| Age | Commit message (Collapse) | Author |
|---|
|
This change adds a trace API implementation for the Azure VM traces.
|
|
This change fixes an issue where the last column in the Solvinity traces
is not parsed correctly, due to the last column having no whitespace at
the end to seek to.
|
|
This change removes the external class that holds the state of the
reader and instead puts the state in the reader implementation.
Maintaining a separate class for the state increases the complexity and
has worse performance characteristics due to the bytecode produced by
Kotlin for property accesses.
|
|
This change moves the fault injection logic directly into the
opendc-compute-simulator module, so that it can operate at a higher
abstraction. In the future, we might again split the module if we can
re-use some of its logic.
|
|
This change updates the Capelin experiment helpers to terminate a server
when it has reached its end-date.
|
|
This change adds support for specifying the distribution of the
failures, group size and duration for the fault injector.
|
|
|
|
This change moves the metric collection outside the Capelin codebase in
a separate module so other modules can also benefit from the compute
metric collection code.
|
|
|
|
|
|
This change updates the trace reading classes in the Capelin experiment
to use the new trace API in order to re-use many of the trace reading
parts.
|
|
This change updates the WTF trace reader to support the new streaming
trace API.
|
|
This change moves Bitbrains trace support into a separate module and
adds support for the new trace api.
|
|
This change removes the environment reader from the format library since
they are highly specific for the particular experiment. In the future,
we hope to have a single format to setup the entire datacenter (perhaps
similar to the format used by the web runner).
|
|
This change extracts the Parquet helpers outside format module into a
new module, in order to improve re-usability of these helpers.
|
|
This change updates the SimHost implementation to measure the power draw
of the machine without PSU overhead to make the results more realistic.
|
|
This change updates the metric exporter logic in the Capelin module and
reduces the number of allocations by looping directly over the
collection of metrics.
|
|
This change eliminates the unnecessary conversions from double to long
in the Capelin metric processing code.
|
|
This change upgrades the OpenTelemetry dependency to version 1.5, which
contains various breaking changes in the metrics API.
|
|
This change adds tests to the Capelin integration suite for performance
interference as well as failures. These test more accurately the
experiment setup.
|
|
This change updates the Bitbrains trace tests with the updated trace
that does not hardcode the duration of the trace fragments.
|
|
This change fixes an issue with the workload sampler where the resulting
workload entries would not be ordered properly according to their
submission time.
|
|
This change updates the code for the Bitbrains trace reader and upgrades
the TraceConverter to re-use existing code of the Bitbrains trace
reader.
|
|
|
|
This change fixes an issue with the simulator where it would record
overcomitted work if the output was updated before the deadline was
reached.
|
|
This change refactors the trace workload in the OpenDC simulator to
track execute a fragment based on the fragment's timestamp. This makes
sure that the trace is replayed identically to the original execution.
|
|
This change updates the FilterScheduler implementation to follow more
closely the scheduler implementation in OpenStack's Nova. We now
normalize the weights, support many of the filters and weights in
OpenStack and support overcommitting resources.
|
|
This change updates the Kotlin dependencies used by OpenDC to their
latest version.
|
|
This change updates reimplements the performance interference model to
work on top of the universal resource model in
`opendc-simulator-resources`. This enables us to model interference and
performance variability of other resources such as disk or network in
the future.
|
|
This change updates the trace reader implementation to remove their
dependency on the performance interference model. In a future commit, we
will instead pass the performance interference model via the
host/hypervisor.
|
|
This change re-organizes the classes of the compute simulator module to
make a clearer distinction between the hardware, firmware and software
interfaces in this module.
|
|
This change enables the experiments to share the SimResourceInterpreter
across multiple hosts, which allows updates to be scheduled efficiently
for all machines at the same time. This is especially beneficial if the
machines operate on the same time slices.
|
|
This change renames the opendc-serverless module to opendc-faas to
better distinguish between the two terms (Serverless and FaaS) and be
clearer about the intent of the module.
The opendc-faas module holds the code for the FaaS platform on top of
OpenDC. Although this is one approach of doing serverless, serverless
can also entail other services that will not be covered by this module.
|
|
This change fixes an issue where the power in the energy experiments is
always reported as zero due to the changes in commit 652b869.
|
|
This change fixes the execution of the Energy21 experiments which failed
due to various changes in the OpenDC codebase. First, the directory
structure is now required to be pre-generated before the writer starts
writing the experiment output. Second, we must include the configuration
of the Capelin experiment in this experiment in order to workaround an
issue with harness filtering.
|
|
This change integrates the power subsystem of the simulator with the
compute subsystem by exposing a new field on a SimBareMetalMachine, psu,
which provides access to the machine's PSU, which in turn can be
connected to a SimPowerOutlet.
|
|
This change eliminates all Hadoop dependencies that are not necessary
for Parquet to work correctly. As a result, the number of dependencies
should now be greatly reduced, which in turn leads to less artifacts
that need to be retrieved at build time.
|
|
This change updates the Parquet writers used in the Capelin experiments
to use our OutputFile implementation for local files, to reduce our
dependency on Apache Hadoop.
|
|
This change updates the Parquet readers used in the Capelin experiments
to use our InputFile implementation for local files, to reduce our
dependency on Apache Hadoop.
|
|
This change removes the Jupyter Notebook that was shipped with the
initial version of the Energy21 experiments. At the moment, it is not
up to date anymore and we will probably move the plotting facility to
the web interface.
|
|
This change splits the functionality present in the CPUFreq subsystem of
the compute simulation. Currently, the DVFS functionality is embedded in
SimBareMetalMachine. However, this functionality should not exist within
the firmware layer of a machine. Instead, the operating system should
perform this logic (in OpenDC this should be the hypervisor).
Furthermore, this change moves the scaling driver into the power
package. The power driver is a machine/firmware specific implementation
that computes the power consumption of a machine.
|
|
This change updates the SimWorkload interfaces to allow
implementations to start consumers for the machine resource providers
directly.
|
|
This change adds a new interface to the resources library for accessing
metrics of resources such as work, demand and overcommitted work. With
this change, we do not need an implementation specific listener
interface in SimResourceSwitchMaxMin anymore.
Another benefit of this approach is that updates will be scheduled more
efficiently and progress will only be reported once the system has
reached a steady-state for that timestamp.
|
|
This change introduces the SimResourceInterpreter which centralizes the
logic for scheduling and interpreting the communication between resource
consumer and provider.
This approach offers better performance due to avoiding invalidating the
state of the resource context when not necessary. Benchmarks show in the
best case a 5x performance improvement and at worst a 2x improvement.
|
|
This change addresses the deprecations that were caused by the migration
to Kotlin 1.5.
|
|
|
|
|
|
|
|
|
|
|
