| Commit message (Collapse) | Author | Age | |
|---|---|---|---|
| * | Tasks are now scheduled using serversrtas12-mc-beta-exp | Jonathan Herman | 2011-10-14 |
| | | |||
| * | paranoid android | Jonathan Herman | 2011-10-14 |
| | | |||
| * | Merge branch 'wip-mc' of ↵ | Jonathan Herman | 2011-10-14 |
| |\ | | | | | | | ssh://cvs.cs.unc.edu/cvs/proj/litmus/repo/litmus2010 into wip-mc | ||
| | * | revert the cpu mask changes | Christopher Kenna | 2011-10-14 |
| | | | |||
| | * | Had to change TRACE messages to print messages to see them at boot | Jonathan Herman | 2011-10-14 |
| | | | |||
| | * | Debug stuff | Jonathan Herman | 2011-10-14 |
| | | | |||
| | * | Removed possible super error | Jonathan Herman | 2011-10-14 |
| | | | |||
| | * | Fixed dummy page fault thing | Jonathan Herman | 2011-10-14 |
| | | | |||
| * | | Checkpoint | Jonathan Herman | 2011-10-14 |
| |/ | |||
| * | Freeing a cpu for ftracing | Jonathan Herman | 2011-10-13 |
| | | |||
| * | Merge branch 'wip-mc' of ↵ | Jonathan Herman | 2011-10-13 |
| |\ | | | | | | | ssh://cvs.cs.unc.edu/cvs/proj/litmus/repo/litmus2010 into wip-mc | ||
| | * | fix level-a schedule event id and a bad define in rt_domain.h | Christopher Kenna | 2011-10-12 |
| | | | |||
| | * | add level-A scheduling event | Christopher Kenna | 2011-10-11 |
| | | | |||
| * | | Merge branch 'wip-mc' of ↵ | Jonathan Herman | 2011-10-11 |
| |\| | | | | | | | ssh://cvs.cs.unc.edu/cvs/proj/litmus/repo/litmus2010 into wip-mc | ||
| | * | Add level-A release and remove some bad time-trace macros. | Christopher Kenna | 2011-10-11 |
| | | | |||
| * | | Added task level to records | Jonathan Herman | 2011-10-11 |
| |/ | |||
| * | Fixed issue where long delay in VM could lose global tasks. | Jonathan Herman | 2011-10-10 |
| | | |||
| * | Merge branch 'wip-mc' of ↵ | Jonathan Herman | 2011-10-10 |
| |\ | | | | | | | | | | | | | ssh://cvs.cs.unc.edu/cvs/proj/litmus/repo/litmus2010 into wip-mc Conflicts: include/litmus/trace.h | ||
| | * | Litmus core: trace syscall overhead in sched_yield() | Bjoern B. Brandenburg | 2011-10-10 |
| | | | |||
| | * | Feather-Trace: Simplify syscall-in overhead tracing | Bjoern B. Brandenburg | 2011-10-10 |
| | | | | | | | | | | | Just stick TS_SYSCALL_IN_START into any system call that needs tracing. | ||
| | * | Feather-Trace: record PID fragments for locking overheads | Bjoern B. Brandenburg | 2011-10-10 |
| | | | | | | | | | | | | | | | We need to be able to figure out overlapping suspensions, etc. So to reuse the existing format, just encode the lower 16bits of the PID in the cpu and task-type fields (which we don't care about when collecting locking overheads). | ||
| | * | locking: use correct timestamp | Bjoern B. Brandenburg | 2011-10-10 |
| | | | |||
| | * | ftdev: don't hold lock while sleeping | Bjoern B. Brandenburg | 2011-10-10 |
| | | | | | | | | | Holding the lock prevents other tasks from opening the device. | ||
| | * | locking: trace system call entry/exit cost | Bjoern B. Brandenburg | 2011-10-10 |
| | | | |||
| | * | ftdev: remove event activation hack | Bjoern B. Brandenburg | 2011-10-10 |
| | | | | | | | | | | | Instead of doing the hackisch 'write commands to device' thing, let's just use a real ioctl() interface. | ||
| * | | Fixed level-A crash when cancel task execution | Jonathan Herman | 2011-10-10 |
| | | | |||
| * | | Adding events is now accomplished in O(1) time | Jonathan Herman | 2011-10-10 |
| | | | |||
| * | | Fixed potential race condition in event group timer | Jonathan Herman | 2011-10-10 |
| |/ | |||
| * | Allow events to be cancelled when their list is processed | Jonathan Herman | 2011-10-09 |
| | | |||
