Traceable performance evaluation: Difference between revisions
(Created page with "This page presents good practices when performing benchmarks using Grid'5000 nodes. It is not about benchmarking Grid'5000. = About the nodes system = Grid'5000 nodes can be...") |
No edit summary |
||
| Line 1: | Line 1: | ||
This page presents good practices when performing benchmarks using Grid'5000 nodes. It is not about benchmarking Grid'5000. | This page presents good practices when performing benchmarks using Grid'5000 nodes. It is not about benchmarking Grid'5000 itself. | ||
= About the nodes system = | = About the nodes system = | ||
Grid'5000 nodes can be used with different environments: either with the default (standard) environment which is pre-provisioned on | Grid'5000 nodes can be used with different system environments: either with the default (standard) environment which is pre-provisioned on nodes, or with a variety of environments deployed on demand by the user. We compare the several options. | ||
== Benchmarking on node running the default (standard) environment == | == Benchmarking on node running the default (standard) environment == | ||
In this case, access to the system of the node does not require a deployment (kadeploy), so access is quicker. The system however comes with a lot of functionalities that may impact benchmarks. It may be relevant to | In this case, access to the system of the node does not require a deployment (kadeploy), so access is quicker. The system however comes with a lot of functionalities that may impact benchmarks. It may be relevant to uninstall/deactivate them before running the benchmark. | ||
The list of services running on the system can be shown using <code class=command>systemctl</code> | The list of services running on the system can be shown using <code class=command>systemctl</code> | ||
Services can be uninstalled (e.g. with <code class=command>apt-get</code>) or just deactivated (with <code class=command>systemctl stop </code><code class=replace>service</code>) after becoming root (with <code class=command>sudo-g5k</code>). | Services can be uninstalled (e.g. with <code class=command>apt-get remove </code><code class=replace>package</code>) or just deactivated (with <code class=command>systemctl stop </code><code class=replace>service</code>) after becoming root (with <code class=command>sudo-g5k</code>). | ||
The following services is known to possibly impact benchmarks: | The following services is known to possibly impact benchmarks: | ||
| Line 15: | Line 14: | ||
* ... | * ... | ||
== Benchmarking on an environment deployed on demand == | == Benchmarking on an environment deployed on-demand == | ||
Using kadeploy is very relevant for benchmarking, as it allows the user to operate the nodes with a most minimalistic system that is sufficient for the benchmark. For instance, one can deploy the <code class=replace>-min> variant of one of the Grid'5000 supported environments, or a customized environment possibly built on top of a minimalistic environment but including software required for running the benchmark. | |||
Revision as of 16:49, 8 September 2021
This page presents good practices when performing benchmarks using Grid'5000 nodes. It is not about benchmarking Grid'5000 itself.
About the nodes system
Grid'5000 nodes can be used with different system environments: either with the default (standard) environment which is pre-provisioned on nodes, or with a variety of environments deployed on demand by the user. We compare the several options.
Benchmarking on node running the default (standard) environment
In this case, access to the system of the node does not require a deployment (kadeploy), so access is quicker. The system however comes with a lot of functionalities that may impact benchmarks. It may be relevant to uninstall/deactivate them before running the benchmark.
The list of services running on the system can be shown using systemctl
Services can be uninstalled (e.g. with apt-get remove package) or just deactivated (with systemctl stop service) after becoming root (with sudo-g5k).
The following services is known to possibly impact benchmarks:
- ...
- ...
Benchmarking on an environment deployed on-demand
Using kadeploy is very relevant for benchmarking, as it allows the user to operate the nodes with a most minimalistic system that is sufficient for the benchmark. For instance, one can deploy the -min> variant of one of the Grid'5000 supported environments, or a customized environment possibly built on top of a minimalistic environment but including software required for running the benchmark.