Commit 960ccca6 authored by Dana How's avatar Dana How Committed by Junio C Hamano

Custom compression levels for objects and packs

Add config variables pack.compression and core.loosecompression ,
and switch --compression=level to pack-objects.

Loose objects will be compressed using core.loosecompression if set,
else core.compression if set, else Z_BEST_SPEED.
Packed objects will be compressed using --compression=level if seen,
else pack.compression if set, else core.compression if set,
else Z_DEFAULT_COMPRESSION.  This is the "pack compression level".

Loose objects added to a pack undeltified will be recompressed
to the pack compression level if it is unequal to the current
loose compression level by the preceding rules,  or if the loose
object was written while core.legacyheaders = true.  Newly
deltified loose objects are always compressed to the current
pack compression level.

Previously packed objects added to a pack are recompressed
to the current pack compression level exactly when their
deltification status changes,  since the previous pack data
cannot be reused.

In either case,  the --no-reuse-object switch from the first
patch below will always force recompression to the current pack
compression level,  instead of assuming the pack compression level
hasn't changed and pack data can be reused when possible.

This applies on top of the following patches from Nicolas Pitre:
[PATCH] allow for undeltified objects not to be reused
[PATCH] make "repack -f" imply "pack-objects --no-reuse-object"
Signed-off-by: default avatarDana L. How <danahow@gmail.com>
Signed-off-by: default avatarJunio C Hamano <junkio@cox.net>
parent 479b56ba
......@@ -204,10 +204,16 @@ core.warnAmbiguousRefs::
and might match multiple refs in the .git/refs/ tree. True by default.
core.compression::
An integer -1..9, indicating a default compression level.
-1 is the zlib default. 0 means no compression,
and 1..9 are various speed/size tradeoffs, 9 being slowest.
core.loosecompression::
An integer -1..9, indicating the compression level for objects that
are not in a pack file. -1 is the zlib and git default. 0 means no
are not in a pack file. -1 is the zlib default. 0 means no
compression, and 1..9 are various speed/size tradeoffs, 9 being
slowest.
slowest. If not set, defaults to core.compression. If that is
not set, defaults to 0 (best speed).
core.legacyheaders::
A boolean which
......@@ -550,6 +556,13 @@ pack.depth::
The maximum delta depth used by gitlink:git-pack-objects[1] when no
maximum depth is given on the command line. Defaults to 50.
pack.compression::
An integer -1..9, indicating the compression level for objects
in a pack file. -1 is the zlib default. 0 means no
compression, and 1..9 are various speed/size tradeoffs, 9 being
slowest. If not set, defaults to core.compression. If that is
not set, defaults to -1.
pull.octopus::
The default merge strategy to use when pulling multiple branches
at once.
......
......@@ -130,10 +130,22 @@ base-name::
--no-reuse-object::
This flag tells the command not to reuse existing object data at all,
including non deltified object, forcing recompression of everything.
This implies --no-reuse-delta. Useful only in the obscur case where
This implies --no-reuse-delta. Useful only in the obscure case where
wholesale enforcement of a different compression level on the
packed data is desired.
--compression=[N]::
Specifies compression level for newly-compressed data in the
generated pack. If not specified, pack compression level is
determined first by pack.compression, then by core.compression,
and defaults to -1, the zlib default, if neither is set.
Data copied from loose objects will be recompressed
if core.legacyheaders was true when they were created or if
the loose compression level (see core.loosecompression and
core.compression) is now a different value than the pack
compression level. Add --no-reuse-object if you want to force
a uniform compression level on all data no matter the source.
--delta-base-offset::
A packed archive can express base object of a delta as
either 20-byte object name or as an offset in the
......
......@@ -68,6 +68,8 @@ static int depth = 50;
static int pack_to_stdout;
static int num_preferred_base;
static struct progress progress_state;
static int pack_compression_level = Z_DEFAULT_COMPRESSION;
static int pack_compression_seen;
/*
* The object names in objects array are hashed with this hashtable,
......@@ -427,7 +429,10 @@ static unsigned long write_object(struct sha1file *f,
* and we do not need to deltify it.
*/
if (!no_reuse_object && !entry->in_pack && !entry->delta) {
