#!/usr/bin/env bash
# GENERATED by make standalone — do not edit
#
# rigmini.sh for profile 'client', flattened from:
#   ctrl/mem.sh
#   ctrl/lib/config.sh
# Edit those and run `make standalone`. Changes made here are lost, and
# `make selftest` fails while this file differs from what rig generates.

# ── from the libraries ──
declare -- CONFIG_OVERRIDABLE=$'PROFILE CLUSTER K8S_VERSION KIND_CONFIG ADDONS\n                    REGISTRY_MODE INGRESS_MODE DNS_MODE TILT_PORT\n                    SOURCE ARCH DEPS_SOURCE HTTP_PORT HTTPS_PORT\n                    REGISTRY_PORT MANIFESTS_DIR'
_config_restore () 
{ 
    local line;
    while IFS= read -r line; do
        if [ -n "$line" ]; then
            eval "export $line";
        fi;
    done <<< "$1";
    return 0
}
default_cluster_name () 
{ 
    local n;
    n=$(basename "$(cd .. && pwd)");
    n=$(echo "$n" | tr '[:upper:]' '[:lower:]' | tr -c 'a-z0-9-' '-');
    n=$(echo "$n" | sed 's/^-*//; s/-*$//');
    echo "${n:-rig}"
}
derive_port_base () 
{ 
    local h;
    h=$(printf '%s' "$1" | cksum | awk '{print $1}');
    echo $((20000 + (h % 200) * 10))
}
render_kind_config () 
{ 
    local host_workdir="${HOST_WORKDIR:-$(cd .. && pwd)}";
    sed -e "s|\${CLUSTER}|${CLUSTER}|g" -e "s|\${NODE_IMAGE}|${NODE_IMAGE}|g" -e "s|\${HTTP_PORT}|${HTTP_PORT}|g" -e "s|\${HOST_WORKDIR}|${host_workdir}|g" "$KIND_CONFIG_PATH"
}

