[PATCH v4 6/7] gc --auto: exclude base pack if not enough mem to "repack -ad"

From

Nguyễn Thái Ngọc Duy <pclouds@gmail.com>

Date

Mar 24, 2018, 07:42 UTC

Message-ID

<20180324074308.18934-12-pclouds@gmail.com>

In-Reply-To

<20180324074308.18934-1-pclouds@gmail.com>

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Documentation/git-gc.txt |  9 +++-
 builtin/gc.c             | 98 +++++++++++++++++++++++++++++++++++++++-
 builtin/pack-objects.c   |  2 +-
 config.mak.uname         |  1 +
 git-compat-util.h        |  4 ++
 pack-objects.h           |  2 +
 t/t6500-gc.sh            |  7 +++
 7 files changed, 119 insertions(+), 4 deletions(-)

diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index 0adf381b52..7549094900 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -58,8 +58,13 @@ If the number of packs exceeds the value of `gc.autoPackLimit`,
 then existing packs (except those marked with a `.keep` file
 or over `gc.bigPackThreshold` limit)
 are consolidated into a single pack by using the `-A` option of
-'git repack'. Setting `gc.autoPackLimit` to 0 disables
-automatic consolidation of packs.
+'git repack'.
+If the amount of memory is estimated not enough for `git repack` to
+run smoothly and `gc.bigPackThreshold` is not set, the largest
+pack will also be excluded (this is the equivalent of running `git gc`
+with `--keep-base-pack`).
+Setting `gc.autoPackLimit` to 0 disables automatic consolidation of
+packs.
 
 --prune=<date>::
 	Prune loose objects older than date (default is 2 weeks ago,
diff --git a/builtin/gc.c b/builtin/gc.c
index 74d3aaa270..d0b04e369e 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -20,6 +20,10 @@
 #include "argv-array.h"
 #include "commit.h"
 #include "packfile.h"
+#include "pack.h"
+#include "pack-objects.h"
+#include "blob.h"
+#include "tree.h"
 
 #define FAILED_RUN "failed to run %s"
 
@@ -40,6 +44,7 @@ static const char *gc_log_expire = "1.day.ago";
 static const char *prune_expire = "2.weeks.ago";
 static const char *prune_worktrees_expire = "3.months.ago";
 static unsigned long big_pack_threshold;
+static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
 
 static struct argv_array pack_refs_cmd = ARGV_ARRAY_INIT;
 static struct argv_array reflog = ARGV_ARRAY_INIT;
@@ -128,6 +133,7 @@ static void gc_config(void)
 	git_config_get_expiry("gc.logexpiry", &gc_log_expire);
 
 	git_config_get_ulong("gc.bigpackthreshold", &big_pack_threshold);
+	git_config_get_ulong("pack.deltacachesize", &max_delta_cache_size);
 
 	git_config(git_default_config, NULL);
 }
@@ -167,7 +173,8 @@ static int too_many_loose_objects(void)
 	return needed;
 }
 
-static void find_base_packs(struct string_list *packs, unsigned long limit)
+static struct packed_git *find_base_packs(struct string_list *packs,
+					  unsigned long limit)
 {
 	struct packed_git *p, *base = NULL;
 
@@ -186,6 +193,8 @@ static void find_base_packs(struct string_list *packs, unsigned long limit)
 
 	if (base)
 		string_list_append(packs, base->pack_name);
+
+	return base;
 }
 
 static int too_many_packs(void)
@@ -211,6 +220,79 @@ static int too_many_packs(void)
 	return gc_auto_pack_limit < cnt;
 }
 
