are split but we lost the information about the beginning of the HTTP message once it's being forwarded. While it seems normal, it happens that several parts of the code currently rely on this ability to inspect a buffer containing old contents : - balance uri - balance url_param - balance url_param check_post - balance hdr() - balance rdp-cookie() - http-send-name-header All these happen after the data are scheduled for being forwarded, which also causes a server to be selected. So for a long time we've been relying on supposedly sent data that we still had a pointer to. Now that we don't have such a pointer anymore, we only have one possibility : when we need to inspect such data, we have to rewind the buffer so that ->p points to where it previously was. We're lucky, no data can leave the buffer before it's being connecting outside, and since no inspection can begin until it's empty, we know that the skipped data are exactly ->o. So we rewind the buffer by ->o to get headers and advance it back by the same amount. Proceeding this way is particularly important when dealing with chunked- encoded requests, because the ->som and ->sov fields may be reused by the chunk parser before the connection attempt is made, so we cannot rely on them. Also, we need to be able to come back after retries and redispatches, which might change the size of the request if http-send-name-header is set. All of this is accounted for by the output queue so in the end it does not look like a bad solution. No backport is needed.
2012-05-18 20:12:14 +00:00
if (ret == 0 || (smp.flags & SMP_F_MAY_CHANGE) || len == 0)
return NULL;
/* note: we won't hash if there's only one server left */
if (px->lbprm.tot_used == 1)
goto hash_done;
/* Found a the hh_name in the headers.
* we will compute the hash based on this value ctx.val.
*/
hash = gen_hash(px, smp.data.u.str.str, len);
2013-11-05 16:54:02 +00:00
if ((px->lbprm.algo & BE_LB_HASH_MOD) == BE_LB_HMOD_AVAL)
hash = full_hash(hash);
hash_done:
if (px->lbprm.algo & BE_LB_LKUP_CHTREE)
return chash_get_server_hash(px, hash);
else
return map_get_server_hash(px, hash);
}
/*
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 22:22:06 +00:00
* This function applies the load-balancing algorithm to the stream, as
* defined by the backend it is assigned to. The stream is then marked as
* 'assigned'.
*
* This function MAY NOT be called with SF_ASSIGNED already set. If the stream
* had a server previously assigned, it is rebalanced, trying to avoid the same
* server, which should still be present in target_srv(&s->target) before the call.
* The function tries to keep the original connection slot if it reconnects to
* the same server, otherwise it releases it and tries to offer it.
*
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 22:22:06 +00:00
* It is illegal to call this function with a stream in a queue.
*
* It may return :
* SRV_STATUS_OK if everything is OK. ->srv and ->target are assigned.
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 22:22:06 +00:00
* SRV_STATUS_NOSRV if no server is available. Stream is not ASSIGNED
* SRV_STATUS_FULL if all servers are saturated. Stream is not ASSIGNED
* SRV_STATUS_INTERNAL for other unrecoverable errors.
*
* Upon successful return, the stream flag SF_ASSIGNED is set to indicate that
* it does not need to be called anymore. This means that target_srv(&s->target)
* can be trusted in balance and direct modes.
*
*/
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 22:22:06 +00:00
int assign_server(struct stream *s)
{
struct connection *conn;
struct server *conn_slot;
struct server *srv, *prev_srv;
int err;
[MEDIUM]: Prevent redispatcher from selecting the same server, version #3 When haproxy decides that session needs to be redispatched it chose a server, but there is no guarantee for it to be a different one. So, it often happens that selected server is exactly the same that it was previously, so a client ends up with a 503 error anyway, especially when one sever has much bigger weight than others. Changes from the previous version: - drop stupid and unnecessary SN_DIRECT changes - assign_server(): use srvtoavoid to keep the old server and clear s->srv so SRV_STATUS_NOSRV guarantees that t->srv == NULL (again) and get_server_rr_with_conns has chances to work (previously we were passing a NULL here) - srv_redispatch_connect(): remove t->srv->cum_sess and t->srv->failed_conns incrementing as t->srv was guaranteed to be NULL - add avoididx to get_server_rr_with_conns. I hope I correctly understand this code. - fix http_flush_cookie_flags() and move it to assign_server_and_queue() directly. The code here was supposed to set CK_DOWN and clear CK_VALID, but: (TX_CK_VALID | TX_CK_DOWN) == TX_CK_VALID == TX_CK_MASK so: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags ^= (TX_CK_VALID | TX_CK_DOWN); was really a: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags &= TX_CK_VALID Now haproxy logs "--DI" after redispatching connection. - defer srv->redispatches++ and s->be->redispatches++ so there are called only if a conenction was redispatched, not only supposed to. - don't increment lbconn if redispatcher selected the same sarver - don't count unsuccessfully redispatched connections as redispatched connections - don't count redispatched connections as errors, so: - the number of connections effectively served by a server is: srv->cum_sess - srv->failed_conns - srv->retries - srv->redispatches and SUM(servers->failed_conns) == be->failed_conns - requires the "Don't increment server connections too much + fix retries" patch - needs little more testing and probably some discussion so reverting to the RFC state Tests #1: retries 4 redispatch i) 1 server(s): b (wght=1, down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request failed ii) server(s): b (wght=1, down), u (wght=1, down) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=1, retr=0, redis=0 -> request FAILED iii) 2 server(s): b (wght=1, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK iv) 2 server(s): b (wght=100, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK v) 1 server(s): b (down for first 4 SYNS) b) sessions=5, lbtot=1, err_conn=0, retr=4, redis=0 -> request OK Tests #2: retries 4 i) 1 server(s): b (down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request FAILED
2008-02-22 02:50:19 +00:00
DPRINTF(stderr,"assign_server : s=%p\n",s);
err = SRV_STATUS_INTERNAL;
if (unlikely(s->pend_pos || s->flags & SF_ASSIGNED))
goto out_err;
[MEDIUM]: Prevent redispatcher from selecting the same server, version #3 When haproxy decides that session needs to be redispatched it chose a server, but there is no guarantee for it to be a different one. So, it often happens that selected server is exactly the same that it was previously, so a client ends up with a 503 error anyway, especially when one sever has much bigger weight than others. Changes from the previous version: - drop stupid and unnecessary SN_DIRECT changes - assign_server(): use srvtoavoid to keep the old server and clear s->srv so SRV_STATUS_NOSRV guarantees that t->srv == NULL (again) and get_server_rr_with_conns has chances to work (previously we were passing a NULL here) - srv_redispatch_connect(): remove t->srv->cum_sess and t->srv->failed_conns incrementing as t->srv was guaranteed to be NULL - add avoididx to get_server_rr_with_conns. I hope I correctly understand this code. - fix http_flush_cookie_flags() and move it to assign_server_and_queue() directly. The code here was supposed to set CK_DOWN and clear CK_VALID, but: (TX_CK_VALID | TX_CK_DOWN) == TX_CK_VALID == TX_CK_MASK so: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags ^= (TX_CK_VALID | TX_CK_DOWN); was really a: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags &= TX_CK_VALID Now haproxy logs "--DI" after redispatching connection. - defer srv->redispatches++ and s->be->redispatches++ so there are called only if a conenction was redispatched, not only supposed to. - don't increment lbconn if redispatcher selected the same sarver - don't count unsuccessfully redispatched connections as redispatched connections - don't count redispatched connections as errors, so: - the number of connections effectively served by a server is: srv->cum_sess - srv->failed_conns - srv->retries - srv->redispatches and SUM(servers->failed_conns) == be->failed_conns - requires the "Don't increment server connections too much + fix retries" patch - needs little more testing and probably some discussion so reverting to the RFC state Tests #1: retries 4 redispatch i) 1 server(s): b (wght=1, down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request failed ii) server(s): b (wght=1, down), u (wght=1, down) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=1, retr=0, redis=0 -> request FAILED iii) 2 server(s): b (wght=1, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK iv) 2 server(s): b (wght=100, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK v) 1 server(s): b (down for first 4 SYNS) b) sessions=5, lbtot=1, err_conn=0, retr=4, redis=0 -> request OK Tests #2: retries 4 i) 1 server(s): b (down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request FAILED
2008-02-22 02:50:19 +00:00
prev_srv = objt_server(s->target);
conn_slot = s->srv_conn;
/* We have to release any connection slot before applying any LB algo,
* otherwise we may erroneously end up with no available slot.
*/
if (conn_slot)
sess_change_server(s, NULL);
/* We will now try to find the good server and store it into <objt_server(s->target)>.
* Note that <objt_server(s->target)> may be NULL in case of dispatch or proxy mode,
* as well as if no server is available (check error code).
*/
srv = NULL;
s->target = NULL;
conn = objt_conn(s->si[1].end);
if (conn &&
(conn->flags & CO_FL_CONNECTED) &&
objt_server(conn->target) && __objt_server(conn->target)->proxy == s->be &&
((s->txn && s->txn->flags & TX_PREFER_LAST) ||
((s->be->options & PR_O_PREF_LAST) &&
(!s->be->max_ka_queue ||
server_has_room(__objt_server(conn->target)) ||
(__objt_server(conn->target)->nbpend + 1) < s->be->max_ka_queue))) &&
srv_is_usable(__objt_server(conn->target))) {
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 22:22:06 +00:00
/* This stream was relying on a server in a previous request
* and the proxy has "option prefer-last-server" set, so
* let's try to reuse the same server.
