#!/usr/bin/env bash
# KNELPerf perfsnap — periodic /proc+cgroupfs snapshot collector.
# Ported from ultix staged/reachableceo-perfsnap.sh (#826); generalizations:
#   - watched cgroups and interfaces are env/conf-driven lists (no baked-in
#     user ids or NIC names)
#   - log dir env-driven; same pipe-delimited format for awk analysis
#
# Env (or /etc/knelperf/perfsnap.conf):
#   KNELPERF_PERF_LOGDIR   default /var/log/knelperf-perf
#   KNELPERF_SNAP_CGROUPS  space-separated "label:/sys/fs/cgroup/path" list
#   KNELPERF_SNAP_IFACES   space-separated interface names
# Fields (snap.log): ts|l1|l5|l15|run|blocked|memavail_kb|psi_cpu|psi_mem|
#   psi_io|<cgroup usage_usec per label>|<iface rx tx per label>
# psi_* = avg60 "some" percentages. *_usec = cgroup cpu.stat usage_usec
# (cumulative; analyze deltas).
set -u
CONF=/etc/knelperf/perfsnap.conf
[ -r "$CONF" ] && . "$CONF"
LOGDIR=${KNELPERF_PERF_LOGDIR:-/var/log/knelperf-perf}
SNAP_CGROUPS=${KNELPERF_SNAP_CGROUPS:-}
SNAP_IFACES=${KNELPERF_SNAP_IFACES:-}
mkdir -p "$LOGDIR"
ts=$(date +%s)

read -r l1 l5 l15 _ < /proc/loadavg
run=$(awk '/procs_running/{print $2}' /proc/stat)
blocked=$(awk '/procs_blocked/{print $2}' /proc/stat)
memavail=$(awk '/MemAvailable/{print $2}' /proc/meminfo)

psi() { awk '$1=="some"{for(i=2;i<=NF;i++) if($i ~ /^avg60=/){sub("avg60=","",$i); print $i; exit}}' "/proc/pressure/$1" 2>/dev/null || echo 0; }

line="$ts|$l1|$l5|$l15|$run|$blocked|$memavail|$(psi cpu)|$(psi memory)|$(psi io)"

cgusec() { awk '/^usage_usec/{print $2}' "$1/cpu.stat" 2>/dev/null || echo 0; }
for spec in $SNAP_CGROUPS; do
  line="$line|$(cgusec "${spec#*:}")"
done

nd() { awk -v i="$1" '$1==i":":{print $2" "$10}' /proc/net/dev 2>/dev/null || echo "0 0"; }
for ifc in $SNAP_IFACES; do
  read -r rx tx <<< "$(nd "$ifc")"
  line="$line|$rx|$tx"
done

echo "$line" >> "$LOGDIR/snap.log"

ps -eo pcpu,pid,comm --sort=-pcpu --no-headers | head -5 \
  | awk -v t="$ts" '{print t"|"$1"|"$2"|"$3}' >> "$LOGDIR/procs.log"

# retention: 14 days; rotate anything over 50MB
find "$LOGDIR" -name '*.log' -mtime +14 -delete 2>/dev/null
for f in "$LOGDIR"/*.log; do
  [ "$(wc -c <"$f" 2>/dev/null || echo 0)" -gt 52428800 ] && mv "$f" "$f.1"
done
exit 0