From 8b604d19515c4be18403047045faa363d4de217b Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 6 Sep 2017 15:43:48 +0000 Subject: hashmap: add API to disable item counting when threaded This is to address concerns raised by ThreadSanitizer on the mailing list about threaded unprotected R/W access to map.size with my previous "disallow rehash" change (0607e10009ee4e37cb49b4cec8d28a9dda1656a4). See: https://public-inbox.org/git/adb37b70139fd1e2bac18bfd22c8b96683ae18eb.1502780344.git.martin.agren@gmail.com/ Add API to hashmap to disable item counting and thus automatic rehashing. Also include API to later re-enable them. When item counting is disabled, the map.size field is invalid. So to prevent accidents, the field has been renamed and an accessor function hashmap_get_size() has been added. All direct references to this field have been been updated. And the name of the field changed to map.private_size to communicate this. Here is the relevant output from ThreadSanitizer showing the problem: WARNING: ThreadSanitizer: data race (pid=10554) Read of size 4 at 0x00000082d488 by thread T2 (mutexes: write M16): #0 hashmap_add hashmap.c:209 #1 hash_dir_entry_with_parent_and_prefix name-hash.c:302 #2 handle_range_dir name-hash.c:347 #3 handle_range_1 name-hash.c:415 #4 lazy_dir_thread_proc name-hash.c:471 #5 Previous write of size 4 at 0x00000082d488 by thread T1 (mutexes: write M31): #0 hashmap_add hashmap.c:209 #1 hash_dir_entry_with_parent_and_prefix name-hash.c:302 #2 handle_range_dir name-hash.c:347 #3 handle_range_1 name-hash.c:415 #4 handle_range_dir name-hash.c:380 #5 handle_range_1 name-hash.c:415 #6 lazy_dir_thread_proc name-hash.c:471 #7 Martin gives instructions for running TSan on test t3008 in this post: https://public-inbox.org/git/CAN0heSoJDL9pWELD6ciLTmWf-a=oyxe4EXXOmCKvsG5MSuzxsA@mail.gmail.com/ Signed-off-by: Jeff Hostetler Signed-off-by: Junio C Hamano --- name-hash.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'name-hash.c') diff --git a/name-hash.c b/name-hash.c index bd8dc7a6a7..45c98db0a0 100644 --- a/name-hash.c +++ b/name-hash.c @@ -584,9 +584,15 @@ static void lazy_init_name_hash(struct index_state *istate) hashmap_init(&istate->dir_hash, dir_entry_cmp, NULL, istate->cache_nr); if (lookup_lazy_params(istate)) { - hashmap_disallow_rehash(&istate->dir_hash, 1); + /* + * Disable item counting and automatic rehashing because + * we do per-chain (mod n) locking rather than whole hashmap + * locking and we need to prevent the table-size from changing + * and bucket items from being redistributed. + */ + hashmap_disable_item_counting(&istate->dir_hash); threaded_lazy_init_name_hash(istate); - hashmap_disallow_rehash(&istate->dir_hash, 0); + hashmap_enable_item_counting(&istate->dir_hash); } else { int nr; for (nr = 0; nr < istate->cache_nr; nr++) -- cgit v1.2.3