| * | Fixed bug where finish switch could strand level-C tasks in neverland | Jonathan Herman | 2011-10-09 |
| | | |||
| * | Fixed a timer bug and implemented finish switch. | Jonathan Herman | 2011-10-09 |
| | | | | | | | | | | The logic for cancelling a remote timer allowed timers to be enqueued twice in the pull list. A method hrtimer_pull_cancel() was added to hrtimer.c to cancel the timers properly. Finish-switch was added to fix a stack bug. This required a change to the global_preempt check in update_crit_levels | ||
| * | Fixed bug with CE higher priority | Jonathan Herman | 2011-10-09 |
| | | |||
| * | Renamed list variables for clarity in event_list | Jonathan Herman | 2011-10-08 |
| | | |||
| * | Allow scheduler to 'logically' remove crit_entry's from level-C heap. | Jonathan Herman | 2011-10-08 |
| | | | | | | This required fixes to hrtimer_start_on code so that events can be cancelled or re-armed while an hrtimer pull is in progress. | ||
| * | Fixed timer issue and atomic remove issue in level A domain. | Jonathan Herman | 2011-10-08 |
| | | | | | | | | | | | | Timers had an issue where they couldn't be cancelled before they migrated. Now when you set the start_on_info to inactive, it will prevent a timer from being armed. When a task is being blocked and preempted concurrently, the blocking code needs to be able to prevent the task from being scheduled on another CPU. This did not work for CE domains. Added a per-domain remove function which, for ce domains, will prevent a task from being returned by the domain. | ||
| * | Newline consistency... | Jonathan Herman | 2011-10-07 |
| | | |||
| * | Fixed global task deadlock | Jonathan Herman | 2011-10-07 |
| | | |||
| * | more bugfixes | Christopher Kenna | 2011-10-07 |
| | | |||
| * | debugging | Christopher Kenna | 2011-10-07 |
| | | |||
| * | Bug fix for cancel events | Jonathan Herman | 2011-09-30 |
| | | |||
| * | Debug commit. | Christopher Kenna | 2011-09-30 |
| | | | | | | | | Some things are working, but the kernel panics when you try and deallocate an event group. Committed so Jonathan can look at it. | ||
| * | Merge branch 'wip-mc' of ↵ | Jonathan Herman | 2011-09-30 |
| |\ | | | | | | | ssh://cvs.cs.unc.edu/cvs/proj/litmus/repo/litmus2010 into wip-mc | ||
| | * | Refactor timer merging and add it to CE plugin. | Christopher Kenna | 2011-09-30 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | THIS CODE IS UNTESTED We now initialize one event group for each cpu on system start. We can get the event group for a CPU via a function in event_group.c Another change is that an event now stores what group it is in when it add_event() is called on it. This lets us cancel it without knowing what event group it is in. The above is important because Level-C events (like releases) have a NULL event group. When calling add_event(), it will get the event group of the current CPU. If the event needs to be canceled later, we need that saved group in the event so we know where to remove it from. | ||
| * | | Added display of number of timers merged | Jonathan Herman | 2011-09-28 |
| |/ | |||
| * | Merged with ce domains | Jonathan Herman | 2011-09-27 |
| |\ | |||
| | * | Debugged ghosts in the MC scheduler for CE tasks. | Christopher Kenna | 2011-09-27 |
| | | | |||
| | * | Checkpoint commit. Testing begins. | Christopher Kenna | 2011-09-26 |
| | | | |||
| | * | checkpoint before refactor | Christopher Kenna | 2011-09-26 |
| | | | |||
| | * | Untested merge of CE and MC plugins | Christopher Kenna | 2011-09-25 |
| | | | |||
| * | | Timer merging | Jonathan Herman | 2011-09-27 |
| |/ | |||
 |
index : litmus-rt.git | |
| The LITMUS^RT kernel. | Bjoern Brandenburg |
| aboutsummaryrefslogtreecommitdiffstats |