summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDerrick Stolee <dstolee@microsoft.com>2019-01-16 18:25:58 (GMT)
committerJunio C Hamano <gitster@pobox.com>2019-01-17 21:44:39 (GMT)
commit4f6d26b16703e59e009fe5dde923b87793c5f561 (patch)
tree845da1e4fe86e63b5ea131cb65fda1d1a98b2dec
parentf1f5de442faf85724e67917cd24df6b7275ca360 (diff)
downloadgit-4f6d26b16703e59e009fe5dde923b87793c5f561.zip
git-4f6d26b16703e59e009fe5dde923b87793c5f561.tar.gz
git-4f6d26b16703e59e009fe5dde923b87793c5f561.tar.bz2
list-objects: consume sparse tree walk
When creating a pack-file using 'git pack-objects --revs' we provide a list of interesting and uninteresting commits. For example, a push operation would make the local topic branch be interesting and the known remote refs as uninteresting. We want to discover the set of new objects to send to the server as a thin pack. We walk these commits until we discover a frontier of commits such that every commit walk starting at interesting commits ends in a root commit or unintersting commit. We then need to discover which non-commit objects are reachable from uninteresting commits. This commit walk is not changing during this series. The mark_edges_uninteresting() method in list-objects.c iterates on the commit list and does the following: * If the commit is UNINTERSTING, then mark its root tree and every object it can reach as UNINTERESTING. * If the commit is interesting, then mark the root tree of every UNINTERSTING parent (and all objects that tree can reach) as UNINTERSTING. At the very end, we repeat the process on every commit directly given to the revision walk from stdin. This helps ensure we properly cover shallow commits that otherwise were not included in the frontier. The logic to recursively follow trees is in the mark_tree_uninteresting() method in revision.c. The algorithm avoids duplicate work by not recursing into trees that are already marked UNINTERSTING. Add a new 'sparse' option to the mark_edges_uninteresting() method that performs this logic in a slightly different way. As we iterate over the commits, we add all of the root trees to an oidset. Then, call mark_trees_uninteresting_sparse() on that oidset. Note that we include interesting trees in this process. The current implementation of mark_trees_unintersting_sparse() will walk the same trees as the old logic, but this will be replaced in a later change. Add a '--sparse' flag in 'git pack-objects' to call this new logic. Add a new test script t/t5322-pack-objects-sparse.sh that tests this option. The tests currently demonstrate that the resulting object list is the same as the old algorithm. This includes a case where both algorithms pack an object that is not needed by a remote due to limits on the explored set of trees. When the sparse algorithm is changed in a later commit, we will add a test that demonstrates a change of behavior in some cases. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--Documentation/git-pack-objects.txt11
-rw-r--r--bisect.c2
-rw-r--r--builtin/pack-objects.c5
-rw-r--r--builtin/rev-list.c2
-rw-r--r--http-push.c2
-rw-r--r--list-objects.c70
-rw-r--r--list-objects.h4
-rwxr-xr-xt/t5322-pack-objects-sparse.sh113
8 files changed, 192 insertions, 17 deletions
diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt
index 40c825c..e45f3e6 100644
--- a/Documentation/git-pack-objects.txt
+++ b/Documentation/git-pack-objects.txt
@@ -14,7 +14,7 @@ SYNOPSIS
[--local] [--incremental] [--window=<n>] [--depth=<n>]
[--revs [--unpacked | --all]] [--keep-pack=<pack-name>]
[--stdout [--filter=<filter-spec>] | base-name]
- [--shallow] [--keep-true-parents] < object-list
+ [--shallow] [--keep-true-parents] [--sparse] < object-list
DESCRIPTION
@@ -196,6 +196,15 @@ depth is 4095.
Add --no-reuse-object if you want to force a uniform compression
level on all data no matter the source.
+--sparse::
+ Use the "sparse" algorithm to determine which objects to include in
+ the pack, when combined with the "--revs" option. This algorithm
+ only walks trees that appear in paths that introduce new objects.
+ This can have significant performance benefits when computing
+ a pack to send a small change. However, it is possible that extra
+ objects are added to the pack-file if the included commits contain
+ certain types of direct renames.