/* differing core & pack compression when loose object -> must recompress */
if (!entry->in_pack && pack_compression_level != zlib_compression_level)
to_reuse = 0;
else if (!no_reuse_object && !entry->in_pack && !entry->delta) {
unsigned char *map;
unsigned long mapsize;
map = map_sha1_file(entry->sha1, &mapsize);
......@@ -487,7 +492,7 @@ static unsigned long write_object(struct sha1file *f,
sha1write(f, entry->delta->sha1, 20);
hdrlen += 20;
}
datalen = sha1write_compressed(f, buf, size);
datalen = sha1write_compressed(f, buf, size, pack_compression_level);
free(buf);
}
else {
......@@ -1496,6 +1501,16 @@ static int git_pack_config(const char *k, const char *v)
depth = git_config_int(k, v);
return 0;
}
if (!strcmp(k, "pack.compression")) {
int level = git_config_int(k, v);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die("bad pack compression level %d", level);
pack_compression_level = level;
pack_compression_seen = 1;
return 0;
}
return git_default_config(k, v);
}
......@@ -1607,6 +1622,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
rp_ac = 2;
git_config(git_pack_config);
if (!pack_compression_seen && core_compression_seen)
pack_compression_level = core_compression_level;
progress = isatty(2);
for (i = 1; i < argc; i++) {
......@@ -1627,6 +1644,18 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
incremental = 1;
continue;
}
if (!prefixcmp(arg, "--compression=")) {
char *end;
int level = strtoul(arg+14, &end, 0);
if (!arg[14] || *end)
usage(pack_usage);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die("bad pack compression level %d", level);
pack_compression_level = level;
continue;
}
if (!prefixcmp(arg, "--window=")) {
char *end;
window = strtoul(arg+9, &end, 0);
......
......@@ -283,6 +283,8 @@ extern int warn_ambiguous_refs;
extern int shared_repository;
extern const char *apply_default_whitespace;
extern int zlib_compression_level;
extern int core_compression_level;
extern int core_compression_seen;
extern size_t packed_git_window_size;
extern size_t packed_git_limit;
extern size_t delta_base_cache_limit;
......
......@@ -12,6 +12,8 @@
static FILE *config_file;
static const char *config_file_name;
static int config_linenr;
static int zlib_compression_seen;
static int get_next_char(void)
{
int c;
......@@ -304,13 +306,27 @@ int git_default_config(const char *var, const char *value)
return 0;
}
if (!strcmp(var, "core.compression")) {
if (!strcmp(var, "core.loosecompression")) {
int level = git_config_int(var, value);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die("bad zlib compression level %d", level);
zlib_compression_level = level;
zlib_compression_seen = 1;
return 0;
}
if (!strcmp(var, "core.compression")) {
int level = git_config_int(var, value);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die("bad zlib compression level %d", level);
core_compression_level = level;
core_compression_seen = 1;
if (!zlib_compression_seen)
zlib_compression_level = level;
return 0;
}
......
......@@ -119,14 +119,14 @@ struct sha1file *sha1fd(int fd, const char *name)
return f;
}
int sha1write_compressed(struct sha1file *f, void *in, unsigned int size)
int sha1write_compressed(struct sha1file *f, void *in, unsigned int size, int level)
{
z_stream stream;
unsigned long maxsize;
void *out;
memset(&stream, 0, sizeof(stream));
deflateInit(&stream, zlib_compression_level);
deflateInit(&stream, level);
maxsize = deflateBound(&stream, size);
out = xmalloc(maxsize);
......
......@@ -16,7 +16,7 @@ extern struct sha1file *sha1fd(int fd, const char *name);
extern struct sha1file *sha1create(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
extern int sha1close(struct sha1file *, unsigned char *, int);
extern int sha1write(struct sha1file *, void *, unsigned int);
extern int sha1write_compressed(struct sha1file *, void *, unsigned int);
extern int sha1write_compressed(struct sha1file *, void *, unsigned int, int);
extern void crc32_begin(struct sha1file *);
extern uint32_t crc32_end(struct sha1file *);
......
......@@ -24,7 +24,9 @@ const char *git_commit_encoding;
const char *git_log_output_encoding;
int shared_repository = PERM_UMASK;
const char *apply_default_whitespace;
int zlib_compression_level = Z_DEFAULT_COMPRESSION;
int zlib_compression_level = Z_BEST_SPEED;
int core_compression_level;
int core_compression_seen;
size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE;
size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT;
size_t delta_base_cache_limit = 16 * 1024 * 1024;
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment