##// END OF EJS Templates
util: implement zstd compression engine...
util: implement zstd compression engine Now that zstd is vendored and being built (in some configurations), we can implement a compression engine for zstd! The zstd engine is a little different from existing engines. Because it may not always be present, we have to defer load the module in case importing it fails. We facilitate this via a cached property that holds a reference to the module or None. The "available" method is implemented to reflect reality. The zstd engine declares its ability to handle bundles using the "zstd" human name and the "ZS" internal name. The latter was chosen because internal names are 2 characters (by only convention I think) and "ZS" seems reasonable. The engine, like others, supports specifying the compression level. However, there are no consumers of this API that yet pass in that argument. I have plans to change that, so stay tuned. Since all we need to do to support bundle generation with a new compression engine is implement and register the compression engine, bundle generation with zstd "just works!" Tests demonstrating this have been added. How does performance of zstd for bundle generation compare? On the mozilla-unified repo, `hg bundle --all -t <engine>-v2` yields the following on my i7-6700K on Linux: engine CPU time bundle size vs orig size throughput none 97.0s 4,054,405,584 100.0% 41.8 MB/s bzip2 (l=9) 393.6s 975,343,098 24.0% 10.3 MB/s gzip (l=6) 184.0s 1,140,533,074 28.1% 22.0 MB/s zstd (l=1) 108.2s 1,119,434,718 27.6% 37.5 MB/s zstd (l=2) 111.3s 1,078,328,002 26.6% 36.4 MB/s zstd (l=3) 113.7s 1,011,823,727 25.0% 35.7 MB/s zstd (l=4) 116.0s 1,008,965,888 24.9% 35.0 MB/s zstd (l=5) 121.0s 977,203,148 24.1% 33.5 MB/s zstd (l=6) 131.7s 927,360,198 22.9% 30.8 MB/s zstd (l=7) 139.0s 912,808,505 22.5% 29.2 MB/s zstd (l=12) 198.1s 854,527,714 21.1% 20.5 MB/s zstd (l=18) 681.6s 789,750,690 19.5% 5.9 MB/s On compression, zstd for bundle generation delivers: * better compression than gzip with significantly less CPU utilization * better than bzip2 compression ratios while still being significantly faster than gzip * ability to aggressively tune compression level to achieve significantly smaller bundles That last point is important. With clone bundles, a server can pre-generate a bundle file, upload it to a static file server, and redirect clients to transparently download it during clone. The server could choose to produce a zstd bundle with the highest compression settings possible. This would take a very long time - a magnitude longer than a typical zstd bundle generation - but the result would be hundreds of megabytes smaller! For the clone volume we do at Mozilla, this could translate to petabytes of bandwidth savings per year and faster clones (due to smaller transfer size). I don't have detailed numbers to report on decompression. However, zstd decompression is fast: >1 GB/s output throughput on this machine, even through the Python bindings. And it can do that regardless of the compression level of the input. By the time you have enough data to worry about overhead of decompression, you have plenty of other things to worry about performance wise. zstd is wins all around. I can't wait to implement support for it on the wire protocol and in revlogs.

File last commit:

r28855:f5764e17 default
r30442:41a81067 default
Show More
util.c
190 lines | 4.0 KiB | text/x-c | CLexer
/*
* Utility functions
*
* Copyright (c) 2011 Yuya Nishihara <yuya@tcha.org>
*
* This software may be used and distributed according to the terms of the
* GNU General Public License version 2 or any later version.
*/
#include <errno.h>
#include <fcntl.h>
#include <signal.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#include "util.h"
static int colorenabled = 0;
static inline void fsetcolor(FILE *fp, const char *code)
{
if (!colorenabled)
return;
fprintf(fp, "\033[%sm", code);
}
static void vabortmsgerrno(int no, const char *fmt, va_list args)
{
fsetcolor(stderr, "1;31");
fputs("chg: abort: ", stderr);
vfprintf(stderr, fmt, args);
if (no != 0)
fprintf(stderr, " (errno = %d, %s)", no, strerror(no));
fsetcolor(stderr, "");
fputc('\n', stderr);
exit(255);
}
void abortmsg(const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
vabortmsgerrno(0, fmt, args);
va_end(args);
}
void abortmsgerrno(const char *fmt, ...)
