Changeset c5831a3f in rtems for cpukit/score/src/threadcreateidle.c

Timestamp:

04/09/14 13:07:54 (9 years ago)

Author:

Sebastian Huber <sebastian.huber@…>

Branches:

4.11, 5, master

Children:

509040f0

Parents:

27270b0d

git-author:

Sebastian Huber <sebastian.huber@…> (04/09/14 13:07:54)

git-committer:

Sebastian Huber <sebastian.huber@…> (04/15/14 08:41:44)

Message:

score: Add clustered/partitioned scheduling

Clustered/partitioned scheduling helps to control the worst-case
latencies in the system. The goal is to reduce the amount of shared
state in the system and thus prevention of lock contention. Modern
multi-processor systems tend to have several layers of data and
instruction caches. With clustered/partitioned scheduling it is
possible to honour the cache topology of a system and thus avoid
expensive cache synchronization traffic.

We have clustered scheduling in case the set of processors of a system
is partitioned into non-empty pairwise-disjoint subsets. These subsets
are called clusters. Clusters with a cardinality of one are partitions.
Each cluster is owned by exactly one scheduler instance.

File:

• cpukit/score/src/threadcreateidle.c (modified) (3 diffs)

cpukit/score/src/threadcreateidle.c

@@ -20 +20 @@
 
 #include <rtems/score/threadimpl.h>
+#include <rtems/score/schedulerimpl.h>
 #include <rtems/score/stackimpl.h>
 #include <rtems/config.h>
@@ -40 +41 @@
     &_Thread_Internal_information,
     idle,
+    _Scheduler_Get_by_CPU( per_cpu ),
     NULL,        /* allocate the stack */
     _Stack_Ensure_minimum( rtems_configuration_get_idle_task_stack_size() ),
@@ -76 +78 @@
     Per_CPU_Control *per_cpu = _Per_CPU_Get_by_index( processor );
 
-    _Thread_Create_idle_for_cpu( per_cpu );
+    if ( _Per_CPU_Is_processor_started( per_cpu ) ) {
+      _Thread_Create_idle_for_cpu( per_cpu );
+    }
   }
 }