Merge branch 'ew/fast-import-unpack-limit'

"git fast-import" learned the same performance trick to avoid
creating too small a packfile as "git fetch" and "git push" have,
using *.unpackLimit configuration.

* ew/fast-import-unpack-limit:
  fast-import: invalidate pack_id references after loosening
  fast-import: implement unpack limit

5 files changed, 179 insertions, 0 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 2e1b2e486e..58673cf21e 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1189,6 +1189,15 @@ difftool.<tool>.cmd::
 difftool.prompt::
 	Prompt before each invocation of the diff tool.
 
+fastimport.unpackLimit::
+	If the number of objects imported by linkgit:git-fast-import[1]
+	is below this limit, then the objects will be unpacked into
+	loose object files.  However if the number of imported objects
+	equals or exceeds this limit then the pack will be stored as a
+	pack.  Storing the pack from a fast-import can make the import
+	operation complete faster, especially on slow filesystems.  If
+	not set, the value of `transfer.unpackLimit` is used instead.
+
 fetch.recurseSubmodules::
 	This option can be either set to a boolean value or to 'on-demand'.
 	Setting it to a boolean changes the behavior of fetch and pull to
diff --git a/Documentation/git-fast-import.txt b/Documentation/git-fast-import.txt
index 66910aa2fa..644df993f9 100644
--- a/Documentation/git-fast-import.txt
+++ b/Documentation/git-fast-import.txt
@@ -136,6 +136,8 @@ Performance and Compression Tuning
 	Maximum size of each output packfile.
 	The default is unlimited.
 
+fastimport.unpackLimit::
+	See linkgit:git-config[1]
 
 Performance
 -----------
diff --git a/fast-import.c b/fast-import.c
index c504ef752d..59630cee14 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -166,6 +166,7 @@ Format of STDIN stream:
 #include "quote.h"
 #include "exec_cmd.h"
 #include "dir.h"
+#include "run-command.h"
 
 #define PACK_ID_BITS 16
 #define MAX_PACK_ID ((1<<PACK_ID_BITS)-1)
@@ -282,6 +283,7 @@ struct recent_command {
 /* Configured limits on output */
 static unsigned long max_depth = 10;
 static off_t max_packsize;
+static int unpack_limit = 100;
 static int force_update;
 static int pack_compression_level = Z_DEFAULT_COMPRESSION;
 static int pack_compression_seen;
@@ -596,6 +598,33 @@ static struct object_entry *insert_object(unsigned char *sha1)
 	return e;
 }
 
+static void invalidate_pack_id(unsigned int id)
+{
+	unsigned int h;
+	unsigned long lu;
+	struct tag *t;
+
+	for (h = 0; h < ARRAY_SIZE(object_table); h++) {
+		struct object_entry *e;
+
+		for (e = object_table[h]; e; e = e->next)
+			if (e->pack_id == id)
+				e->pack_id = MAX_PACK_ID;
+	}
+
+	for (lu = 0; lu < branch_table_sz; lu++) {
+		struct branch *b;
+
+		for (b = branch_table[lu]; b; b = b->table_next_branch)
+			if (b->pack_id == id)
+				b->pack_id = MAX_PACK_ID;
+	}
+
+	for (t = first_tag; t; t = t->next_tag)
+		if (t->pack_id == id)
+			t->pack_id = MAX_PACK_ID;
+}
+
 static unsigned int hc_str(const char *s, size_t len)
 {
 	unsigned int r = 0;
@@ -951,6 +980,23 @@ static void unkeep_all_packs(void)
 	}
 }
 
+static int loosen_small_pack(const struct packed_git *p)
+{
+	struct child_process unpack = CHILD_PROCESS_INIT;
+
+	if (lseek(p->pack_fd, 0, SEEK_SET) < 0)
+		die_errno("Failed seeking to start of '%s'", p->pack_name);
+
+	unpack.in = p->pack_fd;
+	unpack.git_cmd = 1;
+	unpack.stdout_to_stderr = 1;
+	argv_array_push(&unpack.args, "unpack-objects");
+	if (!show_stats)
+		argv_array_push(&unpack.args, "-q");
+
+	return run_command(&unpack);
+}
+
 static void end_packfile(void)
 {
 	static int running;
@@ -973,6 +1019,14 @@ static void end_packfile(void)
 		fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1,
 				    pack_data->pack_name, object_count,
 				    cur_pack_sha1, pack_size);
+
+		if (object_count <= unpack_limit) {
+			if (!loosen_small_pack(pack_data)) {
+				invalidate_pack_id(pack_id);
+				goto discard_pack;
+			}
+		}
+
 		close(pack_data->pack_fd);
 		idx_name = keep_pack(create_index());
 
