view setup_osutil_cffi.py @ 29830:92ac2baaea86

revlog: use an LRU cache for delta chain bases

Profiling using statprof revealed a hotspot during changegroup
application calculating delta chain bases on generaldelta repos.
Essentially, revlog._addrevision() was performing a lot of redundant
work tracing the delta chain as part of determining when the chain
distance was acceptable. This was most pronounced when adding
revisions to manifests, which can have delta chains thousands of
revisions long.

There was a delta chain base cache on revlogs before, but it only
captured a single revision. This was acceptable before generaldelta,
when _addrevision would build deltas from the previous revision and
thus we'd pretty much guarantee a cache hit when resolving the delta
chain base on a subsequent _addrevision call. However, it isn't
suitable for generaldelta because parent revisions aren't necessarily
the last processed revision.

This patch converts the delta chain base cache to an LRU dict cache.
The cache can hold multiple entries, so generaldelta repos have a
higher chance of getting a cache hit.

The impact of this change when processing changegroup additions is
significant. On a generaldelta conversion of the "mozilla-unified"
repo (which contains heads of the main Firefox repositories in
chronological order - this means there are lots of transitions between
heads in revlog order), this change has the following impact when
performing an `hg unbundle` of an uncompressed bundle of the repo:

before: 5:42 CPU time
after:  4:34 CPU time

Most of this time is saved when applying the changelog and manifest
revlogs:

before: 2:30 CPU time
after:  1:17 CPU time

That nearly a 50% reduction in CPU time applying changesets and
manifests!

Applying a gzipped bundle of the same repo (effectively simulating a
`hg clone` over HTTP) showed a similar speedup:

before: 5:53 CPU time
after:  4:46 CPU time

Wall time improvements were basically the same as CPU time.

I didn't measure explicitly, but it feels like most of the time
is saved when processing manifests. This makes sense, as large
manifests tend to have very long delta chains and thus benefit the
most from this cache.

So, this change effectively makes changegroup application (which is
used by `hg unbundle`, `hg clone`, `hg pull`, `hg unshelve`, and
various other commands) significantly faster when delta chains are
long (which can happen on repos with large numbers of files and thus
large manifests).

In theory, this change can result in more memory utilization. However,
we're caching a dict of ints. At most we have 200 ints + Python object
overhead per revlog. And, the cache is really only populated when
performing read-heavy operations, such as adding changegroups or
scanning an individual revlog. For memory bloat to be an issue, we'd
need to scan/read several revisions from several revlogs all while
having active references to several revlogs. I don't think there are
many operations that do this, so I don't think memory bloat from the
cache will be an issue.

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 struct val_attrs {
    uint32_t          length;
    attribute_set_t   returned;
    attrreference_t   name_info;
    uint32_t          obj_type;
    struct timespec   mtime;
    uint32_t          accessmask;
    int               datalength;
    ...;
} val_attrs_t;

/* the exact layout of the above struct will be figured out during build time */

typedef int ... time_t;
typedef int ... off_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()