path: root/cache.h
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 /cache.h
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 'cache.h')
1 files changed, 22 insertions, 13 deletions
diff --git a/cache.h b/cache.h
index 85ac5ec..1784bab 100644
--- a/cache.h
+++ b/cache.h
@@ -16,18 +16,27 @@
#include <zlib.h>
-void git_inflate_init(z_streamp strm);
-void git_inflate_init_gzip_only(z_streamp strm);
-void git_inflate_end(z_streamp strm);
-int git_inflate(z_streamp strm, int flush);
-void git_deflate_init(z_streamp strm, int level);
-void git_deflate_init_gzip(z_streamp strm, int level);
-void git_deflate_end(z_streamp strm);
-int git_deflate_end_gently(z_streamp strm);
-int git_deflate(z_streamp strm, int flush);
-unsigned long git_deflate_bound(z_streamp, unsigned long);
+typedef struct git_zstream {
+ z_stream z;
+ unsigned long avail_in;
+ unsigned long avail_out;
+ unsigned long total_in;
+ unsigned long total_out;
+ unsigned char *next_in;
+ unsigned char *next_out;
+} git_zstream;
+void git_inflate_init(git_zstream *);
+void git_inflate_init_gzip_only(git_zstream *);
+void git_inflate_end(git_zstream *);
+int git_inflate(git_zstream *, int flush);
+void git_deflate_init(git_zstream *, int level);
+void git_deflate_init_gzip(git_zstream *, int level);
+void git_deflate_end(git_zstream *);
+int git_deflate_end_gently(git_zstream *);
+int git_deflate(git_zstream *, int flush);
+unsigned long git_deflate_bound(git_zstream *, unsigned long);
#if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT)
#define DTYPE(de) ((de)->d_type)
@@ -991,7 +1000,7 @@ extern struct packed_git *find_sha1_pack(const unsigned char *sha1,
extern void pack_report(void);
extern int open_pack_index(struct packed_git *);
extern void close_pack_index(struct packed_git *);
-extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned int *);
+extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *);
extern void close_pack_windows(struct packed_git *);
extern void unuse_pack(struct pack_window **);
extern void free_pack_by_name(const char *);