Further apropos(1) speed optimization was trickier than anticipated.

Contrary to what i initially thought, almost all time is now spent
inside sqlite3(3) routines, and i found no easy way calling less of them.
However, sqlite(3) spends substantial time in malloc(3), and even more
(twice that) in its immediate malloc wrapper, sqlite3MemMalloc(),
keeping track of all individual malloc chunk sizes.  Typically about
90% of the malloced memory is used for purposes of the pagecache.

By providing an mmap(3) MAP_ANON SQLITE_CONFIG_PAGECACHE, execution
time decreases by 20-25% for simple (Nd and/or Nm) queries, 10-20% for
non-NAME queries, and even apropos(1) resident memory size as reported
by top(1) decreases by 20% for simple and by 60% for non-NAME queries.
The new function, mansearch_setup(), spends no measurable time.

The pagesize chosen is optimal:
* Substantially smaller pages yield no gain at all.
* Larger pages provide no additional benefit and just waste memory.

The chosen number of pages in the cache is a compromise:
* For simple queries, a handful of pages would suffice to get the full
speed effect, at an apropos(1) resident memory size of about 2.0 MB.
* For non-NAME queries, a large pagecache with 2k pages (2.5 MB) might
gain a few more percent in speed, but at the expense of doubling the
apropos(1) resident memory size for *all* queries.
* The chosen number of 256 pages (330 kB) allows nearly full speed gain
for all queries at the price of a 15% resident memory size increase.

3 files changed, 51 insertions, 0 deletions

diff --git a/apropos.c b/apropos.c
index 086a842e..ac7e6d87 100644
--- a/apropos.c
+++ b/apropos.c
@@ -95,6 +95,7 @@ main(int argc, char *argv[])
 	search.flags = whatis ? MANSEARCH_WHATIS : 0;
 
 	manpath_parse(&paths, conf_file, defpaths, auxpaths);
+	mansearch_setup(1);
 	ch = mansearch(&search, &paths, argc, argv, outkey, &res, &sz);
 	manpath_free(&paths);
 
@@ -110,6 +111,7 @@ main(int argc, char *argv[])
 	}
 
 	free(res);
+	mansearch_setup(0);
 	return(sz ? EXIT_SUCCESS : EXIT_FAILURE);
 usage:
 	fprintf(stderr, "usage: %s [-C file] [-M path] [-m path] "
diff --git a/mansearch.c b/mansearch.c
index a4348d64..b6c00a9a 100644
--- a/mansearch.c
+++ b/mansearch.c
@@ -19,6 +19,7 @@
 #include "config.h"
 #endif
 
+#include <sys/mman.h>
 #include <assert.h>
 #include <fcntl.h>
 #include <getopt.h>
@@ -101,6 +102,53 @@ static	void		 sql_regexp(sqlite3_context *context,
 static	char		*sql_statement(const struct expr *);
 
 int
+mansearch_setup(int start)
+{
+	static void	*pagecache;
+	int		 c;
+
+#define	PC_PAGESIZE	1280
+#define	PC_NUMPAGES	256
+
+	if (start) {
+		if (NULL != pagecache) {
+			fprintf(stderr, "pagecache already enabled\n");
+			return((int)MANDOCLEVEL_BADARG);
+		}
+
+		pagecache = mmap(NULL, PC_PAGESIZE * PC_NUMPAGES,
+		    PROT_READ | PROT_WRITE, MAP_ANON, -1, 0);
+
+		if (MAP_FAILED == pagecache) {
+			perror("mmap");
+			pagecache = NULL;
+			return((int)MANDOCLEVEL_SYSERR);
+		}
+
+		c = sqlite3_config(SQLITE_CONFIG_PAGECACHE,
+		    pagecache, PC_PAGESIZE, PC_NUMPAGES);
+
+		if (SQLITE_OK == c)
+			return((int)MANDOCLEVEL_OK);
+
+		fprintf(stderr, "pagecache: %s\n", sqlite3_errstr(c));
+
+	} else if (NULL == pagecache) {
+		fprintf(stderr, "pagecache missing\n");
+		return((int)MANDOCLEVEL_BADARG);
+	}
+
+	if (-1 == munmap(pagecache, PC_PAGESIZE * PC_NUMPAGES)) {
+		perror("munmap");
+		pagecache = NULL;
+		return((int)MANDOCLEVEL_SYSERR);
+	}
+
+	pagecache = NULL;
+	return((int)MANDOCLEVEL_OK);
+}
+
+int
 mansearch(const struct mansearch *search,
 		const struct manpaths *paths,
 		int argc, char *argv[],
diff --git a/mansearch.h b/mansearch.h
index d5a10ba3..894c8476 100644
--- a/mansearch.h
+++ b/mansearch.h
@@ -85,6 +85,7 @@ struct	mansearch {
 #define	MANSEARCH_WHATIS 0x01 /* whatis mode: equality, no key */
 };
 
+int	mansearch_setup(int);
 int	mansearch(const struct mansearch *cfg, /* options */
 		const struct manpaths *paths, /* manpaths */
 		int argc, /* size of argv */