path: root/builtin/pack-objects.c
diff options
authorJunio C Hamano <>2011-06-10 18:52:15 (GMT)
committerJunio C Hamano <>2011-06-10 18:52:15 (GMT)
commitef49a7a0126d64359c974b4b3b71d7ad42ee3bca (patch)
tree2e9b67a18c4c37802cd7459ff7f3fb9bff4508c3 /builtin/pack-objects.c
parent225a6f1068f71723a910e8565db4e252b3ca21fa (diff)
zlib: zlib can only process 4GB at a time
The size of objects we read from the repository and data we try to put into the repository are represented in "unsigned long", so that on larger architectures we can handle objects that weigh more than 4GB. But the interface defined in zlib.h to communicate with inflate/deflate limits avail_in (how many bytes of input are we calling zlib with) and avail_out (how many bytes of output from zlib are we ready to accept) fields effectively to 4GB by defining their type to be uInt. In many places in our code, we allocate a large buffer (e.g. mmap'ing a large loose object file) and tell zlib its size by assigning the size to avail_in field of the stream, but that will truncate the high octets of the real size. The worst part of this story is that we often pass around z_stream (the state object used by zlib) to keep track of the number of used bytes in input/output buffer by inspecting these two fields, which practically limits our callchain to the same 4GB limit. Wrap z_stream in another structure git_zstream that can express avail_in and avail_out in unsigned long. For now, just die() when the caller gives a size that cannot be given to a single zlib call. In later patches in the series, we would make git_inflate() and git_deflate() internally loop to give callers an illusion that our "improved" version of zlib interface can operate on a buffer larger than 4GB in one go. Signed-off-by: Junio C Hamano <>
Diffstat (limited to 'builtin/pack-objects.c')
1 files changed, 5 insertions, 5 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 8981dd6..c6e2d87 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -126,7 +126,7 @@ static void *get_delta(struct object_entry *entry)
static unsigned long do_compress(void **pptr, unsigned long size)
- z_stream stream;
+ git_zstream stream;
void *in, *out;
unsigned long maxsize;
@@ -160,7 +160,7 @@ static int check_pack_inflate(struct packed_git *p,
off_t len,
unsigned long expect)
- z_stream stream;
+ git_zstream stream;
unsigned char fakebuf[4096], *in;
int st;
@@ -187,12 +187,12 @@ static void copy_pack_data(struct sha1file *f,
off_t len)
unsigned char *in;
- unsigned int avail;
+ unsigned long avail;
while (len) {
in = use_pack(p, w_curs, offset, &avail);
if (avail > len)
- avail = (unsigned int)len;
+ avail = (unsigned long)len;
sha1write(f, in, avail);
offset += avail;
len -= avail;
@@ -994,7 +994,7 @@ static void check_object(struct object_entry *entry)
const unsigned char *base_ref = NULL;
struct object_entry *base_entry;
unsigned long used, used_0;
- unsigned int avail;
+ unsigned long avail;
off_t ofs;
unsigned char *buf, c;