+
--thin::
Create a "thin" pack by omitting the common objects between a
sender and a receiver in order to reduce network transfer. This
diff --git a/bisect.c b/bisect.c
index 487675c..842f8b4 100644
--- a/bisect.c
+++ b/bisect.c
@@ -656,7 +656,7 @@ static void bisect_common(struct rev_info *revs)
if (prepare_revision_walk(revs))
die("revision walk setup failed");
if (revs->tree_objects)
- mark_edges_uninteresting(revs, NULL);
+ mark_edges_uninteresting(revs, NULL, 0);
}
static void exit_if_skipped_commits(struct commit_list *tried,
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 411aefd..7d5b073 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -84,6 +84,7 @@ static unsigned long pack_size_limit;
static int depth = 50;
static int delta_search_threads;
static int pack_to_stdout;
+static int sparse;
static int thin;
static int num_preferred_base;
static struct progress *progress_state;
@@ -3135,7 +3136,7 @@ static void get_object_list(int ac, const char **av)
if (prepare_revision_walk(&revs))
die(_("revision walk setup failed"));
- mark_edges_uninteresting(&revs, show_edge);
+ mark_edges_uninteresting(&revs, show_edge, sparse);
if (!fn_show_object)
fn_show_object = show_object;
@@ -3292,6 +3293,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
{ OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"),
N_("unpack unreachable objects newer than <time>"),
PARSE_OPT_OPTARG, option_parse_unpack_unreachable },
+ OPT_BOOL(0, "sparse", &sparse,
+ N_("use the sparse reachability algorithm")),
OPT_BOOL(0, "thin", &thin,
N_("create thin packs")),
OPT_BOOL(0, "shallow", &shallow,
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
index 2880ed3..9663cbf 100644
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@ -543,7 +543,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
if (prepare_revision_walk(&revs))
die("revision walk setup failed");
if (revs.tree_objects)
- mark_edges_uninteresting(&revs, show_edge);
+ mark_edges_uninteresting(&revs, show_edge, 0);
if (bisect_list) {
int reaches, all;
diff --git a/http-push.c b/http-push.c
index cd48590..ea52d6f 100644
--- a/http-push.c
+++ b/http-push.c
@@ -1933,7 +1933,7 @@ int cmd_main(int argc, const char **argv)
pushing = 0;
if (prepare_revision_walk(&revs))
die("revision walk setup failed");
- mark_edges_uninteresting(&revs, NULL);
+ mark_edges_uninteresting(&revs, NULL, 0);
objects_to_send = get_delta(&revs, ref_lock);
finish_all_active_slots();
diff --git a/list-objects.c b/list-objects.c
index c41cc80..fb728f7 100644
--- a/list-objects.c
+++ b/list-objects.c
@@ -222,25 +222,73 @@ static void mark_edge_parents_uninteresting(struct commit *commit,
}
}
-void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge)
+static void add_edge_parents(struct commit *commit,
+ struct rev_info *revs,
+ show_edge_fn show_edge,
+ struct oidset *set)
+{
+ struct commit_list *parents;
+
+ for (parents = commit->parents; parents; parents = parents->next) {
+ struct commit *parent = parents->item;
+ struct tree *tree = get_commit_tree(parent);
+
+ if (!tree)
+ continue;
+
+ oidset_insert(set, &tree->object.oid);
+
+ if (!(parent->object.flags & UNINTERESTING))
+ continue;
+ tree->object.flags |= UNINTERESTING;
+
+ if (revs->edge_hint && !(parent->object.flags & SHOWN)) {
+ parent->object.flags |= SHOWN;
+ show_edge(parent);
+ }
+ }
+}
+
+void mark_edges_uninteresting(struct rev_info *revs,
+ show_edge_fn show_edge,
+ int sparse)
{
struct commit_list *list;
int i;
- for (list = revs->commits; list; list = list->next) {
- struct commit *commit = list->item;
+ if (sparse) {
+ struct oidset set;
+ oidset_init(&set, 16);
- if (commit->object.flags & UNINTERESTING) {
- mark_tree_uninteresting(revs->repo,
- get_commit_tree(commit));
- if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) {
- commit->object.flags |= SHOWN;
- show_edge(commit);
+ for (list = revs->commits; list; list = list->next) {
+ struct commit *commit = list->item;
+ struct tree *tree = get_commit_tree(commit);
+
+ if (commit->object.flags & UNINTERESTING)
+ tree->object.flags |= UNINTERESTING;
+
+ oidset_insert(&set, &tree->object.oid);
+ add_edge_parents(commit, revs, show_edge, &set);
+ }
+
+ mark_trees_uninteresting_sparse(revs->repo, &set);
+ oidset_clear(&set);
+ } else {
+ for (list = revs->commits; list; list = list->next) {
+ struct commit *commit = list->item;
+ if (commit->object.flags & UNINTERESTING) {
+ mark_tree_uninteresting(revs->repo,
+ get_commit_tree(commit));
+ if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) {
+ commit->object.flags |= SHOWN;
+ show_edge(commit);
+ }
+ continue;
