MEDIUM: log: support a user-configurable max log line length

With all the goodies supported by logformat, people find that the limit
of 1024 chars for log lines is too short. Some servers do not support
larger lines and can simply drop them, so changing the default value is
not always the best choice.

This patch takes a different approach. Log line length is specified per
log server on the "log" line, with a value between 80 and 65535. That
way it's possibly to satisfy all needs, even with some fat local servers
and small remote ones.

doc/configuration.txt

@@ -565,7 +565,7 @@ group <group name>
   Similar to "gid" but uses the GID of group name <group name> from /etc/group.
   See also "gid" and "user".
 
-log <address> <facility> [max level [min level]]
+log <address> [len <length>] <facility> [max level [min level]]
   Adds a global syslog server. Up to two global servers can be defined. They
   will receive logs for startups and exits, as well as all logs from proxies
   configured with "log global".
@@ -590,6 +590,18 @@ log <address> <facility> [max level [min level]]
         optionally enclosing them with braces ('{}'), similarly to what is done
         in Bourne shell.
 
+  <length> is an optional maximum line length. Log lines larger than this value
+           will be truncated before being sent. The reason is that syslog
+           servers act differently on log line length. All servers support the
+           default value of 1024, but some servers simply drop larger lines
+           while others do log them. If a server supports long lines, it may
+           make sense to set this value here in order to avoid truncating long
+           lines. Similarly, if a server drops long lines, it is preferable to
+           truncate them before sending them. Accepted values are 80 to 65535
+           inclusive. The default value of 1024 is generally fine for all
+           standard usages. Some specific cases of long captures or
+           JSON-formated logs may require larger values.
+
   <facility> must be one of the 24 standard syslog facilities :
 
           kern   user   mail   daemon auth   syslog lpr    news
@@ -3358,7 +3370,7 @@ ignore-persist { if | unless } <condition>
 
 
 log global
-log <address> <facility> [<level> [<minlevel>]]
+log <address> [len <length>] <facility> [<level> [<minlevel>]]
 no log
   Enable per-instance logging of events and traffic.
   May be used in sections :   defaults | frontend | listen | backend
@@ -3398,6 +3410,18 @@ no log
                sign ('$') and optionally enclosing them with braces ('{}'),
                similarly to what is done in Bourne shell.
 
+    <length>   is an optional maximum line length. Log lines larger than this
+               value will be truncated before being sent. The reason is that
+               syslog servers act differently on log line length. All servers
+               support the default value of 1024, but some servers simply drop
+               larger lines while others do log them. If a server supports long
+               lines, it may make sense to set this value here in order to avoid
+               truncating long lines. Similarly, if a server drops long lines,
+               it is preferable to truncate them before sending them. Accepted
+               values are 80 to 65535 inclusive. The default value of 1024 is
+               generally fine for all standard usages. Some specific cases of
+               long captures or JSON-formated logs may require larger values.
+
     <facility> must be one of the 24 standard syslog facilities :
 
                  kern   user   mail   daemon auth   syslog lpr    news

include/proto/log.h

@@ -39,6 +39,7 @@ extern char *log_format;
 extern char default_tcp_log_format[];
 extern char default_http_log_format[];
 extern char clf_http_log_format[];
+extern char *logline;
 
 
 int build_logline(struct session *s, char *dst, size_t maxsize, struct list *list_format);

include/types/global.h

@@ -111,6 +111,7 @@ struct global {
 	int last_checks;
 	int spread_checks;
 	int max_spread_checks;
+	int max_syslog_len;
 	char *chroot;
 	char *pidfile;
 	char *node, *desc;		/* node name & description */

include/types/log.h

@@ -152,6 +152,7 @@ struct logsrv {
 	int facility;
 	int level;
 	int minlvl;
+	int maxlen;
 };
 
 #endif /* _TYPES_LOG_H */

src/cfgparse.c

@@ -1257,6 +1257,8 @@ int cfg_parse_global(const char *file, int linenum, char **args, int kwm)
 		struct sockaddr_storage *sk;
 		int port1, port2;
 		struct logsrv *logsrv;
+		int arg = 0;
+		int len = 0;
 
 		if (*(args[1]) == 0 || *(args[2]) == 0) {
 			Alert("parsing [%s:%d] : '%s' expects <address> and <facility> as arguments.\n", file, linenum, args[0]);
@@ -1266,28 +1268,50 @@ int cfg_parse_global(const char *file, int linenum, char **args, int kwm)
 
 		logsrv = calloc(1, sizeof(struct logsrv));
 