# ── configuration, frozen for profile 'client' ──
load_config() {
    local k saved=""
    for k in $CONFIG_OVERRIDABLE; do
        if [ -n "${!k+x}" ]; then saved+="$k=$(printf '%q' "${!k}")"$'\n'; fi
    done
    declare -gx ADDONS="metallb cert-manager metrics-server"
    declare -gx AIRFLOW_IMAGE="apache/airflow:2.10.4"
    declare -g AUDIT="on"
    declare -gx CERT_MANAGER_VERSION="v1.21.1"
    declare -g CLUSTER="rig"
    declare -gx COMPOSE_SHA256="db1889184726840f75c4f9c001048430d4f25b3be3cb084d3ddd762bc0aed576"
    declare -gx COMPOSE_URL="https://github.com/docker/compose/releases/download/v5.5.1/docker-compose-linux-x86_64"
    declare -gx COMPOSE_VERSION="5.5.1"
    declare -gx CTLPTL_SHA256="c63a1ec28e60bc3faf6becb76f53355c5cf5e0143dafdd27ad85db5584fa6b1e"
    declare -gx CTLPTL_URL="https://github.com/tilt-dev/ctlptl/releases/download/v0.9.4/ctlptl.0.9.4.linux.x86_64.tar.gz"
    declare -gx CTLPTL_VERSION="0.9.4"
    declare -gx DNS_MODE="hosts"
    declare -g HTTPS_PORT="20311"
    declare -g HTTP_PORT="20310"
    declare -gx INGRESS_MODE="hostport"
    declare -gx JQ_SHA256="b1c22172dd303f3be49e935aa56aa48a8b7a46e0bc838b4997d3bb451495870f"
    declare -gx JQ_URL="https://github.com/jqlang/jq/releases/download/jq-1.8.2/jq-linux-amd64"
    declare -gx JQ_VERSION="1.8.2"
    declare -gx K8S_VERSION="v1_36"
    declare -gx KIND_CONFIG="kind-config.client.yaml.tpl"
    declare -g KIND_CONFIG_PATH="./k8s/kind-config.client.yaml.tpl"
    declare -g KIND_CONFIG_SHOWN="ctrl/k8s/kind-config.client.yaml.tpl"
    declare -gx KIND_SHA256="50030de23cf40a18505f20426f6a8506bedf13c6e509244bd1fa9463721b0f54"
    declare -gx KIND_URL="https://github.com/kubernetes-sigs/kind/releases/download/v0.32.0/kind-linux-amd64"
    declare -gx KIND_VERSION="v0.32.0"
    declare -g KUBECONTEXT="kind-rig"
    declare -gx KUBECTL_SHA256="ebbd080e7c2e275093b55915722043257eb24004363e20acb3c4d71919f88336"
    declare -gx KUBECTL_URL="https://dl.k8s.io/release/v1.36.3/bin/linux/amd64/kubectl"
    declare -gx KUBECTL_VERSION="v1.36.3"
    declare -g MANIFESTS_DIR="ctrl/k8s/overlays/dev"
    declare -gx METALLB_VERSION="v0.16.0"
    declare -gx METRICS_SERVER_VERSION="v0.9.0"
    declare -g NODES="3"
    declare -g NODE_IMAGE="kindest/node:v1.36.1@sha256:3489c7674813ba5d8b1a9977baea8a6e553784dab7b84759d1014dbd78f7ebd5"
    declare -gx NODE_IMAGE_v1_33="kindest/node:v1.33.12@sha256:3f5c8443c620245e4d355cfe09e96a91ead32ceaa569d3f1ca9edf0cb2fe2ff4"
    declare -gx NODE_IMAGE_v1_34="kindest/node:v1.34.8@sha256:02722c2dedddcfc00febf5d27fbeb9b7b2c14294c82109ff4a85d89ac9ba3256"
    declare -gx NODE_IMAGE_v1_35="kindest/node:v1.35.5@sha256:ce977ae6d65918d0b58a5f8b5e940429c2ce42fa3a5619ec2bbc60b949c0ac95"
    declare -gx NODE_IMAGE_v1_36="kindest/node:v1.36.1@sha256:3489c7674813ba5d8b1a9977baea8a6e553784dab7b84759d1014dbd78f7ebd5"
    declare -g NODE_MB="800"
    declare -gx POSTGRES_IMAGE="postgres:16-alpine"
    declare -gx PROFILE_NAME="client"
    declare -gx REDIS_IMAGE="redis:7-alpine"
    declare -gx REGISTRY_IMAGE="registry:2"
    declare -gx REGISTRY_MODE="mirror"
    declare -g REGISTRY_PORT="20313"
    declare -gx STUB_IMAGE="python:3.12-slim"
    declare -g TILT_PORT="20312"
    declare -gx TILT_SHA256="e9672b8a18d43501f35dcfe98465969a7db0e436b36cf0c50c7e6f8d40de5fe6"
    declare -gx TILT_URL="https://github.com/tilt-dev/tilt/releases/download/v0.37.6/tilt.0.37.6.linux.x86_64.tar.gz"
    declare -gx TILT_VERSION="0.37.6"
    _config_restore "$saved"
}
# ── end of frozen configuration ──

# ── ctrl/mem.sh ──
# How much memory this machine will actually give you before something dies —
# rig's memory tool, and (generated from this file) the standalone rigmini.sh.
#
# There are two numbers and they are rarely the same. `status` reports what the
# machine ADVERTISES and what is quietly capping it. `push` finds what it will
# SURVIVE, by allocating until it stops. `all` does both and weighs the result
# against what this profile's cluster needs.
#
# The gap between them is the whole reason this exists. Under WSL the cap lives
# in .wslconfig; in a container or a managed workspace it is a cgroup limit, and
# there /proc/meminfo reports the HOST's memory while the kernel kills you at a
# fraction of it. A script that only read MemTotal would confidently report 32 GB
# on a box that OOMs at 2.
#
# Runs on native Linux and under WSL. On WSL the memory you see is a VM
# allocation that can be raised, and the commonest failure is raising it without
# restarting — so status compares what .wslconfig says with what actually booted.
#
# Reports and instructs. It never raises a limit, frees anything or installs a
# package. The one write it can make is `backup`, which copies .wslconfig beside
# itself, so that `restore` has something to put back after a hand edit.
#
# Usage:
#   mem.sh status                                  what it has, what caps it
#   mem.sh push [--to GB] [--to-oom]               climb until it stops
#   mem.sh all  [--budget GB]                      both, then the verdict
#   mem.sh backup | restore                        .wslconfig, WSL only
set -euo pipefail
cd "$(dirname "$0")"
# (sourced library inlined above)

