git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Shawn O. Pearce" <spearce@spearce.org>
To: Junio C Hamano <gitster@pobox.com>
To: Junio C Hamano <gitster@pobox.com>
Cc: git@vger.kernel.org, Stephan Hennig <mailing_list@arcor.de>,
	Nicolas Pitre <nico@cam.org>, Andreas Ericsson <ae@op5.se>
Subject: [PATCH 1/4] index-pack: Refactor base arguments of resolve_delta into a struct
Date: Sun, 13 Jul 2008 22:07:44 -0400	[thread overview]
Message-ID: <1216001267-33235-2-git-send-email-spearce@spearce.org> (raw)
In-Reply-To: <1216001267-33235-1-git-send-email-spearce@spearce.org>
In-Reply-To: <20080713011512.GB31050@spearce.org>

We need to discard base objects which are not recently used if our
memory gets low, such as when we are unpacking a long delta chain
of a very large object.

To support tracking the available base objects we combine the
pointer and size into a struct.  Future changes would allow the
data pointer to be free'd and marked NULL if memory gets low.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
---
 index-pack.c |   60 +++++++++++++++++++++++++++++++--------------------------
 1 files changed, 33 insertions(+), 27 deletions(-)

diff --git a/index-pack.c b/index-pack.c
index 25db5db..db03478 100644
--- a/index-pack.c
+++ b/index-pack.c
@@ -26,6 +26,11 @@ union delta_base {
 	off_t offset;
 };
 
+struct base_data {
+	void *data;
+	unsigned long size;
+};
+
 /*
  * Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
  * to memcmp() only the first 20 bytes.
@@ -426,25 +431,25 @@ static void sha1_object(const void *data, unsigned long size,
 	}
 }
 
-static void resolve_delta(struct object_entry *delta_obj, void *base_data,
-			  unsigned long base_size, enum object_type type)
+static void resolve_delta(struct object_entry *delta_obj,
+			  struct base_data *base_obj, enum object_type type)
 {
 	void *delta_data;
 	unsigned long delta_size;
-	void *result;
-	unsigned long result_size;
 	union delta_base delta_base;
 	int j, first, last;
+	struct base_data result;
 
 	delta_obj->real_type = type;
 	delta_data = get_data_from_pack(delta_obj);
 	delta_size = delta_obj->size;
-	result = patch_delta(base_data, base_size, delta_data, delta_size,
-			     &result_size);
+	result.data = patch_delta(base_obj->data, base_obj->size,
+			     delta_data, delta_size,
+			     &result.size);
 	free(delta_data);
-	if (!result)
+	if (!result.data)
 		bad_object(delta_obj->idx.offset, "failed to apply delta");
-	sha1_object(result, result_size, type, delta_obj->idx.sha1);
+	sha1_object(result.data, result.size, type, delta_obj->idx.sha1);
 	nr_resolved_deltas++;
 
 	hashcpy(delta_base.sha1, delta_obj->idx.sha1);
@@ -452,7 +457,7 @@ static void resolve_delta(struct object_entry *delta_obj, void *base_data,
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
 			if (child->real_type == OBJ_REF_DELTA)
-				resolve_delta(child, result, result_size, type);
+				resolve_delta(child, &result, type);
 		}
 	}
 
@@ -462,11 +467,11 @@ static void resolve_delta(struct object_entry *delta_obj, void *base_data,
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
 			if (child->real_type == OBJ_OFS_DELTA)
-				resolve_delta(child, result, result_size, type);
+				resolve_delta(child, &result, type);
 		}
 	}
 
-	free(result);
+	free(result.data);
 }
 
 static int compare_delta_entry(const void *a, const void *b)
@@ -481,7 +486,6 @@ static void parse_pack_objects(unsigned char *sha1)
 {
 	int i;
 	struct delta_entry *delta = deltas;
-	void *data;
 	struct stat st;
 
 	/*
@@ -496,7 +500,7 @@ static void parse_pack_objects(unsigned char *sha1)
 				nr_objects);
 	for (i = 0; i < nr_objects; i++) {
 		struct object_entry *obj = &objects[i];
-		data = unpack_raw_entry(obj, &delta->base);
+		void *data = unpack_raw_entry(obj, &delta->base);
 		obj->real_type = obj->type;
 		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
 			nr_deltas++;
@@ -545,6 +549,7 @@ static void parse_pack_objects(unsigned char *sha1)
 		struct object_entry *obj = &objects[i];
 		union delta_base base;
 		int j, ref, ref_first, ref_last, ofs, ofs_first, ofs_last;
+		struct base_data base_obj;
 
 		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
 			continue;
@@ -555,22 +560,22 @@ static void parse_pack_objects(unsigned char *sha1)
 		ofs = !find_delta_children(&base, &ofs_first, &ofs_last);
 		if (!ref && !ofs)
 			continue;
-		data = get_data_from_pack(obj);
+		base_obj.data = get_data_from_pack(obj);
+		base_obj.size = obj->size;
+
 		if (ref)
 			for (j = ref_first; j <= ref_last; j++) {
 				struct object_entry *child = objects + deltas[j].obj_no;
 				if (child->real_type == OBJ_REF_DELTA)
-					resolve_delta(child, data,
-						      obj->size, obj->type);
+					resolve_delta(child, &base_obj, obj->type);
 			}
 		if (ofs)
 			for (j = ofs_first; j <= ofs_last; j++) {
 				struct object_entry *child = objects + deltas[j].obj_no;
 				if (child->real_type == OBJ_OFS_DELTA)
-					resolve_delta(child, data,
-						      obj->size, obj->type);
+					resolve_delta(child, &base_obj, obj->type);
 			}
-		free(data);
+		free(base_obj.data);
 		display_progress(progress, nr_resolved_deltas);
 	}
 }
@@ -656,28 +661,29 @@ static void fix_unresolved_deltas(int nr_unresolved)
 
