#!/usr/bin/env bash
# scripts/verify-netem.sh — confirm tc-netem is actually applying loss, in
# the direction(s) you think it is.
#
# Usage:
#   ./scripts/verify-netem.sh <peer-ip> [interface] [loss_pct]
#
#   peer-ip     IP of the other machine (the simulator's IP when run on the CM5,
#               or the CM5's IP when run on the Mac).
#   interface   Interface tc-netem is applied to. Default: eth0.
#   loss_pct    Loss percentage to apply. Default: 5.
#
# Modes (env var):
#   BIDI=0  (default)   Egress-only. Shapes outgoing traffic from <interface>.
#                       Use a single ping from this host to verify.
#   BIDI=1              Bidirectional via ifb ingress redirect. Shapes BOTH
#                       outgoing AND incoming traffic on <interface>. Pings
#                       run from THIS host verify egress; the script also
#                       prompts you to ping back FROM THE PEER to verify
#                       ingress (the script holds the qdisc up until you press
#                       Enter, then tears everything down).
#
# What it does:
#   1. Prints the current qdisc state (sanity check before).
#   2. Applies the configured netem loss (egress, or egress + ingress).
#   3. Re-prints the qdisc state (confirms the rule is installed).
#   4. Sends 100 ICMP echo requests to <peer-ip> and reports the observed loss.
#   5. BIDI=1 only: waits for you to run `ping -c 100 <this-host>` from the
#      peer machine and report what it saw.
#   6. Removes the qdiscs (and brings ifb0 down) on exit, even on Ctrl-C.

set -euo pipefail

PEER="${1:-}"
IFACE="${2:-eth0}"
LOSS="${3:-5}"
BIDI="${BIDI:-0}"
IFB_DEV="${IFB_DEV:-ifb0}"

if [[ -z "$PEER" ]]; then
    echo "Usage: $0 <peer-ip> [interface] [loss_pct]"
    echo "Example: $0 192.168.1.42 eth0 5"
    exit 1
fi

if [[ -t 1 ]]; then
    BOLD=$'\033[1m'; DIM=$'\033[2m'; GREEN=$'\033[32m'; YELLOW=$'\033[33m'
    RED=$'\033[31m'; RESET=$'\033[0m'
else
    BOLD=; DIM=; GREEN=; YELLOW=; RED=; RESET=
fi
step()  { printf '\n%s» %s%s\n' "$BOLD" "$1" "$RESET"; }
ok()    { printf '%s  ✓ %s%s\n' "$GREEN" "$1" "$RESET"; }
warn()  { printf '%s  ! %s%s\n' "$YELLOW" "$1" "$RESET"; }
fail()  { printf '%s  ✗ %s%s\n' "$RED" "$1" "$RESET"; }

# Sanity: tc + ping + interface
for cmd in tc ping ip; do
    command -v "$cmd" >/dev/null || { fail "missing: $cmd"; exit 1; }
done
ip link show "$IFACE" >/dev/null 2>&1 || { fail "interface $IFACE not found"; exit 1; }

# Print the route to the peer so the user can see which iface the kernel
# actually uses — if it's not $IFACE, the netem rule won't apply.
step "Route to peer $PEER"
ROUTE_OUT="$(ip route get "$PEER" 2>&1 || true)"
printf '  %s\n' "$ROUTE_OUT"
ROUTE_IFACE="$(echo "$ROUTE_OUT" | awk '/dev/ {for(i=1;i<=NF;i++) if($i=="dev"){print $(i+1); exit}}')"
if [[ -n "$ROUTE_IFACE" && "$ROUTE_IFACE" != "$IFACE" ]]; then
    warn "kernel routes $PEER via '$ROUTE_IFACE' but you're shaping '$IFACE'."
    warn "the netem rule will have NO effect on this peer's traffic."
fi

# State BEFORE
step "Current qdisc on $IFACE (before)"
sudo tc qdisc show dev "$IFACE" | sed 's/^/  /'

# If bidi, ensure ifb device is up before installing qdiscs.
if [[ "$BIDI" -eq 1 ]]; then
    step "Bringing up $IFB_DEV (BIDI mode)"
    sudo modprobe ifb numifbs=1 2>/dev/null || true
    if ! ip link show "$IFB_DEV" >/dev/null 2>&1; then
        fail "ifb device $IFB_DEV not present after modprobe; cannot run BIDI mode"
        exit 1
    fi
    sudo ip link set "$IFB_DEV" up
    ok "$IFB_DEV is up"
fi