# ── defaults ───────────────────────────────────────────────────────────────

STEP_MB=0             # per allocation; 0 means scale it to the ceiling. See push().
STEP_EXPLICIT=no      # whether --step was given, which turns the scaling off.
TO_MB=""              # --to: stop here regardless. Empty means no hard cap.
TO_OOM=no             # --to-oom: opt in to running until the kernel intervenes.
BUDGET_GB=""          # --budget; empty means what this profile's cluster needs, from rig.
BUDGET_EXPLICIT=no    # whether --budget was given, which retires the guess below.

# ── platform ───────────────────────────────────────────────────────────────

# Windows outside WSL — Git Bash, MSYS, Cygwin — looks close enough to work and
# then fails in a pile of confusing ways: no /proc, no docker socket, none of
# the tooling. Detectable, so name it instead.
require_linux() {
    case "$(uname -s)" in
        MINGW*|MSYS*|CYGWIN*)
            cat >&2 <<'EOF'
This has to run inside WSL, not Git Bash / MSYS / Cygwin.

If WSL is not installed yet, from an elevated PowerShell or Command Prompt:

    wsl --install

That enables Windows features and needs a reboot, so it is not something this
script will do for you. Afterwards, open the Linux shell it installs and run
this from there.
EOF
            exit 1 ;;
    esac

    # Everything below reads /proc. Without it there is nothing to measure, and
    # failing here beats printing a page of empty fields.
    if [ ! -r /proc/meminfo ]; then
        echo "no readable /proc/meminfo — this needs a Linux kernel." >&2
        echo "On macOS or a BSD none of the numbers below exist." >&2
        exit 1
    fi
}

is_wsl() { grep -qi microsoft /proc/version 2>/dev/null; }

is_container() {
    [ -f /.dockerenv ] && return 0
    grep -qE '(docker|containerd|kubepods|lxc|podman)' /proc/1/cgroup 2>/dev/null
}

platform() {
    if is_wsl; then echo WSL
    elif is_container; then echo container
    else echo "native linux"
    fi
}

# ── reading memory ─────────────────────────────────────────────────────────

mb() { echo $(( $(awk "/^$1:/{print \$2}" /proc/meminfo) / 1024 )); }

# MemAvailable arrived in kernel 3.14. Older kernels — and they turn up on
# corporate images — need the estimate it replaced, which is worse but not wrong.
avail_meminfo_mb() {
    if grep -q '^MemAvailable:' /proc/meminfo; then
        mb MemAvailable
    else
        awk '/^(MemFree|Buffers|Cached):/{t+=$2} END{print int(t/1024)}' /proc/meminfo
    fi
}

# Where a cgroup records this cgroup's own limit and usage. Set once by
# find_cgroup, because every later reading needs both and hunting for the files
# on each call would be the slow part of the poll loop.
CG_MAX_FILE=""
CG_CUR_FILE=""
CG_VERSION=""

find_cgroup() {
    local rel

    # Inside a container the cgroup namespace makes the top of the tree BE the
    # container's own cgroup, so the unqualified path is already the right one.
    # On a host it is the root cgroup, which is never limited — hence the second
    # attempt via /proc/self/cgroup, which names the slice this shell is in.
    if [ -r /sys/fs/cgroup/memory.max ]; then
        CG_VERSION=v2
        CG_MAX_FILE=/sys/fs/cgroup/memory.max
        CG_CUR_FILE=/sys/fs/cgroup/memory.current
    elif [ -r /sys/fs/cgroup/memory/memory.limit_in_bytes ]; then
        CG_VERSION=v1
        CG_MAX_FILE=/sys/fs/cgroup/memory/memory.limit_in_bytes
        CG_CUR_FILE=/sys/fs/cgroup/memory/memory.usage_in_bytes
    fi

