git/csum-file.c

190 lines
4.2 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 "progress.h"
#include "csum-file.h"
static void flush(struct hashfile *f, const void *buf, unsigned int count)
{
if (0 <= f->check_fd && count) {
unsigned char check_buffer[8192];
ssize_t ret = read_in_full(f->check_fd, check_buffer, count);
if (ret < 0)
die_errno("%s: sha1 file read error", f->name);
if (ret != count)
die("%s: sha1 file truncated", f->name);
if (memcmp(buf, check_buffer, count))
die("sha1 file '%s' validation error", f->name);
}
for (;;) {
int ret = xwrite(f->fd, buf, count);
if (ret > 0) {
f->total += ret;
display_throughput(f->tp, f->total);
buf = (char *) buf + ret;
count -= ret;
if (count)
continue;
return;
}
if (!ret)
die("sha1 file '%s' write error. Out of diskspace", f->name);
die_errno("sha1 file '%s' write error", f->name);
}
}
void hashflush(struct hashfile *f)
{
unsigned offset = f->offset;
if (offset) {
the_hash_algo->update_fn(&f->ctx, f->buffer, offset);
flush(f, f->buffer, offset);
f->offset = 0;
}
}
int finalize_hashfile(struct hashfile *f, unsigned char *result, unsigned int flags)
{
int fd;
hashflush(f);
the_hash_algo->final_fn(f->buffer, &f->ctx);
if (result)
hashcpy(result, f->buffer);
if (flags & CSUM_HASH_IN_STREAM)
flush(f, f->buffer, the_hash_algo->rawsz);
if (flags & CSUM_FSYNC)
fsync_or_die(f->fd, f->name);
if (flags & CSUM_CLOSE) {
if (close(f->fd))
die_errno("%s: sha1 file error on close", f->name);
fd = 0;
} else
fd = f->fd;
if (0 <= f->check_fd) {
char discard;
int cnt = read_in_full(f->check_fd, &discard, 1);
if (cnt < 0)
die_errno("%s: error when reading the tail of sha1 file",
f->name);
if (cnt)
die("%s: sha1 file has trailing garbage", f->name);
if (close(f->check_fd))
die_errno("%s: sha1 file error on close", f->name);
}
free(f);
return fd;
}
void hashwrite(struct hashfile *f, const void *buf, unsigned int count)
{
while (count) {
csum-file: make hashwrite() more readable The hashwrite() method takes an input buffer and updates a hashfile's hash function while writing the data to a file. To avoid overuse of flushes, the hashfile has an internal buffer and most writes will use memcpy() to transfer data from the input 'buf' to the hashfile's buffer of size 8 * 1024 bytes. Logic introduced by a8032d12 (sha1write: don't copy full sized buffers, 2008-09-02) reduces the number of memcpy() calls when the input buffer is sufficiently longer than the hashfile's buffer, causing nr to be the length of the full buffer. In these cases, the input buffer is used directly in chunks equal to the hashfile's buffer size. This method caught my attention while investigating some performance issues, but it turns out that these performance issues were noise within the variance of the experiment. However, during this investigation, I inspected hashwrite() and misunderstood it, even after looking closely and trying to make it faster. This change simply reorganizes some parts of the loop within hashwrite() to make it clear that each batch either uses memcpy() to the hashfile's buffer or writes directly from the input buffer. The previous code relied on indirection through local variables and essentially inlined the implementation of hashflush() to reduce lines of code. Helped-by: Jeff King <peff@peff.net> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-26 20:38:11 +08:00
unsigned left = sizeof(f->buffer) - f->offset;
unsigned nr = count > left ? left : count;
if (f->do_crc)
f->crc32 = crc32(f->crc32, buf, nr);
if (nr == sizeof(f->buffer)) {
csum-file: make hashwrite() more readable The hashwrite() method takes an input buffer and updates a hashfile's hash function while writing the data to a file. To avoid overuse of flushes, the hashfile has an internal buffer and most writes will use memcpy() to transfer data from the input 'buf' to the hashfile's buffer of size 8 * 1024 bytes. Logic introduced by a8032d12 (sha1write: don't copy full sized buffers, 2008-09-02) reduces the number of memcpy() calls when the input buffer is sufficiently longer than the hashfile's buffer, causing nr to be the length of the full buffer. In these cases, the input buffer is used directly in chunks equal to the hashfile's buffer size. This method caught my attention while investigating some performance issues, but it turns out that these performance issues were noise within the variance of the experiment. However, during this investigation, I inspected hashwrite() and misunderstood it, even after looking closely and trying to make it faster. This change simply reorganizes some parts of the loop within hashwrite() to make it clear that each batch either uses memcpy() to the hashfile's buffer or writes directly from the input buffer. The previous code relied on indirection through local variables and essentially inlined the implementation of hashflush() to reduce lines of code. Helped-by: Jeff King <peff@peff.net> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-26 20:38:11 +08:00
/*
* Flush a full batch worth of data directly
* from the input, skipping the memcpy() to
* the hashfile's buffer. In this block,
* f->offset is necessarily zero.
