From: Derrick Stolee <stolee@gmail.com>
To: git@vger.kernel.org
Cc: dstolee@microsoft.com, stolee@gmail.com, git@jeffhostetler.com,
peff@peff.net, gitster@pobox.com, Johannes.Shindelin@gmx.de,
jrnieder@gmail.com
Subject: [RFC PATCH 10/18] midx: use existing midx when writing
Date: Sun, 7 Jan 2018 13:14:51 -0500 [thread overview]
Message-ID: <20180107181459.222909-11-dstolee@microsoft.com> (raw)
In-Reply-To: <20180107181459.222909-1-dstolee@microsoft.com>
When writing a new MIDX file, it is faster to use an existing MIDX file
to load the object list and pack offsets and to only inspect pack-indexes
for packs not already covered by the MIDX file.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
builtin/midx.c | 34 +++++++++++++++++++++++++++++++---
midx.c | 23 +++++++++++++++++++++++
midx.h | 2 ++
3 files changed, 56 insertions(+), 3 deletions(-)
diff --git a/builtin/midx.c b/builtin/midx.c
index ee9234583d..aff2085771 100644
--- a/builtin/midx.c
+++ b/builtin/midx.c
@@ -73,7 +73,7 @@ static int midx_read(void)
static int build_midx_from_packs(
const char *pack_dir,
const char **pack_names, uint32_t nr_packs,
- const char **midx_id)
+ const char **midx_id, struct midxed_git *midx)
{
struct packed_git **packs;
const char **installed_pack_names;
@@ -86,6 +86,9 @@ static int build_midx_from_packs(
struct strbuf pack_path = STRBUF_INIT;
int baselen;
+ if (midx)
+ nr_total_packs += midx->num_packs;
+
if (!nr_total_packs) {
*midx_id = NULL;
return 0;
@@ -94,6 +97,12 @@ static int build_midx_from_packs(
ALLOC_ARRAY(packs, nr_total_packs);
ALLOC_ARRAY(installed_pack_names, nr_total_packs);
+ if (midx) {
+ for (i = 0; i < midx->num_packs; i++)
+ installed_pack_names[nr_installed_packs++] = midx->pack_names[i];
+ pack_offset = midx->num_packs;
+ }
+
strbuf_addstr(&pack_path, pack_dir);
strbuf_addch(&pack_path, '/');
baselen = pack_path.len;
@@ -101,6 +110,9 @@ static int build_midx_from_packs(
strbuf_setlen(&pack_path, baselen);
strbuf_addstr(&pack_path, pack_names[i]);
+ if (midx && contains_pack(midx, pack_names[i]))
+ continue;
+
strbuf_strip_suffix(&pack_path, ".pack");
strbuf_addstr(&pack_path, ".idx");
@@ -120,13 +132,24 @@ static int build_midx_from_packs(
if (!nr_objects || !nr_installed_packs) {
FREE_AND_NULL(packs);
FREE_AND_NULL(installed_pack_names);
- *midx_id = NULL;
+
+ if (opts.has_existing)
+ *midx_id = oid_to_hex(&opts.old_midx_oid);
+ else
+ *midx_id = NULL;
+
return 0;
}
+ if (midx)
+ nr_objects += midx->num_objects;
+
ALLOC_ARRAY(objects, nr_objects);
nr_objects = 0;
+ for (i = 0; midx && i < midx->num_objects; i++)
+ nth_midxed_object_entry(midx, i, &objects[nr_objects++]);
+
for (i = pack_offset; i < nr_installed_packs; i++) {
struct packed_git *p = packs[i];
@@ -184,6 +207,10 @@ static int midx_write(void)
const char *midx_id = 0;
DIR *dir;
struct dirent *de;
+ struct midxed_git *midx = NULL;
+
+ if (opts.has_existing)
+ midx = get_midxed_git(opts.pack_dir, &opts.old_midx_oid);
dir = opendir(opts.pack_dir);
if (!dir) {
@@ -212,7 +239,8 @@ static int midx_write(void)
if (!nr_packs)
goto cleanup;
- if (build_midx_from_packs(opts.pack_dir, pack_names, nr_packs, &midx_id))
+ if (build_midx_from_packs(opts.pack_dir, pack_names,
+ nr_packs, &midx_id, midx))
die("failed to build MIDX");
if (midx_id == NULL)
diff --git a/midx.c b/midx.c
index 4e0df0285a..53eb29dac3 100644
--- a/midx.c
+++ b/midx.c
@@ -257,6 +257,29 @@ const struct object_id *nth_midxed_object_oid(struct object_id *oid,
return oid;
}
+int contains_pack(struct midxed_git *m, const char *pack_name)
+{
+ uint32_t first = 0, last = m->num_packs;
+
+ while (first < last) {
+ uint32_t mid = first + (last - first) / 2;
+ const char *current;
+ int cmp;
+
+ current = m->pack_names[mid];
+ cmp = strcmp(pack_name, current);
+ if (!cmp)
+ return 1;
+ if (cmp > 0) {
+ first = mid + 1;
+ continue;
+ }
+ last = mid;
+ }
+
+ return 0;
+}
+
static int midx_sha1_compare(const void *_a, const void *_b)
{
struct pack_midx_entry *a = *(struct pack_midx_entry **)_a;
diff --git a/midx.h b/midx.h
