git-commit-vandalism/csum-file.c

161 lines
3.1 KiB
C
Raw Normal View History

/*
* csum-file.c
*
* Copyright (C) 2005 Linus Torvalds
*
* Simple file write infrastructure for writing SHA1-summed
* files. Useful when you write a file that you want to be
* able to verify hasn't been messed with afterwards.
*/
#include "cache.h"
#include "csum-file.h"
static void sha1flush(struct sha1file *f, unsigned int count)
{
void *buf = f->buffer;
for (;;) {
int ret = xwrite(f->fd, buf, count);
if (ret > 0) {
buf = (char *) buf + ret;
count -= ret;
if (count)
continue;
return;
}
if (!ret)
die("sha1 file '%s' write error. Out of diskspace", f->name);
die("sha1 file '%s' write error (%s)", f->name, strerror(errno));
}
}
int sha1close(struct sha1file *f, unsigned char *result, int update)
{
unsigned offset = f->offset;
if (offset) {
SHA1_Update(&f->ctx, f->buffer, offset);
sha1flush(f, offset);
}
SHA1_Final(f->buffer, &f->ctx);
if (result)
hashcpy(result, f->buffer);
if (update)
sha1flush(f, 20);
if (close(f->fd))
die("%s: sha1 file error on close (%s)", f->name, strerror(errno));
free(f);
return 0;
}
int sha1write(struct sha1file *f, void *buf, unsigned int count)
{
compute a CRC32 for each object as stored in a pack The most important optimization for performance when repacking is the ability to reuse data from a previous pack as is and bypass any delta or even SHA1 computation by simply copying the raw data from one pack to another directly. The problem with this is that any data corruption within a copied object would go unnoticed and the new (repacked) pack would be self-consistent with its own checksum despite containing a corrupted object. This is a real issue that already happened at least once in the past. In some attempt to prevent this, we validate the copied data by inflating it and making sure no error is signaled by zlib. But this is still not perfect as a significant portion of a pack content is made of object headers and references to delta base objects which are not deflated and therefore not validated when repacking actually making the pack data reuse still not as safe as it could be. Of course a full SHA1 validation could be performed, but that implies full data inflating and delta replaying which is extremely costly, which cost the data reuse optimization was designed to avoid in the first place. So the best solution to this is simply to store a CRC32 of the raw pack data for each object in the pack index. This way any object in a pack can be validated before being copied as is in another pack, including header and any other non deflated data. Why CRC32 instead of a faster checksum like Adler32? Quoting Wikipedia: Jonathan Stone discovered in 2001 that Adler-32 has a weakness for very short messages. He wrote "Briefly, the problem is that, for very short packets, Adler32 is guaranteed to give poor coverage of the available bits. Don't take my word for it, ask Mark Adler. :-)" The problem is that sum A does not wrap for short messages. The maximum value of A for a 128-byte message is 32640, which is below the value 65521 used by the modulo operation. An extended explanation can be found in RFC 3309, which mandates the use of CRC32 instead of Adler-32 for SCTP, the Stream Control Transmission Protocol. In the context of a GIT pack, we have lots of small objects, especially deltas, which are likely to be quite small and in a size range for which Adler32 is dimed not to be sufficient. Another advantage of CRC32 is the possibility for recovery from certain types of small corruptions like single bit errors which are the most probable type of corruptions. OK what this patch does is to compute the CRC32 of each object written to a pack within pack-objects. It is not written to the index yet and it is obviously not validated when reusing pack data yet either. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-04-09 07:06:31 +02:00
if (f->do_crc)
f->crc32 = crc32(f->crc32, buf, count);
while (count) {
unsigned offset = f->offset;
unsigned left = sizeof(f->buffer) - offset;
unsigned nr = count > left ? left : count;
memcpy(f->buffer + offset, buf, nr);
count -= nr;
offset += nr;
buf = (char *) buf + nr;
left -= nr;
if (!left) {
SHA1_Update(&f->ctx, f->buffer, offset);
sha1flush(f, offset);
offset = 0;
}
f->offset = offset;
}
return 0;
}
struct sha1file *sha1create(const char *fmt, ...)