-		logsrv->facility = get_log_facility(args[2]);
+		/* just after the address, a length may be specified */
+		if (strcmp(args[arg+2], "len") == 0) {
+			len = atoi(args[arg+3]);
+			if (len < 80 || len > 65535) {
+				Alert("parsing [%s:%d] : invalid log length '%s', must be between 80 and 65535.\n",
+				      file, linenum, args[arg+3]);
+				err_code |= ERR_ALERT | ERR_FATAL;
+				goto out;
+			}
+			logsrv->maxlen = len;
+
+			/* skip these two args */
+			arg += 2;
+		}
+		else
+			logsrv->maxlen = MAX_SYSLOG_LEN;
+
+		if (logsrv->maxlen > global.max_syslog_len) {
+			global.max_syslog_len = logsrv->maxlen;
+			logline = realloc(logline, global.max_syslog_len + 1);
+		}
+
+		logsrv->facility = get_log_facility(args[arg+2]);
 		if (logsrv->facility < 0) {
-			Alert("parsing [%s:%d] : unknown log facility '%s'\n", file, linenum, args[2]);
+			Alert("parsing [%s:%d] : unknown log facility '%s'\n", file, linenum, args[arg+2]);
 			err_code |= ERR_ALERT | ERR_FATAL;
 			logsrv->facility = 0;
 		}
 
 		logsrv->level = 7; /* max syslog level = debug */
-		if (*(args[3])) {
+		if (*(args[arg+3])) {
-			logsrv->level = get_log_level(args[3]);
+			logsrv->level = get_log_level(args[arg+3]);
 			if (logsrv->level < 0) {
-				Alert("parsing [%s:%d] : unknown optional log level '%s'\n", file, linenum, args[3]);
+				Alert("parsing [%s:%d] : unknown optional log level '%s'\n", file, linenum, args[arg+3]);
 				err_code |= ERR_ALERT | ERR_FATAL;
 				logsrv->level = 0;
 			}
 		}
 
 		logsrv->minlvl = 0; /* limit syslog level to this level (emerg) */
-		if (*(args[4])) {
+		if (*(args[arg+4])) {
-			logsrv->minlvl = get_log_level(args[4]);
+			logsrv->minlvl = get_log_level(args[arg+4]);
 			if (logsrv->minlvl < 0) {
-				Alert("parsing [%s:%d] : unknown optional minimum log level '%s'\n", file, linenum, args[4]);
+				Alert("parsing [%s:%d] : unknown optional minimum log level '%s'\n", file, linenum, args[arg+4]);
 				err_code |= ERR_ALERT | ERR_FATAL;
 				logsrv->minlvl = 0;
 			}
@@ -4843,22 +4867,46 @@ stats_error_parsing:
 		else if (*(args[1]) && *(args[2])) {
 			struct sockaddr_storage *sk;
 			int port1, port2;
+			int arg = 0;
+			int len = 0;
 
 			logsrv = calloc(1, sizeof(struct logsrv));
 
-			logsrv->facility = get_log_facility(args[2]);
+			/* just after the address, a length may be specified */
+			if (strcmp(args[arg+2], "len") == 0) {
+				len = atoi(args[arg+3]);
+				if (len < 80 || len > 65535) {
+					Alert("parsing [%s:%d] : invalid log length '%s', must be between 80 and 65535.\n",
+					      file, linenum, args[arg+3]);
+					err_code |= ERR_ALERT | ERR_FATAL;
+					goto out;
+				}
+				logsrv->maxlen = len;
+
+				/* skip these two args */
+				arg += 2;
+			}
+			else
+				logsrv->maxlen = MAX_SYSLOG_LEN;
+
+			if (logsrv->maxlen > global.max_syslog_len) {
+				global.max_syslog_len = logsrv->maxlen;
+				logline = realloc(logline, global.max_syslog_len + 1);
+			}
+
+			logsrv->facility = get_log_facility(args[arg+2]);
 			if (logsrv->facility < 0) {
-				Alert("parsing [%s:%d] : unknown log facility '%s'\n", file, linenum, args[2]);
+				Alert("parsing [%s:%d] : unknown log facility '%s'\n", file, linenum, args[arg+2]);
 				err_code |= ERR_ALERT | ERR_FATAL;
 				goto out;
 
 			}
 	    
 			logsrv->level = 7; /* max syslog level = debug */
-			if (*(args[3])) {
+			if (*(args[arg+3])) {
-				logsrv->level = get_log_level(args[3]);
+				logsrv->level = get_log_level(args[arg+3]);
 				if (logsrv->level < 0) {
-					Alert("parsing [%s:%d] : unknown optional log level '%s'\n", file, linenum, args[3]);
+					Alert("parsing [%s:%d] : unknown optional log level '%s'\n", file, linenum, args[arg+3]);
 					err_code |= ERR_ALERT | ERR_FATAL;
 					goto out;
 
