view mercurial/exewrapper.c @ 30451:94ca0e13d1fc

perf: add command for measuring revlog chunk operations Upcoming commits will teach revlogs to leverage the new compression engine API so that new compression formats can more easily be leveraged in revlogs. We want to be sure this refactoring doesn't regress performance. So this commit introduces "perfrevchunks" to explicitly test performance of reading, decompressing, and recompressing revlog chunks. Here is output when run on the mozilla-unified repo: $ hg perfrevlogchunks -c ! read ! wall 0.346603 comb 0.350000 user 0.340000 sys 0.010000 (best of 28) ! read w/ reused fd ! wall 0.337707 comb 0.340000 user 0.320000 sys 0.020000 (best of 30) ! read batch ! wall 0.013206 comb 0.020000 user 0.000000 sys 0.020000 (best of 221) ! read batch w/ reused fd ! wall 0.013259 comb 0.030000 user 0.010000 sys 0.020000 (best of 222) ! chunk ! wall 1.909939 comb 1.910000 user 1.900000 sys 0.010000 (best of 6) ! chunk batch ! wall 1.750677 comb 1.760000 user 1.740000 sys 0.020000 (best of 6) ! compress ! wall 5.668004 comb 5.670000 user 5.670000 sys 0.000000 (best of 3) $ hg perfrevlogchunks -m ! read ! wall 0.365834 comb 0.370000 user 0.350000 sys 0.020000 (best of 26) ! read w/ reused fd ! wall 0.350160 comb 0.350000 user 0.320000 sys 0.030000 (best of 28) ! read batch ! wall 0.024777 comb 0.020000 user 0.000000 sys 0.020000 (best of 119) ! read batch w/ reused fd ! wall 0.024895 comb 0.030000 user 0.000000 sys 0.030000 (best of 118) ! chunk ! wall 2.514061 comb 2.520000 user 2.480000 sys 0.040000 (best of 4) ! chunk batch ! wall 2.380788 comb 2.380000 user 2.360000 sys 0.020000 (best of 5) ! compress ! wall 9.815297 comb 9.820000 user 9.820000 sys 0.000000 (best of 3) We already see some interesting data, such as how much slower non-batched chunk reading is and that zlib compression appears to be >2x slower than decompression. I didn't have the data when I wrote this commit message, but I ran this on Mozilla's NFS-based Mercurial server and the time for reading with a reused file descriptor was faster. So I think it is worth testing both with and without file descriptor reuse so we can make informed decisions about recycling file descriptors.
author Gregory Szorc <gregory.szorc@gmail.com>
date Thu, 17 Nov 2016 20:17:51 -0800
parents 210bb28ca4fb
children 0241dd94ed38
line wrap: on
line source

/*
 exewrapper.c - wrapper for calling a python script on Windows

 Copyright 2012 Adrian Buehlmann <adrian@cadifra.com> and others

 This software may be used and distributed according to the terms of the
 GNU General Public License version 2 or any later version.
*/

#include <stdio.h>
#include <windows.h>

#include "hgpythonlib.h"

#ifdef __GNUC__
int strcat_s(char *d, size_t n, const char *s)
{
	return !strncat(d, s, n);
}
int strcpy_s(char *d, size_t n, const char *s)
{
	return !strncpy(d, s, n);
}
#endif


static char pyscript[MAX_PATH + 10];
static char pyhome[MAX_PATH + 10];
static char envpyhome[MAX_PATH + 10];
static char pydllfile[MAX_PATH + 10];

int main(int argc, char *argv[])
{
	char *p;
	int ret;
	int i;
	int n;
	char **pyargv;
	WIN32_FIND_DATA fdata;
	HANDLE hfind;
	const char *err;
	HMODULE pydll;
	void (__cdecl *Py_SetPythonHome)(char *home);
	int (__cdecl *Py_Main)(int argc, char *argv[]);

	if (GetModuleFileName(NULL, pyscript, sizeof(pyscript)) == 0)
	{
		err = "GetModuleFileName failed";
		goto bail;
	}

