From 2db1a43f41880bb4aeea9dee8a7d13c5ad76db3f Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Fri, 28 Mar 2014 06:00:43 -0400 Subject: add `ignore_missing_links` mode to revwalk When pack-objects is computing the reachability bitmap to serve a fetch request, it can erroneously die() if some of the UNINTERESTING objects are not present. Upload-pack throws away HAVE lines from the client for objects we do not have, but we may have a tip object without all of its ancestors (e.g., if the tip is no longer reachable and was new enough to survive a `git prune`, but some of its reachable objects did get pruned). In the non-bitmap case, we do a revision walk with the HAVE objects marked as UNINTERESTING. The revision walker explicitly ignores errors in accessing UNINTERESTING commits to handle this case (and we do not bother looking at UNINTERESTING trees or blobs at all). When we have bitmaps, however, the process is quite different. The bitmap index for a pack-objects run is calculated in two separate steps: First, we perform an extensive walk from all the HAVEs to find the full set of objects reachable from them. This walk is usually optimized away because we are expected to hit an object with a bitmap during the traversal, which allows us to terminate early. Secondly, we perform an extensive walk from all the WANTs, which usually also terminates early because we hit a commit with an existing bitmap. Once we have the resulting bitmaps from the two walks, we AND-NOT them together to obtain the resulting set of objects we need to pack. When we are walking the HAVE objects, the revision walker does not know that we are walking it only to mark the results as uninteresting. We strip out the UNINTERESTING flag, because those objects _are_ interesting to us during the first walk. We want to keep going to get a complete set of reachable objects if we can. We need some way to tell the revision walker that it's OK to silently truncate the HAVE walk, just like it does for the UNINTERESTING case. This patch introduces a new `ignore_missing_links` flag to the `rev_info` struct, which we set only for the HAVE walk. It also adds tests to cover UNINTERESTING objects missing from several positions: a missing blob, a missing tree, and a missing parent commit. The missing blob already worked (as we do not care about its contents at all), but the other two cases caused us to die(). Note that there are a few cases we do not need to test: 1. We do not need to test a missing tree, with the blob still present. Without the tree that refers to it, we would not know that the blob is relevant to our walk. 2. We do not need to test a tip commit that is missing. Upload-pack omits these for us (and in fact, we complain even in the non-bitmap case if it fails to do so). Reported-by: Siddharth Agarwal Signed-off-by: Vicent Marti Signed-off-by: Jeff King Signed-off-by: Junio C Hamano diff --git a/list-objects.c b/list-objects.c index 6cbedf0..b2db6ba 100644 --- a/list-objects.c +++ b/list-objects.c @@ -81,8 +81,11 @@ static void process_tree(struct rev_info *revs, die("bad tree object"); if (obj->flags & (UNINTERESTING | SEEN)) return; - if (parse_tree(tree) < 0) + if (parse_tree(tree) < 0) { + if (revs->ignore_missing_links) + return; die("bad tree object %s", sha1_to_hex(obj->sha1)); + } obj->flags |= SEEN; show(obj, path, name, cb_data); me.up = path; diff --git a/pack-bitmap.c b/pack-bitmap.c index ae0b57b..91e4101 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -727,8 +727,10 @@ int prepare_bitmap_walk(struct rev_info *revs) revs->pending.objects = NULL; if (haves) { + revs->ignore_missing_links = 1; haves_bitmap = find_objects(revs, haves, NULL); reset_revision_walk(); + revs->ignore_missing_links = 0; if (haves_bitmap == NULL) die("BUG: failed to perform bitmap walk"); diff --git a/revision.c b/revision.c index cddd605..520b3e7 100644 --- a/revision.c +++ b/revision.c @@ -2866,9 +2866,11 @@ static struct commit *get_revision_1(struct rev_info *revs) if (revs->max_age != -1 && (commit->date < revs->max_age)) continue; - if (add_parents_to_list(revs, commit, &revs->commits, NULL) < 0) - die("Failed to traverse parents of commit %s", - sha1_to_hex(commit->object.sha1)); + if (add_parents_to_list(revs, commit, &revs->commits, NULL) < 0) { + if (!revs->ignore_missing_links) + die("Failed to traverse parents of commit %s", + sha1_to_hex(commit->object.sha1)); + } } switch (simplify_commit(revs, commit)) { diff --git a/revision.h b/revision.h index 9957f3c..4f051d2 100644 --- a/revision.h +++ b/revision.h @@ -69,7 +69,8 @@ struct rev_info { enum rev_sort_order sort_order; unsigned int early_output:1, - ignore_missing:1; + ignore_missing:1, + ignore_missing_links:1; /* Traversal flags */ unsigned int dense:1, diff --git a/t/t5310-pack-bitmaps.sh b/t/t5310-pack-bitmaps.sh index f13525c..f4f02ba 100755 --- a/t/t5310-pack-bitmaps.sh +++ b/t/t5310-pack-bitmaps.sh @@ -3,6 +3,10 @@ test_description='exercise basic bitmap functionality' . ./test-lib.sh +objpath () { + echo ".git/objects/$(echo "$1" | sed -e 's|\(..\)|\1/|')" +} + test_expect_success 'setup repo with moderate-sized history' ' for i in $(test_seq 1 10); do test_commit $i @@ -115,6 +119,33 @@ test_expect_success 'fetch (full bitmap)' ' test_cmp expect actual ' +test_expect_success 'create objects for missing-HAVE tests' ' + blob=$(echo "missing have" | git hash-object -w --stdin) && + tree=$(printf "100644 blob $blob\tfile\n" | git mktree) && + parent=$(echo parent | git commit-tree $tree) && + commit=$(echo commit | git commit-tree $tree -p $parent) && + cat >revs <<-EOF + HEAD + ^HEAD^ + ^$commit + EOF +' + +test_expect_success 'pack with missing blob' ' + rm $(objpath $blob) && + git pack-objects --stdout --revs /dev/null +' + +test_expect_success 'pack with missing tree' ' + rm $(objpath $tree) && + git pack-objects --stdout --revs /dev/null +' + +test_expect_success 'pack with missing parent' ' + rm $(objpath $parent) && + git pack-objects --stdout --revs /dev/null +' + test_lazy_prereq JGIT ' type jgit ' -- cgit v0.10.2-6-g49f6