From ddea504a7d69d76de6da243d71b507df91d05593 Mon Sep 17 00:00:00 2001 From: Jon Olav Hauglid Date: Wed, 16 Dec 2009 12:32:11 +0100 Subject: [PATCH] Bug #48541 Deadlock between LOCK_open and LOCK_mdl The reason for the deadlock was an improper exit from MDL_context::wait_for_locks() which caused mysys_var->current_mutex to remain LOCK_mdl even though LOCK_mdl was no longer held by that connection. This could for example lead to a deadlock in the following way: 1) INSERT DELAYED tries to open a table but fails, and trying to recover it calls wait_for_locks(). 2) Due to a pending exclusive request, wait_for_locks() fails and exits without resetting mysys_var->current_mutex for the delayed insert handler thread. So it continues to point to LOCK_mdl. 3) The handler thread manages to open a table. 4) A different connection takes LOCK_open and tries to take LOCK_mdl. 5) FLUSH TABLES from a third connection notices that the handler thread has a table open, and tries to kill it. This involves locking mysys_var->current_mutex while having LOCK_open locked. Since current_mutex mistakenly points to LOCK_mdl, we have a deadlock. This patch makes sure MDL_EXIT_COND() is called before exiting wait_for_locks(). This clears mysys->current_mutex which resolves the issue. An assert is added to recover_from_failed_open_table_attempt() after wait_for_locks() is called, to check that current_mutex is indeed reset. With this assert in place, existing tests in (e.g.) mdl_sync.test will fail without this patch. --- sql/mdl.cc | 3 ++- sql/sql_base.cc | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/sql/mdl.cc b/sql/mdl.cc index a883b21423e..6187d4515a3 100644 --- a/sql/mdl.cc +++ b/sql/mdl.cc @@ -1254,7 +1254,8 @@ MDL_context::wait_for_locks(MDL_request_list *mdl_requests) } if (!mdl_request) { - pthread_mutex_unlock(&LOCK_mdl); + /* As a side-effect MDL_EXIT_COND() unlocks LOCK_mdl. */ + MDL_EXIT_COND(m_thd, mysys_var, old_msg); break; } pthread_cond_wait(&COND_mdl, &LOCK_mdl); diff --git a/sql/sql_base.cc b/sql/sql_base.cc index 99a0b33f213..61028f692b3 100644 --- a/sql/sql_base.cc +++ b/sql/sql_base.cc @@ -3693,6 +3693,7 @@ recover_from_failed_open_table_attempt(THD *thd, TABLE_LIST *table) case OT_WAIT: result= (thd->mdl_context.wait_for_locks(&m_mdl_requests) || tdc_wait_for_old_versions(thd, &m_mdl_requests)); + DBUG_ASSERT(thd->mysys_var->current_mutex == NULL); break; case OT_DISCOVER: {