git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
To: pclouds@gmail.com
Cc: Ben.Peart@microsoft.com, git@vger.kernel.org, gitster@pobox.com,
	peartben@gmail.com
Subject: [PATCH v2 0/1] optimize reading index format v4
Date: Sun,  2 Sep 2018 15:19:32 +0200	[thread overview]
Message-ID: <20180902131933.27484-1-pclouds@gmail.com> (raw)
In-Reply-To: <20180825064458.28484-1-pclouds@gmail.com>

v2 removes unrelated changes and the dummy_entry. strip_len is also
replaced with copy_len to reduce repeated subtraction calculation.
Diff: 

diff --git a/read-cache.c b/read-cache.c
index 5c04c8f200..8628d0f3a8 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1713,7 +1713,7 @@ int read_index(struct index_state *istate)
 	return read_index_from(istate, get_index_file(), get_git_dir());
 }
 
-static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
+static struct cache_entry *create_from_disk(struct index_state *istate,
 					    struct ondisk_cache_entry *ondisk,
 					    unsigned long *ent_size,
 					    const struct cache_entry *previous_ce)
@@ -1722,7 +1722,15 @@ static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
 	size_t len;
 	const char *name;
 	unsigned int flags;
-	size_t strip_len;
+	size_t copy_len;
+	/*
+	 * Adjacent cache entries tend to share the leading paths, so it makes
+	 * sense to only store the differences in later entries.  In the v4
+	 * on-disk format of the index, each on-disk cache entry stores the
+	 * number of bytes to be stripped from the end of the previous name,
+	 * and the bytes to append to the result, to come up with its name.
+	 */
+	int expand_name_field = istate->version == 4;
 
 	/* On-disk flags are just 16 bits */
 	flags = get_be16(&ondisk->flags);
@@ -1735,37 +1743,37 @@ static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
 		extended_flags = get_be16(&ondisk2->flags2) << 16;
 		/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
 		if (extended_flags & ~CE_EXTENDED_FLAGS)
-			die(_("unknown index entry format %08x"), extended_flags);
+			die("Unknown index entry format %08x", extended_flags);
 		flags |= extended_flags;
 		name = ondisk2->name;
 	}
 	else
 		name = ondisk->name;
 
-	/*
-	 * Adjacent cache entries tend to share the leading paths, so it makes
-	 * sense to only store the differences in later entries.  In the v4
-	 * on-disk format of the index, each on-disk cache entry stores the
-	 * number of bytes to be stripped from the end of the previous name,
-	 * and the bytes to append to the result, to come up with its name.
-	 */
-	if (previous_ce) {
+	if (expand_name_field) {
 		const unsigned char *cp = (const unsigned char *)name;
+		size_t strip_len, previous_len;
 
+		previous_len = previous_ce ? previous_ce->ce_namelen : 0;
 		strip_len = decode_varint(&cp);
-		if (previous_ce->ce_namelen < strip_len)
-			die(_("malformed name field in the index, path '%s'"),
-			    previous_ce->name);
+		if (previous_len < strip_len) {
+			if (previous_ce)
+				die(_("malformed name field in the index, near path '%s'"),
+				    previous_ce->name);
+			else
+				die(_("malformed name field in the index in the first path"));
+		}
+		copy_len = previous_len - strip_len;
 		name = (const char *)cp;
 	}
 
 	if (len == CE_NAMEMASK) {
 		len = strlen(name);
-		if (previous_ce)
-			len += previous_ce->ce_namelen - strip_len;
+		if (expand_name_field)
+			len += copy_len;
 	}
 
-	ce = mem_pool__ce_alloc(mem_pool, len);
+	ce = mem_pool__ce_alloc(istate->ce_mem_pool, len);
 
 	ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec);
 	ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec);
@@ -1782,9 +1790,9 @@ static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
 	ce->index = 0;
 	hashcpy(ce->oid.hash, ondisk->sha1);
 
