diff mbox series

[v3,4/4] midx: during verify group objects by packfile to speed verification

Message ID 7e98ea005aa62ca36af7da34dc6c21a1f77b351e.1553196970.git.gitgitgadget@gmail.com (mailing list archive)
State New, archived
Headers show
Series multi-pack-index: fix verify on large repos | expand

Commit Message

Linus Arver via GitGitGadget March 21, 2019, 7:36 p.m. UTC
From: Jeff Hostetler <jeffhost@microsoft.com>

Teach `multi-pack-index verify` to sort the set of object by
packfile so that only one packfile needs to be open at a time.

This is a performance improvement.  Previously, objects were
verified in OID order.  This essentially requires all packfiles
to be open at the same time.  If the number of packfiles exceeds
the open file limit, packfiles would be LRU-closed and re-opened
many times.

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
---
 midx.c     | 49 ++++++++++++++++++++++++++++++++++++++++++++++---
 packfile.c |  2 +-
 packfile.h |  2 ++
 3 files changed, 49 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/midx.c b/midx.c
index e3919387d9..f1cd868f8c 100644
--- a/midx.c
+++ b/midx.c
@@ -962,6 +962,20 @@  static void midx_report(const char *fmt, ...)
 	va_end(ap);
 }
 
+struct pair_pos_vs_id
+{
+	uint32_t pos;
+	uint32_t pack_int_id;
+};
+
+static int compare_pair_pos_vs_id(const void *_a, const void *_b)
+{
+	struct pair_pos_vs_id *a = (struct pair_pos_vs_id *)_a;
+	struct pair_pos_vs_id *b = (struct pair_pos_vs_id *)_b;
+
+	return b->pack_int_id - a->pack_int_id;
+}
+
 /*
  * Limit calls to display_progress() for performance reasons.
  * The interval here was arbitrarily chosen.
@@ -976,6 +990,7 @@  static void midx_report(const char *fmt, ...)
 
 int verify_midx_file(const char *object_dir)
 {
+	struct pair_pos_vs_id *pairs = NULL;
 	uint32_t i;
 	struct progress *progress;
 	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
@@ -1019,16 +1034,42 @@  int verify_midx_file(const char *object_dir)
 	}
 	stop_progress(&progress);
 
+	/*
+	 * Create an array mapping each object to its packfile id.  Sort it
+	 * to group the objects by packfile.  Use this permutation to visit
+	 * each of the objects and only require 1 packfile to be open at a
+	 * time.
+	 */
+	ALLOC_ARRAY(pairs, m->num_objects);
+	for (i = 0; i < m->num_objects; i++) {
+		pairs[i].pos = i;
+		pairs[i].pack_int_id = nth_midxed_pack_int_id(m, i);
+	}
+
+	progress = start_sparse_progress(_("Sorting objects by packfile"),
+					 m->num_objects);
+	display_progress(progress, 0); /* TODO: Measure QSORT() progress */
+	QSORT(pairs, m->num_objects, compare_pair_pos_vs_id);
+	stop_progress(&progress);
+
 	progress = start_sparse_progress(_("Verifying object offsets"), m->num_objects);
 	for (i = 0; i < m->num_objects; i++) {
 		struct object_id oid;
 		struct pack_entry e;
 		off_t m_offset, p_offset;
 
-		nth_midxed_object_oid(&oid, m, i);
+		if (i > 0 && pairs[i-1].pack_int_id != pairs[i].pack_int_id &&
+		    m->packs[pairs[i-1].pack_int_id])
+		{
+			close_pack_fd(m->packs[pairs[i-1].pack_int_id]);
+			close_pack_index(m->packs[pairs[i-1].pack_int_id]);
+		}
+
+		nth_midxed_object_oid(&oid, m, pairs[i].pos);
+
 		if (!fill_midx_entry(&oid, &e, m)) {
 			midx_report(_("failed to load pack entry for oid[%d] = %s"),
-				    i, oid_to_hex(&oid));
+				    pairs[i].pos, oid_to_hex(&oid));
 			continue;
 		}
 
@@ -1043,11 +1084,13 @@  int verify_midx_file(const char *object_dir)
 
 		if (m_offset != p_offset)
 			midx_report(_("incorrect object offset for oid[%d] = %s: %"PRIx64" != %"PRIx64),
-				    i, oid_to_hex(&oid), m_offset, p_offset);
+				    pairs[i].pos, oid_to_hex(&oid), m_offset, p_offset);
 
 		midx_display_sparse_progress(progress, i + 1);
 	}
 	stop_progress(&progress);
 
+	free(pairs);
+
 	return verify_midx_error;
 }
diff --git a/packfile.c b/packfile.c
index 16bcb75262..d2bcb2f860 100644
--- a/packfile.c
+++ b/packfile.c
@@ -309,7 +309,7 @@  void close_pack_windows(struct packed_git *p)
 	}
 }
 
-static int close_pack_fd(struct packed_git *p)
+int close_pack_fd(struct packed_git *p)
 {
 	if (p->pack_fd < 0)
 		return 0;
diff --git a/packfile.h b/packfile.h
index d70c6d9afb..b1c18504eb 100644
--- a/packfile.h
+++ b/packfile.h
@@ -76,6 +76,8 @@  extern int open_pack_index(struct packed_git *);
  */
 extern void close_pack_index(struct packed_git *);
 
+int close_pack_fd(struct packed_git *p);
+
 extern uint32_t get_pack_fanout(struct packed_git *p, uint32_t value);
 
 extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *);