bug#58558: 29.0.50; re-search-forward is slow in some buffers

["Mattias Engdegård" <mattias.engdegard@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 220 bytes --]

Ihor, would you consider the possibility of regexp cache thrashing? It does occur from time to time; that cache is quite small. Try this instrumentation patch. (We should probably have something like it permanently.)


[-- Attachment #2: 0001-Add-regexp-cache-hit-miss-counters.patch --]
[-- Type: application/octet-stream, Size: 1785 bytes --]

From 978ce66e9bd50da11997aeadcc3508549863a116 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mattias=20Engdeg=C3=A5rd?= <mattiase@acm.org>
Date: Sat, 7 Nov 2020 17:00:53 +0100
Subject: [PATCH 1/2] Add regexp cache hit/miss counters

---
 src/search.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/src/search.c b/src/search.c
index 4eb634a3c0..358b82da2e 100644
--- a/src/search.c
+++ b/src/search.c
@@ -222,7 +222,10 @@ compile_pattern (Lisp_Object pattern, struct re_registers *regp,
 	      || EQ (cp->syntax_table, BVAR (current_buffer, syntax_table)))
 	  && !NILP (Fequal (cp->f_whitespace_regexp, Vsearch_spaces_regexp))
 	  && cp->buf.charset_unibyte == charset_unibyte)
-	break;
+        {
+          regexp_cache_hit++;
+          break;
+        }
 
       /* If we're at the end of the cache, compile into the last
 	 (least recently used) non-busy cell in the cache.  */
@@ -234,6 +237,7 @@ compile_pattern (Lisp_Object pattern, struct re_registers *regp,
           cp = *cpp;
 	compile_it:
           eassert (!cp->busy);
+          regexp_cache_miss++;
 	  compile_pattern_1 (cp, pattern, translate, posix);
 	  break;
 	}
@@ -3390,6 +3394,13 @@ syms_of_search (void)
 is to bind it with `let' around a small expression.  */);
   Vinhibit_changing_match_data = Qnil;
 
+  DEFVAR_INT("regexp-cache-hit", regexp_cache_hit,
+             doc: /* Regexp cache hit count.  Internal use only. */);
+  regexp_cache_hit = 0;
+  DEFVAR_INT("regexp-cache-miss", regexp_cache_miss,
+             doc: /* Regexp cache miss count.  Internal use only. */);
+  regexp_cache_miss = 0;
+
   defsubr (&Slooking_at);
   defsubr (&Sposix_looking_at);
   defsubr (&Sstring_match);
-- 
2.21.1 (Apple Git-122.3)