view mercurial/bitmanipulation.h @ 39576:84bf6ded9317

wireprotoframing: buffer emitted data to reduce frame count

An upcoming commit introduces a wire protocol command that can emit
hundreds of thousands of small objects. Without a buffering layer,
we would emit a single, small frame for every object. Performance
profiling revealed this to be a source of significant overhead for
both client and server.

This commit introduces a very crude buffering layer so that we emit
fewer, bigger frames in such a scenario. This code will likely get
rewritten in the future to be part of the streams API, as we'll
need a similar strategy for compressing data. I don't want to think
about it too much at the moment though.

server
before: user 32.500+0.000 sys 1.160+0.000
after:  user 20.230+0.010 sys 0.180+0.000

client
before: user 133.400+0.000 sys 93.120+0.000
after:  user  68.370+0.000 sys 32.950+0.000

This appears to indicate we have significant overhead in the frame
processing code on both client and server. It might be worth profiling
that at some point...

Differential Revision: https://phab.mercurial-scm.org/D4473

#ifndef _HG_BITMANIPULATION_H_
#define _HG_BITMANIPULATION_H_

#include <string.h>

#include "compat.h"

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]));
}

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