    rel=$(awk -F: '$1=="0"{print $3; exit}' /proc/self/cgroup 2>/dev/null || true)
    if [ -n "$rel" ] && [ "$rel" != "/" ] && [ -r "/sys/fs/cgroup${rel}/memory.max" ]; then
        CG_VERSION=v2
        CG_MAX_FILE="/sys/fs/cgroup${rel}/memory.max"
        CG_CUR_FILE="/sys/fs/cgroup${rel}/memory.current"
        return 0
    fi

    rel=$(awk -F: '$2 ~ /(^|,)memory(,|$)/{print $3; exit}' /proc/self/cgroup 2>/dev/null || true)
    if [ -n "$rel" ] && [ "$rel" != "/" ] \
       && [ -r "/sys/fs/cgroup/memory${rel}/memory.limit_in_bytes" ]; then
        CG_VERSION=v1
        CG_MAX_FILE="/sys/fs/cgroup/memory${rel}/memory.limit_in_bytes"
        CG_CUR_FILE="/sys/fs/cgroup/memory${rel}/memory.usage_in_bytes"
    fi
    return 0
}

# The cap in MB, or "" when there is none worth reporting. v2 spells unlimited
# "max"; v1 spells it as a number near 2^63, which is why this compares against
# MemTotal rather than testing for a magic value — a "limit" above the machine's
# own memory is not a limit, however it is written.
cgroup_cap_mb() {
    local raw cap
    [ -n "$CG_MAX_FILE" ] && [ -r "$CG_MAX_FILE" ] || { echo ""; return 0; }
    raw=$(cat "$CG_MAX_FILE" 2>/dev/null || echo max)
    [ "$raw" = "max" ] && { echo ""; return 0; }
    case "$raw" in ''|*[!0-9]*) echo ""; return 0 ;; esac
    cap=$((raw / 1024 / 1024))
    [ "$cap" -ge "$(mb MemTotal)" ] && { echo ""; return 0; }
    echo "$cap"
}

cgroup_used_mb() {
    local raw
    [ -n "$CG_CUR_FILE" ] && [ -r "$CG_CUR_FILE" ] || { echo ""; return 0; }
    raw=$(cat "$CG_CUR_FILE" 2>/dev/null || echo "")
    case "$raw" in ''|*[!0-9]*) echo ""; return 0 ;; esac
    echo $((raw / 1024 / 1024))
}

# ulimit -v is a per-process address-space cap. It stops YOU long before the box
# does, and because it is inherited from a login shell it is easy to hit without
# knowing it is set.
ulimit_v_mb() {
    local v; v=$(ulimit -v 2>/dev/null || echo unlimited)
    [ "$v" = "unlimited" ] && { echo ""; return 0; }
    case "$v" in ''|*[!0-9]*) echo ""; return 0 ;; esac
    echo $((v / 1024))
}

# The number everything else is about: the lowest of the things that can stop
# you. Printed at the end of `status` and used as the sanity bound in `push`.
effective_ceiling_mb() {
    local c; c=$(mb MemTotal)
    local cap; cap=$(cgroup_cap_mb)
    local ul;  ul=$(ulimit_v_mb)
    [ -n "$cap" ] && [ "$cap" -lt "$c" ] && c="$cap"
    [ -n "$ul" ]  && [ "$ul"  -lt "$c" ] && c="$ul"
    echo "$c"
}

# How much room is left RIGHT NOW, from whichever accounting actually governs.
# In a capped container /proc/meminfo describes the host and is worse than
# useless for this — it would report tens of gigabytes free on a box that is one
# allocation from being killed.
headroom_mb() {
    local cap used
    cap=$(cgroup_cap_mb)
    used=$(cgroup_used_mb)
    if [ -n "$cap" ] && [ -n "$used" ]; then
        echo $(( cap - used ))
    else
        avail_meminfo_mb
    fi
}

