##// END OF EJS Templates
util: optimize cost auditing on insert...
util: optimize cost auditing on insert Calling popoldest() on insert with cost auditing enabled introduces significant overhead. The primary reason for this overhead is that popoldest() needs to walk the linked list to find the first non-empty node. When we call popoldest() within a loop, this can become quadratic. The performance impact is more pronounced on caches with large capacities. This commit effectively inlines the popoldest() call into _enforcecostlimit(). By doing so, we only do the backwards walk to find the first empty node once. However, we still may still perform this work on insert when the cache is near cost capacity. So this is only a partial performance win. $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! gets w/ cost limit ! wall 0.598737 comb 0.590000 user 0.590000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 1.694282 comb 1.700000 user 1.700000 sys 0.000000 (best of 6) ! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7) ! mixed w/ cost limit ! wall 1.157655 comb 1.150000 user 1.150000 sys 0.000000 (best of 9) ! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! gets w/ cost limit ! wall 0.598526 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.601993 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.838315 comb 37.840000 user 37.840000 sys 0.000000 (best of 3) ! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 18.060198 comb 18.060000 user 18.060000 sys 0.000000 (best of 3) ! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! gets w/ cost limit ! wall 0.600024 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.614439 comb 0.620000 user 0.620000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.154547 comb 37.120000 user 37.120000 sys 0.000000 (best of 3) ! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 4.381602 comb 4.380000 user 4.370000 sys 0.010000 (best of 3) ! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4) Differential Revision: https://phab.mercurial-scm.org/D4504

File last commit:

r32506:2dcb3d52 default
r39605:cc23c09b default
Show More
osutilbuild.py
102 lines | 2.4 KiB | text/x-python | PythonLexer
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()