Mitchell-JohnsonandClaude Opus 5.5 70bebcb18b Top: one beat — graphs, numbers and the process table change on the same tick ...

Graphs stepped once a history point (1 s at a 5 min window) while the numbers changed every
tick; they now slide a fraction of a column each tick. The process table (and the GPU boxes,
MHz and watts it carries) was polled on its own timer; it is now read per sample and committed
with it. GPU clients are walked every sample, and the 1–2 s floors on the gallery, Network,
Docker and ZFS ARC live views are gone.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-23 01:13:19 -07:00

..

arc.go

The ZFS tab shows the ARC, and names every caching tier a pool has or lacks

2026-10-02 18:30:02 -07:00

cpupower_test.go

Processes: CPU power beside the clock, from the packages' energy counters

2026-10-10 23:58:35 -07:00

cpupower.go

Processes: CPU power beside the clock, from the packages' energy counters

2026-10-10 23:58:35 -07:00

fold_test.go

A drive is a drive: NVMe namespaces fold into their controller

2026-09-22 09:11:03 -07:00

fold.go

Processes: CPU power beside the clock, from the packages' energy counters

2026-10-10 23:58:35 -07:00

gpu_test.go

Top: one beat — graphs, numbers and the process table change on the same tick

2026-10-23 01:13:19 -07:00

gpu.go

Top: one beat — graphs, numbers and the process table change on the same tick

2026-10-23 01:13:19 -07:00

metrics.go

Processes: CPU power beside the clock, from the packages' energy counters

2026-10-10 23:58:35 -07:00

pciids_gpu.txt

A GPU is named from an embedded PCI ID table, the same on every machine

2026-10-02 23:48:05 -07:00

pciids.go

A GPU is named from an embedded PCI ID table, the same on every machine

2026-10-02 23:48:05 -07:00

sensors_test.go

The full switch: Monitors and Disks read only the sensor API; /api/metrics retired

2026-09-19 07:52:14 -07:00

sensors.go

Processes: CPU power beside the clock, from the packages' energy counters

2026-10-10 23:58:35 -07:00