*/
srv = __objt_server(conn->target);
s->target = &srv->obj_type;
}
else if (s->be->lbprm.algo & BE_LB_KIND) {
/* we must check if we have at least one server available */
if (!s->be->lbprm.tot_weight) {
err = SRV_STATUS_NOSRV;
goto out;
}
/* First check whether we need to fetch some data or simply call
* the LB lookup function. Only the hashing functions will need
* some input data in fact, and will support multiple algorithms.
*/
switch (s->be->lbprm.algo & BE_LB_LKUP) {
case BE_LB_LKUP_RRTREE:
srv = fwrr_get_next_server(s->be, prev_srv);
break;
case BE_LB_LKUP_FSTREE:
srv = fas_get_next_server(s->be, prev_srv);
break;
case BE_LB_LKUP_LCTREE:
srv = fwlc_get_next_server(s->be, prev_srv);
break;
case BE_LB_LKUP_CHTREE:
case BE_LB_LKUP_MAP:
if ((s->be->lbprm.algo & BE_LB_KIND) == BE_LB_KIND_RR) {
if (s->be->lbprm.algo & BE_LB_LKUP_CHTREE)
srv = chash_get_next_server(s->be, prev_srv);
else
srv = map_get_server_rr(s->be, prev_srv);
break;
}
else if ((s->be->lbprm.algo & BE_LB_KIND) != BE_LB_KIND_HI) {
/* unknown balancing algorithm */
err = SRV_STATUS_INTERNAL;
goto out;
}
switch (s->be->lbprm.algo & BE_LB_PARM) {
case BE_LB_HASH_SRC:
conn = objt_conn(strm_orig(s));
if (conn && conn->addr.from.ss_family == AF_INET) {
srv = get_server_sh(s->be,
(void *)&((struct sockaddr_in *)&conn->addr.from)->sin_addr,
4);
}
else if (conn && conn->addr.from.ss_family == AF_INET6) {
srv = get_server_sh(s->be,
(void *)&((struct sockaddr_in6 *)&conn->addr.from)->sin6_addr,
16);
}
else {
/* unknown IP family */
err = SRV_STATUS_INTERNAL;
goto out;
}
break;
case BE_LB_HASH_URI:
/* URI hashing */
if (!s->txn || s->txn->req.msg_state < HTTP_MSG_BODY)
break;
srv = get_server_uh(s->be,
b_ptr(s->req.buf, -http_uri_rewind(&s->txn->req)),
s->txn->req.sl.rq.u_l);
break;
case BE_LB_HASH_PRM:
/* URL Parameter hashing */
if (!s->txn || s->txn->req.msg_state < HTTP_MSG_BODY)
break;
srv = get_server_ph(s->be,
b_ptr(s->req.buf, -http_uri_rewind(&s->txn->req)),
s->txn->req.sl.rq.u_l);
if (!srv && s->txn->meth == HTTP_METH_POST)
srv = get_server_ph_post(s);
break;
case BE_LB_HASH_HDR:
/* Header Parameter hashing */
if (!s->txn || s->txn->req.msg_state < HTTP_MSG_BODY)
break;
srv = get_server_hh(s);
break;
case BE_LB_HASH_RDP:
/* RDP Cookie hashing */
srv = get_server_rch(s);
break;
default:
/* unknown balancing algorithm */
err = SRV_STATUS_INTERNAL;
goto out;
}
/* If the hashing parameter was not found, let's fall
* back to round robin on the map.
*/
if (!srv) {
if (s->be->lbprm.algo & BE_LB_LKUP_CHTREE)
srv = chash_get_next_server(s->be, prev_srv);
else
srv = map_get_server_rr(s->be, prev_srv);
}
/* end of map-based LB */
break;
default:
/* unknown balancing algorithm */
err = SRV_STATUS_INTERNAL;
goto out;
}
if (!srv) {
err = SRV_STATUS_FULL;
goto out;
}
else if (srv != prev_srv) {
s->be->be_counters.cum_lbconn++;
srv->counters.cum_lbconn++;
}
s->target = &srv->obj_type;
}
else if (s->be->options & (PR_O_DISPATCH | PR_O_TRANSP)) {
s->target = &s->be->obj_type;
}
else if ((s->be->options & PR_O_HTTP_PROXY) &&
(conn = objt_conn(s->si[1].end)) &&
is_addr(&conn->addr.to)) {
/* in proxy mode, we need a valid destination address */
s->target = &s->be->obj_type;
}
else {
err = SRV_STATUS_NOSRV;
goto out;
}
s->flags |= SF_ASSIGNED;
err = SRV_STATUS_OK;
out:
/* Either we take back our connection slot, or we offer it to someone
* else if we don't need it anymore.
*/
if (conn_slot) {
if (conn_slot == srv) {
sess_change_server(s, srv);
} else {
if (may_dequeue_tasks(conn_slot, s->be))
process_srv_queue(conn_slot);
}
}
out_err:
return err;
}
/*
* This function assigns a server address to a stream, and sets SF_ADDR_SET.
* The address is taken from the currently assigned server, or from the
* dispatch or transparent address.
*
* It may return :
* SRV_STATUS_OK if everything is OK.
* SRV_STATUS_INTERNAL for other unrecoverable errors.
*
* Upon successful return, the stream flag SF_ADDR_SET is set. This flag is
* not cleared, so it's to the caller to clear it if required.
*
* The caller is responsible for having already assigned a connection
* to si->end.
*
*/
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 22:22:06 +00:00
int assign_server_address(struct stream *s)
{
struct connection *cli_conn = objt_conn(strm_orig(s));
struct connection *srv_conn = objt_conn(s->si[1].end);
#ifdef DEBUG_FULL
fprintf(stderr,"assign_server_address : s=%p\n",s);
#endif
if ((s->flags & SF_DIRECT) || (s->be->lbprm.algo & BE_LB_KIND)) {
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 22:22:06 +00:00
/* A server is necessarily known for this stream */
if (!(s->flags & SF_ASSIGNED))
return SRV_STATUS_INTERNAL;
srv_conn->addr.to = objt_server(s->target)->addr;
if (!is_addr(&srv_conn->addr.to) && cli_conn) {
/* if the server has no address, we use the same address
* the client asked, which is handy for remapping ports
* locally on multiple addresses at once. Nothing is done
* for AF_UNIX addresses.
*/
conn_get_to_addr(cli_conn);
if (cli_conn->addr.to.ss_family == AF_INET) {
((struct sockaddr_in *)&srv_conn->addr.to)->sin_addr = ((struct sockaddr_in *)&cli_conn->addr.to)->sin_addr;
} else if (cli_conn->addr.to.ss_family == AF_INET6) {
((struct sockaddr_in6 *)&srv_conn->addr.to)->sin6_addr = ((struct sockaddr_in6 *)&cli_conn->addr.to)->sin6_addr;
}
}
/* if this server remaps proxied ports, we'll use
* the port the client connected to with an offset. */
if ((objt_server(s->target)->flags & SRV_F_MAPPORTS) && cli_conn) {
int base_port;
conn_get_to_addr(cli_conn);
/* First, retrieve the port from the incoming connection */
base_port = get_host_port(&cli_conn->addr.to);
/* Second, assign the outgoing connection's port */
base_port += get_host_port(&srv_conn->addr.to);
set_host_port(&srv_conn->addr.to, base_port);
}
}
else if (s->be->options & PR_O_DISPATCH) {
/* connect to the defined dispatch addr */
srv_conn->addr.to = s->be->dispatch_addr;
}
else if ((s->be->options & PR_O_TRANSP) && cli_conn) {
/* in transparent mode, use the original dest addr if no dispatch specified */
conn_get_to_addr(cli_conn);
if (cli_conn->addr.to.ss_family == AF_INET || cli_conn->addr.to.ss_family == AF_INET6)
srv_conn->addr.to = cli_conn->addr.to;
}
else if (s->be->options & PR_O_HTTP_PROXY) {
/* If HTTP PROXY option is set, then server is already assigned
* during incoming client request parsing. */
}
else {
/* no server and no LB algorithm ! */
return SRV_STATUS_INTERNAL;
}
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 14:11:45 +00:00
/* Copy network namespace from client connection */
srv_conn->proxy_netns = cli_conn ? cli_conn->proxy_netns : NULL;
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 14:11:45 +00:00
s->flags |= SF_ADDR_SET;
return SRV_STATUS_OK;
}
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 22:22:06 +00:00
/* This function assigns a server to stream <s> if required, and can add the
* connection to either the assigned server's queue or to the proxy's queue.
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 22:22:06 +00:00
* If ->srv_conn is set, the stream is first released from the server.
* It may also be called with SF_DIRECT and/or SF_ASSIGNED though. It will
* be called before any connection and after any retry or redispatch occurs.
*
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 22:22:06 +00:00
* It is not allowed to call this function with a stream in a queue.
*
* Returns :
*
* SRV_STATUS_OK if everything is OK.
* SRV_STATUS_NOSRV if no server is available. objt_server(s->target) = NULL.
