bundle2: inline changegroup.readexactly()
Profiling reveals this loop is pretty tight. Literally any
function call elimination can make a big difference.
This commit inlines the relatively trivial changegroup.readexactly()
method inside the loop.
The results with `hg perfbundleread` on a bundle of the Firefox repo
speak for themselves:
! read(8k)
! wall 0.679730 comb 0.680000 user 0.140000 sys 0.540000 (best of 15)
! read(16k)
! wall 0.577228 comb 0.570000 user 0.080000 sys 0.490000 (best of 17)
! read(32k)
! wall 0.516060 comb 0.520000 user 0.040000 sys 0.480000 (best of 20)
! read(128k)
! wall 0.496378 comb 0.490000 user 0.010000 sys 0.480000 (best of 20)
! bundle2 iterparts()
! wall 3.460903 comb 3.460000 user 2.760000 sys 0.700000 (best of 3)
! wall 3.056811 comb 3.050000 user 2.340000 sys 0.710000 (best of 4)
! bundle2 iterparts() seekable
! wall 4.312722 comb 4.310000 user 3.480000 sys 0.830000 (best of 3)
! wall 4.007676 comb 4.000000 user 3.170000 sys 0.830000 (best of 3)
! bundle2 part seek()
! wall 6.754764 comb 6.740000 user 3.970000 sys 2.770000 (best of 3)
! wall 6.267110 comb 6.250000 user 3.480000 sys 2.770000 (best of 3)
! bundle2 part read(8k)
! wall 3.668004 comb 3.660000 user 2.960000 sys 0.700000 (best of 3)
! wall 3.404164 comb 3.400000 user 2.650000 sys 0.750000 (best of 3)
! bundle2 part read(16k)
! wall 3.489196 comb 3.480000 user 2.750000 sys 0.730000 (best of 3)
! wall 3.197972 comb 3.200000 user 2.490000 sys 0.710000 (best of 4)
! bundle2 part read(32k)
! wall 3.388569 comb 3.380000 user 2.640000 sys 0.740000 (best of 3)
! wall 3.060557 comb 3.060000 user 2.340000 sys 0.720000 (best of 4)
! bundle2 part read(128k)
! wall 3.276415 comb 3.270000 user 2.560000 sys 0.710000 (best of 4)
! wall 2.952209 comb 2.950000 user 2.230000 sys 0.720000 (best of 4)
Differential Revision: https://phab.mercurial-scm.org/D1392
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()