Get rid of O(N^2) script-parsing overhead in pgbench.

pgbench wants to record the starting line number of each command
in its scripts.  It was computing that by scanning from the script
start and counting newlines, so that O(N^2) work had to be done
for an N-command script.  In a script with 50K lines, this adds
up to about 10 seconds on my machine.

To add insult to injury, the results were subtly wrong, because
expr_scanner_offset() scanned to find the NUL that flex inserts
at the end of the current token --- and before the first yylex
call, no such NUL has been inserted.  So we ended by computing the
script's last line number not its first one.  This was visible only
in case of \gset at the start of a script, which perhaps accounts
for the lack of complaints.

To fix, steal an idea from plpgsql and track the current lexer
ending position and line count as we advance through the script.
(It's a bit simpler than plpgsql since we can't need to back up.)
Also adjust a couple of other places that were invoking scans
from script start when they didn't really need to.  I made a new
psqlscan function psql_scan_get_location() that replaces both
expr_scanner_offset() and expr_scanner_get_lineno(), since in
practice expr_scanner_get_lineno() was only being invoked to find
the line number of the current lexer end position.

Reported-by: Daniel Vérité <daniel@manitou-mail.org>
Author: Tom Lane <tgl@sss.pgh.pa.us>
Discussion: https://postgr.es/m/84a8a89e-adb8-47a9-9d34-c13f7150ee45@manitou-mail.org

src/bin/pgbench/exprscan.l

@@ -271,10 +271,14 @@ void
 expr_yyerror_more(yyscan_t yyscanner, const char *message, const char *more)
 {
 	PsqlScanState state = yyget_extra(yyscanner);
-	int			error_detection_offset = expr_scanner_offset(state) - 1;
+	int			lineno;
+	int			error_detection_offset;
 	YYSTYPE		lval;
 	char	   *full_line;
 
+	psql_scan_get_location(state, &lineno, &error_detection_offset);
+	error_detection_offset--;
+
 	/*
 	 * While parsing an expression, we may not have collected the whole line
 	 * yet from the input source.  Lex till EOL so we can report whole line.
@@ -289,7 +293,6 @@ expr_yyerror_more(yyscan_t yyscanner, const char *message, const char *more)
 	/* Extract the line, trimming trailing newline if any */
 	full_line = expr_scanner_get_substring(state,
 										   expr_start_offset,
-										   expr_scanner_offset(state),
 										   true);
 
 	syntax_error(expr_source, expr_lineno, full_line, expr_command,
@@ -336,12 +339,15 @@ expr_lex_one_word(PsqlScanState state, PQExpBuffer word_buf, int *offset)
 	/* And lex. */
 	lexresult = yylex(&lval, state->scanner);
 
-	/*
-	 * Save start offset of word, if any.  We could do this more efficiently,
-	 * but for now this seems fine.
-	 */
+	/* Save start offset of word, if any. */
 	if (lexresult)
-		*offset = expr_scanner_offset(state) - word_buf->len;
+	{
+		int			lineno;
+		int			end_offset;
+
+		psql_scan_get_location(state, &lineno, &end_offset);
+		*offset = end_offset - word_buf->len;
+	}
 	else
 		*offset = -1;
 
@@ -404,35 +410,25 @@ expr_scanner_finish(yyscan_t yyscanner)
 }
 
 /*
- * Get offset from start of string to end of current lexer token.
+ * Get a malloc'd copy of the lexer input string from start_offset
+ * to end of current lexer token.  If chomp is true, drop any trailing
+ * newline(s).
  *
  * We rely on the knowledge that flex modifies the scan buffer by storing
  * a NUL at the end of the current token (yytext).  Note that this might
  * not work quite right if we were parsing a sub-buffer, but since pgbench
- * never invokes that functionality, it doesn't matter.
- */
-int
-expr_scanner_offset(PsqlScanState state)
-{
-	return strlen(state->scanbuf);
-}
-
-/*
- * Get a malloc'd copy of the lexer input string from start_offset
- * to just before end_offset.  If chomp is true, drop any trailing
- * newline(s).
+ * never invokes that functionality, it doesn't matter.  Also, this will
+ * give the wrong answer (the whole remainder of the input) if called
+ * before any yylex() call has been done.
  */
 char *
 expr_scanner_get_substring(PsqlScanState state,
-						   int start_offset, int end_offset,
+						   int start_offset,
 						   bool chomp)
 {
 	char	   *result;
 	const char *scanptr = state->scanbuf + start_offset;
-	int			slen = end_offset - start_offset;
-
-	Assert(slen >= 0);
-	Assert(end_offset <= strlen(state->scanbuf));
+	size_t		slen = strlen(scanptr);
 
