git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 22/32] split-index: the reading part

From
Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date
Jun 13, 2014, 12:19 UTC
Message-ID
<1402661991-14977-23-git-send-email-pclouds@gmail.com>
In-Reply-To
<1402661991-14977-1-git-send-email-pclouds@gmail.com>

CE_REMOVE'd entries are removed here because only parts of the code base (unpack_trees in fact) test this bit when they look for the presence of an entry. Leaving them may confuse the code ignores this bit and expects to see a real entry.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 read-cache.c  |  2 --
 split-index.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 split-index.h |  2 ++
 3 files changed, 84 insertions(+), 4 deletions(-)
diff --git a/read-cache.c b/read-cache.c
index 7966fb7..1a7ef7f 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1569,8 +1569,6 @@ int read_index_from(struct index_state *istate, const char *path)
 
 	if (is_null_sha1(split_index->base_sha1))
 		return ret;
-	if (istate->cache_nr)
-		die("index in split-index mode must contain no entries");
 
 	if (split_index->base)
 		discard_index(split_index->base);
diff --git a/split-index.c b/split-index.c
index 5708807..b03a250 100644
--- a/split-index.c
+++ b/split-index.c
@@ -16,13 +16,27 @@ int read_link_extension(struct index_state *istate,
 {
 	const unsigned char *data = data_;
 	struct split_index *si;
+	int ret;
+
 	if (sz < 20)
 		return error("corrupt link extension (too short)");
 	si = init_split_index(istate);
 	hashcpy(si->base_sha1, data);
 	data += 20;
 	sz -= 20;
-	if (sz)
+	if (!sz)
+		return 0;
+	si->delete_bitmap = ewah_new();
+	ret = ewah_read_mmap(si->delete_bitmap, data, sz);
+	if (ret < 0)
+		return error("corrupt delete bitmap in link extension");
+	data += ret;
+	sz -= ret;
+	si->replace_bitmap = ewah_new();
+	ret = ewah_read_mmap(si->replace_bitmap, data, sz);
+	if (ret < 0)
+		return error("corrupt replace bitmap in link extension");
+	if (ret != sz)
 		return error("garbage at the end of link extension");
 	return 0;
 }
@@ -60,15 +74,81 @@ static void mark_base_index_entries(struct index_state *base)
 		base->cache[i]->index = i + 1;
 }
 
+static void mark_entry_for_delete(size_t pos, void *data)
+{
+	struct index_state *istate = data;
+	if (pos >= istate->cache_nr)
+		die("position for delete %d exceeds base index size %d",
+		    (int)pos, istate->cache_nr);
+	istate->cache[pos]->ce_flags |= CE_REMOVE;
+	istate->split_index->nr_deletions = 1;
+}
+
+static void replace_entry(size_t pos, void *data)
+{
+	struct index_state *istate = data;
+	struct split_index *si = istate->split_index;
+	struct cache_entry *dst, *src;
+	if (pos >= istate->cache_nr)
+		die("position for replacement %d exceeds base index size %d",
+		    (int)pos, istate->cache_nr);
+	if (si->nr_replacements >= si->saved_cache_nr)
+		die("too many replacements (%d vs %d)",
+		    si->nr_replacements, si->saved_cache_nr);
+	dst = istate->cache[pos];
+	if (dst->ce_flags & CE_REMOVE)
+		die("entry %d is marked as both replaced and deleted",
+		    (int)pos);
+	src = si->saved_cache[si->nr_replacements];
+	src->index = pos + 1;
+	src->ce_flags |= CE_UPDATE_IN_BASE;
+	free(dst);
+	dst = src;
+	si->nr_replacements++;
+}
+
 void merge_base_index(struct index_state *istate)
 {
 	struct split_index *si = istate->split_index;
+	unsigned int i;
 
 	mark_base_index_entries(si->base);
-	istate->cache_nr = si->base->cache_nr;
+
+	si->saved_cache	    = istate->cache;
+	si->saved_cache_nr  = istate->cache_nr;
+	istate->cache_nr    = si->base->cache_nr;
+	istate->cache	    = NULL;
+	istate->cache_alloc = 0;
 	ALLOC_GROW(istate->cache, istate->cache_nr, istate->cache_alloc);
 	memcpy(istate->cache, si->base->cache,
 	       sizeof(*istate->cache) * istate->cache_nr);
+
+	si->nr_deletions = 0;
+	si->nr_replacements = 0;
+	ewah_each_bit(si->replace_bitmap, replace_entry, istate);
+	ewah_each_bit(si->delete_bitmap, mark_entry_for_delete, istate);
+	if (si->nr_deletions)
+		remove_marked_cache_entries(istate);
+
+	for (i = si->nr_replacements; i < si->saved_cache_nr; i++) {
+		add_index_entry(istate, si->saved_cache[i],
+				ADD_CACHE_OK_TO_ADD |
+				/*
+				 * we may have to replay what
+				 * merge-recursive.c:update_stages()
+				 * does, which has this flag on
+				 */
+				ADD_CACHE_SKIP_DFCHECK);
+		si->saved_cache[i] = NULL;
+	}
+
+	ewah_free(si->delete_bitmap);
+	ewah_free(si->replace_bitmap);
+	free(si->saved_cache);
+	si->delete_bitmap  = NULL;
+	si->replace_bitmap = NULL;
+	si->saved_cache	   = NULL;
+	si->saved_cache_nr = 0;
 }
 
 void prepare_to_write_split_index(struct index_state *istate)
diff --git a/split-index.h b/split-index.h
index 53b778f..c1324f5 100644
--- a/split-index.h
+++ b/split-index.h
@@ -12,6 +12,8 @@ struct split_index {
 	struct ewah_bitmap *replace_bitmap;
 	struct cache_entry **saved_cache;
 	unsigned int saved_cache_nr;
+	unsigned int nr_deletions;
+	unsigned int nr_replacements;
 	int refcount;
 };
 