{
struct sha1file *f;
unsigned len;
va_list arg;
int fd;
f = xmalloc(sizeof(*f));
va_start(arg, fmt);
len = vsnprintf(f->name, sizeof(f->name), fmt, arg);
va_end(arg);
if (len >= PATH_MAX)
die("you wascally wabbit, you");
f->namelen = len;
fd = open(f->name, O_CREAT | O_EXCL | O_WRONLY, 0666);
if (fd < 0)
die("unable to open %s (%s)", f->name, strerror(errno));
f->fd = fd;
f->error = 0;
f->offset = 0;
compute a CRC32 for each object as stored in a pack The most important optimization for performance when repacking is the ability to reuse data from a previous pack as is and bypass any delta or even SHA1 computation by simply copying the raw data from one pack to another directly. The problem with this is that any data corruption within a copied object would go unnoticed and the new (repacked) pack would be self-consistent with its own checksum despite containing a corrupted object. This is a real issue that already happened at least once in the past. In some attempt to prevent this, we validate the copied data by inflating it and making sure no error is signaled by zlib. But this is still not perfect as a significant portion of a pack content is made of object headers and references to delta base objects which are not deflated and therefore not validated when repacking actually making the pack data reuse still not as safe as it could be. Of course a full SHA1 validation could be performed, but that implies full data inflating and delta replaying which is extremely costly, which cost the data reuse optimization was designed to avoid in the first place. So the best solution to this is simply to store a CRC32 of the raw pack data for each object in the pack index. This way any object in a pack can be validated before being copied as is in another pack, including header and any other non deflated data. Why CRC32 instead of a faster checksum like Adler32? Quoting Wikipedia: Jonathan Stone discovered in 2001 that Adler-32 has a weakness for very short messages. He wrote "Briefly, the problem is that, for very short packets, Adler32 is guaranteed to give poor coverage of the available bits. Don't take my word for it, ask Mark Adler. :-)" The problem is that sum A does not wrap for short messages. The maximum value of A for a 128-byte message is 32640, which is below the value 65521 used by the modulo operation. An extended explanation can be found in RFC 3309, which mandates the use of CRC32 instead of Adler-32 for SCTP, the Stream Control Transmission Protocol. In the context of a GIT pack, we have lots of small objects, especially deltas, which are likely to be quite small and in a size range for which Adler32 is dimed not to be sufficient. Another advantage of CRC32 is the possibility for recovery from certain types of small corruptions like single bit errors which are the most probable type of corruptions. OK what this patch does is to compute the CRC32 of each object written to a pack within pack-objects. It is not written to the index yet and it is obviously not validated when reusing pack data yet either. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-04-09 07:06:31 +02:00
f->do_crc = 0;
SHA1_Init(&f->ctx);
return f;
}
struct sha1file *sha1fd(int fd, const char *name)
{
struct sha1file *f;
unsigned len;
f = xmalloc(sizeof(*f));
len = strlen(name);
if (len >= PATH_MAX)
die("you wascally wabbit, you");
f->namelen = len;
memcpy(f->name, name, len+1);
f->fd = fd;
f->error = 0;
f->offset = 0;
compute a CRC32 for each object as stored in a pack The most important optimization for performance when repacking is the ability to reuse data from a previous pack as is and bypass any delta or even SHA1 computation by simply copying the raw data from one pack to another directly. The problem with this is that any data corruption within a copied object would go unnoticed and the new (repacked) pack would be self-consistent with its own checksum despite containing a corrupted object. This is a real issue that already happened at least once in the past. In some attempt to prevent this, we validate the copied data by inflating it and making sure no error is signaled by zlib. But this is still not perfect as a significant portion of a pack content is made of object headers and references to delta base objects which are not deflated and therefore not validated when repacking actually making the pack data reuse still not as safe as it could be. Of course a full SHA1 validation could be performed, but that implies full data inflating and delta replaying which is extremely costly, which cost the data reuse optimization was designed to avoid in the first place. So the best solution to this is simply to store a CRC32 of the raw pack data for each object in the pack index. This way any object in a pack can be validated before being copied as is in another pack, including header and any other non deflated data. Why CRC32 instead of a faster checksum like Adler32? Quoting Wikipedia: Jonathan Stone discovered in 2001 that Adler-32 has a weakness for very short messages. He wrote "Briefly, the problem is that, for very short packets, Adler32 is guaranteed to give poor coverage of the available bits. Don't take my word for it, ask Mark Adler. :-)" The problem is that sum A does not wrap for short messages. The maximum value of A for a 128-byte message is 32640, which is below the value 65521 used by the modulo operation. An extended explanation can be found in RFC 3309, which mandates the use of CRC32 instead of Adler-32 for SCTP, the Stream Control Transmission Protocol. In the context of a GIT pack, we have lots of small objects, especially deltas, which are likely to be quite small and in a size range for which Adler32 is dimed not to be sufficient. Another advantage of CRC32 is the possibility for recovery from certain types of small corruptions like single bit errors which are the most probable type of corruptions. OK what this patch does is to compute the CRC32 of each object written to a pack within pack-objects. It is not written to the index yet and it is obviously not validated when reusing pack data yet either. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-04-09 07:06:31 +02:00
f->do_crc = 0;
SHA1_Init(&f->ctx);
return f;
}