-	if (previous_ce) {
-		size_t copy_len = previous_ce->ce_namelen - strip_len;
-		memcpy(ce->name, previous_ce->name, copy_len);
+	if (expand_name_field) {
+		if (copy_len)
+			memcpy(ce->name, previous_ce->name, copy_len);
 		memcpy(ce->name + copy_len, name, len + 1 - copy_len);
 		*ent_size = (name - ((char *)ondisk)) + len + 1 - copy_len;
 	} else {
@@ -1885,7 +1893,6 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	void *mmap;
 	size_t mmap_size;
 	const struct cache_entry *previous_ce = NULL;
-	struct cache_entry *dummy_entry = NULL;
 
 	if (istate->initialized)
 		return istate->cache_nr;
@@ -1923,7 +1930,6 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	istate->initialized = 1;
 
 	if (istate->version == 4) {
-		previous_ce = dummy_entry = make_empty_transient_cache_entry(0);
 		mem_pool_init(&istate->ce_mem_pool,
 			      estimate_cache_size_from_compressed(istate->cache_nr));
 	} else {
@@ -1938,14 +1944,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 		unsigned long consumed;
 
 		disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset);
-		ce = create_from_disk(istate->ce_mem_pool, disk_ce, &consumed, previous_ce);
+		ce = create_from_disk(istate, disk_ce, &consumed, previous_ce);
 		set_index_entry(istate, i, ce);
 
 		src_offset += consumed;
-		if (previous_ce)
-			previous_ce = ce;
+		previous_ce = ce;
 	}
-	free(dummy_entry);
 	istate->timestamp.sec = st.st_mtime;
 	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 


Nguyễn Thái Ngọc Duy (1):
  read-cache.c: optimize reading index format v4

 read-cache.c | 128 ++++++++++++++++++++++++---------------------------
 1 file changed, 60 insertions(+), 68 deletions(-)

-- 
2.19.0.rc0.337.ge906d732e7


  parent reply	other threads:[~2018-09-02 13:19 UTC|newest]

