Commit message (Collapse) | Author | Files | Lines | ||
---|---|---|---|---|---|
2016-01-11 | smptests/README: Delete obsolete information | Sebastian Huber | 1 | -5/+0 | |
2015-06-03 | smptests/smpscheduler02: Reduce required CPU count | Sebastian Huber | 1 | -41/+50 | |
2015-06-03 | smptests/smpmrsp01: Reduce required CPU count | Sebastian Huber | 1 | -8/+13 | |
2015-06-03 | smptests/smpscheduler03: Use proper lock | Sebastian Huber | 1 | -9/+9 | |
2015-05-19 | smptests/smpscheduler03: Restructure | Sebastian Huber | 1 | -41/+42 | |
Restructure to avoid large maximum thread dispatch disabled times. | |||||
2015-05-19 | score: Rework _Thread_Change_priority() | Sebastian Huber | 1 | -19/+43 | |
Move the writes to Thread_Control::current_priority and Thread_Control::real_priority into _Thread_Change_priority() under the protection of the thread lock. Add a filter function to _Thread_Change_priority() to enable specialized variants. Avoid race conditions during a thread priority restore with the new Thread_Control::priority_restore_hint for an important average case optimizations used by priority inheritance mutexes. Update #2273. | |||||
2015-05-15 | smptests/smpcache01: Restructure | Sebastian Huber | 2 | -109/+105 | |
Restructure to avoid large maximum thread dispatch disabled times. | |||||
2015-05-11 | score: Fix scheduler helping protocol | Sebastian Huber | 2 | -250/+478 | |
Account for priority changes of threads executing in a foreign partition. Exchange idle threads in case a victim node uses an idle thread and the new scheduled node needs an idle thread. | |||||
2015-04-22 | smptests/smpcache01: Enable interrupts before waiting for other CPUs | Daniel Cederman | 1 | -2/+2 | |
Otherwise there is a risk that a CPU misses a cache manager message from another CPU and the test hangs. | |||||
2015-04-20 | score: Refactor SMP cache manager support | Sebastian Huber | 1 | -17/+6 | |
2015-03-25 | smpmigration01: Delete timing dependent assert | Sebastian Huber | 1 | -3/+6 | |
The cycles per runner depends too heavily on the hardware timing making the assert unreliable. Delete runner tasks before we print out the status. | |||||
2015-03-24 | smptests/smpfatal08: Workaround for QorIQ BSPs | Sebastian Huber | 1 | -0/+8 | |
2015-03-17 | testsupport: Add worker setup handler | Sebastian Huber | 1 | -11/+24 | |
Add rtems_test_parallel_get_task_id(). | |||||
2015-03-06 | testsupport: Add cascade option to parallel test | Alexander Krutwig | 1 | -30/+60 | |
2015-03-05 | tests: Refactor parallel test execution | Alexander Krutwig | 1 | -147/+140 | |
2015-03-04 | smptests/smpcapture01: Avoid livelock condition | Sebastian Huber | 2 | -41/+54 | |
2015-03-04 | smptests: Do not use Giant directly | Sebastian Huber | 2 | -6/+6 | |
This ensures that thread dispatching is disabled. A Giant acquire/release pair must take place in the same processor. | |||||
2015-02-19 | score: Make <rtems/score/atomic.h> available | Sebastian Huber | 2 | -207/+0 | |
Make <rtems/score/atomic.h> available for all RTEMS configurations. Use inline functions instead of macros. Use ISR disable/enable on uni-processor configurations to ensure atomicity. Update #2273. | |||||
2015-02-17 | score: Add _CPU_SMP_Prepare_start_multitasking() | Sebastian Huber | 1 | -7/+5 | |
Update #2268. | |||||
2015-02-11 | smpcapture02: Add test of functionality to add custom entries to capture trace | Daniel Cederman | 6 | -0/+478 | |
2015-01-14 | smptests/smpmrsp01: Fix task delete race condition | Sebastian Huber | 1 | -2/+3 | |
Do not supsend self while waiting for termination since the rtems_task_delete() may take place while the rtems_task_suspend() waits for the Giant lock preventing delivery of the inter-processor interrupt. The result is a suspended and terminated thread (this is a valid state, but leads in this case to a test failure). | |||||
2015-01-09 | smptests/smpwakeafter01: Fix task count | Sebastian Huber | 1 | -1/+1 | |
2015-01-09 | smptests/smpmrsp01: Update run indicator only once | Sebastian Huber | 1 | -1/+3 | |
On the Freescale T2080 the excessive concurrent write/read lead to a livelock condition. | |||||
2014-12-18 | smp: Fix timeout for MrsP semaphores | Sebastian Huber | 2 | -32/+93 | |
