commit-graph: expire commit-graph files
As we merge commit-graph files in a commit-graph chain, we should clean up the files that are no longer used. This change introduces an 'expiry_window' value to the context, which is always zero (for now). We then check the modified time of each graph-{hash}.graph file in the $OBJDIR/info/commit-graphs folder and unlink the files that are older than the expiry_window. Since this is always zero, this immediately clears all unused graph files. We will update the value to match a config setting in a future change. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Derrick Stolee committed
Jun 18, 2019 at 11:14 UTC
8d84097f9655a954ea7e94ba08d93e5940ccb2ae
3 files changed
+85
-1
Documentation/technical/commit-graph.txt
+15
@@ -266,6 +266,21 @@ The merge strategy values (2 for the size multiple, 64,000 for the maximum
266
number of commits) could be extracted into config settings for full
267
flexibility.
268
269
+## Deleting graph-{hash} files
270
+
271
+After a new tip file is written, some `graph-{hash}` files may no longer
272
+be part of a chain. It is important to remove these files from disk, eventually.
273
+The main reason to delay removal is that another process could read the
274
+`commit-graph-chain` file before it is rewritten, but then look for the
275
+`graph-{hash}` files after they are deleted.
276
+
277
+To allow holding old split commit-graphs for a while after they are unreferenced,
278
+we update the modified times of the files when they become unreferenced. Then,
279
+we scan the `$OBJDIR/info/commit-graphs/` directory for `graph-{hash}`
280
+files whose modified times are older than a given expiry window. This window
281
+defaults to zero, but can be changed using command-line arguments or a config
282
+setting.
283
+
284
## Chains across multiple object directories
285
286
In a repo with alternates, we look for the `commit-graph-chain` file starting
commit-graph.c
+69
@@ -1652,6 +1652,70 @@ static void merge_commit_graphs(struct write_commit_graph_context *ctx)
1652
sort_and_scan_merged_commits(ctx);
1653
}
1654
1655
+static void mark_commit_graphs(struct write_commit_graph_context *ctx)
1656
+{
1657
+ uint32_t i;
1658
+ time_t now = time(NULL);
1659
+
1660
+ for (i = ctx->num_commit_graphs_after - 1; i < ctx->num_commit_graphs_before; i++) {
1661
+ struct stat st;
1662
+ struct utimbuf updated_time;
1663
+
1664
+ stat(ctx->commit_graph_filenames_before[i], &st);
1665
+
1666
+ updated_time.actime = st.st_atime;
1667
+ updated_time.modtime = now;
1668
+ utime(ctx->commit_graph_filenames_before[i], &updated_time);
1669
+ }
1670
+}
1671
+
1672
+static void expire_commit_graphs(struct write_commit_graph_context *ctx)
1673
+{
1674
+ struct strbuf path = STRBUF_INIT;
1675
+ DIR *dir;
1676
+ struct dirent *de;
1677
+ size_t dirnamelen;
1678
+ time_t expire_time = time(NULL);
1679
+
1680
+ strbuf_addstr(&path, ctx->obj_dir);
1681
+ strbuf_addstr(&path, "/info/commit-graphs");
1682
+ dir = opendir(path.buf);
1683
+
1684
+ if (!dir) {
1685
+ strbuf_release(&path);
1686
+ return;
1687
+ }
1688
+
1689
+ strbuf_addch(&path, '/');
1690
+ dirnamelen = path.len;
1691
+ while ((de = readdir(dir)) != NULL) {
1692
+ struct stat st;
1693
+ uint32_t i, found = 0;
1694
+
1695
+ strbuf_setlen(&path, dirnamelen);
1696
+ strbuf_addstr(&path, de->d_name);
1697
+
1698
+ stat(path.buf, &st);
1699
+
1700
+ if (st.st_mtime > expire_time)
1701
+ continue;
1702
+ if (path.len < 6 || strcmp(path.buf + path.len - 6, ".graph"))
1703
+ continue;
1704
+
1705
+ for (i = 0; i < ctx->num_commit_graphs_after; i++) {
1706
+ if (!strcmp(ctx->commit_graph_filenames_after[i],
1707
+ path.buf)) {
1708
+ found = 1;
1709
+ break;
1710
+ }
1711
+ }
1712
+
1713
+ if (!found)
1714
+ unlink(path.buf);
1715
+
1716
+ }
1717
+}
1718
+
1719
int write_commit_graph(const char *obj_dir,
1720
struct string_list *pack_indexes,
1721
struct string_list *commit_hex,
@@ -1764,6 +1828,11 @@ int write_commit_graph(const char *obj_dir,
1828
1829
res = write_commit_graph_file(ctx);
1830
1831
+ if (ctx->split) {
1832
+ mark_commit_graphs(ctx);
1833
+ expire_commit_graphs(ctx);
1834
+ }
1835
+
1836
cleanup:
1837
free(ctx->graph_name);
1838
free(ctx->commits.list);
t/t5324-split-commit-graph.sh
+1
-1
@@ -141,7 +141,7 @@ test_expect_success 'add one commit, write a merged graph' '
141
test_path_is_file $graphdir/commit-graph-chain &&
142
test_line_count = 2 $graphdir/commit-graph-chain &&
143
ls $graphdir/graph-*.graph >graph-files &&
144
- test_line_count = 4 graph-files &&
144
+ test_line_count = 2 graph-files &&
145
verify_chain_files_exist $graphdir
146
'
147