git/builtin/prune.c
Jeff King d3038d22f9 prune: keep objects reachable from recent objects
Our current strategy with prune is that an object falls into
one of three categories:

  1. Reachable (from ref tips, reflogs, index, etc).

  2. Not reachable, but recent (based on the --expire time).

  3. Not reachable and not recent.

We keep objects from (1) and (2), but prune objects in (3).
The point of (2) is that these objects may be part of an
in-progress operation that has not yet updated any refs.

However, it is not always the case that objects for an
in-progress operation will have a recent mtime. For example,
the object database may have an old copy of a blob (from an
abandoned operation, a branch that was deleted, etc). If we
create a new tree that points to it, a simultaneous prune
will leave our tree, but delete the blob. Referencing that
tree with a commit will then work (we check that the tree is
in the object database, but not that all of its referred
objects are), as will mentioning the commit in a ref. But
the resulting repo is corrupt; we are missing the blob
reachable from a ref.

One way to solve this is to be more thorough when
referencing a sha1: make sure that not only do we have that
sha1, but that we have objects it refers to, and so forth
recursively. The problem is that this is very expensive.
Creating a parent link would require traversing the entire
object graph!

Instead, this patch pushes the extra work onto prune, which
runs less frequently (and has to look at the whole object
graph anyway). It creates a new category of objects: objects
which are not recent, but which are reachable from a recent
object. We do not prune these objects, just like the
reachable and recent ones.

This lets us avoid the recursive check above, because if we
have an object, even if it is unreachable, we should have
its referent. We can make a simple inductive argument that
with this patch, this property holds (that there are no
objects with missing referents in the repository):

  0. When we have no objects, we have nothing to refer or be
     referred to, so the property holds.

  1. If we add objects to the repository, their direct
     referents must generally exist (e.g., if you create a
     tree, the blobs it references must exist; if you create
     a commit to point at the tree, the tree must exist).
     This is already the case before this patch. And it is
     not 100% foolproof (you can make bogus objects using
     `git hash-object`, for example), but it should be the
     case for normal usage.

     Therefore for any sequence of object additions, the
     property will continue to hold.

  2. If we remove objects from the repository, then we will
     not remove a child object (like a blob) if an object
     that refers to it is being kept. That is the part
     implemented by this patch.

     Note, however, that our reachability check and the
     actual pruning are not atomic. So it _is_ still
     possible to violate the property (e.g., an object
     becomes referenced just as we are deleting it). This
     patch is shooting for eliminating problems where the
     mtimes of dependent objects differ by hours or days,
     and one is dropped without the other. It does nothing
     to help with short races.

Naively, the simplest way to implement this would be to add
all recent objects as tips to the reachability traversal.
However, this does not perform well. In a recently-packed
repository, all reachable objects will also be recent, and
therefore we have to look at each object twice. This patch
instead performs the reachability traversal, then follows up
with a second traversal for recent objects, skipping any
that have already been marked.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-10-16 10:10:42 -07:00

154 lines
3.7 KiB
C

#include "cache.h"
#include "commit.h"
#include "diff.h"
#include "revision.h"
#include "builtin.h"
#include "reachable.h"
#include "parse-options.h"
#include "progress.h"
#include "dir.h"
static const char * const prune_usage[] = {
N_("git prune [-n] [-v] [--expire <time>] [--] [<head>...]"),
NULL
};
static int show_only;
static int verbose;
static unsigned long expire;
static int show_progress = -1;
static int prune_tmp_file(const char *fullpath)
{
struct stat st;
if (lstat(fullpath, &st))
return error("Could not stat '%s'", fullpath);
if (st.st_mtime > expire)
return 0;
if (show_only || verbose)
printf("Removing stale temporary file %s\n", fullpath);
if (!show_only)
unlink_or_warn(fullpath);
return 0;
}
static int prune_object(const unsigned char *sha1, const char *fullpath,
void *data)
{
struct stat st;
/*
* Do we know about this object?
* It must have been reachable
*/
if (lookup_object(sha1))
return 0;
if (lstat(fullpath, &st)) {
/* report errors, but do not stop pruning */
error("Could not stat '%s'", fullpath);
return 0;
}
if (st.st_mtime > expire)
return 0;
if (show_only || verbose) {
enum object_type type = sha1_object_info(sha1, NULL);
printf("%s %s\n", sha1_to_hex(sha1),
(type > 0) ? typename(type) : "unknown");
}
if (!show_only)
unlink_or_warn(fullpath);
return 0;
}
static int prune_cruft(const char *basename, const char *path, void *data)
{
if (starts_with(basename, "tmp_obj_"))
prune_tmp_file(path);
else
fprintf(stderr, "bad sha1 file: %s\n", path);
return 0;
}
static int prune_subdir(int nr, const char *path, void *data)
{
if (!show_only)
rmdir(path);
return 0;
}
/*
* Write errors (particularly out of space) can result in
* failed temporary packs (and more rarely indexes and other
* files beginning with "tmp_") accumulating in the object
* and the pack directories.
*/
static void remove_temporary_files(const char *path)
{
DIR *dir;
struct dirent *de;
dir = opendir(path);
if (!dir) {
fprintf(stderr, "Unable to open directory %s\n", path);
return;
}
while ((de = readdir(dir)) != NULL)
if (starts_with(de->d_name, "tmp_"))
prune_tmp_file(mkpath("%s/%s", path, de->d_name));
closedir(dir);
}
int cmd_prune(int argc, const char **argv, const char *prefix)
{
struct rev_info revs;
struct progress *progress = NULL;
const struct option options[] = {
OPT__DRY_RUN(&show_only, N_("do not remove, show only")),
OPT__VERBOSE(&verbose, N_("report pruned objects")),
OPT_BOOL(0, "progress", &show_progress, N_("show progress")),
OPT_EXPIRY_DATE(0, "expire", &expire,
N_("expire objects older than <time>")),
OPT_END()
};
char *s;
expire = ULONG_MAX;
save_commit_buffer = 0;
check_replace_refs = 0;
init_revisions(&revs, prefix);
argc = parse_options(argc, argv, prefix, options, prune_usage, 0);
while (argc--) {
unsigned char sha1[20];
const char *name = *argv++;
if (!get_sha1(name, sha1)) {
struct object *object = parse_object_or_die(sha1, name);
add_pending_object(&revs, object, "");
}
else
die("unrecognized argument: %s", name);
}
if (show_progress == -1)
show_progress = isatty(2);
if (show_progress)
progress = start_progress_delay(_("Checking connectivity"), 0, 0, 2);
mark_reachable_objects(&revs, 1, expire, progress);
stop_progress(&progress);
for_each_loose_file_in_objdir(get_object_directory(), prune_object,
prune_cruft, prune_subdir, NULL);
prune_packed_objects(show_only ? PRUNE_PACKED_DRY_RUN : 0);
remove_temporary_files(get_object_directory());
s = mkpathdup("%s/pack", get_object_directory());
remove_temporary_files(s);
free(s);
if (is_repository_shallow())
prune_shallow(show_only);
return 0;
}