| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Use variable i instead of variable cpus as an index to get correct kseq. | davidxu | 2005-12-27 | 1 | -1/+1 |
| * | Fix a bug in slice calculation code, current code uses hz but | davidxu | 2005-12-19 | 1 | -19/+31 |
| * | Temporarily disable nice threshold detection code, as it can starve | davidxu | 2005-09-22 | 1 | -1/+3 |
| * | Move up code for testing KEF_HOLD to avoid ke_cpu being changed unexpectly | davidxu | 2005-08-19 | 1 | -8/+8 |
| * | Try best to keep a preempted thread at front of run queue, this seems | davidxu | 2005-08-08 | 1 | -1/+9 |
| * | If a thread was removed from system run queue, kse_assign shouldn't | davidxu | 2005-07-31 | 1 | -0/+4 |
| * | Cast to uintptr_t when the compiler complains. This unbreaks ULE | delphij | 2005-07-25 | 1 | -2/+4 |
| * | Move HWPMC_HOOKS into its own opt_hwpmc_hooks.h file. It doesn't merit | peter | 2005-06-24 | 1 | -1/+2 |
| * | - Fix the case where we're not preempting but there is already a newtd | jeff | 2005-06-07 | 1 | -3/+11 |
| * | - It's 2005 already, I've been working on this for three years. | jeff | 2005-06-04 | 1 | -1/+1 |
| * | - Don't SLOT_USE() in the preempt case, sched_add() has already taken the | jeff | 2005-06-04 | 1 | -72/+37 |
| * | Bring a working snapshot of hwpmc(4), its associated libraries, userland util... | jkoshy | 2005-04-19 | 1 | -1/+22 |
| * | Sprinkle some volatile magic and rearrange things a bit to avoid race | ups | 2005-04-08 | 1 | -1/+1 |
| * | - A test in sched_switch() is no longer necessary and it is incorrect | jeff | 2005-02-23 | 1 | -2/+0 |
| * | - Add ke_runq == NULL to the conditions which will cause us to abort | jeff | 2005-02-04 | 1 | -2/+2 |
| * | Fix a typo and two whitespace nits. | jhb | 2004-12-30 | 1 | -3/+3 |
| * | Rework the interface between priority propagation (lending) and the | jhb | 2004-12-30 | 1 | -20/+77 |
| * | - Unintentionally checked in a debugging panic. Remove that. | jeff | 2004-12-26 | 1 | -4/+0 |
| * | - Fix a long standing problem where an ithread would not honor sched_pin(). | jeff | 2004-12-26 | 1 | -127/+140 |
| * | - Remove earlier KTR_ULE tracepoints. | jeff | 2004-12-26 | 1 | -32/+14 |
| * | - Garbage collect several unused members of struct kse and struce ksegrp. | jeff | 2004-12-14 | 1 | -9/+0 |
| * | - In kseq_choose(), don't recalculate slice values for processes with a | jeff | 2004-12-14 | 1 | -11/+25 |
| * | - Take up a 'slot' while we're on the assigned queue, waiting to be | jeff | 2004-12-13 | 1 | -16/+16 |
| * | - Temporarily disable the nice -20 throttling code. It has some interaction | jeff | 2004-11-11 | 1 | -0/+4 |
| * | - When choosing a thread on the run queue, check to see if its nice is | jeff | 2004-10-30 | 1 | -2/+4 |
| * | - In sched_prio() check to see if the kse is assigned to a runq as the | jeff | 2004-10-30 | 1 | -1/+1 |
| * | Fix whitespace botch that only showed up in the commit message diff :-/ | julian | 2004-10-05 | 1 | -1/+1 |
| * | When preempting a thread, put it back on the HEAD of its run queue. | julian | 2004-10-05 | 1 | -6/+14 |
| * | Oops. left out part of the diff. | julian | 2004-10-05 | 1 | -0/+2 |
| * | Use some macros to trach available scheduler slots to allow | julian | 2004-10-05 | 1 | -16/+30 |
| * | clean up thread runq accounting a bit. | julian | 2004-09-16 | 1 | -0/+2 |
| * | Revert the previous round of changes to td_pinned. The scheduler isn't | scottl | 2004-09-11 | 1 | -24/+2 |
| * | Try committing from the right tree this time | julian | 2004-09-11 | 1 | -3/+3 |
| * | Make up my mind if cpu pinning is stored in the thread structure or the | julian | 2004-09-10 | 1 | -1/+22 |
| * | Add some code to allow threads to nominat a sibling to run if theyu are going... | julian | 2004-09-10 | 1 | -1/+1 |
| * | Refactor a bunch of scheduler code to give basically the same behaviour | julian | 2004-09-05 | 1 | -108/+163 |
| * | Turn PREEMPTION into a kernel option. Make sure that it's defined if | scottl | 2004-09-02 | 1 | -0/+14 |
| * | Give setrunqueue() and sched_add() more of a clue as to | julian | 2004-09-01 | 1 | -4/+13 |
| * | Commit Jeff's suggested changes for avoiding a bug that is exposed by | peter | 2004-08-28 | 1 | -4/+2 |
| * | - Introduce a new flag KEF_HOLD that prevents sched_add() from doing a | jeff | 2004-08-12 | 1 | -7/+19 |
| * | - Use a new flag, KEF_XFERABLE, to record with certainty that this kse had | jeff | 2004-08-10 | 1 | -34/+76 |
| * | Avoid casts as lvalues. | kan | 2004-07-28 | 1 | -2/+2 |
| * | Clean up whitespace, increase consistency and correctness. | scottl | 2004-07-23 | 1 | -5/+3 |
| * | When calling scheduler entrypoints for creating new threads and processes, | julian | 2004-07-18 | 1 | -15/+18 |
| * | - Move TDF_OWEPREEMPT, TDF_OWEUPC, and TDF_USTATCLOCK over to td_pflags | jhb | 2004-07-16 | 1 | -1/+2 |
| * | Update for the KDB framework: | marcel | 2004-07-10 | 1 | -4/+2 |
| * | - Move contents of sched_add() into a sched_add_internal() function that | jhb | 2004-07-08 | 1 | -5/+11 |
| * | Temporarily disable preemption in SCHED_ULE due to reported panics and | rwatson | 2004-07-06 | 1 | -0/+2 |
| * | Add NULL arg to mi_switch() call to stop kernel compiles from breaking. | phk | 2004-07-03 | 1 | -1/+1 |
| * | Fix SCHED_ULE build on SMP. The previous revision (1.110) | bmilekic | 2004-07-03 | 1 | -1/+1 |
