summaryrefslogtreecommitdiff
path: root/shallow.c
diff options
context:
space:
mode:
authorNguyễn Thái Ngọc Duy <pclouds@gmail.com>2013-12-05 20:02:35 +0700
committerJunio C Hamano <gitster@pobox.com>2013-12-10 16:14:16 -0800
commit58babfffdeeecaa4d6edecaac1fb0c595218b801 (patch)
treeb94599443a17e383355af675b94f05624563e2aa /shallow.c
parent1a30f5a2f2a3d5d9b3cf6e126ac19deb40324515 (diff)
downloadgit-58babfffdeeecaa4d6edecaac1fb0c595218b801.tar.gz
shallow.c: the 8 steps to select new commits for .git/shallow
Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'shallow.c')
-rw-r--r--shallow.c72
1 files changed, 72 insertions, 0 deletions
diff --git a/shallow.c b/shallow.c
index 822c626600..ecd950fd04 100644
--- a/shallow.c
+++ b/shallow.c
@@ -2,6 +2,12 @@
#include "commit.h"
#include "tag.h"
#include "pkt-line.h"
+#include "remote.h"
+#include "refs.h"
+#include "sha1-array.h"
+#include "diff.h"
+#include "revision.h"
+#include "commit-slab.h"
static int is_shallow = -1;
static struct stat shallow_stat;
@@ -245,3 +251,69 @@ void advertise_shallow_grafts(int fd)
return;
for_each_commit_graft(advertise_shallow_grafts_cb, &fd);
}
+
+#define TRACE_KEY "GIT_TRACE_SHALLOW"
+
+/*
+ * Step 1, split sender shallow commits into "ours" and "theirs"
+ * Step 2, clean "ours" based on .git/shallow
+ */
+void prepare_shallow_info(struct shallow_info *info, struct sha1_array *sa)
+{
+ int i;
+ trace_printf_key(TRACE_KEY, "shallow: prepare_shallow_info\n");
+ memset(info, 0, sizeof(*info));
+ info->shallow = sa;
+ if (!sa)
+ return;
+ info->ours = xmalloc(sizeof(*info->ours) * sa->nr);
+ info->theirs = xmalloc(sizeof(*info->theirs) * sa->nr);
+ for (i = 0; i < sa->nr; i++) {
+ if (has_sha1_file(sa->sha1[i])) {
+ struct commit_graft *graft;
+ graft = lookup_commit_graft(sa->sha1[i]);
+ if (graft && graft->nr_parent < 0)
+ continue;
+ info->ours[info->nr_ours++] = i;
+ } else
+ info->theirs[info->nr_theirs++] = i;
+ }
+}
+
+void clear_shallow_info(struct shallow_info *info)
+{
+ free(info->ours);
+ free(info->theirs);
+}
+
+/* Step 4, remove non-existent ones in "theirs" after getting the pack */
+
+void remove_nonexistent_theirs_shallow(struct shallow_info *info)
+{
+ unsigned char (*sha1)[20] = info->shallow->sha1;
+ int i, dst;
+ trace_printf_key(TRACE_KEY, "shallow: remove_nonexistent_theirs_shallow\n");
+ for (i = dst = 0; i < info->nr_theirs; i++) {
+ if (i != dst)
+ info->theirs[dst] = info->theirs[i];
+ if (has_sha1_file(sha1[info->theirs[i]]))
+ dst++;
+ }
+ info->nr_theirs = dst;
+}
+
+/* Step 5, remove non-existent ones in "ours" in the pack */
+void remove_nonexistent_ours_in_pack(struct shallow_info *info,
+ struct packed_git *p)
+{
+ unsigned char (*sha1)[20] = info->shallow->sha1;
+ int i, dst;
+ trace_printf_key(TRACE_KEY, "shallow: remove_nonexistent_ours_in_pack\n");
+ for (i = dst = 0; i < info->nr_ours; i++) {
+ if (i != dst)
+ info->ours[dst] = info->ours[i];
+ if (find_pack_entry_one(sha1[info->ours[i]], p))
+ dst++;
+ }
+ info->nr_ours = dst;
+}