Alumet v0.8.4

What's Changed

• feat(plugin-oar2): add attributes to harmonize with other plugins by @ahuret in #185
• Fix/fix bugs in energy attribution by @titouanj in #189
• bug(core): counter diff corrected difference overflow by @ahuret in #188
• Rename cgroup metrics in default config of other plugins by @TheElectronWill in #192

Full Changelog: v0.8.3...v0.8.4

Alumet v0.8.3

This is a fix release for v0.8.2. See the release notes of v0.8.2.

• Hotfix: more lenient metric registration by @TheElectronWill in #181
  This resolves an issue that prevented the plugins procfs and k8s from being enabled at the same time (among others).

Alumet v0.8.2

What's Changed

Noteworthy:

• Bugfixes for influxdb and cgroupv2 plugins
  • fix(plugin-cgroupv2): Remove bad retry in K8S probe by @TheElectronWill in #178
  • fix(plugin-influxdb): Retry on write error and print server response by @TheElectronWill in #179
• OpenSearch/ElasticSearch is now directly supported as an output: by @TheElectronWill in #166
• Some refactoring around cgroup plugins:
  • refactor(plugin-procfs): standardize plugin-procfs metrics - cpu and memory metrics by @ahuret in #151
  • Refactor cgroupv2 plugin - metrics harmonization by @ahuret in #152
  • Refactor/plugin oar v2 by @AngeCyp in #143
  • Refactor/plugin cgroupv1 for harmonized metrics across plugins by @ahuret in #160
  • refactor(plugin-cgroupv1): factorized code in prevision for slurm submodule by @ahuret in #169
  • refactor(plugin-cgroupv2): k8s submodule - rework TokenRetrieval by @ahuret in #164

Full Changelog: v0.8.1...v0.8.2

Alumet v0.8.1

What's Changed

Main change: he following plugins are now part of the standard agent, as a beta version (they will change in the future): aggregation, energy-attribution, energy-estimation-tdp.

• ci(release): change trigger for CI workflow by @AngeCyp in #150
• feat(tests): plugin-influxdb- unit tests + integration tests by @ahuret in #138
• Quick 0.8.1 release by @TheElectronWill in #158

Full Changelog: v0.8.0...v0.8.1

Alumet v0.8.0

Core changes

• make measurement add_attr public by @guigomcha in #99
• Alumet core: changes in naming of pipeline elements by @TheElectronWill in #106
• Extract FFI C interface into a separate crate by @TheElectronWill in #113
• Core interface for end-to-end plugin testing by @TheElectronWill and @AngeCyp in #121
• New control API by @TheElectronWill in #127
• feature(core): Add introspection powers to the pipeline control API by @TheElectronWill in #134
• Make metric registration more configurable by @TheElectronWill in #139
• doc: Improve readme of core and repo by @TheElectronWill in #146

Repository changes

• Reorganize CircleCI workflow and require manual approval for long jobs by @TheElectronWill in #88
• Markdown lint workflow by @guigomcha in #78
• Build/create release action by @AngeCyp in #133
• Add docker images build/push to release action by @ahuret in #140

Standard agent changes

• agent: Improve exec error message by @AngeCyp in #71
• The one and only standard agent - unify and expand 🚀 by @TheElectronWill in #93
• agent: Fix --plugins ignored when config regen by @TheElectronWill in #108
• Only enable the plugins that are mentioned in the agent config by @TheElectronWill in #128

Plugin changes

• Feature/plugin_cgroupv2_k8s_memory by @victoryeagle77 in #63
• Fix/relay client as attribute by @TheElectronWill in #102
• plugin-tdp: Create metric using the transform builder by @cuttingl in #86
• plugin-procfs: Automatically increase file descriptors soft limit by @ahuret in #118
• plugin-mongodb: Test for mongodb plugin helpers by @kelyaenn in #125
• Feature/add the aggregation transform plugin by @titouanj in #111
• OpenTelemetry output for OpenSearch demo by @guigomcha in #117
• plugin-nvidia: collect nvml process metrics by @victoryeagle77 in #89
• Don't use block_on on the runtime by @TheElectronWill in #136
• Plugin to export metrics to prometheus by @guigomcha in #123
• Push interval in opentelemetry plugin by @guigomcha in #144
• Jetson fixes and upgrades by @victoryeagle77 and @TheElectronWill in #104
• Fix issue with memory measurements unit by @ahuret in #145

New Contributors

• @cuttingl made their first contribution in #76
• @guigomcha made their first contribution in #78
• @victoryeagle77 made their first contribution in #63
• @ahuret made their first contribution in #118

Full Changelog: v0.7.0...v0.8.0

Alumet v0.7.0

Framework changes

• The number of threads can now be configured, by @TheElectronWill in #77
• Output builders now have read-only access to the MetricRegistry
• Some bugfixes

Agent changes

• Config options can now be passed as environment variable now, by @AngeCyp in #73
• Release mode is more efficient because trace logs are now disabled at compile-time

Like the previous release, pre-compiled binaries of the agents are attached below.