# Apply netem
if [[ "$BIDI" -eq 1 ]]; then
    step "Applying netem loss ${LOSS}% on $IFACE (egress + ingress via $IFB_DEV)"
else
    step "Applying netem loss ${LOSS}% on $IFACE (egress only)"
fi
sudo tc qdisc del dev "$IFACE" root 2>/dev/null || true
sudo tc qdisc del dev "$IFACE" ingress 2>/dev/null || true
[[ "$BIDI" -eq 1 ]] && sudo tc qdisc del dev "$IFB_DEV" root 2>/dev/null || true
sudo tc qdisc add dev "$IFACE" root netem loss "${LOSS}%"
if [[ "$BIDI" -eq 1 ]]; then
    sudo tc qdisc add dev "$IFACE" handle ffff: ingress
    sudo tc filter add dev "$IFACE" parent ffff: protocol all u32 \
        match u32 0 0 action mirred egress redirect dev "$IFB_DEV"
    sudo tc qdisc add dev "$IFB_DEV" root netem loss "${LOSS}%"
fi
ok "qdisc(s) installed"

# Trap to clean up on any exit path
cleanup() {
    step "Removing netem qdiscs"
    sudo tc qdisc del dev "$IFACE" root 2>/dev/null || true
    sudo tc qdisc del dev "$IFACE" ingress 2>/dev/null || true
    if [[ "$BIDI" -eq 1 ]]; then
        sudo tc qdisc del dev "$IFB_DEV" root 2>/dev/null || true
        sudo ip link set "$IFB_DEV" down 2>/dev/null || true
    fi
    ok "qdiscs removed; $IFACE back to default"
}
trap cleanup EXIT INT TERM

# State AFTER install
step "Current qdisc state (after netem applied)"
sudo tc qdisc show dev "$IFACE" | sed 's/^/  /'
if [[ "$BIDI" -eq 1 ]]; then
    sudo tc qdisc show dev "$IFB_DEV" | sed 's/^/  /'
    echo "  filter on $IFACE ingress:"
    sudo tc filter show dev "$IFACE" parent ffff: 2>/dev/null | sed 's/^/    /'
fi

# Ping the peer and parse loss
step "Pinging $PEER with 100 echoes (egress goes through netem)"
PING_OUT="$(ping -c 100 -i 0.05 -W 1 "$PEER" 2>&1 || true)"
echo "$PING_OUT" | tail -3 | sed 's/^/  /'

# Parse "X% packet loss" — works on both Linux and macOS ping output.
OBSERVED="$(echo "$PING_OUT" | grep -oE '[0-9.]+% packet loss' | head -1 | awk '{print $1}' | tr -d '%')"
if [[ -z "$OBSERVED" ]]; then
    fail "could not parse ping output"
    exit 1
fi

# Sanity bracket: configured loss is ±3 percentage points absolute is fine for n=100.
ABS_DELTA=$(awk -v o="$OBSERVED" -v l="$LOSS" 'BEGIN{d=o-l; if(d<0)d=-d; printf "%.1f", d}')
step "Result"
printf '  configured: %s%%\n  observed:   %s%%\n  |delta|:    %s pp\n' "$LOSS" "$OBSERVED" "$ABS_DELTA"

if awk -v o="$OBSERVED" -v l="$LOSS" 'BEGIN{exit !(o > l*0.4 && o < l*2.0 + 3)}'; then
    ok "loss is being applied in the egress direction of $IFACE"
else
    fail "observed loss ($OBSERVED%) does not match configured ($LOSS%)"
    warn "either the qdisc isn't routing as expected, or the kernel's netem"
    warn "build doesn't include the loss module. Check 'modprobe sch_netem'."
fi

if [[ "$BIDI" -eq 1 ]]; then
    step "Now verify the INGRESS direction"
    THIS_IP="$(ip -4 addr show dev "$IFACE" | awk '/inet / {print $2}' | cut -d/ -f1 | head -1)"
    cat <<EOF
  From the peer machine, run:
    ping -c 100 -i 0.05 ${THIS_IP:-<this host\'s IP on $IFACE>}
  You should see ~${LOSS}% packet loss in the peer's ping output. That confirms
  ingress shaping is dropping packets arriving here on $IFACE.

  Press Enter when done to tear everything down.
EOF
    read -r _ </dev/tty || true
fi