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: Dana L. How <danahow@gmail.com> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-05-09 22:56:50 +02:00
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));
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: Dana L. How <danahow@gmail.com> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-05-09 22:56:50 +02:00
deflateInit(&stream, level);
maxsize = deflateBound(&stream, size);
out = xmalloc(maxsize);
/* Compress it */
stream.next_in = in;
stream.avail_in = size;
stream.next_out = out;
stream.avail_out = maxsize;
while (deflate(&stream, Z_FINISH) == Z_OK)
/* nothing */;
deflateEnd(&stream);
size = stream.total_out;
sha1write(f, out, size);
free(out);
return size;
}
compute a CRC32 for each object as stored in a pack The most important optimization for performance when repacking is the ability to reuse data from a previous pack as is and bypass any delta or even SHA1 computation by simply copying the raw data from one pack to another directly. The problem with this is that any data corruption within a copied object would go unnoticed and the new (repacked) pack would be self-consistent with its own checksum despite containing a corrupted object. This is a real issue that already happened at least once in the past. In some attempt to prevent this, we validate the copied data by inflating it and making sure no error is signaled by zlib. But this is still not perfect as a significant portion of a pack content is made of object headers and references to delta base objects which are not deflated and therefore not validated when repacking actually making the pack data reuse still not as safe as it could be. Of course a full SHA1 validation could be performed, but that implies full data inflating and delta replaying which is extremely costly, which cost the data reuse optimization was designed to avoid in the first place. So the best solution to this is simply to store a CRC32 of the raw pack data for each object in the pack index. This way any object in a pack can be validated before being copied as is in another pack, including header and any other non deflated data. Why CRC32 instead of a faster checksum like Adler32? Quoting Wikipedia: Jonathan Stone discovered in 2001 that Adler-32 has a weakness for very short messages. He wrote "Briefly, the problem is that, for very short packets, Adler32 is guaranteed to give poor coverage of the available bits. Don't take my word for it, ask Mark Adler. :-)" The problem is that sum A does not wrap for short messages. The maximum value of A for a 128-byte message is 32640, which is below the value 65521 used by the modulo operation. An extended explanation can be found in RFC 3309, which mandates the use of CRC32 instead of Adler-32 for SCTP, the Stream Control Transmission Protocol. In the context of a GIT pack, we have lots of small objects, especially deltas, which are likely to be quite small and in a size range for which Adler32 is dimed not to be sufficient. Another advantage of CRC32 is the possibility for recovery from certain types of small corruptions like single bit errors which are the most probable type of corruptions. OK what this patch does is to compute the CRC32 of each object written to a pack within pack-objects. It is not written to the index yet and it is obviously not validated when reusing pack data yet either. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-04-09 07:06:31 +02:00
void crc32_begin(struct sha1file *f)
{
f->crc32 = crc32(0, Z_NULL, 0);
f->do_crc = 1;
}
compute a CRC32 for each object as stored in a pack The most important optimization for performance when repacking is the ability to reuse data from a previous pack as is and bypass any delta or even SHA1 computation by simply copying the raw data from one pack to another directly. The problem with this is that any data corruption within a copied object would go unnoticed and the new (repacked) pack would be self-consistent with its own checksum despite containing a corrupted object. This is a real issue that already happened at least once in the past. In some attempt to prevent this, we validate the copied data by inflating it and making sure no error is signaled by zlib. But this is still not perfect as a significant portion of a pack content is made of object headers and references to delta base objects which are not deflated and therefore not validated when repacking actually making the pack data reuse still not as safe as it could be. Of course a full SHA1 validation could be performed, but that implies full data inflating and delta replaying which is extremely costly, which cost the data reuse optimization was designed to avoid in the first place. So the best solution to this is simply to store a CRC32 of the raw pack data for each object in the pack index. This way any object in a pack can be validated before being copied as is in another pack, including header and any other non deflated data. Why CRC32 instead of a faster checksum like Adler32? Quoting Wikipedia: Jonathan Stone discovered in 2001 that Adler-32 has a weakness for very short messages. He wrote "Briefly, the problem is that, for very short packets, Adler32 is guaranteed to give poor coverage of the available bits. Don't take my word for it, ask Mark Adler. :-)" The problem is that sum A does not wrap for short messages. The maximum value of A for a 128-byte message is 32640, which is below the value 65521 used by the modulo operation. An extended explanation can be found in RFC 3309, which mandates the use of CRC32 instead of Adler-32 for SCTP, the Stream Control Transmission Protocol. In the context of a GIT pack, we have lots of small objects, especially deltas, which are likely to be quite small and in a size range for which Adler32 is dimed not to be sufficient. Another advantage of CRC32 is the possibility for recovery from certain types of small corruptions like single bit errors which are the most probable type of corruptions. OK what this patch does is to compute the CRC32 of each object written to a pack within pack-objects. It is not written to the index yet and it is obviously not validated when reusing pack data yet either. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-04-09 07:06:31 +02:00
uint32_t crc32_end(struct sha1file *f)
{
f->do_crc = 0;
return f->crc32;
}