The previous timeout handling was flawed. In case a waiting thread helped out the owner could use the scheduler node indefinitely long. Update the resource tree in _MRSP_Timeout() to avoid this issue. Bug reported by Luca Bonato. | |||||
2014-12-05 | Update bug report URL | Sebastian Huber | 1 | -1/+1 | |
2014-11-27 | smptests/smpmrsp01: Use busy waits | Sebastian Huber | 1 | -18/+20 | |
Use busy waits instead of sleeps to avoid unnecessary switches to the idle thread. | |||||
2014-11-27 | smp: Fix scheduler helping protocol | Sebastian Huber | 2 | -32/+206 | |
Ensure that scheduler nodes in the SCHEDULER_HELP_ACTIVE_OWNER or SCHEDULER_HELP_ACTIVE_RIVAL helping state are always SCHEDULER_SMP_NODE_READY or SCHEDULER_SMP_NODE_SCHEDULED to ensure the MrsP protocol properties. | |||||
2014-11-25 | smp09: Resolve missing prototype warning. | Jennifer Averett | 1 | -0/+8 | |
2014-11-25 | smp07: Resolve missing prototype warning. | Jennifer Averett | 1 | -1/+9 | |
2014-11-25 | smp05: Resolve missing prototype warning. | Jennifer Averett | 1 | -0/+9 | |
2014-11-25 | smp02: Resolve unused method warnings. | Jennifer Averett | 1 | -7/+1 | |
2014-11-25 | smp03: Remove set but not used warning. | Jennifer Averett | 1 | -0/+4 | |
Added status validation. | |||||
2014-11-25 | smpschedsem01: Remove unused variable warning. | Jennifer Averett | 1 | -1/+0 | |
2014-11-25 | smpschedaffinity02: Remove unused prototype. | Jennifer Averett | 1 | -1/+0 | |
2014-11-24 | smpcapture01: New test. | Jennifer Averett | 6 | -0/+389 | |
2014-11-24 | smp: Fix scheduler helping protocol | Luca Bonato | 2 | -0/+191 | |
New test case for smptests/smpmrsp01. Fix _Scheduler_Block_node() in case the node is in the SCHEDULER_HELP_ACTIVE_RIVAL helping state. For example a rtems_task_suspend() on a task waiting for a MrsP semaphore. Fix _Scheduler_Unblock_node() in case the node is in the SCHEDULER_SMP_NODE_READY state. For example a rtems_task_resume() on a task owning or waiting for a MrsP semaphore. | |||||
2014-11-20 | smpschedaffinity05: Change semaphore attributes. | Jennifer Averett | 1 | -6/+4 | |
Change semaphore attributes to resolve problem where semaphore is not released upon a context switch. | |||||
2014-11-20 | smpschedaffinity04: Change semaphore attributes. | Jennifer Averett | 1 | -5/+3 | |
Change semaphore attributes to prevent semaphore from being locked and never released upon a context switch. | |||||
2014-11-20 | smpschedaffinity02: Change semaphore attributes. | Jennifer Averett | 1 | -5/+4 | |
Change semaphore attributes to prevent semaphore from being locked and never released upon a context switch. | |||||
2014-10-24 | smptests/smpfatal03: Wait for end of test msg | Sebastian Huber | 1 | -0/+2 | |
2014-10-24 | tests/smptests: Normal use of test extension | Sebastian Huber | 2 | -4/+4 | |
2014-10-23 | tests/smptests: Use barriers in smpfatal0{12} | Sebastian Huber | 2 | -4/+18 | |
Call the test extension explicitly and wait for report output using a barrier. This avoids problems with an early shutdown of the system. | |||||
2014-09-17 | smptests/smpload01: Report profiling only once | Sebastian Huber | 2 | -184/+0 | |
Rely on test extension to report profiling. | |||||
2014-09-16 | smptests/smpcache01: Remove invalidation of data cache lines from test | Daniel Cederman | 3 | -33/+33 | |
Invalidation of entire data cache might cause data written to the stack to get lost. | |||||
2014-09-01 | smptests/smplock01: Update screen file | Sebastian Huber | 1 | -1/+1 | |
2014-09-01 | tests: Add documentation | Sebastian Huber | 9 | -13/+75 | |
2014-09-01 | smptests/smpfatal08: Fix link error | Sebastian Huber | 1 | -0/+7 | |
2014-08-22 | smptests/smpcache01: Test the SMP cache manager | Daniel Cederman | 6 | -0/+342 | |
Invokes SMP cache management routines under different scenarios. | |||||
2014-07-11 | smpschedsem01: new test. | Jennifer Averett | 6 | -0/+134 | |
This test verifies priority is inherited from a high priority semaphore by a lower priority task. | |||||
2014-07-11 | smpschedaffinity05: Add test for worst case migration for affintiy scheduler. | Jennifer Averett | 6 | -0/+295 | |
This test uses a combination of priority and affinity to cause the tasks running on all 4 cores to change due to one task priority change. |