* SRV_STATUS_QUEUED if the connection has been queued.
* SRV_STATUS_FULL if the server(s) is/are saturated and the
* connection could not be queued at the server's,
* which may be NULL if we queue on the backend.
* SRV_STATUS_INTERNAL for other unrecoverable errors.
*
*/
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 22:22:06 +00:00
int assign_server_and_queue(struct stream *s)
{
struct pendconn *p;
struct server *srv;
int err;
if (s->pend_pos)
return SRV_STATUS_INTERNAL;
err = SRV_STATUS_OK;
if (!(s->flags & SF_ASSIGNED)) {
struct server *prev_srv = objt_server(s->target);
err = assign_server(s);
if (prev_srv) {
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 22:22:06 +00:00
/* This stream was previously assigned to a server. We have to
* update the stream's and the server's stats :
* - if the server changed :
* - set TX_CK_DOWN if txn.flags was TX_CK_VALID
* - set SF_REDISP if it was successfully redispatched
* - increment srv->redispatches and be->redispatches
* - if the server remained the same : update retries.
[MEDIUM]: Prevent redispatcher from selecting the same server, version #3 When haproxy decides that session needs to be redispatched it chose a server, but there is no guarantee for it to be a different one. So, it often happens that selected server is exactly the same that it was previously, so a client ends up with a 503 error anyway, especially when one sever has much bigger weight than others. Changes from the previous version: - drop stupid and unnecessary SN_DIRECT changes - assign_server(): use srvtoavoid to keep the old server and clear s->srv so SRV_STATUS_NOSRV guarantees that t->srv == NULL (again) and get_server_rr_with_conns has chances to work (previously we were passing a NULL here) - srv_redispatch_connect(): remove t->srv->cum_sess and t->srv->failed_conns incrementing as t->srv was guaranteed to be NULL - add avoididx to get_server_rr_with_conns. I hope I correctly understand this code. - fix http_flush_cookie_flags() and move it to assign_server_and_queue() directly. The code here was supposed to set CK_DOWN and clear CK_VALID, but: (TX_CK_VALID | TX_CK_DOWN) == TX_CK_VALID == TX_CK_MASK so: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags ^= (TX_CK_VALID | TX_CK_DOWN); was really a: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags &= TX_CK_VALID Now haproxy logs "--DI" after redispatching connection. - defer srv->redispatches++ and s->be->redispatches++ so there are called only if a conenction was redispatched, not only supposed to. - don't increment lbconn if redispatcher selected the same sarver - don't count unsuccessfully redispatched connections as redispatched connections - don't count redispatched connections as errors, so: - the number of connections effectively served by a server is: srv->cum_sess - srv->failed_conns - srv->retries - srv->redispatches and SUM(servers->failed_conns) == be->failed_conns - requires the "Don't increment server connections too much + fix retries" patch - needs little more testing and probably some discussion so reverting to the RFC state Tests #1: retries 4 redispatch i) 1 server(s): b (wght=1, down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request failed ii) server(s): b (wght=1, down), u (wght=1, down) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=1, retr=0, redis=0 -> request FAILED iii) 2 server(s): b (wght=1, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK iv) 2 server(s): b (wght=100, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK v) 1 server(s): b (down for first 4 SYNS) b) sessions=5, lbtot=1, err_conn=0, retr=4, redis=0 -> request OK Tests #2: retries 4 i) 1 server(s): b (down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request FAILED
2008-02-22 02:50:19 +00:00
*/
if (prev_srv != objt_server(s->target)) {
if (s->txn && (s->txn->flags & TX_CK_MASK) == TX_CK_VALID) {
s->txn->flags &= ~TX_CK_MASK;
s->txn->flags |= TX_CK_DOWN;
}
s->flags |= SF_REDISP;
prev_srv->counters.redispatches++;
s->be->be_counters.redispatches++;
} else {
prev_srv->counters.retries++;
s->be->be_counters.retries++;
[MEDIUM]: Prevent redispatcher from selecting the same server, version #3 When haproxy decides that session needs to be redispatched it chose a server, but there is no guarantee for it to be a different one. So, it often happens that selected server is exactly the same that it was previously, so a client ends up with a 503 error anyway, especially when one sever has much bigger weight than others. Changes from the previous version: - drop stupid and unnecessary SN_DIRECT changes - assign_server(): use srvtoavoid to keep the old server and clear s->srv so SRV_STATUS_NOSRV guarantees that t->srv == NULL (again) and get_server_rr_with_conns has chances to work (previously we were passing a NULL here) - srv_redispatch_connect(): remove t->srv->cum_sess and t->srv->failed_conns incrementing as t->srv was guaranteed to be NULL - add avoididx to get_server_rr_with_conns. I hope I correctly understand this code. - fix http_flush_cookie_flags() and move it to assign_server_and_queue() directly. The code here was supposed to set CK_DOWN and clear CK_VALID, but: (TX_CK_VALID | TX_CK_DOWN) == TX_CK_VALID == TX_CK_MASK so: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags ^= (TX_CK_VALID | TX_CK_DOWN); was really a: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags &= TX_CK_VALID Now haproxy logs "--DI" after redispatching connection. - defer srv->redispatches++ and s->be->redispatches++ so there are called only if a conenction was redispatched, not only supposed to. - don't increment lbconn if redispatcher selected the same sarver - don't count unsuccessfully redispatched connections as redispatched connections - don't count redispatched connections as errors, so: - the number of connections effectively served by a server is: srv->cum_sess - srv->failed_conns - srv->retries - srv->redispatches and SUM(servers->failed_conns) == be->failed_conns - requires the "Don't increment server connections too much + fix retries" patch - needs little more testing and probably some discussion so reverting to the RFC state Tests #1: retries 4 redispatch i) 1 server(s): b (wght=1, down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request failed ii) server(s): b (wght=1, down), u (wght=1, down) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=1, retr=0, redis=0 -> request FAILED iii) 2 server(s): b (wght=1, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK iv) 2 server(s): b (wght=100, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK v) 1 server(s): b (down for first 4 SYNS) b) sessions=5, lbtot=1, err_conn=0, retr=4, redis=0 -> request OK Tests #2: retries 4 i) 1 server(s): b (down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request FAILED
2008-02-22 02:50:19 +00:00
}
}
}
switch (err) {
case SRV_STATUS_OK:
/* we have SF_ASSIGNED set */
srv = objt_server(s->target);
if (!srv)
return SRV_STATUS_OK; /* dispatch or proxy mode */
/* If we already have a connection slot, no need to check any queue */
if (s->srv_conn == srv)
return SRV_STATUS_OK;
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 22:22:06 +00:00
/* OK, this stream already has an assigned server, but no
* connection slot yet. Either it is a redispatch, or it was
* assigned from persistence information (direct mode).
*/
if ((s->flags & SF_REDIRECTABLE) && srv->rdr_len) {
/* server scheduled for redirection, and already assigned. We
* don't want to go further nor check the queue.
*/
sess_change_server(s, srv); /* not really needed in fact */
return SRV_STATUS_OK;
}
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 22:22:06 +00:00
/* We might have to queue this stream if the assigned server is full.
* We know we have to queue it into the server's queue, so if a maxqueue
* is set on the server, we must also check that the server's queue is
* not full, in which case we have to return FULL.
*/
if (srv->maxconn &&
(srv->nbpend || srv->served >= srv_dynamic_maxconn(srv))) {
if (srv->maxqueue > 0 && srv->nbpend >= srv->maxqueue)
return SRV_STATUS_FULL;
p = pendconn_add(s);
if (p)
return SRV_STATUS_QUEUED;
else
return SRV_STATUS_INTERNAL;
}
/* OK, we can use this server. Let's reserve our place */
sess_change_server(s, srv);
return SRV_STATUS_OK;
case SRV_STATUS_FULL:
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 22:22:06 +00:00
/* queue this stream into the proxy's queue */
p = pendconn_add(s);
if (p)
return SRV_STATUS_QUEUED;
else
return SRV_STATUS_INTERNAL;
case SRV_STATUS_NOSRV:
return err;
case SRV_STATUS_INTERNAL:
return err;
default:
return SRV_STATUS_INTERNAL;
}
}
/* If an explicit source binding is specified on the server and/or backend, and
* this source makes use of the transparent proxy, then it is extracted now and
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 22:22:06 +00:00
* assigned to the stream's pending connection. This function assumes that an
* outgoing connection has already been assigned to s->si[1].end.