Plugins changes

• New optimized relay mode (with postcard), by @TheElectronWill in #67
• New MongoDB plugin, by @kelyaenn in #68
• New TDP-based estimation plugin, by @ezychlagre in #62

New Contributors

• @kelyaenn made their first contribution in #68
• @ezychlagre made their first contribution in #62

Full Changelog: v0.6.1...v0.7.0

Alumet v0.6.1

Bugfixes

• Refactor and fix the way that CLI arguments are handled by @TheElectronWill in #51
• core: Make threading::use_realtime_scheduling work with musl by @TheElectronWill in #57
• fix(plugin_k8s): don't explore folder which don't end with .slice by @AngeCyp in #61

Minor changes

• docs(README): Add some badges by @titouanj in #47
• docs(README): Add link to crates.io to the badge by @titouanj in #48

Pre-compiled binaries

You can find below pre-compiled binaries of the Alumet agents. They are compiled on Ubuntu 22.04 LTS and will work on any system with a glibc version >= 2.35. They include a set of plugins, but not all. Refer to the docs to build your custom Alumet agent and choose the measurement plugins that you want to deploy.

Full Changelog: v0.6.0...v0.6.1

Alumet v0.6.0

What's new in the core

• Big refactoring of Alumet's core library.
• Better error handling and recovery.
• Cleaner builders for pipeline and agent.
• Alumet now supports async outputs.
• Global metric registry: the metrics can now be accessed from any element of the pipeline (see #19)
• The configuration can now disable individual plugins
• Environment variables can now be used in the config
• More possibilities of control
• More tests
• Bugfixes

Plugin changes

• New plugin: first version (alpha) of the energy attribution plugin, tested on K8S clusters at 1Hz.
• New plugin: system and processes monitoring via /proc
• The output of the relay client now uses a buffer for better performance.
• The k8s plugin has been generalized to a cgroupv2 plugin.
• The k8s plugin handles API tokens a little better.
• More config options

Details

• feat/Add a config field for the relay server plugin address by @titouanj in #26
• Feature/Add some configurations possibility by @titouanj in #27
• Pipeline rework: global metric registry, simplified tasks and better control by @TheElectronWill in #19
• Stricter CI checks by @TheElectronWill in #29
• fix(plugin-influxdb): Skip empty MeasurementBuffers in write by @titouanj in #31
• feat(alumet): Add environment variable interpolation for config files by @titouanj in #32
• Feature/system and processes monitoring by @TheElectronWill in #33
• Summer core improvements by @TheElectronWill in #35
• Allow the config file to disable individual plugins by @TheElectronWill in #37
• Merge the agents in a single crate by @TheElectronWill in #38
• Refactor/split k8s from cgroupv2 by @AngeCyp in #36
• Improvements for the relay mode by @TheElectronWill in #39
• Fixes for the exec mode by @TheElectronWill in #41
• doc: Rewrite the readme and add a contributing guide by @TheElectronWill in #43
• Feature: Add the first implementation of the k8s energy attribution by @titouanj in #44
• fix(plugin-energy-attribution): Change the cgroup metric name in the pre_pipeline_start by @titouanj in #45
• Last features and fixes for v0.6 by @TheElectronWill in #46

New Contributors

• @titouanj made their first contribution in #26

Full Changelog: v0.5.0...v0.6.0

ALUMET v0.5.0

This new release features the support of Kubernetes clusters and OAR2 clusters.

Plugin changes

• Discovering folders for pods by @AngeCyp in #3
• Watch new pods created during measures by @AngeCyp in #5
• Retrieve K8S pods names by @AngeCyp in #17
• Cgroups v1 and OAR2 Plugin by @sofiaduqueg in #12
• Improved error messages and RAPL hints by @TheElectronWill

New Contributors

• @sofiaduqueg made their first contribution in #12

Full Changelog: v0.4.0...v0.5.0

ALUMET v0.4.0

Core changes

• It is now possible to add new measurement sources at runtime, after the pipeline has been built.
• Event handlers now return a Result to handle errors more gracefully.
• The pipeline now waits for the sources, transforms and outputs to finish before stopping. This allows all the plugins to flush their buffers, avoiding data loss.
• Errors that occur in pipeline elements are handled more effectively.
• Improved ergonomics and robustness of the pipeline builder.
• MeasurementBuffer now implements IntoIterator.
• Other improvements to the plugin API, including more documentation ✍️

The aforementioned improvements have enabled the creation of two new plugins and one agent feature! (see below) 🎉

Plugin changes

• New: perf plugin (#2) for perf_events monitoring and profiling (hardware, software and cache events are supported)
• New: influx plugin to send measurements to InfluxDB v2
• More options for the csv plugin
• More options for the nvidia plugin
• Bug fixes for the rapl plugin: it is now more robust to unexpected situations (such as kernel modules not being loaded)

Agent changes

• The app-agent crate (that produces alumet-agent) has a new "exec mode" that spawns and observes a single process.
• Both the "normal" alumet agent and the relay agent now suggest to regenerate the configuration file if it is invalid.
• Other improvements to the textual output of the agents.

Full Changelog: v0.3.0...v0.4.0