mercurial/exewrapper.c

fncache: avoid loading the filename cache when not actually modifying it

With time, fncache can become very large. The mozilla-central repo for example,
has a 31M and growing fncache file. Loading this file takes time (280ms for the
mozilla-central repository).

In many scenarios, we don't need to load fncache at all. For example, when
committing changes to existing files, or pushing such commits to another clone.
This patch detects when a name is added via store.vfs(), and only loads the
cache if a) the data metadata file doesn't already exist, or b) when opening
for appending, the data or metadata file exists but has size  (a transaction
rollback leaves behind such files).

Benchmarks (run on Macos 10.13 on a 2017-model Macbook Pro with Core i7 2.9GHz
and flash drive), each test without and with patch run 5 times:

* committing to an existing file, against the mozilla-central repository.
  Baseline real time average 2.3736, with patch 1.9884.

* unbundling a large changeset consisting *only* of existing-file modifications
  (159 revisions, 1050 modifications, mozilla-central
  4a250a0e4f29:beea9ac7d823), into a clone limited to the ancestor revision of
  that revset). Baseline real time average 1.5048, with patch 1.3108.

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

 Copyright 2012 Adrian Buehlmann <[e-mail]> 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;

	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 .\hg-python exists. We are probably in HackableMercurial
		scenario, so let's load python dll from this dir. */
		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;
}