@@ -1003,6 +1057,7 @@ static void end_packfile(void)
 		pack_id++;
 	}
 	else {
+discard_pack:
 		close(pack_data->pack_fd);
 		unlink_or_warn(pack_data->pack_name);
 	}
@@ -3320,6 +3375,7 @@ static void parse_option(const char *option)
 static void git_pack_config(void)
 {
 	int indexversion_value;
+	int limit;
 	unsigned long packsizelimit_value;
 
 	if (!git_config_get_ulong("pack.depth", &max_depth)) {
@@ -3344,6 +3400,11 @@ static void git_pack_config(void)
 	if (!git_config_get_ulong("pack.packsizelimit", &packsizelimit_value))
 		max_packsize = packsizelimit_value;
 
+	if (!git_config_get_int("fastimport.unpacklimit", &limit))
+		unpack_limit = limit;
+	else if (!git_config_get_int("transfer.unpacklimit", &limit))
+		unpack_limit = limit;
+
 	git_config(git_default_config, NULL);
 }
 
diff --git a/t/t9300-fast-import.sh b/t/t9300-fast-import.sh
index 4bca35c259..74d740de41 100755
--- a/t/t9300-fast-import.sh
+++ b/t/t9300-fast-import.sh
@@ -52,6 +52,7 @@ echo "$@"'
 ###
 
 test_expect_success 'empty stream succeeds' '
+	git config fastimport.unpackLimit 0 &&
 	git fast-import </dev/null
 '
 
@@ -2690,6 +2691,7 @@ test_expect_success 'R: blob bigger than threshold' '
 	echo >>input &&
 
 	test_create_repo R &&
+	git --git-dir=R/.git config fastimport.unpackLimit 0 &&
 	git --git-dir=R/.git fast-import --big-file-threshold=1 <input
 '
 
diff --git a/t/t9302-fast-import-unpack-limit.sh b/t/t9302-fast-import-unpack-limit.sh
new file mode 100755
index 0000000000..a04de14677
--- /dev/null
+++ b/t/t9302-fast-import-unpack-limit.sh
@@ -0,0 +1,105 @@
+#!/bin/sh
+test_description='test git fast-import unpack limit'
+. ./test-lib.sh
+
+test_expect_success 'create loose objects on import' '
+	test_tick &&
+	cat >input <<-INPUT_END &&
+	commit refs/heads/master
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+	data <<COMMIT
+	initial
+	COMMIT
+
+	done
+	INPUT_END
+
+	git -c fastimport.unpackLimit=2 fast-import --done <input &&
+	git fsck --no-progress &&
+	test $(find .git/objects/?? -type f | wc -l) -eq 2 &&
+	test $(find .git/objects/pack -type f | wc -l) -eq 0
+'
+
+test_expect_success 'bigger packs are preserved' '
+	test_tick &&
+	cat >input <<-INPUT_END &&
+	commit refs/heads/master
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+	data <<COMMIT
+	incremental should create a pack
+	COMMIT
+	from refs/heads/master^0
+
+	commit refs/heads/branch
+	committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+	data <<COMMIT
+	branch
+	COMMIT
+
+	done
+	INPUT_END
+
+	git -c fastimport.unpackLimit=2 fast-import --done <input &&
+	git fsck --no-progress &&
+	test $(find .git/objects/?? -type f | wc -l) -eq 2 &&
+	test $(find .git/objects/pack -type f | wc -l) -eq 2
+'
+
+test_expect_success 'lookups after checkpoint works' '
+	hello_id=$(echo hello | git hash-object --stdin -t blob) &&
+	id="$GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE" &&
+	before=$(git rev-parse refs/heads/master^0) &&
+	(
+		cat <<-INPUT_END &&
+		blob
+		mark :1
+		data 6
+		hello
+
+		commit refs/heads/master
+		mark :2
+		committer $id
+		data <<COMMIT
+		checkpoint after this
+		COMMIT
+		from refs/heads/master^0
+		M 100644 :1 hello
+
+		# pre-checkpoint
+		cat-blob :1
+		cat-blob $hello_id
+		checkpoint
+		# post-checkpoint
+		cat-blob :1
+		cat-blob $hello_id
+		INPUT_END
+
+		n=0 &&
+		from=$before &&
+		while test x"$from" = x"$before"
+		do
+			if test $n -gt 30
+			then
+				echo >&2 "checkpoint did not update branch"
+				exit 1
+			else
+				n=$(($n + 1))
+			fi &&
+			sleep 1 &&
+			from=$(git rev-parse refs/heads/master^0)
+		done &&
+		cat <<-INPUT_END &&
+		commit refs/heads/master
+		committer $id
+		data <<COMMIT
+		make sure from "unpacked sha1 reference" works, too
+		COMMIT
+		from $from
+		INPUT_END
+		echo done
+	) | git -c fastimport.unpackLimit=100 fast-import --done &&
+	test $(find .git/objects/?? -type f | wc -l) -eq 6 &&
+	test $(find .git/objects/pack -type f | wc -l) -eq 2
+'
+
+test_done