}
- continue;
+ mark_edge_parents_uninteresting(commit, revs, show_edge);
}
- mark_edge_parents_uninteresting(commit, revs, show_edge);
}
+
if (revs->edge_hint_aggressive) {
for (i = 0; i < revs->cmdline.nr; i++) {
struct object *obj = revs->cmdline.rev[i].item;
diff --git a/list-objects.h b/list-objects.h
index ad40762..a952680 100644
--- a/list-objects.h
+++ b/list-objects.h
@@ -10,7 +10,9 @@ typedef void (*show_object_fn)(struct object *, const char *, void *);
void traverse_commit_list(struct rev_info *, show_commit_fn, show_object_fn, void *);
typedef void (*show_edge_fn)(struct commit *);
-void mark_edges_uninteresting(struct rev_info *, show_edge_fn);
+void mark_edges_uninteresting(struct rev_info *revs,
+ show_edge_fn show_edge,
+ int sparse);
struct oidset;
struct list_objects_filter_options;
diff --git a/t/t5322-pack-objects-sparse.sh b/t/t5322-pack-objects-sparse.sh
new file mode 100755
index 0000000..30aef64
--- /dev/null
+++ b/t/t5322-pack-objects-sparse.sh
@@ -0,0 +1,113 @@
+#!/bin/sh
+
+test_description='pack-objects object selection using sparse algorithm'
+. ./test-lib.sh
+
+test_expect_success 'setup repo' '
+ test_commit initial &&
+ for i in $(test_seq 1 3)
+ do
+ mkdir f$i &&
+ for j in $(test_seq 1 3)
+ do
+ mkdir f$i/f$j &&
+ echo $j >f$i/f$j/data.txt
+ done
+ done &&
+ git add . &&
+ git commit -m "Initialized trees" &&
+ for i in $(test_seq 1 3)
+ do
+ git checkout -b topic$i master &&
+ echo change-$i >f$i/f$i/data.txt &&
+ git commit -a -m "Changed f$i/f$i/data.txt"
+ done &&
+ cat >packinput.txt <<-EOF &&
+ topic1
+ ^topic2
+ ^topic3
+ EOF
+ git rev-parse \
+ topic1 \
+ topic1^{tree} \
+ topic1:f1 \
+ topic1:f1/f1 \
+ topic1:f1/f1/data.txt | sort >expect_objects.txt
+'
+
+test_expect_success 'non-sparse pack-objects' '
+ git pack-objects --stdout --revs <packinput.txt >nonsparse.pack &&
+ git index-pack -o nonsparse.idx nonsparse.pack &&
+ git show-index <nonsparse.idx | awk "{print \$2}" >nonsparse_objects.txt &&
+ test_cmp expect_objects.txt nonsparse_objects.txt
+'
+
+test_expect_success 'sparse pack-objects' '
+ git pack-objects --stdout --revs --sparse <packinput.txt >sparse.pack &&
+ git index-pack -o sparse.idx sparse.pack &&
+ git show-index <sparse.idx | awk "{print \$2}" >sparse_objects.txt &&
+ test_cmp expect_objects.txt sparse_objects.txt
+'
+
+test_expect_success 'duplicate a folder from f3 and commit to topic1' '
+ git checkout topic1 &&
+ echo change-3 >f3/f3/data.txt &&
+ git commit -a -m "Changed f3/f3/data.txt" &&
+ git rev-parse \
+ topic1~1 \
+ topic1~1^{tree} \
+ topic1^{tree} \
+ topic1 \
+ topic1:f1 \
+ topic1:f1/f1 \
+ topic1:f1/f1/data.txt | sort >required_objects.txt
+'
+
+test_expect_success 'non-sparse pack-objects' '
+ git pack-objects --stdout --revs <packinput.txt >nonsparse.pack &&
+ git index-pack -o nonsparse.idx nonsparse.pack &&
+ git show-index <nonsparse.idx | awk "{print \$2}" >nonsparse_objects.txt &&
+ comm -1 -2 required_objects.txt nonsparse_objects.txt >nonsparse_required_objects.txt &&
+ test_cmp required_objects.txt nonsparse_required_objects.txt
+'
+
+test_expect_success 'sparse pack-objects' '
+ git pack-objects --stdout --revs --sparse <packinput.txt >sparse.pack &&
+ git index-pack -o sparse.idx sparse.pack &&
+ git show-index <sparse.idx | awk "{print \$2}" >sparse_objects.txt &&
+ comm -1 -2 required_objects.txt sparse_objects.txt >sparse_required_objects.txt &&
+ test_cmp required_objects.txt sparse_required_objects.txt
+'
+
+test_expect_success 'duplicate a folder from f1 into f3' '
+ mkdir f3/f4 &&
+ cp -r f1/f1/* f3/f4 &&
+ git add f3/f4 &&
+ git commit -m "Copied f1/f1 to f3/f4" &&
+ cat >packinput.txt <<-EOF &&
+ topic1
+ ^topic1~1
+ EOF
+ git rev-parse \
+ topic1 \
+ topic1^{tree} \
+ topic1:f3 | sort >required_objects.txt
+'
+
+test_expect_success 'non-sparse pack-objects' '
+ git pack-objects --stdout --revs <packinput.txt >nonsparse.pack &&
+ git index-pack -o nonsparse.idx nonsparse.pack &&
+ git show-index <nonsparse.idx | awk "{print \$2}" >nonsparse_objects.txt &&
+ comm -1 -2 required_objects.txt nonsparse_objects.txt >nonsparse_required_objects.txt &&
+ test_cmp required_objects.txt nonsparse_required_objects.txt
+'
+
+test_expect_success 'sparse pack-objects' '
+ git pack-objects --stdout --revs --sparse <packinput.txt >sparse.pack &&
+ git index-pack -o sparse.idx sparse.pack &&
+ git show-index <sparse.idx | awk "{print \$2}" >sparse_objects.txt &&
+ comm -1 -2 required_objects.txt sparse_objects.txt >sparse_required_objects.txt &&
+ test_cmp required_objects.txt sparse_required_objects.txt
+'
+
+test_done