simulator: Improve simulator resource model (#142)

This pull request improves the existing simulator resource model
that is at the core of all simulation models in OpenDC. 
Most importantly, we have changed the way of how metrics are reported by this layer.

* Add `SimResourceInterpreter` which is responsible for efficiently scheduling 
  communication between resources in OpenDC. The performance gain is in the 2x-5x range.
* Add uniform interface for exposing resource metrics (using `SimResourceCounters`).
* Split the CPUFreq subsystem in the compute simulator as it mixed responsibilities of 
  different layers.

**Breaking API Changes**

* Resource providers now accept a `SimResourceInterpreter` which is
   responsible for coordinating the communication between resources.
* `ScalingGovernor` is not part of the machine layer anymore. Instead, it should 
   move in the OS/Hypervisor layer.
* Workloads should now start CPU consumers using `cpu.startConsumer`.

1 files changed, 4 insertions, 4 deletions

diff --git a/opendc-experiments/opendc-experiments-capelin/src/test/kotlin/org/opendc/experiments/capelin/CapelinIntegrationTest.kt b/opendc-experiments/opendc-experiments-capelin/src/test/kotlin/org/opendc/experiments/capelin/CapelinIntegrationTest.kt
index 2d5cc68c..4b21b4f7 100644
--- a/opendc-experiments/opendc-experiments-capelin/src/test/kotlin/org/opendc/experiments/capelin/CapelinIntegrationTest.kt
+++ b/opendc-experiments/opendc-experiments-capelin/src/test/kotlin/org/opendc/experiments/capelin/CapelinIntegrationTest.kt
@@ -113,8 +113,8 @@ class CapelinIntegrationTest {
             { assertEquals(0, monitorResults.runningVms, "All VMs should finish after a run") },
             { assertEquals(0, monitorResults.unscheduledVms, "No VM should not be unscheduled") },
             { assertEquals(0, monitorResults.queuedVms, "No VM should not be in the queue") },
-            { assertEquals(207389912923, monitor.totalRequestedBurst) { "Incorrect requested burst" } },
-            { assertEquals(207122087280, monitor.totalGrantedBurst) { "Incorrect granted burst" } },
+            { assertEquals(207380244590, monitor.totalRequestedBurst) { "Incorrect requested burst" } },
+            { assertEquals(207112418950, monitor.totalGrantedBurst) { "Incorrect granted burst" } },
             { assertEquals(267825640, monitor.totalOvercommissionedBurst) { "Incorrect overcommitted burst" } },
             { assertEquals(0, monitor.totalInterferedBurst) { "Incorrect interfered burst" } }
         )
@@ -150,8 +150,8 @@ class CapelinIntegrationTest {
 
         // Note that these values have been verified beforehand
         assertAll(
-            { assertEquals(96350072517, monitor.totalRequestedBurst) { "Total requested work incorrect" } },
-            { assertEquals(96330335057, monitor.totalGrantedBurst) { "Total granted work incorrect" } },
+            { assertEquals(96344616902, monitor.totalRequestedBurst) { "Total requested work incorrect" } },
+            { assertEquals(96324879442, monitor.totalGrantedBurst) { "Total granted work incorrect" } },
             { assertEquals(19737460, monitor.totalOvercommissionedBurst) { "Total overcommitted work incorrect" } },
             { assertEquals(0, monitor.totalInterferedBurst) { "Total interfered work incorrect" } }
         )