*/
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 22:22:06 +00:00
static void assign_tproxy_address(struct stream *s)
{
#if defined(CONFIG_HAP_TRANSPARENT)
struct server *srv = objt_server(s->target);
struct conn_src *src;
struct connection *cli_conn;
struct connection *srv_conn = objt_conn(s->si[1].end);
if (srv && srv->conn_src.opts & CO_SRC_BIND)
src = &srv->conn_src;
else if (s->be->conn_src.opts & CO_SRC_BIND)
src = &s->be->conn_src;
else
return;
switch (src->opts & CO_SRC_TPROXY_MASK) {
case CO_SRC_TPROXY_ADDR:
srv_conn->addr.from = src->tproxy_addr;
break;
case CO_SRC_TPROXY_CLI:
case CO_SRC_TPROXY_CIP:
/* FIXME: what can we do if the client connects in IPv6 or unix socket ? */
cli_conn = objt_conn(strm_orig(s));
if (cli_conn)
srv_conn->addr.from = cli_conn->addr.from;
else
memset(&srv_conn->addr.from, 0, sizeof(srv_conn->addr.from));
break;
case CO_SRC_TPROXY_DYN:
if (src->bind_hdr_occ && s->txn) {
char *vptr;
int vlen;
int rewind;
/* bind to the IP in a header */
((struct sockaddr_in *)&srv_conn->addr.from)->sin_family = AF_INET;
((struct sockaddr_in *)&srv_conn->addr.from)->sin_port = 0;
((struct sockaddr_in *)&srv_conn->addr.from)->sin_addr.s_addr = 0;
b_rew(s->req.buf, rewind = http_hdr_rewind(&s->txn->req));
if (http_get_hdr(&s->txn->req, src->bind_hdr_name, src->bind_hdr_len,
&s->txn->hdr_idx, src->bind_hdr_occ, NULL, &vptr, &vlen)) {
((struct sockaddr_in *)&srv_conn->addr.from)->sin_addr.s_addr =
htonl(inetaddr_host_lim(vptr, vptr + vlen));
}
b_adv(s->req.buf, rewind);
}
break;
default:
memset(&srv_conn->addr.from, 0, sizeof(srv_conn->addr.from));
}
#endif
}
/*
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 22:22:06 +00:00
* This function initiates a connection to the server assigned to this stream
* (s->target, s->si[1].addr.to). It will assign a server if none
* is assigned yet.
* It can return one of :
* - SF_ERR_NONE if everything's OK
* - SF_ERR_SRVTO if there are no more servers
* - SF_ERR_SRVCL if the connection was refused by the server
* - SF_ERR_PRXCOND if the connection has been limited by the proxy (maxconn)
* - SF_ERR_RESOURCE if a system resource is lacking (eg: fd limits, ports, ...)
* - SF_ERR_INTERNAL for any other purely internal errors
* Additionally, in the case of SF_ERR_RESOURCE, an emergency log will be emitted.
* The server-facing stream interface is expected to hold a pre-allocated connection
* in s->si[1].conn.
*/
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 22:22:06 +00:00
int connect_server(struct stream *s)
{
struct connection *cli_conn;
struct connection *srv_conn;
struct connection *old_conn;
struct server *srv;
int reuse = 0;
int err;
srv = objt_server(s->target);
srv_conn = objt_conn(s->si[1].end);
if (srv_conn)
reuse = s->target == srv_conn->target;
if (srv && !reuse) {
old_conn = srv_conn;
if (old_conn) {
srv_conn = NULL;
old_conn->owner = NULL;
si_detach_endpoint(&s->si[1]);
/* note: if the connection was in a server's idle
* queue, it doesn't get dequeued.
*/
}
/* Below we pick connections from the safe or idle lists based
* on the strategy, the fact that this is a first or second
* (retryable) request, with the indicated priority (1 or 2) :
*
* SAFE AGGR ALWS
*
* +-----+-----+ +-----+-----+ +-----+-----+
* req| 1st | 2nd | req| 1st | 2nd | req| 1st | 2nd |
* ----+-----+-----+ ----+-----+-----+ ----+-----+-----+
* safe| - | 2 | safe| 1 | 2 | safe| 1 | 2 |
* ----+-----+-----+ ----+-----+-----+ ----+-----+-----+
* idle| - | 1 | idle| - | 1 | idle| 2 | 1 |
* ----+-----+-----+ ----+-----+-----+ ----+-----+-----+
*/
if (!LIST_ISEMPTY(&srv->idle_conns) &&
((s->be->options & PR_O_REUSE_MASK) != PR_O_REUSE_NEVR &&
s->txn && (s->txn->flags & TX_NOT_FIRST))) {
srv_conn = LIST_ELEM(srv->idle_conns.n, struct connection *, list);
}
else if (!LIST_ISEMPTY(&srv->safe_conns) &&
((s->txn && (s->txn->flags & TX_NOT_FIRST)) ||
(s->be->options & PR_O_REUSE_MASK) >= PR_O_REUSE_AGGR)) {
srv_conn = LIST_ELEM(srv->safe_conns.n, struct connection *, list);
}
else if (!LIST_ISEMPTY(&srv->idle_conns) &&
(s->be->options & PR_O_REUSE_MASK) == PR_O_REUSE_ALWS) {
srv_conn = LIST_ELEM(srv->idle_conns.n, struct connection *, list);
}
/* If we've picked a connection from the pool, we now have to
* detach it. We may have to get rid of the previous idle
* connection we had, so for this we try to swap it with the
* other owner's. That way it may remain alive for others to
* pick.
*/
if (srv_conn) {
LIST_DEL(&srv_conn->list);
LIST_INIT(&srv_conn->list);
if (srv_conn->owner) {
si_detach_endpoint(srv_conn->owner);
BUG/MAJOR: http-reuse: fix risk of orphaned connections There is a bug in connect_server() : we use si_attach_conn() to offer the current session's connection to the session we're stealing the connection from. Unfortunately, si_attach_conn() uses the standard data connection operations while here we need to use the idle connection operations. This results in a situation where when the server's idle timeout strikes, the read0 is silently ignored, causes the response channel to be shut down for reads, and the connection remains attached. Next attempt to send a request when using this connection simply results in nothing being done because we try to send over an already closed connection. Worse, if the client aborts, then no timeout remains at all and the session waits forever and remains assigned to the server. A more-or-less easy way to reproduce this bug is to have two concurrent streams each connecting to a different server with "http-reuse aggressive", typically a cache farm using a URL hash : stream1: GET /1 HTTP/1.1 stream2: GET /2 HTTP/1.1 stream1: GET /2 HTTP/1.1 wait for the server 1's connection to timeout stream2: GET /1 HTTP/1.1 The connection hangs here, and "show sess all" shows a closed connection with a SHUTR on the response channel. The fix is very simple though not optimal. It consists in calling si_idle_conn() again after attaching the connection. But in practise it should not be done like this. The real issue is that there's no way to cleanly attach a connection to a stream interface without changing the connection's operations. So the API clearly needs to be revisited to make such operations easier. Many thanks to Yves Lafon from W3C for providing lots of useful dumps and testing patches to help figure the root cause! This fix must be backported to 1.6.
2016-02-02 17:29:05 +00:00
if (old_conn && !(old_conn->flags & CO_FL_PRIVATE)) {
si_attach_conn(srv_conn->owner, old_conn);
BUG/MAJOR: http-reuse: fix risk of orphaned connections There is a bug in connect_server() : we use si_attach_conn() to offer the current session's connection to the session we're stealing the connection from. Unfortunately, si_attach_conn() uses the standard data connection operations while here we need to use the idle connection operations. This results in a situation where when the server's idle timeout strikes, the read0 is silently ignored, causes the response channel to be shut down for reads, and the connection remains attached. Next attempt to send a request when using this connection simply results in nothing being done because we try to send over an already closed connection. Worse, if the client aborts, then no timeout remains at all and the session waits forever and remains assigned to the server. A more-or-less easy way to reproduce this bug is to have two concurrent streams each connecting to a different server with "http-reuse aggressive", typically a cache farm using a URL hash : stream1: GET /1 HTTP/1.1 stream2: GET /2 HTTP/1.1 stream1: GET /2 HTTP/1.1 wait for the server 1's connection to timeout stream2: GET /1 HTTP/1.1 The connection hangs here, and "show sess all" shows a closed connection with a SHUTR on the response channel. The fix is very simple though not optimal. It consists in calling si_idle_conn() again after attaching the connection. But in practise it should not be done like this. The real issue is that there's no way to cleanly attach a connection to a stream interface without changing the connection's operations. So the API clearly needs to be revisited to make such operations easier. Many thanks to Yves Lafon from W3C for providing lots of useful dumps and testing patches to help figure the root cause! This fix must be backported to 1.6.
2016-02-02 17:29:05 +00:00
si_idle_conn(srv_conn->owner, NULL);
}
}
si_attach_conn(&s->si[1], srv_conn);
reuse = 1;
}
/* we may have to release our connection if we couldn't swap it */
if (old_conn && !old_conn->owner) {
LIST_DEL(&old_conn->list);
conn_force_close(old_conn);
conn_free(old_conn);
}
}
if (reuse) {
/* Disable connection reuse if a dynamic source is used.
* As long as we don't share connections between servers,
* we don't need to disable connection reuse on no-idempotent
* requests nor when PROXY protocol is used.
