haproxy/include/proto/backend.h

192 lines
5.2 KiB
C
Raw Normal View History

/*
include/proto/backend.h
Functions prototypes for the backend.
Copyright (C) 2000-2008 Willy Tarreau - w@1wt.eu
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation, version 2.1
exclusively.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef _PROTO_BACKEND_H
#define _PROTO_BACKEND_H
#include <common/config.h>
#include <types/backend.h>
#include <types/session.h>
#include <proto/queue.h>
int assign_server(struct session *s);
int assign_server_address(struct session *s);
int assign_server_and_queue(struct session *s);
int connect_server(struct session *s);
int srv_redispatch_connect(struct session *t);
int backend_parse_balance(const char **args, char *err,
int errlen, struct proxy *curproxy);
void recalc_server_map(struct proxy *px);
[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);
void init_server_map(struct proxy *p);
void fwrr_init_server_groups(struct proxy *p);
void fwlc_init_server_tree(struct proxy *p);
void recount_servers(struct proxy *px);
void update_backend_weight(struct proxy *px);
/* This function returns non-zero if a server with the given weight and state
* is usable for LB, otherwise zero.
*/
static inline int srv_is_usable(int state, int weight)
{
if (!weight)
return 0;
if (state & SRV_GOINGDOWN)
return 0;
if (!(state & SRV_RUNNING))
return 0;
return 1;
}
/*
* This function tries to find a running server with free connection slots for
* the proxy <px> following the round-robin method.
* If any server is found, it will be returned and px->lbprm.map.rr_idx will be updated
* to point to the next server. If no valid server is found, NULL is returned.
*/
[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
static inline struct server *get_server_rr_with_conns(struct proxy *px, struct server *srvtoavoid)
{
[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
int newidx, avoididx;
struct server *srv, *avoided;
if (px->lbprm.tot_weight == 0)
return NULL;
if (px->lbprm.map.state & PR_MAP_RECALC)
recalc_server_map(px);
if (px->lbprm.map.rr_idx < 0 || px->lbprm.map.rr_idx >= px->lbprm.tot_weight)
px->lbprm.map.rr_idx = 0;
newidx = px->lbprm.map.rr_idx;
[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
avoided = NULL;
avoididx = 0; /* shut a gcc warning */
do {
srv = px->lbprm.map.srv[newidx++];
if (!srv->maxconn || srv->cur_sess < srv_dynamic_maxconn(srv)) {
[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
/* make sure it is not the server we are try to exclude... */
if (srv != srvtoavoid) {
px->lbprm.map.rr_idx = newidx;
return srv;
}
avoided = srv; /* ...but remember that is was selected yet avoided */
avoididx = newidx;
}
if (newidx == px->lbprm.tot_weight)
newidx = 0;
} while (newidx != px->lbprm.map.rr_idx);
[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 (avoided)
px->lbprm.map.rr_idx = avoididx;
/* return NULL or srvtoavoid if found */
return avoided;
}
/*
* 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.
*/
static inline 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;
if (px->lbprm.map.state & PR_MAP_RECALC)
recalc_server_map(px);
l = h = 0;
/* note: we won't hash if there's only one server left */
if (px->lbprm.tot_used > 1) {
while ((l + sizeof (int)) <= len) {
h ^= ntohl(*(unsigned int *)(&addr[l]));
l += sizeof (int);
}
h %= px->lbprm.tot_weight;
}
return px->lbprm.map.srv[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.
*
*/
static inline struct server *get_server_uh(struct proxy *px, char *uri, int uri_len)
{
unsigned long hash = 0;
int c;
int slashes = 0;
if (px->lbprm.tot_weight == 0)
return NULL;
if (px->lbprm.map.state & PR_MAP_RECALC)
recalc_server_map(px);
if (px->uri_len_limit)
uri_len = MIN(uri_len, px->uri_len_limit);
while (uri_len--) {
c = *uri++;
if (c == '/') {
slashes++;
if (slashes == px->uri_dirs_depth1) /* depth+1 */
break;
}
else if (c == '?')
break;
hash = c + (hash << 6) + (hash << 16) - hash;
}
return px->lbprm.map.srv[hash % px->lbprm.tot_weight];
}
#endif /* _PROTO_BACKEND_H */
/*
* Local variables:
* c-indent-level: 8
* c-basic-offset: 8
* End:
*/