This ChangeSet must be null-merged to 5.1. Applied innodb-5.0-ss982, -ss998, -ss1003

Fixes:
- Bug #15815: Very poor performance with multiple queries running concurrently
- Bug #22868: 'Thread thrashing' with > 50 concurrent conns under an upd-intensive workloadw
- Bug #23769: Debug assertion failure with innodb_locks_unsafe_for_binlog
- Bug #24089: Race condition in fil_flush_file_spaces()


innobase/buf/buf0buf.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1000:
  branches/5.0: Merge r999 from trunk:
  
  Reduce buffer pool mutex contention under >= 4 big concurrent
  CPU-bound SELECT queries.  (Bug #22868)
  
  Fix: replace the mutex by one mutex protecting the 'flush list'
  (and the free list) and several mutexes protecting portions of the
  buffer pool, where we keep several indivudual LRU lists of pages.
  
  This patch is from Sunny Bains and Heikki Tuuri.
innobase/buf/buf0flu.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1000:
  branches/5.0: Merge r999 from trunk:
  
  Reduce buffer pool mutex contention under >= 4 big concurrent
  CPU-bound SELECT queries.  (Bug #22868)
  
  Fix: replace the mutex by one mutex protecting the 'flush list'
  (and the free list) and several mutexes protecting portions of the
  buffer pool, where we keep several indivudual LRU lists of pages.
  
  This patch is from Sunny Bains and Heikki Tuuri.
innobase/buf/buf0lru.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1000:
  branches/5.0: Merge r999 from trunk:
  
  Reduce buffer pool mutex contention under >= 4 big concurrent
  CPU-bound SELECT queries.  (Bug #22868)
  
  Fix: replace the mutex by one mutex protecting the 'flush list'
  (and the free list) and several mutexes protecting portions of the
  buffer pool, where we keep several indivudual LRU lists of pages.
  
  This patch is from Sunny Bains and Heikki Tuuri.
innobase/dict/dict0crea.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r974:
  branches/5.0: Port r973 from trunk.
  
  Do not break the latching order in TRUNCATE TABLE.
  
  dict_truncate_index_tree(): Replace parameter rec_t* rec with
  btr_pcur_t* pcur.  Reposition pcur before calling btr_create().
  
  sync_thread_add_level(): Remove the relaxation of the assertion added in r968.
innobase/fil/fil0fil.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1003:
  branches/5.0: Merge r1002 from trunk:
  
  fil_flush_file_spaces(): Copy the system->unflushed_spaces list to an
  array while holding the mutex.  This removes the crash-triggering
  race condition that was introduced when fixing Bug 15653.  (Bug #24089)
innobase/include/buf0buf.h:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1000:
  branches/5.0: Merge r999 from trunk:
  
  Reduce buffer pool mutex contention under >= 4 big concurrent
  CPU-bound SELECT queries.  (Bug #22868)
  
  Fix: replace the mutex by one mutex protecting the 'flush list'
  (and the free list) and several mutexes protecting portions of the
  buffer pool, where we keep several indivudual LRU lists of pages.
  
  This patch is from Sunny Bains and Heikki Tuuri.
innobase/include/buf0buf.ic:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1000:
  branches/5.0: Merge r999 from trunk:
  
  Reduce buffer pool mutex contention under >= 4 big concurrent
  CPU-bound SELECT queries.  (Bug #22868)
  
  Fix: replace the mutex by one mutex protecting the 'flush list'
  (and the free list) and several mutexes protecting portions of the
  buffer pool, where we keep several indivudual LRU lists of pages.
  
  This patch is from Sunny Bains and Heikki Tuuri.
innobase/include/dict0crea.h:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r974:
  branches/5.0: Port r973 from trunk.
  
  Do not break the latching order in TRUNCATE TABLE.
  
  dict_truncate_index_tree(): Replace parameter rec_t* rec with
  btr_pcur_t* pcur.  Reposition pcur before calling btr_create().
  
  sync_thread_add_level(): Remove the relaxation of the assertion added in r968.
innobase/include/sync0arr.h:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.
innobase/include/sync0rw.h:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.
innobase/include/sync0rw.ic:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.
innobase/include/sync0sync.h:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.
innobase/os/os0sync.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.
innobase/row/row0mysql.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r974:
  branches/5.0: Port r973 from trunk.
  
  Do not break the latching order in TRUNCATE TABLE.
  
  dict_truncate_index_tree(): Replace parameter rec_t* rec with
  btr_pcur_t* pcur.  Reposition pcur before calling btr_create().
  
  sync_thread_add_level(): Remove the relaxation of the assertion added in r968.
innobase/row/row0sel.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r982:
  branches/5.0: row_sel(): Do not try to acquire a LOCK_REC_NOT_GAP lock
  on the supremum record.  Instead, skip to the next record.  (Bug #23769)
  This fix was backported from r623 in the 5.1 tree.
innobase/srv/srv0start.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r926:
  Refer to bug: 22268. Since no one tries to run 5.0 on Windows 95/ME it was
  decided to raise the limit of srv_max_n_threads to 10000 on Windows.
innobase/sync/sync0arr.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.
innobase/sync/sync0rw.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.
innobase/sync/sync0sync.c:
  Applied innodb-5.0-ss982, -ss998, -ss1003
  
  Revision r969:
  branches/5.0: Port r968 from trunk:
  
  sync_thread_add_level(): When level == SYNC_TREE_NODE, allow the latching
  order to be violated if the thread holds dict_operation_lock, whose level is
  SYNC_DICT_OPERATION.  This removes the assertion failure of TRUNCATE TABLE
  #ifdef UNIV_SYNC_DEBUG.
  
