mercurial/bitmanipulation.h

stream-clone: avoid opening a revlog in case we do not need it

Opening an revlog has a cost, especially if it is inline as we have to scan the
file and construct an index.

To prevent the associated slowdown, we just do a minimal scan to check that an
inline file is still inline, and simply stream the file without creating a
revlog when we can.

This provides a big boost compared to the previous changeset, even if the full
generation is still penalized by the initial gathering of information.

All benchmarks are run on linux with Python 3.10.7.
# benchmark.name             = hg.exchange.stream.generate
# benchmark.variants.version = v2

### Compared to the previous changesets

We get a large win all across the board!

# mercurial-2018-08-01-zstd-sparse-revlog
before:  0.250694 seconds
after:   0.105986 seconds  (-57.72%)
# pypy-2018-08-01-zstd-sparse-revlog
before:  3.885657 seconds
after:   1.709748 seconds  (-56.00%)
# netbeans-2018-08-01-zstd-sparse-revlog
before: 16.679371 seconds
after:   7.687469 seconds  (-53.91%)
# mozilla-central-2018-08-01-zstd-sparse-revlog
before: 38.575482 seconds
after:  17.520316 seconds  (-54.58%)
# mozilla-try-2019-02-18-zstd-sparse-revlog
before: 81.160994 seconds
after:  37.073753 seconds  (-54.32%)



### Compared to 6.4.3

We are still significantly slower than 6.4.3, the extra time is usually twice
slower than the extra time we observe on the locked section, which is a quite
interesting information.

Except for mercurial-central that is much faster. That discrepancy is not really
explained yet.

# mercurial-2018-08-01-zstd-sparse-revlog
6.4.3:  0.072560 seconds
after:  0.105986 seconds  (+46.07%) (- 0.03 seconds)
# pypy-2018-08-01-zstd-sparse-revlog
6.4.3:  1.211193 seconds
after:  1.709748 seconds  (+41.16%) (-0.45 seconds)
# netbeans-2018-08-01-zstd-sparse-revlog
6.4.3:  4.932843 seconds
after:  7.687469 seconds  (+55.84%) (-2.75 seconds)
# mozilla-central-2018-08-01-zstd-sparse-revlog
6.4.3: 34.012226 seconds
after: 17.520316 seconds  (-48.49%) (-16.49 seconds)
# mozilla-try-2019-02-18-zstd-sparse-revlog
6.4.3: 23.850555 seconds
after: 37.073753 seconds  (+55.44%) (+13.22 seconds)

#ifndef HG_BITMANIPULATION_H
#define HG_BITMANIPULATION_H

#include <string.h>

#include "compat.h"

/* Reads a 64 bit integer from big-endian bytes. Assumes that the data is long
 enough */
static inline uint64_t getbe64(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((((uint64_t)d[0]) << 56) | (((uint64_t)d[1]) << 48) |
	        (((uint64_t)d[2]) << 40) | (((uint64_t)d[3]) << 32) |
	        (((uint64_t)d[4]) << 24) | (((uint64_t)d[5]) << 16) |
	        (((uint64_t)d[6]) << 8) | (d[7]));
}

static inline uint32_t getbe32(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((((uint32_t)d[0]) << 24) | (((uint32_t)d[1]) << 16) |
	        (((uint32_t)d[2]) << 8) | (d[3]));
}

static inline int16_t getbeint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

static inline uint16_t getbeuint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

/* Writes a 64 bit integer to bytes in a big-endian format.
 Assumes that the buffer is long enough */
static inline void putbe64(uint64_t x, char *c)
{
	c[0] = (x >> 56) & 0xff;
	c[1] = (x >> 48) & 0xff;
	c[2] = (x >> 40) & 0xff;
	c[3] = (x >> 32) & 0xff;
	c[4] = (x >> 24) & 0xff;
	c[5] = (x >> 16) & 0xff;
	c[6] = (x >> 8) & 0xff;
	c[7] = (x)&0xff;
}

static inline void putbe32(uint32_t x, char *c)
{
	c[0] = (x >> 24) & 0xff;
	c[1] = (x >> 16) & 0xff;
	c[2] = (x >> 8) & 0xff;
	c[3] = (x)&0xff;
}

static inline double getbefloat64(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;
	double ret;
	int i;
	uint64_t t = 0;
	for (i = 0; i < 8; i++) {
		t = (t << 8) + d[i];
	}
	memcpy(&ret, &t, sizeof(t));
	return ret;
}

#endif