 	if (chomp)
 	{
@@ -447,22 +443,3 @@ expr_scanner_get_substring(PsqlScanState state,
 
 	return result;
 }
-
-/*
- * Get the line number associated with the given string offset
- * (which must not be past the end of where we've lexed to).
- */
-int
-expr_scanner_get_lineno(PsqlScanState state, int offset)
-{
-	int			lineno = 1;
-	const char *p = state->scanbuf;
-
-	while (*p && offset > 0)
-	{
-		if (*p == '\n')
-			lineno++;
-		p++, offset--;
-	}
-	return lineno;
-}

src/bin/pgbench/pgbench.c

@@ -5690,8 +5690,8 @@ process_backslash_command(PsqlScanState sstate, const char *source)
 	initPQExpBuffer(&word_buf);
 
 	/* Remember location of the backslash */
-	start_offset = expr_scanner_offset(sstate) - 1;
-	lineno = expr_scanner_get_lineno(sstate, start_offset);
+	psql_scan_get_location(sstate, &lineno, &start_offset);
+	start_offset--;
 
 	/* Collect first word of command */
 	if (!expr_lex_one_word(sstate, &word_buf, &word_offset))
@@ -5747,7 +5747,6 @@ process_backslash_command(PsqlScanState sstate, const char *source)
 		my_command->first_line =
 			expr_scanner_get_substring(sstate,
 									   start_offset,
-									   expr_scanner_offset(sstate),
 									   true);
 
 		expr_scanner_finish(yyscanner);
@@ -5777,7 +5776,6 @@ process_backslash_command(PsqlScanState sstate, const char *source)
 	my_command->first_line =
 		expr_scanner_get_substring(sstate,
 								   start_offset,
-								   expr_scanner_offset(sstate),
 								   true);
 
 	if (my_command->meta == META_SLEEP)
@@ -5952,8 +5950,6 @@ ParseScript(const char *script, const char *desc, int weight)
 	PQExpBufferData line_buf;
 	int			alloc_num;
 	int			index;
-	int			lineno;
-	int			start_offset;
 
 #define COMMANDS_ALLOC_NUM 128
 	alloc_num = COMMANDS_ALLOC_NUM;
@@ -5977,7 +5973,6 @@ ParseScript(const char *script, const char *desc, int weight)
 	 * stdstrings should be true, which is a bit riskier.
 	 */
 	psql_scan_setup(sstate, script, strlen(script), 0, true);
-	start_offset = expr_scanner_offset(sstate) - 1;
 
 	initPQExpBuffer(&line_buf);
 
@@ -5985,12 +5980,15 @@ ParseScript(const char *script, const char *desc, int weight)
 
 	for (;;)
 	{
+		int			lineno;
+		int			start_offset;
 		PsqlScanResult sr;
 		promptStatus_t prompt;
 		Command    *command = NULL;
 
 		resetPQExpBuffer(&line_buf);
-		lineno = expr_scanner_get_lineno(sstate, start_offset);
+
+		psql_scan_get_location(sstate, &lineno, &start_offset);
 
 		sr = psql_scan(sstate, &line_buf, &prompt);
 

src/bin/pgbench/pgbench.h

@@ -149,11 +149,9 @@ extern yyscan_t expr_scanner_init(PsqlScanState state,
 								  const char *source, int lineno, int start_offset,
 								  const char *command);
 extern void expr_scanner_finish(yyscan_t yyscanner);
-extern int	expr_scanner_offset(PsqlScanState state);
 extern char *expr_scanner_get_substring(PsqlScanState state,
-										int start_offset, int end_offset,
+										int start_offset,
 										bool chomp);
-extern int	expr_scanner_get_lineno(PsqlScanState state, int offset);
 