Thread overview: 199+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-23 15:41 [PATCH v1] read-cache: speed up index load through parallelization Ben Peart
2018-08-23 17:31 ` Stefan Beller
2018-08-23 19:44   ` Ben Peart
2018-08-24 18:40   ` Duy Nguyen
2018-08-28 14:53     ` Ben Peart
2018-08-23 18:06 ` Junio C Hamano
2018-08-23 20:33   ` Ben Peart
2018-08-24 15:37     ` Duy Nguyen
2018-08-24 15:57       ` Duy Nguyen
2018-08-24 17:28         ` Ben Peart
2018-08-25  6:44         ` [PATCH] read-cache.c: optimize reading index format v4 Nguyễn Thái Ngọc Duy
2018-08-27 19:36           ` Junio C Hamano
2018-08-28 19:25             ` Duy Nguyen
2018-08-28 23:54               ` Ben Peart
2018-08-29 17:14               ` Junio C Hamano
2018-09-04 16:08             ` Duy Nguyen
2018-09-02 13:19           ` Nguyễn Thái Ngọc Duy [this message]
2018-09-02 13:19             ` [PATCH v2 1/1] " Nguyễn Thái Ngọc Duy
2018-09-04 18:58               ` Junio C Hamano
2018-09-04 19:31               ` Junio C Hamano
2018-08-24 18:20       ` [PATCH v1] read-cache: speed up index load through parallelization Duy Nguyen
2018-08-24 18:40         ` Ben Peart
2018-08-24 19:00           ` Duy Nguyen
2018-08-24 19:57             ` Ben Peart
2018-08-29 15:25 ` [PATCH v2 0/3] " Ben Peart
2018-08-29 15:25   ` [PATCH v2 1/3] " Ben Peart
2018-08-29 17:14     ` Junio C Hamano
2018-08-29 21:35       ` Ben Peart
2018-09-03 19:16     ` Duy Nguyen
2018-08-29 15:25   ` [PATCH v2 2/3] read-cache: load cache extensions on worker thread Ben Peart
2018-08-29 17:12     ` Junio C Hamano
2018-08-29 21:42       ` Ben Peart
2018-08-29 22:19         ` Junio C Hamano
2018-09-03 19:21     ` Duy Nguyen
2018-09-03 19:27       ` Duy Nguyen
2018-08-29 15:25   ` [PATCH v2 3/3] read-cache: micro-optimize expand_name_field() to speed up V4 index parsing Ben Peart
2018-09-06 21:03 ` [PATCH v3 0/4] read-cache: speed up index load through parallelization Ben Peart
2018-09-06 21:03   ` [PATCH v3 1/4] read-cache: optimize expand_name_field() to speed up V4 index parsing Ben Peart
2018-09-06 21:03   ` [PATCH v3 2/4] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-07 17:55     ` Junio C Hamano
2018-09-07 20:23       ` Ben Peart
2018-09-08  6:29         ` Martin Ågren
2018-09-08 14:03           ` Ben Peart
2018-09-08 17:08             ` Martin Ågren
2018-09-06 21:03   ` [PATCH v3 3/4] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-07 21:10     ` Junio C Hamano
2018-09-08 14:56       ` Ben Peart
2018-09-06 21:03   ` [PATCH v3 4/4] read-cache: speed up index load through parallelization Ben Peart
2018-09-07  4:16     ` Torsten Bögershausen
2018-09-07 13:43       ` Ben Peart
2018-09-07 17:21   ` [PATCH v3 0/4] " Junio C Hamano
2018-09-07 18:31     ` Ben Peart
2018-09-08 13:18     ` Duy Nguyen
2018-09-11 23:26 ` [PATCH v4 0/5] " Ben Peart
2018-09-11 23:26   ` [PATCH v4 1/5] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-11 23:26   ` [PATCH v4 2/5] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-11 23:26   ` [PATCH v4 3/5] read-cache: speed up index load through parallelization Ben Peart
2018-09-11 23:26   ` [PATCH v4 4/5] read-cache.c: optimize reading index format v4 Ben Peart
2018-09-11 23:26   ` [PATCH v4 5/5] read-cache: clean up casting and byte decoding Ben Peart
2018-09-12 14:34   ` [PATCH v4 0/5] read-cache: speed up index load through parallelization Ben Peart
2018-09-12 16:18 ` [PATCH v5 " Ben Peart
2018-09-12 16:18   ` [PATCH v5 1/5] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-13 22:44     ` Junio C Hamano
2018-09-15 10:02     ` Duy Nguyen
2018-09-17 14:54       ` Ben Peart
2018-09-17 16:05         ` Duy Nguyen
2018-09-17 17:31           ` Junio C Hamano
2018-09-17 17:38             ` Duy Nguyen
2018-09-17 19:08               ` Junio C Hamano
2018-09-12 16:18   ` [PATCH v5 2/5] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-15 10:22     ` Duy Nguyen
2018-09-15 10:24       ` Duy Nguyen
2018-09-17 16:38         ` Ben Peart
