mrcharles
25299373f7
ci / audit (push) Failing after 26s
- 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
66 lines
2.5 KiB
Bash
Executable File
66 lines
2.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# KNELPerf loop driver — baseline -> audit/benchmark -> tweak -> re-baseline.
|
|
#
|
|
# The heart of KNELPerf v2 (#826). One host, one cycle phase at a time:
|
|
#
|
|
# perf-loop.sh baseline <host> capture baseline bundle (cpu/net/storage/psi)
|
|
# perf-loop.sh audit <host> read-only audit vs baseline (alerts on drift)
|
|
# perf-loop.sh tweak <host> <id> apply a tweak (from tweaks/) after CR gate
|
|
# perf-loop.sh rebaseline <host> capture post-tweak bundle + diff report
|
|
# perf-loop.sh compare <host> <a> <b> diff two stored bundles
|
|
#
|
|
# Bundles live in data/baselines/<host>/<ts>/ and are plain TSV/JSON so diff
|
|
# and jq stay the toolchain. Nothing here mutates a host except `tweak`.
|
|
set -euo pipefail
|
|
REPO_ROOT=$(cd "$(dirname "$0")/.." && pwd)
|
|
DATA_DIR=${KNELPERF_DATA_DIR:-$REPO_ROOT/data/baselines}
|
|
SSH_OPTS=(-o ConnectTimeout=8 -o BatchMode=yes)
|
|
|
|
usage() { sed -n '2,12p' "$0"; exit 2; }
|
|
[ $# -ge 2 ] || usage
|
|
cmd=$1; host=$2
|
|
|
|
now() { date +%Y%m%d-%H%M%S; }
|
|
host_dir() { mkdir -p "$DATA_DIR/$1"; }
|
|
|
|
run_on_host() { # host script-path args...
|
|
local h=$1 script=$2; shift 2
|
|
case $h in
|
|
local) bash "$REPO_ROOT/$script" "$@" ;;
|
|
*) ssh "${SSH_OPTS[@]}" "root@$h" "bash -s" < "$REPO_ROOT/$script" "$@" ;;
|
|
esac
|
|
}
|
|
|
|
case "$cmd" in
|
|
baseline|rebaseline)
|
|
ts=$(now); dir="$DATA_DIR/$host/$ts"; host_dir "$host"; mkdir -p "$dir"
|
|
echo "== KNELPerf $cmd: $host -> $dir"
|
|
# shellcheck disable=SC2043 # single-part list by design; grows as legs are added
|
|
for part in cpu-bench; do
|
|
run_on_host "$host" "loop/$part.sh" > "$dir/$part.tsv" 2> "$dir/$part.err" \
|
|
|| echo "WARN: $part failed (see $dir/$part.err)"
|
|
done
|
|
# storage + network reuse the existing bench harness outputs
|
|
run_on_host "$host" "bench/bench-run.sh" > "$dir/bench-run.tsv" 2> "$dir/bench.err" \
|
|
|| echo "WARN: bench-run failed (see $dir/bench.err)"
|
|
echo "$cmd $host $ts" > "$dir/MANIFEST"
|
|
echo "done: $(ls "$dir")"
|
|
;;
|
|
audit)
|
|
latest=$(find "$DATA_DIR/$host" -maxdepth 1 -mindepth 1 -type d -printf '%f\n' 2>/dev/null | sort | tail -1)
|
|
[ -n "$latest" ] || { echo "no baseline for $host" >&2; exit 3; }
|
|
echo "== KNELPerf audit: $host vs baseline $latest"
|
|
"$REPO_ROOT/loop/baseline-diff.sh" "$DATA_DIR/$host/$latest" "$host"
|
|
;;
|
|
tweak)
|
|
[ $# -ge 3 ] || usage; tweak_id=$3
|
|
echo "== KNELPerf tweak $tweak_id on $host (CR gate applies - see AGENTS.md)"
|
|
run_on_host "$host" "tweaks/$tweak_id.sh"
|
|
;;
|
|
compare)
|
|
[ $# -ge 4 ] || usage
|
|
"$REPO_ROOT/loop/baseline-diff.sh" "$DATA_DIR/$host/$3" "$DATA_DIR/$host/$4"
|
|
;;
|
|
*) usage ;;
|
|
esac
|