merge: Do not require interference model during topology construction (#102)

This pull request refactors the existing workload interference model in order 
to remove a dependency on it during the topology construction. With this change, 
interference domains (e.g., a single host) can be constructed independently of the 
interference profiles of virtual machines. 

## Implementation Notes :hammer_and_pick:

* Move VM interference model into compute simulator
* Remove convergence listener parameter 
* Remove FlowEngine from SimMachineContext 
* Remove timestamp parameter from SimTrace 
* Pass interference key via parameter
* Move interference logic into VmInterferenceMember 
* Prevent boxing in interference algorithm 
* Extract Random dependency from interference model
* Add separate error host state 
* Simplify constructor of SimHost 
* Make interference domain independent of profile 

## External Dependencies :four_leaf_clover:

* N/A

## Breaking API Changes :warning:

* The interface of `VmInterferenceModel` is changed. Users do not need to 
   provide a seed for the model anymore.
* A `VmInterferenceModel` should be passed via the metadata parameter of 
  `startWorkload` to enable workload interference.

1 files changed, 3 insertions, 7 deletions

diff --git a/opendc-experiments/opendc-experiments-capelin/src/main/kotlin/org/opendc/experiments/capelin/CapelinRunner.kt b/opendc-experiments/opendc-experiments-capelin/src/main/kotlin/org/opendc/experiments/capelin/CapelinRunner.kt
index cca5b6cf..dbb5ced3 100644
--- a/opendc-experiments/opendc-experiments-capelin/src/main/kotlin/org/opendc/experiments/capelin/CapelinRunner.kt
+++ b/opendc-experiments/opendc-experiments-capelin/src/main/kotlin/org/opendc/experiments/capelin/CapelinRunner.kt
@@ -22,7 +22,6 @@
 
 package org.opendc.experiments.capelin
 
-import org.opendc.compute.api.Server
 import org.opendc.compute.workload.ComputeServiceHelper
 import org.opendc.compute.workload.ComputeWorkloadLoader
 import org.opendc.compute.workload.createComputeScheduler
@@ -68,18 +67,16 @@ public class CapelinRunner(
                 grid5000(Duration.ofSeconds((operationalPhenomena.failureFrequency * 60).roundToLong()))
             else
                 null
-        val (vms, interferenceModel) = scenario.workload.source.resolve(workloadLoader, seeder)
+        val vms = scenario.workload.source.resolve(workloadLoader, seeder)
         val runner = ComputeServiceHelper(
             coroutineContext,
             clock,
             computeScheduler,
-            failureModel,
-            interferenceModel?.withSeed(seed)
+            seed,
         )
 
         val topology = clusterTopology(File(envPath, "${scenario.topology.name}.txt"))
 
-        val servers = mutableListOf<Server>()
         val partitions = scenario.partitions + ("seed" to seed.toString())
         val partition = partitions.map { (k, v) -> "$k=$v" }.joinToString("/")
         val exporter = if (outputPath != null) {
@@ -87,7 +84,6 @@ public class CapelinRunner(
                 this,
                 clock,
                 runner.service,
-                servers,
                 ParquetComputeMonitor(
                     outputPath,
                     partition,
@@ -104,7 +100,7 @@ public class CapelinRunner(
             runner.apply(topology, optimize = true)
 
             // Run the workload trace
-            runner.run(vms, seeder.nextLong(), servers)
+            runner.run(vms, failureModel = failureModel, interference = operationalPhenomena.hasInterference)
 
             // Stop the metric collection
             exporter?.close()