@@ -4866,10 +4914,10 @@ stats_error_parsing:
 			}
 
 			logsrv->minlvl = 0; /* limit syslog level to this level (emerg) */
-			if (*(args[4])) {
+			if (*(args[arg+4])) {
-				logsrv->minlvl = get_log_level(args[4]);
+				logsrv->minlvl = get_log_level(args[arg+4]);
 				if (logsrv->minlvl < 0) {
-					Alert("parsing [%s:%d] : unknown optional minimum log level '%s'\n", file, linenum, args[4]);
+					Alert("parsing [%s:%d] : unknown optional minimum log level '%s'\n", file, linenum, args[arg+4]);
 					err_code |= ERR_ALERT | ERR_FATAL;
 					goto out;
 

src/log.c

@@ -146,7 +146,7 @@ char *log_format = NULL;
 /* This is a global syslog line, common to all outgoing messages. It begins
  * with the syslog tag and the date that are updated by update_log_hdr().
  */
-static char logline[MAX_SYSLOG_LEN];
+char *logline = NULL;
 
 struct logformat_var_args {
 	char *name;
@@ -736,7 +736,7 @@ static char *update_log_hdr()
 		tvsec = date.tv_sec;
 		get_localtime(tvsec, &tm);
 
-		hdr_len = snprintf(logline, MAX_SYSLOG_LEN,
+		hdr_len = snprintf(logline, global.max_syslog_len,
 				   "<<<<>%s %2d %02d:%02d:%02d %s%s[%d]: ",
 				   monthname[tm.tm_mon],
 				   tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec,
@@ -746,8 +746,8 @@ static char *update_log_hdr()
 		 * either -1 or the number of bytes that would be needed to store
 		 * the total message. In both cases, we must adjust it.
 		 */
-		if (hdr_len < 0 || hdr_len > MAX_SYSLOG_LEN)
+		if (hdr_len < 0 || hdr_len > global.max_syslog_len)
-			hdr_len = MAX_SYSLOG_LEN;
+			hdr_len = global.max_syslog_len;
 
 		dataptr = logline + hdr_len;
 	}
@@ -772,9 +772,9 @@ void send_log(struct proxy *p, int level, const char *format, ...)
 	data_len = dataptr - logline;
 
 	va_start(argp, format);
-	data_len += vsnprintf(dataptr, logline + sizeof(logline) - dataptr, format, argp);
+	data_len += vsnprintf(dataptr, logline + global.max_syslog_len - dataptr, format, argp);
-	if (data_len < 0 || data_len > MAX_SYSLOG_LEN)
+	if (data_len < 0 || data_len > global.max_syslog_len)
-		data_len =  MAX_SYSLOG_LEN;
+		data_len = global.max_syslog_len;
 	va_end(argp);
 
 	__send_log(p, level, logline, data_len);
@@ -811,8 +811,6 @@ void __send_log(struct proxy *p, int level, char *message, size_t size)
 	if (!logsrvs)
 		return;
 
-	message[size - 1] = '\n';
-
 	/* Send log messages to syslog server. */
 	nblogger = 0;
 	list_for_each_entry(tmp, logsrvs, list) {
@@ -820,6 +818,8 @@ void __send_log(struct proxy *p, int level, char *message, size_t size)
 		int *plogfd = logsrv->addr.ss_family == AF_UNIX ?
 			&logfdunix : &logfdinet;
 		int sent;
+		int max;
+		char backup;
 
 		nblogger++;
 
@@ -858,9 +858,23 @@ void __send_log(struct proxy *p, int level, char *message, size_t size)
 		} while (fac_level && log_ptr > dataptr);
 		*log_ptr = '<';
 
-		sent = sendto(*plogfd, log_ptr, size - (log_ptr - dataptr),
+		max = size - (log_ptr - dataptr);
+		if (max > logsrv->maxlen)
+			max = logsrv->maxlen;
+
+		/* insert a \n at the end of the message, but save what was
+		 * there first because we could have different max lengths
+		 * for different log targets.
+		 */
+		backup = log_ptr[max - 1];
+		log_ptr[max - 1] = '\n';
+
+		sent = sendto(*plogfd, log_ptr, max,
 			      MSG_DONTWAIT | MSG_NOSIGNAL,
 			      (struct sockaddr *)&logsrv->addr, get_addr_len(&logsrv->addr));
+
+		log_ptr[max - 1] = backup;
+
 		if (sent < 0) {
 			Alert("sendto logger #%d failed: %s (errno=%d)\n",
 				nblogger, strerror(errno), errno);
@@ -1604,7 +1618,7 @@ void sess_log(struct session *s)
 
 	tmplog = update_log_hdr();
 	size = tmplog - logline;
-	size += build_logline(s, tmplog, sizeof(logline) - size, &s->fe->logformat);
+	size += build_logline(s, tmplog, global.max_syslog_len - size, &s->fe->logformat);
 	if (size > 0) {
 		__send_log(s->fe, level, logline, size + 1);
 		s->logs.logwait = 0;