*/
the_hash_algo->update_fn(&f->ctx, buf, nr);
flush(f, buf, nr);
} else {
csum-file: make hashwrite() more readable The hashwrite() method takes an input buffer and updates a hashfile's hash function while writing the data to a file. To avoid overuse of flushes, the hashfile has an internal buffer and most writes will use memcpy() to transfer data from the input 'buf' to the hashfile's buffer of size 8 * 1024 bytes. Logic introduced by a8032d12 (sha1write: don't copy full sized buffers, 2008-09-02) reduces the number of memcpy() calls when the input buffer is sufficiently longer than the hashfile's buffer, causing nr to be the length of the full buffer. In these cases, the input buffer is used directly in chunks equal to the hashfile's buffer size. This method caught my attention while investigating some performance issues, but it turns out that these performance issues were noise within the variance of the experiment. However, during this investigation, I inspected hashwrite() and misunderstood it, even after looking closely and trying to make it faster. This change simply reorganizes some parts of the loop within hashwrite() to make it clear that each batch either uses memcpy() to the hashfile's buffer or writes directly from the input buffer. The previous code relied on indirection through local variables and essentially inlined the implementation of hashflush() to reduce lines of code. Helped-by: Jeff King <peff@peff.net> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-26 20:38:11 +08:00
/*
* Copy to the hashfile's buffer, flushing only
* if it became full.
*/
memcpy(f->buffer + f->offset, buf, nr);
f->offset += nr;
left -= nr;
if (!left)
hashflush(f);
}
count -= nr;
buf = (char *) buf + nr;
}
}
struct hashfile *hashfd(int fd, const char *name)
{
return hashfd_throughput(fd, name, NULL);
}
struct hashfile *hashfd_check(const char *name)
{
int sink, check;
struct hashfile *f;
sink = open("/dev/null", O_WRONLY);
if (sink < 0)
die_errno("unable to open /dev/null");
check = open(name, O_RDONLY);
if (check < 0)
die_errno("unable to open '%s'", name);
f = hashfd(sink, name);
f->check_fd = check;
return f;
}
struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp)
{
struct hashfile *f = xmalloc(sizeof(*f));
f->fd = fd;
f->check_fd = -1;
f->offset = 0;
f->total = 0;
f->tp = tp;
f->name = name;
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 13:06:31 +08:00
f->do_crc = 0;
the_hash_algo->init_fn(&f->ctx);
return f;
}
void hashfile_checkpoint(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
{
hashflush(f);
checkpoint->offset = f->total;
the_hash_algo->clone_fn(&checkpoint->ctx, &f->ctx);
}
int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
{
off_t offset = checkpoint->offset;
if (ftruncate(f->fd, offset) ||
lseek(f->fd, offset, SEEK_SET) != offset)
return -1;
f->total = offset;
f->ctx = checkpoint->ctx;
f->offset = 0; /* hashflush() was called in checkpoint */
return 0;
}
void crc32_begin(struct hashfile *f)
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 13:06:31 +08:00
{
f->crc32 = crc32(0, NULL, 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 13:06:31 +08:00
f->do_crc = 1;
}
uint32_t crc32_end(struct hashfile *f)
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 13:06:31 +08:00
{
f->do_crc = 0;
return f->crc32;
}