-- 
1.9.1.346.ga2b5940
Previous: Nguyễn Thái Ngọc DuyNext: Nguyễn Thái Ngọc Duy
Message 23 of 33 in “Split index resend”
  1. 00/32 Split index resendNguyễn Thái Ngọc Duy, Jun 13, 2014
  2. 01/32 ewah: fix constness of ewah_read_mmapNguyễn Thái Ngọc Duy, Jun 13, 2014
  3. 02/32 ewah: delete unused ewah_read_mmap_native declarationNguyễn Thái Ngọc Duy, Jun 13, 2014
  4. 03/32 sequencer: do not update/refresh index if the lock cannot be heldNguyễn Thái Ngọc Duy, Jun 13, 2014
  5. 04/32 read-cache: new API write_locked_index instead of write_index/write_cacheNguyễn Thái Ngọc Duy, Jun 13, 2014
  6. 05/32 read-cache: relocate and unexport commit_locked_index()Nguyễn Thái Ngọc Duy, Jun 13, 2014
  7. 06/32 read-cache: store in-memory flags in the first 12 bits of ce_flagsNguyễn Thái Ngọc Duy, Jun 13, 2014
  8. 07/32 read-cache: be strict about "changed" in remove_marked_cache_entries()Nguyễn Thái Ngọc Duy, Jun 13, 2014
  9. 08/32 read-cache: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Jun 13, 2014
  10. 09/32 update-index: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Jun 13, 2014
  11. 10/32 resolve-undo: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Jun 13, 2014
  12. 11/32 unpack-trees: be specific what part of the index has changedNguyễn Thái Ngọc Duy, Jun 13, 2014
  13. 12/32 cache-tree: mark istate->cache_changed on cache tree invalidationNguyễn Thái Ngọc Duy, Jun 13, 2014
  14. 13/32 cache-tree: mark istate->cache_changed on cache tree updateNguyễn Thái Ngọc Duy, Jun 13, 2014
  15. 14/32 cache-tree: mark istate->cache_changed on prime_cache_tree()Nguyễn Thái Ngọc Duy, Jun 13, 2014
  16. 15/32 entry.c: update cache_changed if refresh_cache is set in checkout_entry()Nguyễn Thái Ngọc Duy, Jun 13, 2014
  17. 16/32 read-cache: save index SHA-1 after readingNguyễn Thái Ngọc Duy, Jun 13, 2014
  18. 17/32 read-cache: split-index modeNguyễn Thái Ngọc Duy, Jun 13, 2014
  19. 18/32 read-cache: mark new entries for split indexNguyễn Thái Ngọc Duy, Jun 13, 2014
  20. 19/32 read-cache: save deleted entries in split indexNguyễn Thái Ngọc Duy, Jun 13, 2014
  21. 20/32 read-cache: mark updated entries for split indexNguyễn Thái Ngọc Duy, Jun 13, 2014
  22. 21/32 split-index: the writing partNguyễn Thái Ngọc Duy, Jun 13, 2014
  23. 22/32 split-index: the reading partNguyễn Thái Ngọc Duy, Jun 13, 2014
  24. 23/32 split-index: do not invalidate cache-tree at read timeNguyễn Thái Ngọc Duy, Jun 13, 2014
  25. 24/32 split-index: strip pathname of on-disk replaced entriesNguyễn Thái Ngọc Duy, Jun 13, 2014
  26. 25/32 update-index: new options to enable/disable split index modeNguyễn Thái Ngọc Duy, Jun 13, 2014
  27. 26/32 update-index --split-index: do not split if $GIT_DIR is read onlyNguyễn Thái Ngọc Duy, Jun 13, 2014
  28. 27/32 rev-parse: add --shared-index-path to get shared index pathNguyễn Thái Ngọc Duy, Jun 13, 2014
  29. 28/32 read-tree: force split-index mode off on --index-outputNguyễn Thái Ngọc Duy, Jun 13, 2014
  30. 29/32 read-tree: note about dropping split-index mode or index versionNguyễn Thái Ngọc Duy, Jun 13, 2014
  31. 30/32 read-cache: force split index mode with GIT_TEST_SPLIT_INDEXNguyễn Thái Ngọc Duy, Jun 13, 2014
  32. 31/32 t2104: make sure split index mode is off for the version testNguyễn Thái Ngọc Duy, Jun 13, 2014
  33. 32/32 t1700: new tests for split-index modeNguyễn Thái Ngọc Duy, Jun 13, 2014

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.