git/fsck.h
René Scharfe 3b41fb0cb2 fsck: use oidset instead of oid_array for skipList
Change the implementation of the skipList feature to use oidset
instead of oid_array to store SHA-1s for later lookup.

This list is parsed once on startup by fsck, fetch-pack or
receive-pack depending on the *.skipList config in use. I.e. only once
per invocation, but note that for "clone --recurse-submodules" each
submodule will re-parse the list, in addition to the main project, and
it will be re-parsed when checking .gitmodules blobs, see
fb16287719 ("fsck: check skiplist for object in fsck_blob()",
2018-06-27).

Memory usage is a bit higher, but we don't need to keep track of the
sort order anymore. Embed the oidset into struct fsck_options to make
its ownership clear (no hidden sharing) and avoid unnecessary pointer
indirection.

The cumulative impact on performance of this & the preceding change,
using the test setup described in the previous commit:

    Test                                             HEAD~2            HEAD~                   HEAD
    ----------------------------------------------------------------------------------------------------------------
    1450.3: fsck with 0 skipped bad commits          7.70(7.31+0.38)   7.72(7.33+0.38) +0.3%   7.70(7.30+0.40) +0.0%
    1450.5: fsck with 1 skipped bad commits          7.84(7.47+0.37)   7.69(7.32+0.36) -1.9%   7.71(7.29+0.41) -1.7%
    1450.7: fsck with 10 skipped bad commits         7.81(7.40+0.40)   7.94(7.57+0.36) +1.7%   7.92(7.55+0.37) +1.4%
    1450.9: fsck with 100 skipped bad commits        7.81(7.42+0.38)   7.95(7.53+0.41) +1.8%   7.83(7.42+0.41) +0.3%
    1450.11: fsck with 1000 skipped bad commits      7.99(7.62+0.36)   7.90(7.50+0.40) -1.1%   7.86(7.49+0.37) -1.6%
    1450.13: fsck with 10000 skipped bad commits     7.98(7.57+0.40)   7.94(7.53+0.40) -0.5%   7.90(7.45+0.44) -1.0%
    1450.15: fsck with 100000 skipped bad commits    7.97(7.57+0.39)   8.03(7.67+0.36) +0.8%   7.84(7.43+0.41) -1.6%
    1450.17: fsck with 1000000 skipped bad commits   7.72(7.22+0.50)   7.28(7.07+0.20) -5.7%   7.13(6.87+0.25) -7.6%

Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Rene Scharfe <l.s.r@web.de>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-09-12 15:17:46 -07:00

67 lines
2.0 KiB
C

#ifndef GIT_FSCK_H
#define GIT_FSCK_H
#include "oidset.h"
#define FSCK_ERROR 1
#define FSCK_WARN 2
#define FSCK_IGNORE 3
struct fsck_options;
struct object;
void fsck_set_msg_type(struct fsck_options *options,
const char *msg_id, const char *msg_type);
void fsck_set_msg_types(struct fsck_options *options, const char *values);
int is_valid_msg_type(const char *msg_id, const char *msg_type);
/*
* callback function for fsck_walk
* type is the expected type of the object or OBJ_ANY
* the return value is:
* 0 everything OK
* <0 error signaled and abort
* >0 error signaled and do not abort
*/
typedef int (*fsck_walk_func)(struct object *obj, int type, void *data, struct fsck_options *options);
/* callback for fsck_object, type is FSCK_ERROR or FSCK_WARN */
typedef int (*fsck_error)(struct fsck_options *o,
struct object *obj, int type, const char *message);
int fsck_error_function(struct fsck_options *o,
struct object *obj, int type, const char *message);
struct fsck_options {
fsck_walk_func walk;
fsck_error error_func;
unsigned strict:1;
int *msg_type;
struct oidset skiplist;
struct decoration *object_names;
};
#define FSCK_OPTIONS_DEFAULT { NULL, fsck_error_function, 0, NULL, OIDSET_INIT }
#define FSCK_OPTIONS_STRICT { NULL, fsck_error_function, 1, NULL, OIDSET_INIT }
/* descend in all linked child objects
* the return value is:
* -1 error in processing the object
* <0 return value of the callback, which lead to an abort
* >0 return value of the first signaled error >0 (in the case of no other errors)
* 0 everything OK
*/
int fsck_walk(struct object *obj, void *data, struct fsck_options *options);
/* If NULL is passed for data, we assume the object is local and read it. */
int fsck_object(struct object *obj, void *data, unsigned long size,
struct fsck_options *options);
/*
* Some fsck checks are context-dependent, and may end up queued; run this
* after completing all fsck_object() calls in order to resolve any remaining
* checks.
*/
int fsck_finish(struct fsck_options *options);
#endif