*/
if (srv && srv->conn_src.opts & CO_SRC_BIND) {
if ((srv->conn_src.opts & CO_SRC_TPROXY_MASK) == CO_SRC_TPROXY_DYN)
reuse = 0;
}
else if (s->be->conn_src.opts & CO_SRC_BIND) {
if ((s->be->conn_src.opts & CO_SRC_TPROXY_MASK) == CO_SRC_TPROXY_DYN)
reuse = 0;
}
}
if (!reuse)
srv_conn = si_alloc_conn(&s->si[1]);
else {
/* reusing our connection, take it out of the idle list */
LIST_DEL(&srv_conn->list);
LIST_INIT(&srv_conn->list);
}
if (!srv_conn)
return SF_ERR_RESOURCE;
if (!(s->flags & SF_ADDR_SET)) {
err = assign_server_address(s);
if (err != SRV_STATUS_OK)
return SF_ERR_INTERNAL;
}
if (!conn_xprt_ready(srv_conn)) {
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 22:22:06 +00:00
/* the target was only on the stream, assign it to the SI now */
srv_conn->target = s->target;
/* set the correct protocol on the output stream interface */
if (srv) {
conn_prepare(srv_conn, protocol_by_family(srv_conn->addr.to.ss_family), srv->xprt);
}
else if (obj_type(s->target) == OBJ_TYPE_PROXY) {
/* proxies exclusively run on raw_sock right now */
conn_prepare(srv_conn, protocol_by_family(srv_conn->addr.to.ss_family), &raw_sock);
if (!objt_conn(s->si[1].end) || !objt_conn(s->si[1].end)->ctrl)
return SF_ERR_INTERNAL;
}
else
return SF_ERR_INTERNAL; /* how did we get there ? */
/* process the case where the server requires the PROXY protocol to be sent */
srv_conn->send_proxy_ofs = 0;
if (srv && srv->pp_opts) {
srv_conn->flags |= CO_FL_PRIVATE;
srv_conn->send_proxy_ofs = 1; /* must compute size */
cli_conn = objt_conn(strm_orig(s));
if (cli_conn)
conn_get_to_addr(cli_conn);
}
si_attach_conn(&s->si[1], srv_conn);
assign_tproxy_address(s);
}
else {
/* the connection is being reused, just re-attach it */
si_attach_conn(&s->si[1], srv_conn);
s->flags |= SF_SRV_REUSED;
}
/* flag for logging source ip/port */
if (strm_fe(s)->options2 & PR_O2_SRC_ADDR)
s->si[1].flags |= SI_FL_SRC_ADDR;
/* disable lingering */
if (s->be->options & PR_O_TCP_NOLING)
s->si[1].flags |= SI_FL_NOLINGER;
err = si_connect(&s->si[1]);
if (err != SF_ERR_NONE)
return err;
/* set connect timeout */
s->si[1].exp = tick_add_ifset(now_ms, s->be->timeout.connect);
if (srv) {
s->flags |= SF_CURR_SESS;
srv->cur_sess++;
if (srv->cur_sess > srv->counters.cur_sess_max)
srv->counters.cur_sess_max = srv->cur_sess;
if (s->be->lbprm.server_take_conn)
s->be->lbprm.server_take_conn(srv);
#ifdef USE_OPENSSL
if (srv->ssl_ctx.sni) {
struct sample *smp;
int rewind;
/* Tricky case : we have already scheduled the pending
* HTTP request or TCP data for leaving. So in HTTP we
* rewind exactly the headers, otherwise we rewind the
* output data.
*/
rewind = s->txn ? http_hdr_rewind(&s->txn->req) : s->req.buf->o;
b_rew(s->req.buf, rewind);
smp = sample_fetch_as_type(s->be, s->sess, s, SMP_OPT_DIR_REQ | SMP_OPT_FINAL, srv->ssl_ctx.sni, SMP_T_STR);
/* restore the pointers */
b_adv(s->req.buf, rewind);
if (smp_make_safe(smp)) {
ssl_sock_set_servername(srv_conn, smp->data.u.str.str);
srv_conn->flags |= CO_FL_PRIVATE;
}
}
#endif /* USE_OPENSSL */
}
return SF_ERR_NONE; /* connection is OK */
}
/* This function performs the "redispatch" part of a connection attempt. It
* will assign a server if required, queue the connection if required, and
* handle errors that might arise at this level. It can change the server
* state. It will return 1 if it encounters an error, switches the server
* state, or has to queue a connection. Otherwise, it will return 0 indicating
* that the connection is ready to use.
*/
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 22:22:06 +00:00
int srv_redispatch_connect(struct stream *s)
{
struct server *srv;
int conn_err;
/* We know that we don't have any connection pending, so we will
* try to get a new one, and wait in this state if it's queued
*/
redispatch:
conn_err = assign_server_and_queue(s);
srv = objt_server(s->target);
switch (conn_err) {
case SRV_STATUS_OK:
break;
case SRV_STATUS_FULL:
/* The server has reached its maxqueue limit. Either PR_O_REDISP is set
* and we can redispatch to another server, or it is not and we return
* 503. This only makes sense in DIRECT mode however, because normal LB
* algorithms would never select such a server, and hash algorithms
* would bring us on the same server again. Note that s->target is set
* in this case.
*/
if (((s->flags & (SF_DIRECT|SF_FORCE_PRST)) == SF_DIRECT) &&
(s->be->options & PR_O_REDISP)) {
s->flags &= ~(SF_DIRECT | SF_ASSIGNED | SF_ADDR_SET);
goto redispatch;
}
if (!s->si[1].err_type) {
s->si[1].err_type = SI_ET_QUEUE_ERR;
[MAJOR] rework of the server FSM srv_state has been removed from HTTP state machines, and states have been split in either TCP states or analyzers. For instance, the TARPIT state has just become a simple analyzer. New flags have been added to the struct buffer to compensate this. The high-level stream processors sometimes need to force a disconnection without touching a file-descriptor (eg: report an error). But if they touched BF_SHUTW or BF_SHUTR, the file descriptor would not be closed. Thus, the two SHUT?_NOW flags have been added so that an application can request a forced close which the stream interface will be forced to obey. During this change, a new BF_HIJACK flag was added. It will be used for data generation, eg during a stats dump. It prevents the producer on a buffer from sending data into it. BF_SHUTR_NOW /* the producer must shut down for reads ASAP */ BF_SHUTW_NOW /* the consumer must shut down for writes ASAP */ BF_HIJACK /* the producer is temporarily replaced */ BF_SHUTW_NOW has precedence over BF_HIJACK. BF_HIJACK has precedence over BF_MAY_FORWARD (so that it does not need it). New functions buffer_shutr_now(), buffer_shutw_now(), buffer_abort() are provided to manipulate BF_SHUT* flags. A new type "stream_interface" has been added to describe both sides of a buffer. A stream interface has states and error reporting. The session now has two stream interfaces (one per side). Each buffer has stream_interface pointers to both consumer and producer sides. The server-side file descriptor has moved to its stream interface, so that even the buffer has access to it. process_srv() has been split into three parts : - tcp_get_connection() obtains a connection to the server - tcp_connection_failed() tests if a previously attempted connection has succeeded or not. - process_srv_data() only manages the data phase, and in this sense should be roughly equivalent to process_cli. Little code has been removed, and a lot of old code has been left in comments for now.
2008-10-19 05:30:41 +00:00
}
srv->counters.failed_conns++;
s->be->be_counters.failed_conns++;
return 1;
case SRV_STATUS_NOSRV:
/* note: it is guaranteed that srv == NULL here */
if (!s->si[1].err_type) {
s->si[1].err_type = SI_ET_CONN_ERR;
[MAJOR] rework of the server FSM srv_state has been removed from HTTP state machines, and states have been split in either TCP states or analyzers. For instance, the TARPIT state has just become a simple analyzer. New flags have been added to the struct buffer to compensate this. The high-level stream processors sometimes need to force a disconnection without touching a file-descriptor (eg: report an error). But if they touched BF_SHUTW or BF_SHUTR, the file descriptor would not be closed. Thus, the two SHUT?_NOW flags have been added so that an application can request a forced close which the stream interface will be forced to obey. During this change, a new BF_HIJACK flag was added. It will be used for data generation, eg during a stats dump. It prevents the producer on a buffer from sending data into it. BF_SHUTR_NOW /* the producer must shut down for reads ASAP */ BF_SHUTW_NOW /* the consumer must shut down for writes ASAP */ BF_HIJACK /* the producer is temporarily replaced */ BF_SHUTW_NOW has precedence over BF_HIJACK. BF_HIJACK has precedence over BF_MAY_FORWARD (so that it does not need it). New functions buffer_shutr_now(), buffer_shutw_now(), buffer_abort() are provided to manipulate BF_SHUT* flags. A new type "stream_interface" has been added to describe both sides of a buffer. A stream interface has states and error reporting. The session now has two stream interfaces (one per side). Each buffer has stream_interface pointers to both consumer and producer sides. The server-side file descriptor has moved to its stream interface, so that even the buffer has access to it. process_srv() has been split into three parts : - tcp_get_connection() obtains a connection to the server - tcp_connection_failed() tests if a previously attempted connection has succeeded or not. - process_srv_data() only manages the data phase, and in this sense should be roughly equivalent to process_cli. Little code has been removed, and a lot of old code has been left in comments for now.
