git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "SZEDER Gábor" <szeder.dev@gmail.com>
To: git@vger.kernel.org
Cc: "Junio C Hamano" <gitster@pobox.com>,
	"Garima Singh" <garima.singh@microsoft.com>,
	"Derrick Stolee" <stolee@gmail.com>,
	"Jakub Narebski" <jnareb@gmail.com>, "Jeff King" <peff@peff.net>,
	"Taylor Blau" <me@ttaylorr.com>,
	"SZEDER Gábor" <szeder.dev@gmail.com>
Subject: [PATCH 27/34] commit-graph: load modified path Bloom filters for merge commits
Date: Fri, 29 May 2020 10:50:31 +0200	[thread overview]
Message-ID: <20200529085038.26008-28-szeder.dev@gmail.com> (raw)
In-Reply-To: <20200529085038.26008-1-szeder.dev@gmail.com>

---
 commit-graph.c | 53 +++++++++++++++++++++++++++++++++++++++++++++-----
 commit-graph.h |  2 ++
 2 files changed, 50 insertions(+), 5 deletions(-)

diff --git a/commit-graph.c b/commit-graph.c
index 178bbf0113..32738ba4b8 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -26,6 +26,7 @@
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
 #define GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTER_INDEX 0x4d504249 /* "MPBI" */
+#define GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTER_MERGE_INDEX 0x4d50424d /* "MPBM" */
 #define GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTERS 0x4d504246 /* "MPBF" */
 #define GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTER_EXCLUDES 0x4d504258 /* "MPBX" */
 
@@ -328,6 +329,15 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 			}
 			break;
 
+		case GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTER_MERGE_INDEX:
+			if (graph->chunk_mpbf_merge_index)
+				chunk_repeated = 1;
+			else {
+				graph->chunk_mpbf_merge_index = data + chunk_offset;
+				graph->chunk_mpbf_merge_index_size = next_chunk_offset - chunk_offset;
+			}
+			break;
+
 		case GRAPH_CHUNKID_MODIFIED_PATH_BLOOM_FILTERS:
 			if (graph->chunk_mpbf_filters)
 				chunk_repeated = 1;
@@ -869,11 +879,44 @@ static int load_modified_path_bloom_filter_from_graph(
 		bf->bits = (uint8_t*) bloom_index;
 		return 1;
 	} else if (bloom_index[0] & (1 << 6)) {
-		/*
-		 * Modified path Bloom filters for second..nth parents of
-		 * merge commits are not implemented yet.
-		 */
-		return 0;
+		struct commit_list *p;
+		uint32_t pos;
+		int found = 0;
+
+		pos = get_be32(bloom_index + sizeof(uint32_t));
+
+		if (!graph->chunk_mpbf_merge_index)
+			BUG("commit %s refers to position %u in the Modified Path Bloom Filter Merge Index chunk, but that chunk is missing",
+			    oid_to_hex(&commit->object.oid), pos);
+
+		for (p = commit->parents; p; p = p->next, pos++)
+			if (p->item == parent) {
+				found = 1;
+				break;
+			}
+		if (!found)
+			BUG("commit %s has no parent %s\n",
+			    oid_to_hex(&commit->object.oid),
+			    oid_to_hex(&parent->object.oid));
+
+		if (pos * sizeof(uint64_t) > graph->chunk_mpbf_merge_index_size)
+			BUG("commit %s and parent %s refer to position %u in the Modified Path Bloom Filter Merge Index chunk, but that's too large for a chunk of size %lu bytes",
+			    oid_to_hex(&commit->object.oid),
+			    oid_to_hex(&parent->object.oid), pos,
+			    graph->chunk_mpbf_merge_index_size);
+		bloom_index = graph->chunk_mpbf_merge_index + sizeof(uint64_t) * pos;
+		if (bloom_index[0] & (1 << 7)) {
+			uint64_t v;
+			memcpy(&v, bloom_index, sizeof(v));
+			if (v == GRAPH_MODIFIED_PATH_BLOOM_FILTER_NONE)
+				return 0;
+
+			/* embedded modified path Bloom filter */
+			bf->nr_bits = GRAPH_MODIFIED_PATH_BLOOM_FILTER_EMBEDDED_NR_BITS;
+			bf->bits = (uint8_t*) bloom_index;
+			return 1;
+		} else
+			offset = get_be64(bloom_index);
 	} else {
 		if (!first_parent)
 			return 0;
diff --git a/commit-graph.h b/commit-graph.h
index cde0d7fa30..b2605a0e3b 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -69,6 +69,8 @@ struct commit_graph {
 	const unsigned char *chunk_base_graphs;
 	const unsigned char *chunk_mpbf_index;
 	uint64_t chunk_mpbf_index_size;
+	const unsigned char *chunk_mpbf_merge_index;
+	uint64_t chunk_mpbf_merge_index_size;
 	const unsigned char *chunk_mpbf_filters;
 	uint64_t chunk_mpbf_filters_size;
 	const unsigned char *chunk_mpbf_excludes;
-- 
2.27.0.rc1.431.g5c813f95dc