2018-09-15 16:23       ` Duy Nguyen
2018-09-17 17:19         ` Junio C Hamano
2018-09-17 16:26       ` Ben Peart
2018-09-17 16:45         ` Duy Nguyen
2018-09-17 21:32       ` Junio C Hamano
2018-09-12 16:18   ` [PATCH v5 3/5] read-cache: load cache entries on worker threads Ben Peart
2018-09-15 10:31     ` Duy Nguyen
2018-09-17 17:25       ` Ben Peart
2018-09-15 11:07     ` Duy Nguyen
2018-09-15 11:09       ` Duy Nguyen
2018-09-17 18:52         ` Ben Peart
2018-09-15 11:29     ` Duy Nguyen
2018-09-12 16:18   ` [PATCH v5 4/5] read-cache.c: optimize reading index format v4 Ben Peart
2018-09-12 16:18   ` [PATCH v5 5/5] read-cache: clean up casting and byte decoding Ben Peart
2018-09-26 19:54 ` [PATCH v6 0/7] speed up index load through parallelization Ben Peart
2018-09-26 19:54   ` [PATCH v6 1/7] read-cache.c: optimize reading index format v4 Ben Peart
2018-09-26 19:54   ` [PATCH v6 2/7] read-cache: clean up casting and byte decoding Ben Peart
2018-09-26 19:54   ` [PATCH v6 3/7] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-28  0:19     ` SZEDER Gábor
2018-09-28 18:38       ` Ben Peart
2018-09-29  0:51     ` SZEDER Gábor
2018-09-29  5:45     ` Duy Nguyen
2018-09-29 18:24       ` Junio C Hamano
2018-09-26 19:54   ` [PATCH v6 4/7] config: add new index.threads config setting Ben Peart
2018-09-28  0:26     ` SZEDER Gábor
2018-09-28 13:39       ` Ben Peart
2018-09-28 17:07         ` Junio C Hamano
2018-09-28 19:41           ` Ben Peart
2018-09-28 20:30             ` Ramsay Jones
2018-09-28 22:15               ` Junio C Hamano
2018-10-01 13:17                 ` Ben Peart
2018-10-01 15:06                   ` SZEDER Gábor
2018-09-26 19:54   ` [PATCH v6 5/7] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-26 19:54   ` [PATCH v6 6/7] ieot: add Index Entry Offset Table (IEOT) extension Ben Peart
2018-09-26 19:54   ` [PATCH v6 7/7] read-cache: load cache entries on worker threads Ben Peart
2018-09-26 22:06   ` [PATCH v6 0/7] speed up index load through parallelization Junio C Hamano
2018-09-27 17:13   ` Duy Nguyen
2018-10-01 13:45 ` [PATCH v7 " Ben Peart
2018-10-01 13:45   ` [PATCH v7 1/7] read-cache.c: optimize reading index format v4 Ben Peart
2018-10-01 13:45   ` [PATCH v7 2/7] read-cache: clean up casting and byte decoding Ben Peart
2018-10-01 15:10     ` Duy Nguyen
2018-10-01 13:45   ` [PATCH v7 3/7] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-10-01 15:17     ` SZEDER Gábor
2018-10-02 14:34       ` Ben Peart
2018-10-01 15:30     ` Duy Nguyen
2018-10-02 15:13       ` Ben Peart
2018-10-01 13:45   ` [PATCH v7 4/7] config: add new index.threads config setting Ben Peart
2018-10-01 13:45   ` [PATCH v7 5/7] read-cache: load cache extensions on a worker thread Ben Peart
2018-10-01 15:50     ` Duy Nguyen
2018-10-02 15:00       ` Ben Peart
2018-10-01 13:45   ` [PATCH v7 6/7] ieot: add Index Entry Offset Table (IEOT) extension Ben Peart
2018-10-01 16:27     ` Duy Nguyen
2018-10-02 16:34       ` Ben Peart
2018-10-02 17:02         ` Duy Nguyen
2018-10-01 13:45   ` [PATCH v7 7/7] read-cache: load cache entries on worker threads Ben Peart
2018-10-01 17:09     ` Duy Nguyen
2018-10-02 19:09       ` Ben Peart
2018-10-10 15:59 ` [PATCH v8 0/7] speed up index load through parallelization Ben Peart
2018-10-10 15:59   ` [PATCH v8 1/7] read-cache.c: optimize reading index format v4 Ben Peart
2018-10-10 15:59   ` [PATCH v8 2/7] read-cache: clean up casting and byte decoding Ben Peart
2018-10-10 15:59   ` [PATCH v8 3/7] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-10-10 15:59   ` [PATCH v8 4/7] config: add new index.threads config setting Ben Peart
2018-10-10 15:59   ` [PATCH v8 5/7] read-cache: load cache extensions on a worker thread Ben Peart
2018-10-10 15:59   ` [PATCH v8 6/7] ieot: add Index Entry Offset Table (IEOT) extension Ben Peart
2018-10-10 15:59   ` [PATCH v8 7/7] read-cache: load cache entries on worker threads Ben Peart
2018-10-19 16:11     ` Jeff King
2018-10-22  2:14       ` Junio C Hamano
2018-10-22 14:40         ` Ben Peart