2008-10-19 05:30:41 +00:00
}
[MEDIUM]: Prevent redispatcher from selecting the same server, version #3 When haproxy decides that session needs to be redispatched it chose a server, but there is no guarantee for it to be a different one. So, it often happens that selected server is exactly the same that it was previously, so a client ends up with a 503 error anyway, especially when one sever has much bigger weight than others. Changes from the previous version: - drop stupid and unnecessary SN_DIRECT changes - assign_server(): use srvtoavoid to keep the old server and clear s->srv so SRV_STATUS_NOSRV guarantees that t->srv == NULL (again) and get_server_rr_with_conns has chances to work (previously we were passing a NULL here) - srv_redispatch_connect(): remove t->srv->cum_sess and t->srv->failed_conns incrementing as t->srv was guaranteed to be NULL - add avoididx to get_server_rr_with_conns. I hope I correctly understand this code. - fix http_flush_cookie_flags() and move it to assign_server_and_queue() directly. The code here was supposed to set CK_DOWN and clear CK_VALID, but: (TX_CK_VALID | TX_CK_DOWN) == TX_CK_VALID == TX_CK_MASK so: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags ^= (TX_CK_VALID | TX_CK_DOWN); was really a: if ((txn->flags & TX_CK_MASK) == TX_CK_VALID) txn->flags &= TX_CK_VALID Now haproxy logs "--DI" after redispatching connection. - defer srv->redispatches++ and s->be->redispatches++ so there are called only if a conenction was redispatched, not only supposed to. - don't increment lbconn if redispatcher selected the same sarver - don't count unsuccessfully redispatched connections as redispatched connections - don't count redispatched connections as errors, so: - the number of connections effectively served by a server is: srv->cum_sess - srv->failed_conns - srv->retries - srv->redispatches and SUM(servers->failed_conns) == be->failed_conns - requires the "Don't increment server connections too much + fix retries" patch - needs little more testing and probably some discussion so reverting to the RFC state Tests #1: retries 4 redispatch i) 1 server(s): b (wght=1, down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request failed ii) server(s): b (wght=1, down), u (wght=1, down) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=1, retr=0, redis=0 -> request FAILED iii) 2 server(s): b (wght=1, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK iv) 2 server(s): b (wght=100, down), u (wght=1, up) b) sessions=4, lbtot=1, err_conn=0, retr=3, redis=1 u) sessions=1, lbtot=1, err_conn=0, retr=0, redis=0 -> request OK v) 1 server(s): b (down for first 4 SYNS) b) sessions=5, lbtot=1, err_conn=0, retr=4, redis=0 -> request OK Tests #2: retries 4 i) 1 server(s): b (down) b) sessions=5, lbtot=1, err_conn=1, retr=4, redis=0 -> request FAILED
2008-02-22 02:50:19 +00:00
s->be->be_counters.failed_conns++;
return 1;
case SRV_STATUS_QUEUED:
s->si[1].exp = tick_add_ifset(now_ms, s->be->timeout.queue);
s->si[1].state = SI_ST_QUE;
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 22:22:06 +00:00
/* do nothing else and do not wake any other stream up */
return 1;
case SRV_STATUS_INTERNAL:
default:
if (!s->si[1].err_type) {
s->si[1].err_type = SI_ET_CONN_OTHER;
[MAJOR] rework of the server FSM srv_state has been removed from HTTP state machines, and states have been split in either TCP states or analyzers. For instance, the TARPIT state has just become a simple analyzer. New flags have been added to the struct buffer to compensate this. The high-level stream processors sometimes need to force a disconnection without touching a file-descriptor (eg: report an error). But if they touched BF_SHUTW or BF_SHUTR, the file descriptor would not be closed. Thus, the two SHUT?_NOW flags have been added so that an application can request a forced close which the stream interface will be forced to obey. During this change, a new BF_HIJACK flag was added. It will be used for data generation, eg during a stats dump. It prevents the producer on a buffer from sending data into it. BF_SHUTR_NOW /* the producer must shut down for reads ASAP */ BF_SHUTW_NOW /* the consumer must shut down for writes ASAP */ BF_HIJACK /* the producer is temporarily replaced */ BF_SHUTW_NOW has precedence over BF_HIJACK. BF_HIJACK has precedence over BF_MAY_FORWARD (so that it does not need it). New functions buffer_shutr_now(), buffer_shutw_now(), buffer_abort() are provided to manipulate BF_SHUT* flags. A new type "stream_interface" has been added to describe both sides of a buffer. A stream interface has states and error reporting. The session now has two stream interfaces (one per side). Each buffer has stream_interface pointers to both consumer and producer sides. The server-side file descriptor has moved to its stream interface, so that even the buffer has access to it. process_srv() has been split into three parts : - tcp_get_connection() obtains a connection to the server - tcp_connection_failed() tests if a previously attempted connection has succeeded or not. - process_srv_data() only manages the data phase, and in this sense should be roughly equivalent to process_cli. Little code has been removed, and a lot of old code has been left in comments for now.
2008-10-19 05:30:41 +00:00
}
if (srv)
srv_inc_sess_ctr(srv);
if (srv)
srv_set_sess_last(srv);
if (srv)
srv->counters.failed_conns++;
s->be->be_counters.failed_conns++;
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 22:22:06 +00:00
/* release other streams waiting for this server */
if (may_dequeue_tasks(srv, s->be))
process_srv_queue(srv);
return 1;
}
/* if we get here, it's because we got SRV_STATUS_OK, which also
* means that the connection has not been queued.
*/
return 0;
}
/* sends a log message when a backend goes down, and also sets last
* change date.
*/
void set_backend_down(struct proxy *be)
{
be->last_change = now.tv_sec;
be->down_trans++;
if (!(global.mode & MODE_STARTING)) {
Alert("%s '%s' has no server available!\n", proxy_type_str(be), be->id);
send_log(be, LOG_EMERG, "%s %s has no server available!\n", proxy_type_str(be), be->id);
}
}
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 22:22:06 +00:00
/* Apply RDP cookie persistence to the current stream. For this, the function
* tries to extract an RDP cookie from the request buffer, and look for the
* matching server in the list. If the server is found, it is assigned to the
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 22:22:06 +00:00
* stream. This always returns 1, and the analyser removes itself from the
* list. Nothing is performed if a server was already assigned.
*/
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 22:22:06 +00:00
int tcp_persist_rdp_cookie(struct stream *s, struct channel *req, int an_bit)
{
struct proxy *px = s->be;
int ret;
struct sample smp;
struct server *srv = px->srv;
struct sockaddr_in addr;
char *p;
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 22:22:06 +00:00
DPRINTF(stderr,"[%u] %s: stream=%p b=%p, exp(r,w)=%u,%u bf=%08x bh=%d analysers=%02x\n",
now_ms, __FUNCTION__,
s,
req,
req->rex, req->wex,
req->flags,
req->buf->i,
req->analysers);
if (s->flags & SF_ASSIGNED)
goto no_cookie;
memset(&smp, 0, sizeof(smp));
ret = fetch_rdp_cookie_name(s, &smp, s->be->rdp_cookie_name, s->be->rdp_cookie_len);
if (ret == 0 || (smp.flags & SMP_F_MAY_CHANGE) || smp.data.u.str.len == 0)
goto no_cookie;
memset(&addr, 0, sizeof(addr));
addr.sin_family = AF_INET;
/* Considering an rdp cookie detected using acl, str ended with <cr><lf> and should return */
addr.sin_addr.s_addr = strtoul(smp.data.u.str.str, &p, 10);
if (*p != '.')
goto no_cookie;
p++;
addr.sin_port = (unsigned short)strtoul(p, &p, 10);
if (*p != '.')
