setup_mpatch_cffi.py

revlog: optimize _chunkraw when startrev==endrev

In many cases, _chunkraw() is called with startrev==endrev. When
this is true, we can avoid an extra index lookup and some other
minor operations.

On the mozilla-unified repo, `hg perfrevlogchunks -c` says this
has the following impact:

! read w/ reused fd
! wall 0.371846 comb 0.370000 user 0.350000 sys 0.020000 (best of 27)
! wall 0.337930 comb 0.330000 user 0.300000 sys 0.030000 (best of 30)

! read batch w/ reused fd
! wall 0.014952 comb 0.020000 user 0.000000 sys 0.020000 (best of 197)
! wall 0.014866 comb 0.010000 user 0.000000 sys 0.010000 (best of 196)

So, we've gone from ~25x slower than batch to ~22.5x slower.

At this point, there's probably not much else we can do except
implement an optimized function in the index itself, including in C.

from __future__ import absolute_import

import cffi
import os

ffi = cffi.FFI()
mpatch_c = os.path.join(os.path.join(os.path.dirname(__file__), 'mercurial',
                                     'mpatch.c'))
ffi.set_source("_mpatch_cffi", open(mpatch_c).read(),
               include_dirs=["mercurial"])
ffi.cdef("""

struct mpatch_frag {
       int start, end, len;
       const char *data;
};

struct mpatch_flist {
       struct mpatch_frag *base, *head, *tail;
};

extern "Python" struct mpatch_flist* cffi_get_next_item(void*, ssize_t);

int mpatch_decode(const char *bin, ssize_t len, struct mpatch_flist** res);
ssize_t mpatch_calcsize(size_t len, struct mpatch_flist *l);
void mpatch_lfree(struct mpatch_flist *a);
static int mpatch_apply(char *buf, const char *orig, size_t len,
                        struct mpatch_flist *l);
struct mpatch_flist *mpatch_fold(void *bins,
                       struct mpatch_flist* (*get_next_item)(void*, ssize_t),
                       ssize_t start, ssize_t end);
""")

if __name__ == '__main__':
    ffi.compile()