[PATCH v2] name-hash: don't add sparse directories in threaded lazy init

["Alex Mironov via GitGitGadget" <gitgitgadget@xxxxxxxxx>]

From: Alex Mironov <alexandrfox@xxxxxxxxx>

Ensure that logic added in 5f11669586 (name-hash: don't add directories
to name_hash, 2021-04-12) also applies in multithreaded hashtable init
path.

Sparse directory entries represent a directory that is outside the
sparse-checkout definition. These are not paths to blobs, so should not
be added to the name_hash table as they must never be queried.

Signed-off-by: Alex Mironov <alexandrfox@xxxxxxxxx>
---
    name-hash: don't add sparse directories in threaded lazy init
    
    Changes since v1:
    
     * addressed feedback (code-style)

Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-git-1970%2Falexandrfox%2Ffix-threaded-hash-name-v2
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-git-1970/alexandrfox/fix-threaded-hash-name-v2
Pull-Request: https://github.com/git/git/pull/1970

Range-diff vs v1:

 1:  d12ebc612c2 ! 1:  fb378147c73 name-hash: don't add sparse directories in threaded lazy init
     @@ Metadata
       ## Commit message ##
          name-hash: don't add sparse directories in threaded lazy init
      
     -    Similarly to 5f116695864788d1fe45ff06bfad7a71a8d98d0a
     -    make sure to avoid placing sparse directories into the name_hash
     -    hashtable whenever multithreaded initialization is performed.
     +    Ensure that logic added in 5f11669586 (name-hash: don't add directories
     +    to name_hash, 2021-04-12) also applies in multithreaded hashtable init
     +    path.
      
          Sparse directory entries represent a directory that is outside the
          sparse-checkout definition. These are not paths to blobs, so should not
     @@ name-hash.c: static void *lazy_name_thread_proc(void *_data)
       	for (k = 0; k < d->istate->cache_nr; k++) {
       		struct cache_entry *ce_k = d->istate->cache[k];
       		ce_k->ce_flags |= CE_HASHED;
     -+		if (S_ISSPARSEDIR(ce_k->ce_mode)) {
     -+			continue;
     +-		hashmap_entry_init(&ce_k->ent, d->lazy_entries[k].hash_name);
     +-		hashmap_add(&d->istate->name_hash, &ce_k->ent);
     ++		if (!S_ISSPARSEDIR(ce_k->ce_mode)) {
     ++			hashmap_entry_init(&ce_k->ent, d->lazy_entries[k].hash_name);
     ++			hashmap_add(&d->istate->name_hash, &ce_k->ent);
      +		}
     - 		hashmap_entry_init(&ce_k->ent, d->lazy_entries[k].hash_name);
     - 		hashmap_add(&d->istate->name_hash, &ce_k->ent);
       	}
     + 
     + 	return NULL;


 name-hash.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/name-hash.c b/name-hash.c
index d66de1cdfd5..b91e2762678 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -492,8 +492,10 @@ static void *lazy_name_thread_proc(void *_data)
 	for (k = 0; k < d->istate->cache_nr; k++) {
 		struct cache_entry *ce_k = d->istate->cache[k];
 		ce_k->ce_flags |= CE_HASHED;
-		hashmap_entry_init(&ce_k->ent, d->lazy_entries[k].hash_name);
-		hashmap_add(&d->istate->name_hash, &ce_k->ent);
+		if (!S_ISSPARSEDIR(ce_k->ce_mode)) {
+			hashmap_entry_init(&ce_k->ent, d->lazy_entries[k].hash_name);
+			hashmap_add(&d->istate->name_hash, &ce_k->ent);
+		}
 	}
 
 	return NULL;

base-commit: 8613c2bb6cd16ef530dc5dd74d3b818a1ccbf1c0
-- 
gitgitgadget