2018-10-12  3:18   ` [PATCH v8 0/7] speed up index load through parallelization Junio C Hamano
2018-10-14 12:28   ` Duy Nguyen
2018-10-15 17:33     ` Ben Peart
2018-11-13  0:38   ` [PATCH 0/3] Avoid confusing messages from new index extensions (Re: [PATCH v8 0/7] speed up index load through parallelization) Jonathan Nieder
2018-11-13  0:39     ` [PATCH 1/3] eoie: default to not writing EOIE section Jonathan Nieder
2018-11-13  1:05       ` Junio C Hamano
2018-11-13 15:14         ` Ben Peart
2018-11-13 18:25           ` Jonathan Nieder
2018-11-14  1:36             ` Junio C Hamano
2018-11-15  0:19               ` Jonathan Nieder
2018-11-13  0:39     ` [PATCH 2/3] ieot: default to not writing IEOT section Jonathan Nieder
2018-11-13  0:58       ` Jonathan Tan
2018-11-13  1:09       ` Junio C Hamano
2018-11-13  1:12         ` Jonathan Nieder
2018-11-13 15:37           ` Duy Nguyen
2018-11-13 18:09         ` Jonathan Nieder
2018-11-13 15:22       ` Ben Peart
2018-11-13 18:18         ` Jonathan Nieder
2018-11-13 19:15           ` Ben Peart
2018-11-13 21:08             ` Jonathan Nieder
2018-11-14 18:09               ` Ben Peart
2018-11-15  0:05                 ` Jonathan Nieder
2018-11-14  3:05         ` Junio C Hamano
2018-11-20  6:09           ` [PATCH v2 0/5] Avoid confusing messages from new index extensions Jonathan Nieder
2018-11-20  6:11             ` [PATCH 1/5] eoie: default to not writing EOIE section Jonathan Nieder
2018-11-20 13:06               ` Ben Peart
2018-11-20 13:21                 ` SZEDER Gábor
2018-11-21 16:46                   ` Jeff King
2018-11-22  0:47                     ` Junio C Hamano
2018-11-20 15:01               ` Ben Peart
2018-11-20  6:12             ` [PATCH 2/5] ieot: default to not writing IEOT section Jonathan Nieder
2018-11-20 13:07               ` Ben Peart
2018-11-26 19:59                 ` Stefan Beller
2018-11-26 21:47                   ` Ben Peart
2018-11-26 22:02                     ` Stefan Beller
2018-11-27  0:50                   ` Junio C Hamano
2018-11-20  6:12             ` [PATCH 3/5] index: do not warn about unrecognized extensions Jonathan Nieder
2018-11-20  6:14             ` [PATCH 4/5] index: make index.threads=true enable ieot and eoie Jonathan Nieder
2018-11-20 13:24               ` Ben Peart
2018-11-20  6:15             ` [PATCH 5/5] index: offer advice for unknown index extensions Jonathan Nieder
2018-11-20  9:26               ` Ævar Arnfjörð Bjarmason
2018-11-20 13:30                 ` Ben Peart
2018-11-21  0:22                   ` Junio C Hamano
2018-11-21  0:39                     ` Jonathan Nieder
2018-11-21  0:44                       ` Jonathan Nieder
2018-11-21  5:01                       ` Junio C Hamano
2018-11-21  5:04                         ` Jonathan Nieder
2018-11-21  5:15                         ` Junio C Hamano
2018-11-21  5:31                           ` Junio C Hamano
2018-11-21  1:03                     ` Jonathan Nieder
2018-11-21  4:23                       ` Junio C Hamano
2018-11-21  4:57                         ` Jonathan Nieder
2018-11-21  9:30                       ` Ævar Arnfjörð Bjarmason
2018-11-13  0:40     ` [PATCH 3/3] index: do not warn about unrecognized extensions Jonathan Nieder
2018-11-13  1:10       ` Junio C Hamano
2018-11-13 15:25       ` Ben Peart
2018-11-14  3:24       ` Junio C Hamano
2018-11-14 18:19         ` Ben Peart

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

  List information: http://vger.kernel.org/majordomo-info.html

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

  git send-email \
    --in-reply-to=20180902131933.27484-1-pclouds@gmail.com \
    --to=pclouds@gmail.com \
    --cc=Ben.Peart@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=peartben@gmail.com \
    /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.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

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 read-only IMAP folder(s) and NNTP newsgroup(s).