goto no_cookie;
s->target = NULL;
while (srv) {
if (srv->addr.ss_family == AF_INET &&
memcmp(&addr, &(srv->addr), sizeof(addr)) == 0) {
if ((srv->state != SRV_ST_STOPPED) || (px->options & PR_O_PERSIST)) {
/* we found the server and it is usable */
s->flags |= SF_DIRECT | SF_ASSIGNED;
s->target = &srv->obj_type;
break;
}
}
srv = srv->next;
}
no_cookie:
req->analysers &= ~an_bit;
req->analyse_exp = TICK_ETERNITY;
return 1;
}
[MEDIUM] stats: report server and backend cumulated downtime Hello, This patch implements new statistics for SLA calculation by adding new field 'Dwntime' with total down time since restart (both HTTP/CSV) and extending status field (HTTP) or inserting a new one (CSV) with time showing how long each server/backend is in a current state. Additionaly, down transations are also calculated and displayed for backends, so it is possible to know how many times selected backend was down, generating "No server is available to handle this request." error. New information are presentetd in two different ways: - for HTTP: a "human redable form", one of "100000d 23h", "23h 59m" or "59m 59s" - for CSV: seconds I believe that seconds resolution is enough. As there are more columns in the status page I decided to shrink some names to make more space: - Weight -> Wght - Check -> Chk - Down -> Dwn Making described changes I also made some improvements and fixed some small bugs: - don't increment s->health above 's->rise + s->fall - 1'. Previously it was incremented an then (re)set to 's->rise + s->fall - 1'. - do not set server down if it is down already - do not set server up if it is up already - fix colspan in multiple places (mostly introduced by my previous patch) - add missing "status" header to CSV - fix order of retries/redispatches in server (CSV) - s/Tthen/Then/ - s/server/backend/ in DATA_ST_PX_BE (dumpstats.c) Changes from previous version: - deal with negative time intervales - don't relay on s->state (SRV_RUNNING) - little reworked human_time + compacted format (no spaces). If needed it can be used in the future for other purposes by optionally making "cnt" as an argument - leave set_server_down mostly unchanged - only little reworked "process_chk: 9" - additional fields in CSV are appended to the rigth - fix "SEC" macro - named arguments (human_time, be_downtime, srv_downtime) Hope it is OK. If there are only cosmetic changes needed please fill free to correct it, however if there are some bigger changes required I would like to discuss it first or at last to know what exactly was changed especially since I already put this patch into my production server. :) Thank you, Best regards, Krzysztof Oledzki
2007-10-22 14:21:10 +00:00
int be_downtime(struct proxy *px) {
if (px->lbprm.tot_weight && px->last_change < now.tv_sec) // ignore negative time
[MEDIUM] stats: report server and backend cumulated downtime Hello, This patch implements new statistics for SLA calculation by adding new field 'Dwntime' with total down time since restart (both HTTP/CSV) and extending status field (HTTP) or inserting a new one (CSV) with time showing how long each server/backend is in a current state. Additionaly, down transations are also calculated and displayed for backends, so it is possible to know how many times selected backend was down, generating "No server is available to handle this request." error. New information are presentetd in two different ways: - for HTTP: a "human redable form", one of "100000d 23h", "23h 59m" or "59m 59s" - for CSV: seconds I believe that seconds resolution is enough. As there are more columns in the status page I decided to shrink some names to make more space: - Weight -> Wght - Check -> Chk - Down -> Dwn Making described changes I also made some improvements and fixed some small bugs: - don't increment s->health above 's->rise + s->fall - 1'. Previously it was incremented an then (re)set to 's->rise + s->fall - 1'. - do not set server down if it is down already - do not set server up if it is up already - fix colspan in multiple places (mostly introduced by my previous patch) - add missing "status" header to CSV - fix order of retries/redispatches in server (CSV) - s/Tthen/Then/ - s/server/backend/ in DATA_ST_PX_BE (dumpstats.c) Changes from previous version: - deal with negative time intervales - don't relay on s->state (SRV_RUNNING) - little reworked human_time + compacted format (no spaces). If needed it can be used in the future for other purposes by optionally making "cnt" as an argument - leave set_server_down mostly unchanged - only little reworked "process_chk: 9" - additional fields in CSV are appended to the rigth - fix "SEC" macro - named arguments (human_time, be_downtime, srv_downtime) Hope it is OK. If there are only cosmetic changes needed please fill free to correct it, however if there are some bigger changes required I would like to discuss it first or at last to know what exactly was changed especially since I already put this patch into my production server. :) Thank you, Best regards, Krzysztof Oledzki
2007-10-22 14:21:10 +00:00
return px->down_time;
return now.tv_sec - px->last_change + px->down_time;
}
/*
* This function returns a string containing the balancing
* mode of the proxy in a format suitable for stats.
*/
const char *backend_lb_algo_str(int algo) {
if (algo == BE_LB_ALGO_RR)
return "roundrobin";
else if (algo == BE_LB_ALGO_SRR)
return "static-rr";
else if (algo == BE_LB_ALGO_FAS)
return "first";
else if (algo == BE_LB_ALGO_LC)
return "leastconn";
else if (algo == BE_LB_ALGO_SH)
return "source";
else if (algo == BE_LB_ALGO_UH)
return "uri";
else if (algo == BE_LB_ALGO_PH)
return "url_param";
else if (algo == BE_LB_ALGO_HH)
return "hdr";
else if (algo == BE_LB_ALGO_RCH)
return "rdp-cookie";
else if (algo == BE_LB_ALGO_NONE)
return "none";
else
return "unknown";
}
/* This function parses a "balance" statement in a backend section describing
* <curproxy>. It returns -1 if there is any error, otherwise zero. If it
* returns -1, it will write an error message into the <err> buffer which will
* automatically be allocated and must be passed as NULL. The trailing '\n'
* will not be written. The function must be called with <args> pointing to the
* first word after "balance".
*/
int backend_parse_balance(const char **args, char **err, struct proxy *curproxy)
{
if (!*(args[0])) {
/* if no option is set, use round-robin by default */
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_RR;
return 0;
}
if (!strcmp(args[0], "roundrobin")) {
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_RR;
}
else if (!strcmp(args[0], "static-rr")) {
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_SRR;
}
else if (!strcmp(args[0], "first")) {
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_FAS;
}
else if (!strcmp(args[0], "leastconn")) {
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_LC;
}
else if (!strcmp(args[0], "source")) {
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_SH;
}
else if (!strcmp(args[0], "uri")) {
int arg = 1;
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_UH;
MINOR: balance uri: added 'whole' parameter to include query string in hash calculation This patch brings a new "whole" parameter to "balance uri" which makes the hash work over the whole uri, not just the part before the query string. Len and depth parameter are still honnored. The reason for this new feature is explained below. I have 3 backend servers, each accepting different form of HTTP queries: http://backend1.server.tld/service1.php?q=... http://backend1.server.tld/service2.php?q=... http://backend2.server.tld/index.php?query=...&subquery=... http://backend3.server.tld/image/49b8c0d9ff Each backend server returns a different response based on either: - the URI path (the left part of the URI before the question mark) - the query string (the right part of the URI after the question mark) - or the combination of both I wanted to set up a common caching cluster (using 6 Squid servers, each configured as reverse proxy for those 3 backends) and have HAProxy balance the queries among the Squid servers based on URL. I also wanted to achieve hight cache hit ration on each Squid server and send the same queries to the same Squid servers. Initially I was considering using the 'balance uri' algorithm, but that would not work as in case of backend2 all queries would go to only one Squid server. The 'balance url_param' would not work either as it would send the backend3 queries to only one Squid server. So I thought the simplest solution would be to use 'balance uri', but to calculate the hash based on the whole URI (URI path + query string), instead of just the URI path.
2012-05-19 09:19:54 +00:00
curproxy->uri_whole = 0;
while (*args[arg]) {
if (!strcmp(args[arg], "len")) {
if (!*args[arg+1] || (atoi(args[arg+1]) <= 0)) {
memprintf(err, "%s : '%s' expects a positive integer (got '%s').", args[0], args[arg], args[arg+1]);
return -1;
}
curproxy->uri_len_limit = atoi(args[arg+1]);
arg += 2;
}
else if (!strcmp(args[arg], "depth")) {
if (!*args[arg+1] || (atoi(args[arg+1]) <= 0)) {
memprintf(err, "%s : '%s' expects a positive integer (got '%s').", args[0], args[arg], args[arg+1]);
return -1;
}
/* hint: we store the position of the ending '/' (depth+1) so
* that we avoid a comparison while computing the hash.
*/
curproxy->uri_dirs_depth1 = atoi(args[arg+1]) + 1;
arg += 2;
}
MINOR: balance uri: added 'whole' parameter to include query string in hash calculation This patch brings a new "whole" parameter to "balance uri" which makes the hash work over the whole uri, not just the part before the query string. Len and depth parameter are still honnored. The reason for this new feature is explained below. I have 3 backend servers, each accepting different form of HTTP queries: http://backend1.server.tld/service1.php?q=... http://backend1.server.tld/service2.php?q=... http://backend2.server.tld/index.php?query=...&subquery=... http://backend3.server.tld/image/49b8c0d9ff Each backend server returns a different response based on either: - the URI path (the left part of the URI before the question mark) - the query string (the right part of the URI after the question mark) - or the combination of both I wanted to set up a common caching cluster (using 6 Squid servers, each configured as reverse proxy for those 3 backends) and have HAProxy balance the queries among the Squid servers based on URL. I also wanted to achieve hight cache hit ration on each Squid server and send the same queries to the same Squid servers. Initially I was considering using the 'balance uri' algorithm, but that would not work as in case of backend2 all queries would go to only one Squid server. The 'balance url_param' would not work either as it would send the backend3 queries to only one Squid server. So I thought the simplest solution would be to use 'balance uri', but to calculate the hash based on the whole URI (URI path + query string), instead of just the URI path.
2012-05-19 09:19:54 +00:00
else if (!strcmp(args[arg], "whole")) {
curproxy->uri_whole = 1;
arg += 1;
}
else {
MINOR: balance uri: added 'whole' parameter to include query string in hash calculation This patch brings a new "whole" parameter to "balance uri" which makes the hash work over the whole uri, not just the part before the query string. Len and depth parameter are still honnored. The reason for this new feature is explained below. I have 3 backend servers, each accepting different form of HTTP queries: http://backend1.server.tld/service1.php?q=... http://backend1.server.tld/service2.php?q=... http://backend2.server.tld/index.php?query=...&subquery=... http://backend3.server.tld/image/49b8c0d9ff Each backend server returns a different response based on either: - the URI path (the left part of the URI before the question mark) - the query string (the right part of the URI after the question mark) - or the combination of both I wanted to set up a common caching cluster (using 6 Squid servers, each configured as reverse proxy for those 3 backends) and have HAProxy balance the queries among the Squid servers based on URL. I also wanted to achieve hight cache hit ration on each Squid server and send the same queries to the same Squid servers. Initially I was considering using the 'balance uri' algorithm, but that would not work as in case of backend2 all queries would go to only one Squid server. The 'balance url_param' would not work either as it would send the backend3 queries to only one Squid server. So I thought the simplest solution would be to use 'balance uri', but to calculate the hash based on the whole URI (URI path + query string), instead of just the URI path.