 	for (i = 0; i < n; i++) {
 		struct delta_entry *d = sorted_by_pos[i];
-		void *data;
-		unsigned long size;
 		enum object_type type;
 		int j, first, last;
+		struct base_data base_obj;
 
 		if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
 			continue;
-		data = read_sha1_file(d->base.sha1, &type, &size);
-		if (!data)
+		base_obj.data = read_sha1_file(d->base.sha1, &type, &base_obj.size);
+		if (!base_obj.data)
 			continue;
 
 		find_delta_children(&d->base, &first, &last);
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
 			if (child->real_type == OBJ_REF_DELTA)
-				resolve_delta(child, data, size, type);
+				resolve_delta(child, &base_obj, type);
 		}
 
-		if (check_sha1_signature(d->base.sha1, data, size, typename(type)))
+		if (check_sha1_signature(d->base.sha1, base_obj.data,
+				base_obj.size, typename(type)))
 			die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
-		append_obj_to_pack(d->base.sha1, data, size, type);
-		free(data);
+		append_obj_to_pack(d->base.sha1, base_obj.data,
+			base_obj.size, type);
+		free(base_obj.data);
 		display_progress(progress, nr_resolved_deltas);
 	}
 	free(sorted_by_pos);
-- 
1.5.6.2.393.g45096


  parent reply	other threads:[~2008-07-14  2:08 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-07-10 14:40 git pull is slow Stephan Hennig
2008-07-10 15:13 ` Martin Langhoff
2008-07-10 15:28 ` Petr Baudis
2008-07-10 15:30 ` Johannes Sixt
2008-07-10 15:45   ` Stephan Hennig
2008-07-10 15:50     ` Petr Baudis
2008-07-10 17:44       ` Stephan Hennig
2008-07-11 12:25 ` Stephan Hennig
2008-07-11 13:34   ` Andreas Ericsson
2008-07-11 14:04     ` Johannes Schindelin
2008-07-12 12:32       ` Stephan Hennig
2008-07-12 17:05         ` Johannes Schindelin
2008-07-13  1:15           ` Shawn O. Pearce
2008-07-13 13:59             ` Johannes Schindelin
2008-07-13 22:11               ` Shawn O. Pearce
2008-07-14  2:07             ` [PATCH 0/4] Honor core.deltaBaseCacheLimit during index-pack Shawn O. Pearce
2008-07-14  2:27               ` Nicolas Pitre
2008-07-14  3:12                 ` Shawn O. Pearce
2008-07-14 11:44                   ` Johannes Schindelin
2008-07-14 11:54                     ` Jakub Narebski
2008-07-14 12:10                       ` Johannes Schindelin
2008-07-14 12:16                       ` Andreas Ericsson
2008-07-14 12:25                         ` Johannes Schindelin
2008-07-14 12:51                           ` Andreas Ericsson
2008-07-14 12:58                             ` Johannes Schindelin
2008-07-15  2:21                             ` Nicolas Pitre
2008-07-15  2:47                               ` Shawn O. Pearce
2008-07-15  3:06                                 ` Nicolas Pitre
2008-07-17 16:06                                 ` Stephan Hennig
2008-07-17 16:25                                   ` Nicolas Pitre
2008-07-17 21:35                                     ` Shawn O. Pearce
2008-07-17 22:02                                       ` [RFC PATCH] index-pack: Issue a warning if deltaBaseCacheLimit is too small Shawn O. Pearce
2008-07-17 23:45                                         ` Nicolas Pitre
2008-07-15  4:19                       ` [PATCH 0/4] Honor core.deltaBaseCacheLimit during index-pack Shawn O. Pearce
2008-07-14  2:07             ` Shawn O. Pearce [this message]
2008-07-15  2:40               ` [PATCH 1/4] index-pack: Refactor base arguments of resolve_delta into a struct Nicolas Pitre
2008-07-14  2:07             ` [PATCH 2/4] index-pack: Chain the struct base_data on the stack for traversal Shawn O. Pearce
2008-07-15  2:48               ` Nicolas Pitre
2008-07-14  2:07             ` [PATCH 3/4] index-pack: Track the object_entry that creates each base_data Shawn O. Pearce
2008-07-14 10:15               ` Johannes Schindelin
2008-07-15  2:50               ` Nicolas Pitre
2008-07-15  3:20                 ` Shawn O. Pearce
2008-07-15  3:42                   ` Nicolas Pitre
2008-07-14  2:07             ` [PATCH 4/4] index-pack: Honor core.deltaBaseCacheLimit when resolving deltas Shawn O. Pearce
2008-07-15  3:05               ` Nicolas Pitre
2008-07-15  3:18                 ` Shawn O. Pearce
2008-07-15  4:45                   ` [PATCH v2] " Shawn O. Pearce
2008-07-15  5:05                     ` Nicolas Pitre
2008-07-15 18:48                     ` Junio C Hamano
2008-07-13  9:01           ` git pull is slow Stephan Hennig
2008-07-11 12:55 ` Stephan Hennig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1216001267-33235-2-git-send-email-spearce@spearce.org \
    --to=spearce@spearce.org \
    --cc=ae@op5.se \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=mailing_list@arcor.de \
    --cc=nico@cam.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).