index 9255909ae8..1e7a94651c 100644
--- a/midx.h
+++ b/midx.h
@@ -100,6 +100,8 @@ extern const struct object_id *nth_midxed_object_oid(struct object_id *oid,
struct midxed_git *m,
uint32_t n);
+extern int contains_pack(struct midxed_git *m, const char *pack_name);
+
/*
* Write a single MIDX file storing the given entries for the
* given list of packfiles. If midx_name is null, then a temp
--
2.15.0
next prev parent reply other threads:[~2018-01-07 18:15 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-07 18:14 [RFC PATCH 00/18] Multi-pack index (MIDX) Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 01/18] docs: Multi-Pack Index (MIDX) Design Notes Derrick Stolee
2018-01-08 19:32 ` Jonathan Tan
2018-01-08 20:35 ` Derrick Stolee
2018-01-08 22:06 ` Jonathan Tan
2018-01-07 18:14 ` [RFC PATCH 02/18] midx: specify midx file format Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 03/18] midx: create core.midx config setting Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 04/18] midx: write multi-pack indexes for an object list Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 05/18] midx: create midx builtin with --write mode Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 06/18] midx: add t5318-midx.sh test script Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 07/18] midx: teach midx --write to update midx-head Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 08/18] midx: teach git-midx to read midx file details Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 09/18] midx: find details of nth object in midx Derrick Stolee
2018-01-07 18:14 ` Derrick Stolee [this message]
2018-01-07 18:14 ` [RFC PATCH 11/18] midx: teach git-midx to clear midx files Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 12/18] midx: teach git-midx to delete expired files Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 13/18] t5318-midx.h: confirm git actions are stable Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 14/18] midx: load midx files when loading packs Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 15/18] midx: use midx for approximate object count Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 16/18] midx: nth_midxed_object_oid() and bsearch_midx() Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 17/18] sha1_name: use midx for abbreviations Derrick Stolee
2018-01-07 18:14 ` [RFC PATCH 18/18] packfile: use midx for object loads Derrick Stolee
2018-01-07 22:42 ` [RFC PATCH 00/18] Multi-pack index (MIDX) Ævar Arnfjörð Bjarmason
2018-01-08 0:08 ` Derrick Stolee
2018-01-08 10:20 ` Jeff King
2018-01-08 10:27 ` Jeff King
2018-01-08 12:28 ` Ævar Arnfjörð Bjarmason
2018-01-08 13:43 ` Johannes Schindelin
2018-01-09 6:50 ` Jeff King
2018-01-09 13:05 ` Johannes Schindelin
2018-01-09 19:51 ` Stefan Beller
2018-01-09 20:12 ` Junio C Hamano
2018-01-09 20:16 ` Stefan Beller
2018-01-09 21:31 ` Junio C Hamano
2018-01-10 17:05 ` Johannes Schindelin
2018-01-10 10:57 ` Jeff King
2018-01-08 13:43 ` Derrick Stolee
2018-01-09 7:12 ` Jeff King
2018-01-08 11:43 ` Ævar Arnfjörð Bjarmason
2018-06-06 8:13 ` Ævar Arnfjörð Bjarmason
2018-06-06 10:27 ` [RFC PATCH 0/2] unconditional O(1) SHA-1 abbreviation Ævar Arnfjörð Bjarmason
2018-06-06 10:27 ` [RFC PATCH 1/2] config.c: use braces on multiple conditional arms Ævar Arnfjörð Bjarmason
2018-06-06 10:27 ` [RFC PATCH 2/2] sha1-name: add core.validateAbbrev & relative core.abbrev Ævar Arnfjörð Bjarmason
2018-06-06 12:04 ` Christian Couder
2018-06-06 11:24 ` [RFC PATCH 00/18] Multi-pack index (MIDX) Derrick Stolee
2018-01-10 18:25 ` Martin Fick
2018-01-10 19:39 ` Derrick Stolee
2018-01-10 21:01 ` Martin Fick
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=20180107181459.222909-11-dstolee@microsoft.com \
--to=stolee@gmail.com \
--cc=Johannes.Shindelin@gmx.de \
--cc=dstolee@microsoft.com \
--cc=git@jeffhostetler.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=jrnieder@gmail.com \
--cc=peff@peff.net \
/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).