builtin/commit-graph.c: introduce split strategy 'replace'

When using split commit-graphs, it is sometimes useful to completely
replace the commit-graph chain with a new base.

For example, consider a scenario in which a repository builds a new
commit-graph incremental for each push. Occasionally (say, after some
fixed number of pushes), they may wish to rebuild the commit-graph chain
with all reachable commits.

They can do so with

  $ git commit-graph write --reachable

but this removes the chain entirely and replaces it with a single
commit-graph in 'objects/info/commit-graph'. Unfortunately, this means
that the next push will have to move this commit-graph into the first
layer of a new chain, and then write its new commits on top.

Avoid such copying entirely by allowing the caller to specify that they
wish to replace the entirety of their commit-graph chain, while also
specifying that the new commit-graph should become the basis of a fresh,
length-one chain.

This addresses the above situation by making it possible for the caller
to instead write:

  $ git commit-graph write --reachable --split=replace

which writes a new length-one chain to 'objects/info/commit-graphs',
making the commit-graph incremental generated by the subsequent push
relatively cheap by avoiding the aforementioned copy.

In order to do this, remove an assumption in 'write_commit_graph_file'
that chains are always at least two incrementals long.

Signed-off-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: ttaylorr

Documentation/git-commit-graph.txt

@@ -64,9 +64,10 @@ strategy and other splitting options. The new commits not already in the
 commit-graph are added in a new "tip" file. This file is merged with the
 existing file if the following merge conditions are met:
 * If `--split=no-merge` is specified, a merge is never performed, and
-the remaining options are ignored. A bare `--split` defers to the
-remaining options. (Note that merging a chain of commit graphs replaces
-the existing chain with a length-1 chain where the first and only
+the remaining options are ignored. `--split=replace` overwrites the
+existing chain with a new one. A bare `--split` defers to the remaining
+options. (Note that merging a chain of commit graphs replaces the
+existing chain with a length-1 chain where the first and only
 incremental holds the entire graph).
 +
 * If `--size-multiple=<X>` is not specified, let `X` equal 2. If the new

builtin/commit-graph.c

@@ -126,6 +126,8 @@ static int write_option_parse_split(const struct option *opt, const char *arg,
 
 	if (!strcmp(arg, "no-merge"))
 		*flags = COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED;
+	else if (!strcmp(arg, "replace"))
+		*flags = COMMIT_GRAPH_SPLIT_REPLACE;
 	else
 		die(_("unrecognized --split argument, %s"), arg);
 

commit-graph.c

@@ -866,7 +866,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -897,7 +897,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -964,7 +964,7 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -1037,6 +1037,8 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct commit *commit;
+	enum commit_graph_split_flags flags = ctx->split_opts ?
+		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
@@ -1066,8 +1068,9 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 		if (!commit)
 			continue;
 		if (ctx->split) {
-			if (!parse_commit(commit) &&
-			    commit->graph_pos == COMMIT_NOT_FROM_GRAPH)
+			if ((!parse_commit(commit) &&
+			     commit->graph_pos == COMMIT_NOT_FROM_GRAPH) ||
+			    flags == COMMIT_GRAPH_SPLIT_REPLACE)
 				add_missing_parents(ctx, commit);
 		} else if (!parse_commit_no_graph(commit))
 			add_missing_parents(ctx, commit);
@@ -1287,6 +1290,8 @@ static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx)
 static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 {
 	uint32_t i;
+	enum commit_graph_split_flags flags = ctx->split_opts ?
+		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	ctx->num_extra_edges = 0;
 	if (ctx->report_progress)
@@ -1303,11 +1308,14 @@ static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 		ALLOC_GROW(ctx->commits.list, ctx->commits.nr + 1, ctx->commits.alloc);
 		ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
-		if (ctx->split &&
+		if (ctx->split && flags != COMMIT_GRAPH_SPLIT_REPLACE &&
 		    ctx->commits.list[ctx->commits.nr]->graph_pos != COMMIT_NOT_FROM_GRAPH)
 			continue;
 