  parent reply	other threads:[~2020-05-29  8:52 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-29  8:50 [PoC PATCH 00/34] An alternative modified path Bloom filters implementation SZEDER Gábor
2020-05-28 22:09 ` Johannes Schindelin
2020-05-29  8:50 ` [PATCH 01/34] tree-walk.c: don't match submodule entries for 'submod/anything' SZEDER Gábor
2020-05-29  8:50 ` [PATCH 02/34] commit-graph: fix parsing the Chunk Lookup table SZEDER Gábor
2020-05-29  8:50 ` [PATCH 03/34] commit-graph-format.txt: all multi-byte numbers are in network byte order SZEDER Gábor
2020-05-29  8:50 ` [PATCH 04/34] commit-slab: add a function to deep free entries on the slab SZEDER Gábor
2020-06-04 16:43   ` Derrick Stolee
2020-06-27 15:56     ` SZEDER Gábor
2020-06-29 11:30       ` Derrick Stolee
2020-05-29  8:50 ` [PATCH 05/34] diff.h: drop diff_tree_oid() & friends' return value SZEDER Gábor
2020-05-29  8:50 ` [PATCH 06/34] commit-graph: clean up #includes SZEDER Gábor
2020-05-29  8:50 ` [PATCH 07/34] commit-graph: simplify parse_commit_graph() #1 SZEDER Gábor
2020-05-29  8:50 ` [PATCH 08/34] commit-graph: simplify parse_commit_graph() #2 SZEDER Gábor
2020-05-29  8:50 ` [PATCH 09/34] commit-graph: simplify write_commit_graph_file() #1 SZEDER Gábor
2020-05-29  8:50 ` [PATCH 10/34] commit-graph: simplify write_commit_graph_file() #2 SZEDER Gábor
2020-05-29  8:50 ` [PATCH 11/34] commit-graph: allocate the 'struct chunk_info' array dinamically SZEDER Gábor
2020-05-29  8:50 ` [PATCH 12/34] commit-graph: unify the signatures of all write_graph_chunk_*() functions SZEDER Gábor
2020-05-29  8:50 ` [PATCH 13/34] commit-graph: simplify write_commit_graph_file() #3 SZEDER Gábor
2020-05-29  8:50 ` [PATCH 14/34] commit-graph: check chunk sizes after writing SZEDER Gábor
2020-05-29  8:50 ` [PATCH 15/34] commit-graph-format.txt: document the modified path Bloom filter chunks SZEDER Gábor
2020-06-02 17:59   ` SZEDER Gábor
2020-05-29  8:50 ` [PATCH 16/34] Add a generic and minimal Bloom filter implementation SZEDER Gábor
2020-05-29  8:50 ` [PATCH 17/34] Import a streaming-capable Murmur3 hash function implementation SZEDER Gábor
2020-05-29  8:50 ` [PATCH 18/34] commit-graph: write "empty" Modified Path Bloom Filter Index chunk SZEDER Gábor
2020-05-29  8:50 ` [PATCH 19/34] commit-graph: add commit slab for modified path Bloom filters SZEDER Gábor
2020-05-29  8:50 ` [PATCH 20/34] commit-graph: fill the Modified Path Bloom Filter Index chunk SZEDER Gábor
2020-05-29  8:50 ` [PATCH 21/34] commit-graph: load and use " SZEDER Gábor
2020-05-29  8:50 ` [PATCH 22/34] commit-graph: write the Modified Path Bloom Filters chunk SZEDER Gábor
2020-05-29  8:50 ` [PATCH 23/34] commit-graph: load and use " SZEDER Gábor
2020-05-29  8:50 ` [PATCH 24/34] commit-graph: check all leading directories in modified path Bloom filters SZEDER Gábor
2020-05-29  8:50 ` [PATCH 25/34] commit-graph: check embedded modified path Bloom filters with a mask SZEDER Gábor
2020-05-29  8:50 ` [PATCH 26/34] commit-graph: deduplicate modified path Bloom filters SZEDER Gábor
2020-05-29  8:50 ` SZEDER Gábor [this message]
2020-05-29  8:50 ` [PATCH 28/34] commit-graph: write Modified Path Bloom Filter Merge Index chunk SZEDER Gábor
2020-05-29  8:50 ` [PATCH 29/34] commit-graph: extract init and free write_commit_graph_context SZEDER Gábor
2020-05-29  8:50 ` [PATCH 30/34] commit-graph: move write_commit_graph_reachable below write_commit_graph SZEDER Gábor
2020-05-29  8:50 ` [PATCH 31/34] t7007-show: make the first test compatible with the next patch SZEDER Gábor
2020-05-29  8:50 ` [PATCH 32/34] PoC commit-graph: use revision walk machinery for '--reachable' SZEDER Gábor
2020-05-29  8:50 ` [PATCH 33/34] commit-graph: write modified path Bloom filters in "history order" SZEDER Gábor
2020-05-29  8:50 ` [PATCH 34/34] commit-graph: use modified path Bloom filters with wildcards, if possible SZEDER Gábor
2020-05-29 13:59 ` [PoC PATCH 00/34] An alternative modified path Bloom filters implementation Derrick Stolee
2020-06-01 23:25 ` Taylor Blau
2020-06-02 17:08   ` Junio C Hamano

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200529085038.26008-28-szeder.dev@gmail.com \
    --to=szeder.dev@gmail.com \
    --cc=garima.singh@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jnareb@gmail.com \
    --cc=me@ttaylorr.com \
    --cc=peff@peff.net \
    --cc=stolee@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).