Mercurial > hg
view setup_osutil_cffi.py @ 30288:ceddc3d94d74
revlog: inline start() and end() for perf reasons
When I implemented `hg perfrevlogchunks`, one of the things that
stood out was N * _chunk() calls was ~38x slower than 1
_chunks() call. Specifically, on the mozilla-unified repo:
N*_chunk: 0.528997s
1*_chunks: 0.013735s
This repo has 352,097 changesets. So the average time per changeset
comes out to:
N*_chunk: 1.502us
1*_chunks: 0.039us
If you extrapolate these numbers to a repository with 1M changesets,
that comes out to 1.502s versus 0.039s, which is significant.
At these latencies, Python attribute lookups and function calls
matter. So, this patch inlines some code to cut down on that overhead.
The impact of this patch on N*_chunk() calls is clear:
! wall 0.528997 comb 0.520000 user 0.500000 sys 0.020000 (best of 19)
! wall 0.367723 comb 0.370000 user 0.350000 sys 0.020000 (best of 27)
So, we go from ~38x slower to ~27x. A nice improvement. But there's
still a long way to go.
It's worth noting that functionality like revsets perform changelog
lookups one revision at a time. So this code path is worth optimizing.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sat, 22 Oct 2016 15:41:23 -0700 |
parents | a043c6d372db |
children |
line wrap: on
line source
from __future__ import absolute_import import cffi ffi = cffi.FFI() ffi.set_source("_osutil_cffi", """ #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()