-		parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
+		if (ctx->split && flags == COMMIT_GRAPH_SPLIT_REPLACE)
+			parse_commit(ctx->commits.list[ctx->commits.nr]);
+		else
+			parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
 
 		num_parents = commit_list_count(ctx->commits.list[ctx->commits.nr]->parents);
 		if (num_parents > 2)
@@ -1488,8 +1496,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		}
 
 		if (ctx->base_graph_name) {
-			const char *dest = ctx->commit_graph_filenames_after[
-						ctx->num_commit_graphs_after - 2];
+			const char *dest;
+			int idx = ctx->num_commit_graphs_after - 1;
+			if (ctx->num_commit_graphs_after > 1)
+				idx--;
+
+			dest = ctx->commit_graph_filenames_after[idx];
 
 			if (strcmp(ctx->base_graph_name, dest)) {
 				result = rename(ctx->base_graph_name, dest);
@@ -1546,9 +1558,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 
 	g = ctx->r->objects->commit_graph;
 	num_commits = ctx->commits.nr;
-	ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
+	if (flags == COMMIT_GRAPH_SPLIT_REPLACE)
+		ctx->num_commit_graphs_after = 1;
+	else
+		ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
 
-	if (flags != COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED) {
+	if (flags != COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED &&
+	    flags != COMMIT_GRAPH_SPLIT_REPLACE) {
 		while (g && (g->num_commits <= size_mult * num_commits ||
 			    (max_commits && num_commits > max_commits))) {
 			if (g->odb != ctx->odb)
@@ -1561,7 +1577,11 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 		}
 	}
 
-	ctx->new_base_graph = g;
+	if (flags != COMMIT_GRAPH_SPLIT_REPLACE)
+		ctx->new_base_graph = g;
+	else if (ctx->num_commit_graphs_after != 1)
+		BUG("split_graph_merge_strategy: num_commit_graphs_after "
+		    "should be 1 with --split=replace");
 
 	if (ctx->num_commit_graphs_after == 2) {
 		char *old_graph_name = get_commit_graph_filename(g->odb);
@@ -1772,6 +1792,7 @@ int write_commit_graph(struct object_directory *odb,
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
 	int res = 0;
+	int replace = 0;
 
 	if (!commit_graph_compatible(the_repository))
 		return 0;
@@ -1806,6 +1827,9 @@ int write_commit_graph(struct object_directory *odb,
 				g = g->base_graph;
 			}
 		}
+
+		if (ctx->split_opts)
+			replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
 	}
 
 	ctx->approx_nr_objects = approximate_object_count();
@@ -1866,13 +1890,14 @@ int write_commit_graph(struct object_directory *odb,
 		goto cleanup;
 	}
 
-	if (!ctx->commits.nr)
+	if (!ctx->commits.nr && !replace)
 		goto cleanup;
 
 	if (ctx->split) {
 		split_graph_merge_strategy(ctx);
 
-		merge_commit_graphs(ctx);
+		if (!replace)
+			merge_commit_graphs(ctx);
 	} else
 		ctx->num_commit_graphs_after = 1;
 

commit-graph.h

@@ -84,7 +84,8 @@ enum commit_graph_write_flags {
 
 enum commit_graph_split_flags {
 	COMMIT_GRAPH_SPLIT_UNSPECIFIED      = 0,
-	COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED = 1
+	COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED = 1,
+	COMMIT_GRAPH_SPLIT_REPLACE          = 2
 };
 
 struct split_commit_graph_opts {

t/t5324-split-commit-graph.sh

@@ -355,4 +355,23 @@ test_expect_success '--split=no-merge always writes an incremental' '
 	test_line_count = 2 $graphdir/commit-graph-chain
 '
 
+test_expect_success '--split=replace replaces the chain' '
+	rm -rf $graphdir $infodir/commit-graph &&
+	git reset --hard commits/3 &&
+	git rev-list -1 HEAD~2 >a &&
+	git rev-list -1 HEAD~1 >b &&
+	git rev-list -1 HEAD >c &&
+	git commit-graph write --split=no-merge --stdin-commits <a &&
+	git commit-graph write --split=no-merge --stdin-commits <b &&
+	git commit-graph write --split=no-merge --stdin-commits <c &&
+	test_line_count = 3 $graphdir/commit-graph-chain &&
+	git commit-graph write --stdin-commits --split=replace <b &&
+	test_path_is_missing $infodir/commit-graph &&
+	test_path_is_file $graphdir/commit-graph-chain &&
+	ls $graphdir/graph-*.graph >graph-files &&
+	test_line_count = 1 graph-files &&
+	verify_chain_files_exist $graphdir &&
+	graph_read_expect 2
+'
+
 test_done