Revision 4f22b1015d4203ccdf2b66f27ee5946504342ace authored by Jeff King on 24 February 2012, 22:10:17 UTC, committed by Junio C Hamano on 24 February 2012, 22:18:20 UTC
Because git's object format requires us to specify the number of bytes in the object in its header, we must know the size before streaming a blob into the object database. This is not a problem when adding a regular file, as we can get the size from stat(). However, when filters are in use (such as autocrlf, or the ident, filter, or eol gitattributes), we have no idea what the ultimate size will be. The current code just punts on the whole issue and ignores filter configuration entirely for files larger than core.bigfilethreshold. This can generate confusing results if you use filters for large binary files, as the filter will suddenly stop working as the file goes over a certain size. Rather than try to handle unknown input sizes with streaming, this patch just turns off the streaming optimization when filters are in use. This has a slight performance regression in a very specific case: if you have autocrlf on, but no gitattributes, a large binary file will avoid the streaming code path because we don't know beforehand whether it will need conversion or not. But if you are handling large binary files, you should be marking them as such via attributes (or at least not using autocrlf, and instead marking your text files as such). And the flip side is that if you have a large _non_-binary file, there is a correctness improvement; before we did not apply the conversion at all. The first half of the new t1051 script covers these failures on input. The second half tests the matching output code paths. These already work correctly, and do not need any adjustment. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
1 parent 4c3b57b
alloc.c
/*
* alloc.c - specialized allocator for internal objects
*
* Copyright (C) 2006 Linus Torvalds
*
* The standard malloc/free wastes too much space for objects, partly because
* it maintains all the allocation infrastructure (which isn't needed, since
* we never free an object descriptor anyway), but even more because it ends
* up with maximal alignment because it doesn't know what the object alignment
* for the new allocation is.
*/
#include "cache.h"
#include "object.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "tag.h"
#define BLOCKING 1024
#define DEFINE_ALLOCATOR(name, type) \
static unsigned int name##_allocs; \
void *alloc_##name##_node(void) \
{ \
static int nr; \
static type *block; \
void *ret; \
\
if (!nr) { \
nr = BLOCKING; \
block = xmalloc(BLOCKING * sizeof(type)); \
} \
nr--; \
name##_allocs++; \
ret = block++; \
memset(ret, 0, sizeof(type)); \
return ret; \
}
union any_object {
struct object object;
struct blob blob;
struct tree tree;
struct commit commit;
struct tag tag;
};
DEFINE_ALLOCATOR(blob, struct blob)
DEFINE_ALLOCATOR(tree, struct tree)
DEFINE_ALLOCATOR(commit, struct commit)
DEFINE_ALLOCATOR(tag, struct tag)
DEFINE_ALLOCATOR(object, union any_object)
static void report(const char *name, unsigned int count, size_t size)
{
fprintf(stderr, "%10s: %8u (%"PRIuMAX" kB)\n",
name, count, (uintmax_t) size);
}
#define REPORT(name) \
report(#name, name##_allocs, name##_allocs*sizeof(struct name) >> 10)
void alloc_report(void)
{
REPORT(blob);
REPORT(tree);
REPORT(commit);
REPORT(tag);
}
Computing file changes ...
