KNELPerf v2 wave 1: Ultix scheduler breakout + loop skeleton + reports (#826)

- scheduler/: day/night engine (conf-driven redesign), psi/perfsnap collectors,
  proxmox-ctl, systemd timer templates — ported from ~/projects/ultix per the
  breakout map in scheduler/README.md
- loop/: perf-loop driver (baseline/audit/tweak/rebaseline), cpu-bench (new CPU
  leg), baseline-diff (tolerance compare) — smoke-tested locally
- docs/ARCHITECTURE.md: full program design (loop, resource groups, VM/spindle
  balancing, k8s-vs-Slurm, beszel+RAPL/iDRAC telemetry spine, workload classes,
  solar/HA + two-site power economics)
- docs/report-amt-power-telemetry.md + docs/report-moonlight-desktop.md

Redmine: https://projects.knownelement.com/issues/826#note-2

loop/cpu-bench.sh

@@ -0,0 +1,51 @@
+#!/usr/bin/env bash
+# KNELPerf CPU benchmark — the missing CPU leg of the perf loop (#826).
+# Runs ON the target host (or locally). Zero-install friendly: uses openssl
+# (always present) plus sysbench when available. Output = TSV tag/value.
+#
+# Design notes:
+#   - openssl speed = single+multi core crypto throughput (stable, comparable)
+#   - sysbench cpu (if installed) = integer event rate
+#   - /proc-derived context: governor, PSI at capture time
+set -u
+DUR=${KNELPERF_CPUBENCH_SECS:-10}
+
+echo -e "metric\tvalue\tunit"
+
+gov=$(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 2>/dev/null || echo none)
+echo -e "governor\t$gov\t-"
+nproc=$(nproc)
+echo -e "nproc\t$nproc\t-"
+
+# openssl: 1 thread then all threads, aes-256-cbc (avx-sensitive) and sha256.
+# Parse: LAST line whose first field is the algo; value = last numeric field
+# (per-thread rows precede the aggregate row in -multi output).
+for algo in aes-256-cbc sha256; do
+  v=$(openssl speed -seconds "$DUR" "$algo" 2>/dev/null \
+    | awk -v a="$algo" '$1==a{v=$NF} END{print v}')
+  [ -n "${v:-}" ] && echo -e "openssl_${algo}_1t\t$v\tk/s"
+  # -multi: per-thread rows precede the aggregate; keep the LAST match
+  v=$(openssl speed -multi "$nproc" -seconds "$DUR" "$algo" 2>/dev/null \
+    | awk -v a="$algo" '$1==a{v=$NF} END{print v}')
+  [ -n "${v:-}" ] && echo -e "openssl_${algo}_${nproc}t\t$v\tk/s"
+done
+
+# sysbench (optional, if installed)
+if command -v sysbench >/dev/null 2>&1; then
+  ev=$(sysbench cpu --time=$((DUR*1000)) --threads=1 run 2>/dev/null \
+    | awk -F'/s|events per second:/{for(i=1;i<=NF;i++) if($i ~ /^[0-9.]+$/){print $i; exit}}')
+  [ -n "${ev:-}" ] && echo -e "sysbench_cpu_1t\t$ev\tevents/s"
+  ev=$(sysbench cpu --time=$((DUR*1000)) --threads="$nproc" run 2>/dev/null \
+    | awk -F'/s|events per second:/{for(i=1;i<=NF;i++) if($i ~ /^[0-9.]+$/){print $i; exit}}')
+  [ -n "${ev:-}" ] && echo -e "sysbench_cpu_${nproc}t\t$ev\tevents/s"
+else
+  echo -e "sysbench_cpu\tabsent\t-"
+fi
+
+# PSI snapshot at capture time (context for the numbers above)
+for res in cpu memory io; do
+  v=$(awk '$1=="some"{for(i=2;i<=NF;i++) if($i ~ /^avg60=/){sub("avg60=","",$i); print $i; exit}}' \
+    "/proc/pressure/$res" 2>/dev/null || echo 0)
+  echo -e "psi_${res}_avg60\t$v\t%"
+done
+exit 0