| Age | Commit message (Collapse) | Author |
|---|
|
This change adds an experiment for the OpenDC Energy project, which
tests various energy models that have been implemented in OpenDC.
|
|
This change fixes an issue in SimTraceWorkload where the CPU usage was
not divided across the cores, but was instead requested for all cores.
|
|
This change updates the logic in SimAbstractMachine to only propagate
usages when the value has changed.
|
|
This change removes the StateFlow speed property on the
SimResourceSource, as the overhead of emitting changes to the StateFlow
is too high in a single-thread context. Our new approach is to use
direct callbacks and counters.
|
|
|
|
This change updates the power models by fixing some of the documentation
and adding toString() methods.
|
|
This change adds a model implementing Dynamic Voltage Frequency Scaling
(DVFS) to OpenDC.
|
|
This pull request resolves issue #91 by adopting the industry-standard OpenTelemetry standard
for collecting traces and metrics in OpenDC simulations:
* Metrics will now be exposed through OpenTelemetry's metrics API
* `opendc-telemetry` provides complementary code to support
gathering telemetry in OpenDC.
**Breaking API Changes**
* `opendc-tracer` has been removed.
* `EventFlow` and all usages of it have been removed.
* `opendc-experiments-sc18` has been removed for now, but a
suitable replacement will follow soon.
|
|
This change updates the compute service simulator to use OpenTelemetry
for reporting metrics of the (simulated) hosts as opposed to using
custom event flows.
This approach is more generic, flexible and possibly offers better
performance as we can collect metrics of all services in a single sweep,
as opposed to listening to several services and each invoking the
handlers.
|
|
This change updates the resource model implementation to cache the
remaining work field, which was being computed multiple times during the
same cycle.
|
|
This change enables the use of the interpolation model testing on the results of the SPEC benchmark.
|
|
This change integrates the OpenTelemetry Metrics API in the OpenDC
Compute Service implementation. This replaces the old infrastructure for
gathering metrics.
|
|
This change moves the power models from the `opendc-compute-simulator`
to the `opendc-simulator-compute` module, since it better fits the scope
of the models and allows them to be re-used for other purposes.
|
|
This change adds support for transforming the resource commands emitted
by the resource consumers. The SimResourceForwarder is modified to also
support transforming the resource commands.
|
|
This change adds benchmarks to the opendc-simulator-compute module in
order to quantify effect of changes on the performance of this module.
|
|
This change re-enables support for VM usage metrics by adding an adapter
for SimResourceConsumer instances that can export the consumer speed.
|
|
This change adds support for dynamically changing the capacity of
resources and propagating this change to consumers.
|
|
This change removes the generic resource constraint (e.g., SimResource)
and replaces it by a simple capacity property. In the future, users
should handle the resource properties on a higher level.
This change simplifies compositions of consumers and providers by not
requiring a translation from resource to capacity.
|
|
This change changes the consumer and context interfaces to expose the
provider capacity and remaining work via the context instance as opposed
to only via the callback. This simplifies aggregation of resources.
|
|
This change adds an initial set of benchmarks for the resource
consumption framework in order to measure the effect of changes on the
performance of the simulator.
|
|
This change re-designs the SimResourceConsumer interface to support in
the future capacity negotiation. This basically means that the consumer
will be informed directly when not enough capacity is available, instead
of after the deadline specified by the consumer.
|
|
This change adds support for aggregating code coverage results from the
different modules.
|
|
This change implements the CPU energy model with p-states from iCanCloud/E-mc2:
- Only pushed a portion of the code for discussion as not sure if the idea is
on track.
- Inline comments have been added, and formal documents will follow once the
model is finalized.
- The p-state power consumptions are currently hard-coded in a companion
object, which should be improved in the next PR(s).
**Breaking Changes**
- CpuPowerModel: directly interact with the machine it is measuring.
- SimBareMetalMachine: expose the speeds of its CPU cores and its clock
instant.
|
|
This change moves the hypervisor implementations to the
opendc-simulator-resources module and makes them generic to the resource
type that is being used (e.g., CPU, disk or networking).
|
|
This change adds a generic framework for modeling resource consumptions and
adapts opendc-simulator-compute to model machines and VMs on top of
this framework.
This framework anticipates the addition of additional resource types
such as memory, disk and network to the OpenDC codebase.
|
|
This change separates the cloud compute layer in OpenDC (e.g., Server)
from the bare-metal layer (e.g., Node), such that Node and
BareMetalDriver are unaware of the existence of Server and co.
|
|
This change uses the Java Platform functionality from Gradle to enable
shared dependency constraints across modules.
|
|
This change updates the Gradle configuration to utilize version
constraints to force the same dependency version across modules.
|
|
This change moves the version of the dependencies from buildSrc to
gradle.properties to prevent recompilation when changing dependency
versions.
|
|
This change extracts the configuration for test from the Kotlin library
conventions.
|
|
This change removes unnecessary dependencies on JUnit Platform launcher
from the repository. Previously, the launcher was used to bootstrap
tests for Gradle when it did not natively support JUnit Platform.
Gradle now has native support for JUnit Platform, so the dependency is
not needed anymore.
|
|
This change allows users to select the hypervisor scheduler to use when
deploying hypervisors onto bare-metal machines.
|
|
This change adds a new hypervisor implementation that supports virtual
machine that have exclusive access to resources (e.g., CPU).
|
|
This change converts the low-level workload model to be pull-based. This
reduces the overhead that we experienced with our previous co-routine
based approach.
|
|
This change updates the workflow service to delegate the resource
scheduling logic to the virtualized resource provisioner.
|
|
|
|
|
|
This change reimplements the performance interference model originally
implemented for the SimpleVirtDriver class, for SimHypervisor.
|
|
This change updates the remainder of the codebase to use the
opendc-simulator-compute module for the simulation of workloads.
|
|
This change adds an implementation of the VirtDriver interface that uses
the functionality provided by the opendc-simulator-compute module.
|
|
This change adds an opendc-simulator-compute module which contains
interfaces related to simulating compute workloads. For future changes,
we intend to decouple the simulation part from the opendc-compute
module.
|
|
This change moves the OpenDC modules previously living in the simulator/opendc
directory to the simulator directory itself given that we do not make a
distinction between OpenDC and odcsim anymore.
|
