setup_osutil_cffi.py

changegroup: increase write buffer size to 128k

By default, Python defers to the operating system for choosing the
default buffer size on opened files. On my Linux machine, the default
is 4k, which is really small for 2016.

This patch bumps the write buffer size when writing
changegroups/bundles to 128k. This matches the 128k read buffer
we already use on revlogs.

It's worth noting that this only impacts when writing to an explicit
file (such as during `hg bundle`). Buffers when writing to bundle
files via the repo vfs or to a temporary file are not impacted.

When producing a none-v2 bundle file of the mozilla-unified repository,
this change caused the number of write() system calls to drop from
952,449 to 29,788. After this change, the most frequent system
calls are fstat(), read(), lseek(), and open(). There were
2,523,672 system calls after this patch (so a net decrease of
~950k is statistically significant).

This change shows no performance change on my system. But I have a
high-end system with a fast SSD. It is quite possible this change
will have a significant impact on network file systems, where
extra network round trips due to excessive I/O system calls could
introduce significant latency.

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()