  
  Revision r974:
  branches/5.0: Port r973 from trunk.
  
  Do not break the latching order in TRUNCATE TABLE.
  
  dict_truncate_index_tree(): Replace parameter rec_t* rec with
  btr_pcur_t* pcur.  Reposition pcur before calling btr_create().
  
  sync_thread_add_level(): Remove the relaxation of the assertion added in r968.
  
  
  Revision r1001:
  branches/5.0: Reduce locking contention:
  
  Bug #15815: 'Thread thrashing' with > 50 concurrent connections under
  an update-intensive workload.
  Fix: Introduce one event per InnoDB semaphore.
  
  This patch is from Sunny Bains and Heikki Tuuri.
  This patch will not be merged to trunk (MySQL/InnoDB 5.1) yet,
  because it tries to address the problem in a different way.

1 files changed, 52 insertions, 3 deletions

diff --git a/innobase/os/os0sync.c b/innobase/os/os0sync.c
index 8bafb73baf8..a3204a7b3e8 100644
--- a/innobase/os/os0sync.c
+++ b/innobase/os/os0sync.c
@@ -21,6 +21,7 @@ Created 9/6/1995 Heikki Tuuri
 
 /* Type definition for an operating system mutex struct */
 struct os_mutex_struct{ 
+	os_event_t	event;	/* Used by sync0arr.c for queing threads */
 	void*		handle;	/* OS handle to mutex */
 	ulint		count;	/* we use this counter to check
 				that the same thread does not
@@ -35,6 +36,7 @@ struct os_mutex_struct{
 /* Mutex protecting counts and the lists of OS mutexes and events */
 os_mutex_t	os_sync_mutex;
 ibool		os_sync_mutex_inited	= FALSE;
+ibool		os_sync_free_called	= FALSE;
 
 /* This is incremented by 1 in os_thread_create and decremented by 1 in
 os_thread_exit */
@@ -50,6 +52,10 @@ ulint	os_event_count		= 0;
 ulint	os_mutex_count		= 0;
 ulint	os_fast_mutex_count	= 0;
 
+/* Because a mutex is embedded inside an event and there is an
+event embedded inside a mutex, on free, this generates a recursive call.
+This version of the free event function doesn't acquire the global lock */
+static void os_event_free_internal(os_event_t	event);
 
 /*************************************************************
 Initializes global event and OS 'slow' mutex lists. */
@@ -76,6 +82,7 @@ os_sync_free(void)
 	os_event_t	event;
 	os_mutex_t	mutex;
 
+	os_sync_free_called = TRUE;
 	event = UT_LIST_GET_FIRST(os_event_list);
 
 	while (event) {
@@ -99,6 +106,7 @@ os_sync_free(void)
 
 	      mutex = UT_LIST_GET_FIRST(os_mutex_list);
 	}
+	os_sync_free_called = FALSE;
 }
 
 /*************************************************************
@@ -146,14 +154,21 @@ os_event_create(
 	event->signal_count = 0;
 #endif /* __WIN__ */
 
-        /* Put to the list of events */
-	os_mutex_enter(os_sync_mutex);
+	/* The os_sync_mutex can be NULL because during startup an event
+	can be created [ because it's embedded in the mutex/rwlock ] before
+	this module has been initialized */
+	if (os_sync_mutex != NULL) {
+		os_mutex_enter(os_sync_mutex);
+	}
 
+	/* Put to the list of events */
 	UT_LIST_ADD_FIRST(os_event_list, os_event_list, event);
 
 	os_event_count++;
 
-	os_mutex_exit(os_sync_mutex);
+	if (os_sync_mutex != NULL) {
+		os_mutex_exit(os_sync_mutex);
+	}
 
 	return(event);
 }
@@ -256,6 +271,35 @@ os_event_reset(
 }
 
 /**************************************************************
+Frees an event object, without acquiring the global lock. */
+static
+void
+os_event_free_internal(
+/*===================*/
+	os_event_t	event)	/* in: event to free */
+{
+#ifdef __WIN__
+	ut_a(event);
+
+	ut_a(CloseHandle(event->handle));
+#else
+	ut_a(event);
+
+	/* This is to avoid freeing the mutex twice */
+	os_fast_mutex_free(&(event->os_mutex));
+
+	ut_a(0 == pthread_cond_destroy(&(event->cond_var)));
+#endif
+	/* Remove from the list of events */
+
+	UT_LIST_REMOVE(os_event_list, os_event_list, event);
+
+	os_event_count--;
+
+	ut_free(event);
+}
+
+/**************************************************************
 Frees an event object. */
 
 void
@@ -456,6 +500,7 @@ os_mutex_create(
 
 	mutex_str->handle = mutex;
 	mutex_str->count = 0;
+	mutex_str->event = os_event_create(NULL);
 
 	if (os_sync_mutex_inited) {
 		/* When creating os_sync_mutex itself we cannot reserve it */
@@ -532,6 +577,10 @@ os_mutex_free(
 {
 	ut_a(mutex);
 
+	if (!os_sync_free_called) {
+		os_event_free_internal(mutex->event);
+	}
+
 	if (os_sync_mutex_inited) {
 		os_mutex_enter(os_sync_mutex);
 	}