Merge branch 'jk/pack-objects-optim'

"git pack-objects" has a few options that tell it not to pack
objects found in certain packfiles, which require it to scan .idx
files of all available packs.  The codepaths involved in these
operations have been optimized for a common case of not having any
non-local pack and/or any .kept pack.

* jk/pack-objects-optim:
  pack-objects: compute local/ignore_pack_keep early
  pack-objects: break out of want_object loop early
  find_pack_entry: replace last_found_pack with MRU cache
  add generic most-recently-used list
  sha1_file: drop free_pack_by_name
  t/perf: add tests for many-pack scenarios

1 files changed, 18 insertions, 48 deletions

diff --git a/sha1_file.c b/sha1_file.c
index cb571ac6e8..3066b5f71c 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -23,6 +23,7 @@
 #include "bulk-checkin.h"
 #include "streaming.h"
 #include "dir.h"
+#include "mru.h"
 
 #ifndef O_NOATIME
 #if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -59,14 +60,6 @@ static struct cached_object empty_tree = {
 	0
 };
 
-/*
- * A pointer to the last packed_git in which an object was found.
- * When an object is sought, we look in this packfile first, because
- * objects that are looked up at similar times are often in the same
- * packfile as one another.
- */
-static struct packed_git *last_found_pack;
-
 static struct cached_object *find_cached_object(const unsigned char *sha1)
 {
 	int i;
@@ -522,6 +515,9 @@ static size_t peak_pack_mapped;
 static size_t pack_mapped;
 struct packed_git *packed_git;
 
+static struct mru packed_git_mru_storage;
+struct mru *packed_git_mru = &packed_git_mru_storage;
+
 void pack_report(void)
 {
 	fprintf(stderr,
@@ -891,36 +887,6 @@ void close_pack_index(struct packed_git *p)
 	}
 }
 
-/*
- * This is used by git-repack in case a newly created pack happens to
- * contain the same set of objects as an existing one.  In that case
- * the resulting file might be different even if its name would be the
- * same.  It is best to close any reference to the old pack before it is
- * replaced on disk.  Of course no index pointers or windows for given pack
- * must subsist at this point.  If ever objects from this pack are requested
- * again, the new version of the pack will be reinitialized through
- * reprepare_packed_git().
- */
-void free_pack_by_name(const char *pack_name)
-{
-	struct packed_git *p, **pp = &packed_git;
-
-	while (*pp) {
-		p = *pp;
-		if (strcmp(pack_name, p->pack_name) == 0) {
-			clear_delta_base_cache();
-			close_pack(p);
-			free(p->bad_object_sha1);
-			*pp = p->next;
-			if (last_found_pack == p)
-				last_found_pack = NULL;
-			free(p);
-			return;
-		}
-		pp = &p->next;
-	}
-}
-
 static unsigned int get_max_fd_limit(void)
 {
 #ifdef RLIMIT_NOFILE
@@ -1385,6 +1351,15 @@ static void rearrange_packed_git(void)
 	free(ary);
 }
 
+static void prepare_packed_git_mru(void)
+{
+	struct packed_git *p;
+
+	mru_clear(packed_git_mru);
+	for (p = packed_git; p; p = p->next)
+		mru_append(packed_git_mru, p);
+}
+
 static int prepare_packed_git_run_once = 0;
 void prepare_packed_git(void)
 {
@@ -1400,6 +1375,7 @@ void prepare_packed_git(void)
 		alt->name[-1] = '/';
 	}
 	rearrange_packed_git();
+	prepare_packed_git_mru();
 	prepare_packed_git_run_once = 1;
 }
 
@@ -2604,21 +2580,15 @@ static int fill_pack_entry(const unsigned char *sha1,
  */
 static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
 {
-	struct packed_git *p;
+	struct mru_entry *p;
 
 	prepare_packed_git();
 	if (!packed_git)
 		return 0;
 
-	if (last_found_pack && fill_pack_entry(sha1, e, last_found_pack))
-		return 1;
-
-	for (p = packed_git; p; p = p->next) {
-		if (p == last_found_pack)
-			continue; /* we already checked this one */
-
-		if (fill_pack_entry(sha1, e, p)) {
-			last_found_pack = p;
+	for (p = packed_git_mru->head; p; p = p->next) {
+		if (fill_pack_entry(sha1, e, p->item)) {
+			mru_mark(packed_git_mru, p);
 			return 1;
 		}
 	}