view mercurial/bitmanipulation.h @ 49622:dcb2581e33be stable

memory-usage: fix `hg log --follow --rev R F` space complexity

When running `hg log --follow --rev REVS FILES`, the log code will walk the
history of all FILES starting from the file revisions that exists in each REVS.

Before doing so, it looks if the files actually exists in the target revisions.
To do so, it opens the manifest of each revision in REVS to look up if we find
the associated items in FILES.

Before this changeset this was done in a way that created a changectx for
each target revision, keeping them in memory while we look into each file.

If the set of REVS is large, this means keeping the manifest for each entry in
REVS in memory. That can be large… if REV is in the form `::X`, this can quickly
become huge and saturate the memory. We have seen usage allocating 2GB per
second until memory runs out.

So this changeset invert the two loop so that only one revision is kept in
memory during the operation. This solve the memory explosion issue.

#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