Kepler Files

What's Changed

🚀 Features

• feat(gpu): add MIG power attribution via dcgm-exporter by @vimalk78 in https://github.com/sustainable-computing-io/kepler/pull/2422
• feat(hwmon): add energy readings to hwmon power meter by @kaiyiliu-strala in https://github.com/sustainable-computing-io/kepler/pull/2428
• feat(build): add multi-arch support for ARM64 builds and container images by @vimalk78 in https://github.com/sustainable-computing-io/kepler/pull/2442
• feat(hwmon): deploy HWMON as backup when RAPL is not available by @kaiyiliu-strala in https://github.com/sustainable-computing-io/kepler/pull/2440
• feat(device): add cpu.meters config and switch-based CPU meter selection by @nikimanoledaki in https://github.com/sustainable-computing-io/kepler/pull/2468
• feat(resource): detect VirtualBox, VMware and Xen VM processes by @younsl in https://github.com/sustainable-computing-io/kepler/pull/2515
• Add liveness and readiness probe, with dedicated endpoint by @leonorfmartins in https://github.com/sustainable-computing-io/kepler/pull/2511

🐛 Bug Fixes

• fix(gpu): URL normalization, port-aware discovery, endpoint validation by @vimalk78 in https://github.com/sustainable-computing-io/kepler/pull/2432
• fix(exporter): avoid exporting node_name as empty string by @egypcio in https://github.com/sustainable-computing-io/kepler/pull/2444
• fix: export missing container CPU time metric by @shellyco-code in https://github.com/sustainable-computing-io/kepler/pull/2501
• nvidia: propagate error when no dcgm-exporter endpoint is reachable by @iacker in https://github.com/sustainable-computing-io/kepler/pull/2497
• fix: preserve accumulated errors in calculateNodePower/firstNodeRead by @KrishnaParihar1 in https://github.com/sustainable-computing-io/kepler/pull/2483
• fix: refactor component initialization to return graceful errors instead of panicking by @shellyco-code in https://github.com/sustainable-computing-io/kepler/pull/2495
• fix(monitor): Fix stale resource utilization due to refresh ordering by @HananAwwad in https://github.com/sustainable-computing-io/kepler/pull/2452
• fix(helm): honor serviceAccount.create instead of rbac.create by @iacker in https://github.com/sustainable-computing-io/kepler/pull/2533
• fix(config): warn about unknown config fields instead of dropping them silently by @iacker in https://github.com/sustainable-computing-io/kepler/pull/2536
• fix(resource): explain permission denied on /proc entries by @iacker in https://github.com/sustainable-computing-io/kepler/pull/2547
• fix(manifests): add NVML init container for NVIDIA GPU Operator support by @bitflicker64 in https://github.com/sustainable-computing-io/kepler/pull/2489

📖 Documentation

• docs: update contents of AGENTS.md by @vprashar2929 in https://github.com/sustainable-computing-io/kepler/pull/2414
• docs(installation): add minimal deployment path without Prometheus Operator by @LarytheLord in https://github.com/sustainable-computing-io/kepler/pull/2431
• docs: update the stale docs by @vprashar2929 in https://github.com/sustainable-computing-io/kepler/pull/2434
• docs(proposal): align EP roles & writing process with KEP conventions by @nikimanoledaki in https://github.com/sustainable-computing-io/kepler/pull/2457
• docs(proposal): convert vm cpu model proposal to explore improvements by @laurall974 in https://github.com/sustainable-computing-io/kepler/pull/2464
• docs(helm): add GitOps deployment section (Flux / Argo CD) by @iacker in https://github.com/sustainable-computing-io/kepler/pull/2509
• docs(metrics): add more information about zones and how to work with them in the kepler rewrite by @JulianLegler in https://github.com/sustainable-computing-io/kepler/pull/2537
• docs: fix broken star history chart by @Dessalines39394 in https://github.com/sustainable-computing-io/kepler/pull/2528
• docs: add team list and corresponding permission by @sunya-ch in https://github.com/sustainable-computing-io/kepler/pull/2546
• docs(maintainers): move laurall974 up to the Maintainers section and leaving Off-cycle maintainers by @laurall974 in https://github.com/sustainable-computing-io/kepler/pull/2553

♻️ Refactor

• refactor(config): move nodename fallback from exporter layer by @vprashar2929 in https://github.com/sustainable-computing-io/kepler/pull/2449
• refactor(config): rename cpu.meters to cpu.preferredMeters by @nikimanoledaki in https://github.com/sustainable-computing-io/kepler/pull/2471

New Contributors

• @stmcginnis made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2401
• @LarytheLord made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2431
• @shellyco-code made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2501
• @iacker made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2497
• @KrishnaParihar1 made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2483
• @HananAwwad made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2452
• @Nachiket-Roy made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2499
• @younsl made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2515
• @JulianLegler made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2537
• @leonorfmartins made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2511
• @Dessalines39394 made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2528
• @angelOlivares made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2525
• @bitflicker64 made their first contribution in https://github.com/sustainable-computing-io/kepler/pull/2489

Full Changelog: https://github.com/sustainable-computing-io/kepler/compare/v0.11.4...v0.12.0