| Age | Commit message (Collapse) | Author |
|
|
|
|
|
|
|
|
|
|
|
|
|
This should make performance interference based onn the colocated VMs possible.
|
|
This change renames the `maxUsage` parameter to `limit` in order to
align terminology with other products/projects such as VMWare vSphere.
|
|
|
|
This change modifies the API of ServerContext to store the remainder
burst into the input burst array instead of returning a new array.
|
|
This change refactors the codebase so that the CPU usage of the server
is only reported per server, instead of per CPU reducing the total
amount of messages needed and additionally simplifying synchronization
of various computations.
|
|
This change adds a simple integration test so we can measure the change
in duration after performance improvements and test whether large
experiments will still function after changes.
|
|
This change updates the terminology in the `opendc-compute` module to
make a distinction between CPU node and CPU core, where we primarly work
with CPU cores. However, if needed, we also provide information for the
different CPU nodes.
|
|
|
|
|
|
|
|
This change moves the simulator terminology from logical processes to
simulation domains. This prevents the clash with "processes" that we are
trying to simulate.
In addition, simulation domains allows us to reduce the amount of
boilerplate and instead allows for simulation modelled using standard
techniques.
|
|
|
|
|
|
|
|
|
|
This change adds support for workflow tasks that have a known duration.
This allows the workflow scheduler to employ heuristics for a faster
schedule.
|
|
This change incorporate a number of extensions and improvements to the
workflow scheduler. These are a result of the Design Space Exploration
for Datacenter Schedulers work.
|
|
|
|
|
|
This change adds support for virtual machines and hypervisors to the
_opendc-compute_ module. Moreover, this change also includes VM trace
reading capabilities.
|
|
This change fixes an issue where the runtime of an image that requested
cpu time was not properly computed.
|
|
|
|
These experiments were originally designed for the SC18 paper.
|
|
|
|
This change renames Flavor to ServerFlavor to be more indicative of its
function. The Flavor name follows the naming of the OpenStack project.
|
|
This change refactors the existing model to use the new interfaces from
the opendc-compute module.
|
|
|
|
This change remodels our model for workloads and compute resources in
order to support VM/container functionality where multiple workloads run
on a single machine.
In particular, we make the following changes:
- Move the compute-related source code into the `opendc-compute` module.
- Change from application-based model to image-based model, where the
image has exclusive access over the machine, instead of applications
that share the machine. We may model in the future again
applications/operating system, but at the moment, we do not need this
granularity, given that the workload traces can be simulated using VMs.
|
|
Add missing dots
|
|
Add missing dot
|
|
|