	p = strrchr(pyscript, '.');
	if (p == NULL) {
		err = "malformed module filename";
		goto bail;
	}
	*p = 0; /* cut trailing ".exe" */
	strcpy_s(pyhome, sizeof(pyhome), pyscript);

	hfind = FindFirstFile(pyscript, &fdata);
	if (hfind != INVALID_HANDLE_VALUE) {
		/* pyscript exists, close handle */
		FindClose(hfind);
	} else {
		/* file pyscript isn't there, take <pyscript>exe.py */
		strcat_s(pyscript, sizeof(pyscript), "exe.py");
	}

	pydll = NULL;
	/*
	We first check, that environment variable PYTHONHOME is *not* set.
	This just mimicks the behavior of the regular python.exe, which uses
	PYTHONHOME to find its installation directory (if it has been set).
	Note: Users of HackableMercurial are expected to *not* set PYTHONHOME!
	*/
	if (GetEnvironmentVariable("PYTHONHOME", envpyhome,
				   sizeof(envpyhome)) == 0)
	{
		/*
		Environment var PYTHONHOME is *not* set. Let's see if we are
		running inside a HackableMercurial.
		*/

		p = strrchr(pyhome, '\\');
		if (p == NULL) {
			err = "can't find backslash in module filename";
			goto bail;
		}
		*p = 0; /* cut at directory */

		/* check for private Python of HackableMercurial */
		strcat_s(pyhome, sizeof(pyhome), "\\hg-python");

		hfind = FindFirstFile(pyhome, &fdata);
		if (hfind != INVALID_HANDLE_VALUE) {
			/* path pyhome exists, let's use it */
			FindClose(hfind);
			strcpy_s(pydllfile, sizeof(pydllfile), pyhome);
			strcat_s(pydllfile, sizeof(pydllfile),
				 "\\" HGPYTHONLIB ".dll");
			pydll = LoadLibrary(pydllfile);
			if (pydll == NULL) {
				err = "failed to load private Python DLL "
				      HGPYTHONLIB ".dll";
				goto bail;
			}
			Py_SetPythonHome = (void*)GetProcAddress(pydll,
							"Py_SetPythonHome");
			if (Py_SetPythonHome == NULL) {
				err = "failed to get Py_SetPythonHome";
				goto bail;
			}
			Py_SetPythonHome(pyhome);
		}
	}

	if (pydll == NULL) {
		pydll = LoadLibrary(HGPYTHONLIB ".dll");
		if (pydll == NULL) {
			err = "failed to load Python DLL " HGPYTHONLIB ".dll";
			goto bail;
		}
	}

	Py_Main = (void*)GetProcAddress(pydll, "Py_Main");
	if (Py_Main == NULL) {
		err = "failed to get Py_Main";
		goto bail;
	}

	/*
	Only add the pyscript to the args, if it's not already there. It may
	already be there, if the script spawned a child process of itself, in
	the same way as it got called, that is, with the pyscript already in
	place. So we optionally accept the pyscript as the first argument
	(argv[1]), letting our exe taking the role of the python interpreter.
	*/
	if (argc >= 2 && strcmp(argv[1], pyscript) == 0) {
		/*
		pyscript is already in the args, so there is no need to copy
		the args and we can directly call the python interpreter with
		the original args.
		*/
		return Py_Main(argc, argv);
	}

	/*
	Start assembling the args for the Python interpreter call. We put the
	name of our exe (argv[0]) in the position where the python.exe
	canonically is, and insert the pyscript next.
	*/
	pyargv = malloc((argc + 5) * sizeof(char*));
	if (pyargv == NULL) {
		err = "not enough memory";
		goto bail;
	}
	n = 0;
	pyargv[n++] = argv[0];
	pyargv[n++] = pyscript;

	/* copy remaining args from the command line */
	for (i = 1; i < argc; i++)
		pyargv[n++] = argv[i];
	/* argv[argc] is guaranteed to be NULL, so we forward that guarantee */
	pyargv[n] = NULL;

	ret = Py_Main(n, pyargv); /* The Python interpreter call */

	free(pyargv);
	return ret;

bail:
	fprintf(stderr, "abort: %s\n", err);
	return 255;
}