2012-05-19 09:19:54 +00:00
memprintf(err, "%s only accepts parameters 'len', 'depth', and 'whole' (got '%s').", args[0], args[arg]);
return -1;
}
}
}
else if (!strcmp(args[0], "url_param")) {
if (!*args[1]) {
memprintf(err, "%s requires an URL parameter name.", args[0]);
return -1;
}
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_PH;
free(curproxy->url_param_name);
curproxy->url_param_name = strdup(args[1]);
curproxy->url_param_len = strlen(args[1]);
if (*args[2]) {
if (strcmp(args[2], "check_post")) {
memprintf(err, "%s only accepts 'check_post' modifier (got '%s').", args[0], args[2]);
return -1;
}
}
}
else if (!strncmp(args[0], "hdr(", 4)) {
const char *beg, *end;
beg = args[0] + 4;
end = strchr(beg, ')');
if (!end || end == beg) {
memprintf(err, "hdr requires an http header field name.");
return -1;
}
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_HH;
free(curproxy->hh_name);
curproxy->hh_len = end - beg;
curproxy->hh_name = my_strndup(beg, end - beg);
curproxy->hh_match_domain = 0;
if (*args[1]) {
if (strcmp(args[1], "use_domain_only")) {
memprintf(err, "%s only accepts 'use_domain_only' modifier (got '%s').", args[0], args[1]);
return -1;
}
curproxy->hh_match_domain = 1;
}
}
else if (!strncmp(args[0], "rdp-cookie", 10)) {
curproxy->lbprm.algo &= ~BE_LB_ALGO;
curproxy->lbprm.algo |= BE_LB_ALGO_RCH;
if ( *(args[0] + 10 ) == '(' ) { /* cookie name */
const char *beg, *end;
beg = args[0] + 11;
end = strchr(beg, ')');
if (!end || end == beg) {
memprintf(err, "rdp-cookie : missing cookie name.");
return -1;
}
free(curproxy->hh_name);
curproxy->hh_name = my_strndup(beg, end - beg);
curproxy->hh_len = end - beg;
}
else if ( *(args[0] + 10 ) == '\0' ) { /* default cookie name 'mstshash' */
free(curproxy->hh_name);
curproxy->hh_name = strdup("mstshash");
curproxy->hh_len = strlen(curproxy->hh_name);
}
else { /* syntax */
memprintf(err, "rdp-cookie : missing cookie name.");
return -1;
}
}
else {
memprintf(err, "only supports 'roundrobin', 'static-rr', 'leastconn', 'source', 'uri', 'url_param', 'hdr(name)' and 'rdp-cookie(name)' options.");
return -1;
}
return 0;
}
/************************************************************************/
/* All supported sample and ACL keywords must be declared here. */
/************************************************************************/
/* set temp integer to the number of enabled servers on the proxy.
* Accepts exactly 1 argument. Argument is a backend, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_nbsrv(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
struct proxy *px;
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
px = args->data.prx;
if (px->srv_act)
smp->data.u.sint = px->srv_act;
else if (px->lbprm.fbck)
smp->data.u.sint = 1;
else
smp->data.u.sint = px->srv_bck;
return 1;
}
/* report in smp->flags a success or failure depending on the designated
* server's state. There is no match function involved since there's no pattern.
* Accepts exactly 1 argument. Argument is a server, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_srv_is_up(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
struct server *srv = args->data.srv;
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_BOOL;
if (!(srv->admin & SRV_ADMF_MAINT) &&
(!(srv->check.state & CHK_ST_CONFIGURED) || (srv->state != SRV_ST_STOPPED)))
smp->data.u.sint = 1;
else
smp->data.u.sint = 0;
return 1;
}
/* set temp integer to the number of enabled servers on the proxy.
* Accepts exactly 1 argument. Argument is a backend, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_connslots(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
struct server *iterator;
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = 0;
for (iterator = args->data.prx->srv; iterator; iterator = iterator->next) {
if (iterator->state == SRV_ST_STOPPED)
continue;
if (iterator->maxconn == 0 || iterator->maxqueue == 0) {
/* configuration is stupid */
smp->data.u.sint = -1; /* FIXME: stupid value! */
return 1;
}
smp->data.u.sint += (iterator->maxconn - iterator->cur_sess)
+ (iterator->maxqueue - iterator->nbpend);
}
return 1;
}
/* set temp integer to the id of the backend */
static int
smp_fetch_be_id(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
if (!smp->strm)
return 0;
smp->flags = SMP_F_VOL_TXN;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = smp->strm->be->uuid;
return 1;
}
/* set string to the name of the backend */
static int
smp_fetch_be_name(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
if (!smp->strm)
return 0;
smp->data.u.str.str = (char *)smp->strm->be->id;
if (!smp->data.u.str.str)
return 0;
smp->data.type = SMP_T_STR;
smp->flags = SMP_F_CONST;
smp->data.u.str.len = strlen(smp->data.u.str.str);
return 1;
}
/* set temp integer to the id of the server */
static int
smp_fetch_srv_id(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
if (!smp->strm)
return 0;
if (!objt_server(smp->strm->target))
return 0;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = objt_server(smp->strm->target)->puid;
return 1;
}
/* set temp integer to the number of connections per second reaching the backend.
* Accepts exactly 1 argument. Argument is a backend, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_be_sess_rate(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = read_freq_ctr(&args->data.prx->be_sess_per_sec);
return 1;
}
/* set temp integer to the number of concurrent connections on the backend.
* Accepts exactly 1 argument. Argument is a backend, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_be_conn(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = args->data.prx->beconn;
return 1;
}
/* set temp integer to the total number of queued connections on the backend.
* Accepts exactly 1 argument. Argument is a backend, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_queue_size(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = args->data.prx->totpend;
return 1;
}
/* set temp integer to the total number of queued connections on the backend divided
* by the number of running servers and rounded up. If there is no running
* server, we return twice the total, just as if we had half a running server.
* This is more or less correct anyway, since we expect the last server to come
* back soon.
* Accepts exactly 1 argument. Argument is a backend, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_avg_queue_size(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
int nbsrv;
struct proxy *px;
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
px = args->data.prx;
if (px->srv_act)
nbsrv = px->srv_act;
else if (px->lbprm.fbck)
nbsrv = 1;
else
nbsrv = px->srv_bck;
if (nbsrv > 0)
smp->data.u.sint = (px->totpend + nbsrv - 1) / nbsrv;
else
smp->data.u.sint = px->totpend * 2;
return 1;
}
/* set temp integer to the number of concurrent connections on the server in the backend.
* Accepts exactly 1 argument. Argument is a server, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_srv_conn(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = args->data.srv->cur_sess;
return 1;
}
/* set temp integer to the number of enabled servers on the proxy.
* Accepts exactly 1 argument. Argument is a server, other types will lead to
* undefined behaviour.
*/
static int
smp_fetch_srv_sess_rate(const struct arg *args, struct sample *smp, const char *kw, void *private)
{
smp->flags = SMP_F_VOL_TEST;
smp->data.type = SMP_T_SINT;
smp->data.u.sint = read_freq_ctr(&args->data.srv->sess_per_sec);
return 1;
}
/* Note: must not be declared <const> as its list will be overwritten.
* Please take care of keeping this list alphabetically sorted.
*/
static struct sample_fetch_kw_list smp_kws = {ILH, {
{ "avg_queue", smp_fetch_avg_queue_size, ARG1(1,BE), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ "be_conn", smp_fetch_be_conn, ARG1(1,BE), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ "be_id", smp_fetch_be_id, 0, NULL, SMP_T_SINT, SMP_USE_BKEND, },
{ "be_name", smp_fetch_be_name, 0, NULL, SMP_T_STR, SMP_USE_BKEND, },
{ "be_sess_rate", smp_fetch_be_sess_rate, ARG1(1,BE), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ "connslots", smp_fetch_connslots, ARG1(1,BE), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ "nbsrv", smp_fetch_nbsrv, ARG1(1,BE), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ "queue", smp_fetch_queue_size, ARG1(1,BE), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ "srv_conn", smp_fetch_srv_conn, ARG1(1,SRV), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ "srv_id", smp_fetch_srv_id, 0, NULL, SMP_T_SINT, SMP_USE_SERVR, },
{ "srv_is_up", smp_fetch_srv_is_up, ARG1(1,SRV), NULL, SMP_T_BOOL, SMP_USE_INTRN, },
{ "srv_sess_rate", smp_fetch_srv_sess_rate, ARG1(1,SRV), NULL, SMP_T_SINT, SMP_USE_INTRN, },
{ /* END */ },
}};
/* Note: must not be declared <const> as its list will be overwritten.
* Please take care of keeping this list alphabetically sorted.
*/
static struct acl_kw_list acl_kws = {ILH, {
{ /* END */ },
}};
__attribute__((constructor))
static void __backend_init(void)
{
sample_register_fetches(&smp_kws);
acl_register_keywords(&acl_kws);
}
/*
* Local variables:
* c-indent-level: 8
* c-basic-offset: 8
* End:
*/