 extern void syntax_error(const char *source, int lineno, const char *line,
 						 const char *command, const char *msg,

src/fe_utils/psqlscan.l

@@ -1079,6 +1079,10 @@ psql_scan_setup(PsqlScanState state,
 	/* Set lookaside data in case we have to map unsafe encoding */
 	state->curline = state->scanbuf;
 	state->refline = state->scanline;
+
+	/* Initialize state for psql_scan_get_location() */
+	state->cur_line_no = 0;		/* yylex not called yet */
+	state->cur_line_ptr = state->scanbuf;
 }
 
 /*
@@ -1136,6 +1140,10 @@ psql_scan(PsqlScanState state,
 	/* And lex. */
 	lexresult = yylex(NULL, state->scanner);
 
+	/* Notify psql_scan_get_location() that a yylex call has been made. */
+	if (state->cur_line_no == 0)
+		state->cur_line_no = 1;
+
 	/*
 	 * Check termination state and return appropriate result info.
 	 */
@@ -1311,6 +1319,52 @@ psql_scan_in_quote(PsqlScanState state)
 		state->start_state != xqs;
 }
 
+/*
+ * Return the current scanning location (end+1 of last scanned token),
+ * as a line number counted from 1 and an offset from string start.
+ *
+ * This considers only the outermost input string, and therefore is of
+ * limited use for programs that use psqlscan_push_new_buffer().
+ *
+ * It would be a bit easier probably to use "%option yylineno" to count
+ * lines, but the flex manual says that has a performance cost, and only
+ * a minority of programs using psqlscan have need for this functionality.
+ * So we implement it ourselves without adding overhead to the lexer itself.
+ */
+void
+psql_scan_get_location(PsqlScanState state,
+					   int *lineno, int *offset)
+{
+	const char *line_end;
+
+	/*
+	 * We rely on flex's having stored a NUL after the current token in
+	 * scanbuf.  Therefore we must specially handle the state before yylex()
+	 * has been called, when obviously that won't have happened yet.
+	 */
+	if (state->cur_line_no == 0)
+	{
+		*lineno = 1;
+		*offset = 0;
+		return;
+	}
+
+	/*
+	 * Advance cur_line_no/cur_line_ptr past whatever has been lexed so far.
+	 * Doing this prevents repeated calls from being O(N^2) for long inputs.
+	 */
+	while ((line_end = strchr(state->cur_line_ptr, '\n')) != NULL)
+	{
+		state->cur_line_no++;
+		state->cur_line_ptr = line_end + 1;
+	}
+	state->cur_line_ptr += strlen(state->cur_line_ptr);
+
+	/* Report current location. */
+	*lineno = state->cur_line_no;
+	*offset = state->cur_line_ptr - state->scanbuf;
+}
+
 /*
  * Push the given string onto the stack of stuff to scan.
  *

src/include/fe_utils/psqlscan.h

@@ -87,4 +87,7 @@ extern void psql_scan_reselect_sql_lexer(PsqlScanState state);
 
 extern bool psql_scan_in_quote(PsqlScanState state);
 
+extern void psql_scan_get_location(PsqlScanState state,
+								   int *lineno, int *offset);
+
 #endif							/* PSQLSCAN_H */

src/include/fe_utils/psqlscan_int.h

@@ -104,6 +104,10 @@ typedef struct PsqlScanStateData
 	const char *curline;		/* actual flex input string for cur buf */
 	const char *refline;		/* original data for cur buffer */
 
+	/* status for psql_scan_get_location() */
+	int			cur_line_no;	/* current line#, or 0 if no yylex done */
+	const char *cur_line_ptr;	/* points into cur_line_no'th line in scanbuf */
+
 	/*
 	 * All this state lives across successive input lines, until explicitly
 	 * reset by psql_scan_reset.  start_state is adopted by yylex() on entry,