+static uint64_t total_ram(void)
+{
+#if defined(HAVE_SYSINFO)
+	struct sysinfo si;
+
+	if (!sysinfo(&si))
+		return si.totalram;
+#elif defined(HAVE_BSD_SYSCTL) && (defined(HW_MEMSIZE) || defined(HW_PHYSMEM))
+	int64_t physical_memory;
+	int mib[2];
+	size_t length;
+
+	mib[0] = CTL_HW;
+# if defined(HW_MEMSIZE)
+	mib[1] = HW_MEMSIZE;
+# else
+	mib[1] = HW_PHYSMEM;
+# endif
+	length = sizeof(int64_t);
+	if (!sysctl(mib, 2, &physical_memory, &length, NULL, 0))
+		return physical_memory;
+#elif defined(GIT_WINDOWS_NATIVE)
+	MEMORYSTATUSEX memInfo;
+
+	memInfo.dwLength = sizeof(MEMORYSTATUSEX);
+	if (GlobalMemoryStatusEx(&memInfo))
+		return memInfo.ullTotalPhys;
+#endif
+	return 0;
+}
+
+static uint64_t estimate_repack_memory(struct packed_git *pack)
+{
+	unsigned long nr_objects = approximate_object_count();
+	size_t os_cache, heap;
+
+	if (!pack || !nr_objects)
+		return 0;
+
+	/*
+	 * First we have to scan through at least one pack.
+	 * Assume enough room in OS file cache to keep the entire pack
+	 * or we may accidentally evict data of other processes from
+	 * the cache.
+	 */
+	os_cache = pack->pack_size + pack->index_size;
+	/* then pack-objects needs lots more for book keeping */
+	heap = sizeof(struct object_entry) * nr_objects;
+	/*
+	 * internal rev-list --all --objects takes up some memory too,
+	 * let's say half of it is for blobs
+	 */
+	heap += sizeof(struct blob) * nr_objects / 2;
+	/*
+	 * and the other half is for trees (commits and tags are
+	 * usually insignificant)
+	 */
+	heap += sizeof(struct tree) * nr_objects / 2;
+	/* and then obj_hash[], underestimated in fact */
+	heap += sizeof(struct object *) * nr_objects;
+	/* revindex is used also */
+	heap += sizeof(struct revindex_entry) * nr_objects;
+	/*
+	 * read_sha1_file() (either at delta calculation phase, or
+	 * writing phase) also fills up the delta base cache
+	 */
+	heap += delta_base_cache_limit;
+	/* and of course pack-objects has its own delta cache */
+	heap += max_delta_cache_size;
+
+	return os_cache + heap;
+}
+
 static int keep_one_pack(struct string_list_item *item, void *data)
 {
 	argv_array_pushf(&repack, "--keep-pack=%s", basename(item->string));
@@ -261,6 +343,20 @@ static int need_to_gc(void)
 				string_list_clear(&keep_pack, 0);
 				find_base_packs(&keep_pack, 0);
 			}
+		} else {
+			struct packed_git *p = find_base_packs(&keep_pack, 0);
+			uint64_t mem_have, mem_want;
+
+			mem_have = total_ram();
+			mem_want = estimate_repack_memory(p);
+
+			/*
+			 * Only allow 1/2 of memory for pack-objects, leave
+			 * the rest for the OS and other processes in the
+			 * system.
+			 */
+			if (!mem_have || mem_want < mem_have / 2)
+				string_list_clear(&keep_pack, 0);
 		}
 
 		add_repack_all_option(&keep_pack);
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 7ec70131a9..8b2f8b72bf 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -80,7 +80,7 @@ static uint16_t write_bitmap_options;
 static int exclude_promisor_objects;
 
 static unsigned long delta_cache_size = 0;
-static unsigned long max_delta_cache_size = 256 * 1024 * 1024;
+static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
 static unsigned long cache_max_small_delta_size = 1000;
 
 static unsigned long window_memory_limit = 0;
diff --git a/config.mak.uname b/config.mak.uname
index 6a1d0de0cc..ae9cbccec1 100644
--- a/config.mak.uname
+++ b/config.mak.uname
@@ -37,6 +37,7 @@ ifeq ($(uname_S),Linux)
 	HAVE_GETDELIM = YesPlease
 	SANE_TEXT_GREP=-a
 	FREAD_READS_DIRECTORIES = UnfortunatelyYes
+	BASIC_CFLAGS += -DHAVE_SYSINFO
 endif
 ifeq ($(uname_S),GNU/kFreeBSD)
 	HAVE_ALLOCA_H = YesPlease
diff --git a/git-compat-util.h b/git-compat-util.h
index 07e383257b..e373af48b8 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -284,6 +284,10 @@ extern char *gitdirname(char *);
 #include <openssl/err.h>
 #endif
 
+#ifdef HAVE_SYSINFO
+# include <sys/sysinfo.h>
+#endif
+
 /* On most systems <netdb.h> would have given us this, but
  * not on some systems (e.g. z/OS).
  */
diff --git a/pack-objects.h b/pack-objects.h
index 03f1191659..af4f46c026 100644
--- a/pack-objects.h
+++ b/pack-objects.h
@@ -1,6 +1,8 @@
 #ifndef PACK_OBJECTS_H
 #define PACK_OBJECTS_H
 
+#define DEFAULT_DELTA_CACHE_SIZE (256 * 1024 * 1024)
+
 struct object_entry {
 	struct pack_idx_entry idx;
 	unsigned long size;	/* uncompressed size */
diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh
index a95969af2a..100f287b97 100755
--- a/t/t6500-gc.sh
+++ b/t/t6500-gc.sh
@@ -5,6 +5,13 @@ test_description='basic git gc tests
 
 . ./test-lib.sh
 
+test_expect_success 'setup' '
+	# do not let the amount of physical memory affects gc
+	# behavior, make sure we always pack everything to one pack by
+	# default
+	git config gc.bigPackThreshold 2g
+'
+
 test_expect_success 'gc empty repository' '
 	git gc
 '

-- 
2.17.0.rc0.348.gd5a49e0b6f