{
int no = errno;
va_list args;
va_start(args, fmt);
vabortmsgerrno(no, fmt, args);
va_end(args);
}
static int debugmsgenabled = 0;
void enablecolor(void)
{
colorenabled = 1;
}
void enabledebugmsg(void)
{
debugmsgenabled = 1;
}
void debugmsg(const char *fmt, ...)
{
if (!debugmsgenabled)
return;
va_list args;
va_start(args, fmt);
fsetcolor(stderr, "1;30");
fputs("chg: debug: ", stderr);
vfprintf(stderr, fmt, args);
fsetcolor(stderr, "");
fputc('\n', stderr);
va_end(args);
}
void fchdirx(int dirfd)
{
int r = fchdir(dirfd);
if (r == -1)
abortmsgerrno("failed to fchdir");
}
void fsetcloexec(int fd)
{
int flags = fcntl(fd, F_GETFD);
if (flags < 0)
abortmsgerrno("cannot get flags of fd %d", fd);
if (fcntl(fd, F_SETFD, flags | FD_CLOEXEC) < 0)
abortmsgerrno("cannot set flags of fd %d", fd);
}
void *mallocx(size_t size)
{
void *result = malloc(size);
if (!result)
abortmsg("failed to malloc");
return result;
}
void *reallocx(void *ptr, size_t size)
{
void *result = realloc(ptr, size);
if (!result)
abortmsg("failed to realloc");
return result;
}
/*
* Execute a shell command in mostly the same manner as system(), with the
* give environment variables, after chdir to the given cwd. Returns a status
* code compatible with the Python subprocess module.
*/
int runshellcmd(const char *cmd, const char *envp[], const char *cwd)
{
enum { F_SIGINT = 1, F_SIGQUIT = 2, F_SIGMASK = 4, F_WAITPID = 8 };
unsigned int doneflags = 0;
int status = 0;
struct sigaction newsa, oldsaint, oldsaquit;
sigset_t oldmask;
/* block or mask signals just as system() does */
memset(&newsa, 0, sizeof(newsa));
newsa.sa_handler = SIG_IGN;
newsa.sa_flags = 0;
if (sigemptyset(&newsa.sa_mask) < 0)
goto done;
if (sigaction(SIGINT, &newsa, &oldsaint) < 0)
goto done;
doneflags |= F_SIGINT;
if (sigaction(SIGQUIT, &newsa, &oldsaquit) < 0)
goto done;
doneflags |= F_SIGQUIT;
if (sigaddset(&newsa.sa_mask, SIGCHLD) < 0)
goto done;
if (sigprocmask(SIG_BLOCK, &newsa.sa_mask, &oldmask) < 0)
goto done;
doneflags |= F_SIGMASK;
pid_t pid = fork();
if (pid < 0)
goto done;
if (pid == 0) {
sigaction(SIGINT, &oldsaint, NULL);
sigaction(SIGQUIT, &oldsaquit, NULL);
sigprocmask(SIG_SETMASK, &oldmask, NULL);
if (cwd && chdir(cwd) < 0)
_exit(127);
const char *argv[] = {"sh", "-c", cmd, NULL};
if (envp) {
execve("/bin/sh", (char **)argv, (char **)envp);
} else {
execv("/bin/sh", (char **)argv);
}
_exit(127);
} else {
if (waitpid(pid, &status, 0) < 0)
goto done;
doneflags |= F_WAITPID;
}
done:
if (doneflags & F_SIGINT)
sigaction(SIGINT, &oldsaint, NULL);
if (doneflags & F_SIGQUIT)
sigaction(SIGQUIT, &oldsaquit, NULL);
if (doneflags & F_SIGMASK)
sigprocmask(SIG_SETMASK, &oldmask, NULL);
/* no way to report other errors, use 127 (= shell termination) */
if (!(doneflags & F_WAITPID))
return 127;
if (WIFEXITED(status))
return WEXITSTATUS(status);
if (WIFSIGNALED(status))
return -WTERMSIG(status);
return 127;
}