##// END OF EJS Templates
upstream » mercurial-mirror
RSS

Clone from https://www.mercurial-scm.org/repo/hg-all

xdiff: add a preprocessing step that trims files...
xdiff: add a preprocessing step that trims files xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable lines. That is in theory good, but happens too late - after splitting, hashing, and adjusting the hash values so they are unique. Those splitting, hashing and adjusting hash values steps could have noticeable overhead. Diffing two large files with minor (one-line-ish) changes are not uncommon. In that case, the raw performance of those preparation steps seriously matter. Even allocating an O(N) array and storing line offsets to it is expensive. Therefore my previous attempts [1] [2] cannot be good enough since they do not remove the O(N) array assignment. This patch adds a preprocessing step - `xdl_trim_files` that runs before other preprocessing steps. It counts common prefix and suffix and lines in them (needed for displaying line number), without doing anything else. Testing with a crafted large (169MB) file, with minor change: ``` open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6000000)) open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6003000)) ``` Running xdiff by a simple binary [3], this patch improves the xdiff perf by more than 10x for the above case: ``` # xdiff before this patch 2.41s user 1.13s system 98% cpu 3.592 total # xdiff after this patch 0.14s user 0.16s system 98% cpu 0.309 total # gnu diffutils 0.12s user 0.15s system 98% cpu 0.272 total # (best of 20 runs) ``` It's still slightly slower than GNU diffutils. But it's pretty close now. Testing with real repo data: For the whole repo, this patch makes xdiff 25% faster: ``` # hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff] # xdiff, after ! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) # xdiff, before ! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91) # bdiff ! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67) ``` For files that are long (ex. commands.py), the speedup is more than 3x, very significant: ``` # hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff] # xdiff, after ! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12) # xdiff, before ! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4) # bdiff ! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4) ``` [1]: https://phab.mercurial-scm.org/D2631 [2]: https://phab.mercurial-scm.org/D2634 [3]: ``` // Code to run xdiff from command line. No proper error handling. #include <stdlib.h> #include <unistd.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include "mercurial/thirdparty/xdiff/xdiff.h" #define ensure(x) if (!(x)) exit(255); mmfile_t readfile(const char *path) { struct stat st; int fd = open(path, O_RDONLY); fstat(fd, &st); mmfile_t file = { malloc(st.st_size), st.st_size }; ensure(read(fd, file.ptr, st.st_size) == st.st_size); close(fd); return file; } int main(int argc, char const *argv[]) { mmfile_t a = readfile(argv[1]), b = readfile(argv[2]); xpparam_t xpp = {0}; xdemitconf_t xecfg = {0}; xdemitcb_t ecb = {0}; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; } ``` Differential Revision: https://phab.mercurial-scm.org/D2686
Yuya Nishihara - - Load All Authors

File last commit:

r32506:2dcb3d52 default
r36838:f33a87cf default
Show More
osutilbuild.py
102 lines | 2.4 KiB | text/x-python | PythonLexer
/ mercurial / cffi / osutilbuild.py
History | Annotation | Raw |Copy content |Copy permalink
from __future__ import absolute_import
import cffi
ffi = cffi.FFI()
ffi.set_source("mercurial.cffi._osutil", """
#include <sys/attr.h>
#include <sys/vnode.h>
#include <unistd.h>
#include <fcntl.h>
#include <time.h>
typedef struct val_attrs {
uint32_t length;
attribute_set_t returned;
attrreference_t name_info;
fsobj_type_t obj_type;
struct timespec mtime;
uint32_t accessmask;
off_t datalength;
} __attribute__((aligned(4), packed)) val_attrs_t;
""", include_dirs=['mercurial'])
ffi.cdef('''
typedef uint32_t attrgroup_t;
typedef struct attrlist {
uint16_t bitmapcount; /* number of attr. bit sets in list */
uint16_t reserved; /* (to maintain 4-byte alignment) */
attrgroup_t commonattr; /* common attribute group */
attrgroup_t volattr; /* volume attribute group */
attrgroup_t dirattr; /* directory attribute group */
attrgroup_t fileattr; /* file attribute group */
attrgroup_t forkattr; /* fork attribute group */
...;
};
typedef struct attribute_set {
...;
} attribute_set_t;
typedef struct attrreference {
int attr_dataoffset;
int attr_length;
...;
} attrreference_t;
typedef int ... off_t;
typedef struct val_attrs {
uint32_t length;
attribute_set_t returned;
attrreference_t name_info;
uint32_t obj_type;
struct timespec mtime;
uint32_t accessmask;
off_t datalength;
...;
} val_attrs_t;
/* the exact layout of the above struct will be figured out during build time */
typedef int ... time_t;
typedef struct timespec {
time_t tv_sec;
...;
};
int getattrlist(const char* path, struct attrlist * attrList, void * attrBuf,
size_t attrBufSize, unsigned int options);
int getattrlistbulk(int dirfd, struct attrlist * attrList, void * attrBuf,
size_t attrBufSize, uint64_t options);
#define ATTR_BIT_MAP_COUNT ...
#define ATTR_CMN_NAME ...
#define ATTR_CMN_OBJTYPE ...
#define ATTR_CMN_MODTIME ...
#define ATTR_CMN_ACCESSMASK ...
#define ATTR_CMN_ERROR ...
#define ATTR_CMN_RETURNED_ATTRS ...
#define ATTR_FILE_DATALENGTH ...
#define VREG ...
#define VDIR ...
#define VLNK ...
#define VBLK ...
#define VCHR ...
#define VFIFO ...
#define VSOCK ...
#define S_IFMT ...
int open(const char *path, int oflag, int perm);
int close(int);
#define O_RDONLY ...
''')
if __name__ == '__main__':
ffi.compile()