merge: Extract scheduler from simulation coroutine dispatcher (#106)

This pull request extracts the scheduler from the `SimulationCoroutineDispatcher` into 
a separate `SimulationScheduler` class which allows users to re-use the scheduler 
between different coroutine dispatchers.

We implement the `SimulationScheduler` in Java, removing the explicit dependency on 
Kotlin or `kotlinx-coroutines`. The scheduler uses a separate specialized priority queue 
implementation that eliminates allocation in the hot path of the simulator.

## Implementation Notes :hammer_and_pick:

* Add Java-based simulator core
* Use SimulationScheduler in coroutine dispatcher
* Rename runBlockingSimulation to runSimulation

## External Dependencies :four_leaf_clover:

* N/A 

## Breaking API Changes :warning:

* The Kotlin API for simulation has been moved to `org.opendc.simulator.kotlin`.
* `runBlockingSImulation` renamed to `runSimulation`

1 files changed, 8 insertions, 8 deletions

diff --git a/opendc-simulator/opendc-simulator-compute/src/jmh/kotlin/org/opendc/simulator/compute/SimMachineBenchmarks.kt b/opendc-simulator/opendc-simulator-compute/src/jmh/kotlin/org/opendc/simulator/compute/SimMachineBenchmarks.kt
index 797d424e..b319a677 100644
--- a/opendc-simulator/opendc-simulator-compute/src/jmh/kotlin/org/opendc/simulator/compute/SimMachineBenchmarks.kt
+++ b/opendc-simulator/opendc-simulator-compute/src/jmh/kotlin/org/opendc/simulator/compute/SimMachineBenchmarks.kt
@@ -33,9 +33,9 @@ import org.opendc.simulator.compute.power.ConstantPowerModel
 import org.opendc.simulator.compute.power.SimplePowerDriver
 import org.opendc.simulator.compute.workload.SimTrace
 import org.opendc.simulator.compute.workload.SimTraceWorkload
-import org.opendc.simulator.core.runBlockingSimulation
 import org.opendc.simulator.flow.FlowEngine
 import org.opendc.simulator.flow.mux.FlowMultiplexerFactory
+import org.opendc.simulator.kotlin.runSimulation
 import org.openjdk.jmh.annotations.*
 import java.util.SplittableRandom
 import java.util.concurrent.ThreadLocalRandom
@@ -70,18 +70,18 @@ class SimMachineBenchmarks {
 
     @Benchmark
     fun benchmarkBareMetal() {
-        return runBlockingSimulation {
+        return runSimulation {
             val engine = FlowEngine(coroutineContext, clock)
             val machine = SimBareMetalMachine(
                 engine, machineModel, SimplePowerDriver(ConstantPowerModel(0.0))
             )
-            return@runBlockingSimulation machine.runWorkload(SimTraceWorkload(trace))
+            return@runSimulation machine.runWorkload(SimTraceWorkload(trace))
         }
     }
 
     @Benchmark
     fun benchmarkSpaceSharedHypervisor() {
-        return runBlockingSimulation {
+        return runSimulation {
             val engine = FlowEngine(coroutineContext, clock)
             val machine = SimBareMetalMachine(engine, machineModel, SimplePowerDriver(ConstantPowerModel(0.0)))
             val hypervisor = SimHypervisor(engine, FlowMultiplexerFactory.forwardingMultiplexer(), SplittableRandom(1), null)
@@ -91,7 +91,7 @@ class SimMachineBenchmarks {
             val vm = hypervisor.newMachine(machineModel)
 
             try {
-                return@runBlockingSimulation vm.runWorkload(SimTraceWorkload(trace))
+                return@runSimulation vm.runWorkload(SimTraceWorkload(trace))
             } finally {
                 vm.cancel()
                 machine.cancel()
@@ -101,7 +101,7 @@ class SimMachineBenchmarks {
 
     @Benchmark
     fun benchmarkFairShareHypervisorSingle() {
-        return runBlockingSimulation {
+        return runSimulation {
             val engine = FlowEngine(coroutineContext, clock)
             val machine = SimBareMetalMachine(engine, machineModel, SimplePowerDriver(ConstantPowerModel(0.0)))
             val hypervisor = SimHypervisor(engine, FlowMultiplexerFactory.maxMinMultiplexer(), SplittableRandom(1), null)
@@ -111,7 +111,7 @@ class SimMachineBenchmarks {
             val vm = hypervisor.newMachine(machineModel)
 
             try {
-                return@runBlockingSimulation vm.runWorkload(SimTraceWorkload(trace))
+                return@runSimulation vm.runWorkload(SimTraceWorkload(trace))
             } finally {
                 vm.cancel()
                 machine.cancel()
@@ -121,7 +121,7 @@ class SimMachineBenchmarks {
 
     @Benchmark
     fun benchmarkFairShareHypervisorDouble() {
-        return runBlockingSimulation {
+        return runSimulation {
             val engine = FlowEngine(coroutineContext, clock)
             val machine = SimBareMetalMachine(engine, machineModel, SimplePowerDriver(ConstantPowerModel(0.0)))
             val hypervisor = SimHypervisor(engine, FlowMultiplexerFactory.maxMinMultiplexer(), SplittableRandom(1), null)