# ── status ─────────────────────────────────────────────────────────────────

# /mnt/c/Users can hold several real accounts — a renamed login leaves the old
# directory behind — so picking the first alphabetically is a coin toss. Ask
# Windows, then fall back to whichever profile actually owns a config.
wslconfig_path() {
    local profile winpath found
    profile=$(cmd.exe /c "echo %USERPROFILE%" 2>/dev/null | tr -d "\r\n" || true)
    case "$profile" in
        ""|*%*) ;;
        *) winpath=$(wslpath -u "$profile" 2>/dev/null || true)
           if [ -n "$winpath" ] && [ -d "$winpath" ]; then
               echo "$winpath/.wslconfig"; return 0
           fi ;;
    esac
    found=$(ls -d /mnt/c/Users/*/.wslconfig 2>/dev/null | head -1 || true)
    [ -n "$found" ] && echo "$found"
    return 0
}

hogs() {
    echo "  holding the most:"
    ps -eo rss,comm --sort=-rss 2>/dev/null \
      | awk 'NR>1 && NR<=6 {printf "    %6.0f MB  %s\n", $1/1024, $2}'
    return 0
}

status() {
    local total avail swap_total swap_free cap ul cur

    echo "host"
    echo "  platform    $(platform)"
    echo "  kernel      $(uname -r)"
    [ -r /etc/os-release ] && \
        echo "  distro      $(sed -n 's/^PRETTY_NAME="\(.*\)"/\1/p' /etc/os-release)"
    echo "  cpu         $(getconf _NPROCESSORS_ONLN 2>/dev/null || echo '?') online, load $(cut -d' ' -f1-3 /proc/loadavg)"

    # ── the caps first, because they decide what the totals below are worth ──
    echo
    echo "caps"
    cap=$(cgroup_cap_mb)
    if [ -n "$cap" ]; then
        cur=$(cgroup_used_mb)
        echo "  cgroup      ${cap} MB  (${CG_VERSION}, ${CG_CUR_FILE##*/} says ${cur:-?} MB used)"
        echo "  ! /proc/meminfo below describes the HOST, not this cgroup."
        echo "    $(mb MemTotal) MB total is not yours; ${cap} MB is."
    elif [ -n "$CG_VERSION" ]; then
        echo "  cgroup      none  (${CG_VERSION} present, no memory limit set)"
    else
        echo "  cgroup      no memory controller found"
    fi

    ul=$(ulimit_v_mb)
    if [ -n "$ul" ]; then
        echo "  ! ulimit -v  ${ul} MB — a per-process cap, inherited from your shell"
        echo "    it stops this process long before the machine runs out"
    else
        echo "  ulimit -v   unlimited"
    fi

    # overcommit_memory=0 is the default heuristic: a large allocation is
    # granted on a guess, and the reckoning arrives later as an OOM kill rather
    # than as a failed malloc. It is why `push` touches every page it asks for.
    local om or_
    om=$(cat /proc/sys/vm/overcommit_memory 2>/dev/null || echo '?')
    or_=$(cat /proc/sys/vm/overcommit_ratio 2>/dev/null || echo '?')
    case "$om" in
        0) echo "  overcommit  0 heuristic — allocations are granted on a guess," ;;
        1) echo "  overcommit  1 always — every allocation succeeds; the OOM killer is the only limit," ;;
        2) echo "  overcommit  2 strict (ratio ${or_}%) — allocation fails honestly instead of killing later," ;;
        *) echo "  overcommit  ${om}" ;;
    esac
    [ "$om" != "?" ] && echo "              so RSS is the number to trust, not what a process asked for"

    # ── what it says it has ──
    total=$(mb MemTotal); avail=$(avail_meminfo_mb)
    swap_total=$(mb SwapTotal); swap_free=$(mb SwapFree)
    echo
    echo "memory"
    echo "  total       ${total} MB"
    echo "  available   ${avail} MB"
    echo "  swap        ${swap_total} MB  ($(( swap_total - swap_free )) MB used)"
    if [ "$swap_total" -eq 0 ]; then
        echo "  - no swap: this box has no cushion. It goes from fine to OOM-killed"
        echo "    with nothing in between, which is the abrupt failure you get in a VM."
    fi

    # postgres puts its shared buffers in /dev/shm. Docker's default is 64 MB,
    # and the resulting failure names neither shm nor the size.
    if [ -d /dev/shm ]; then
        local shm; shm=$(df -Pm /dev/shm 2>/dev/null | awk 'NR==2{print $2}')
        if [ -n "$shm" ]; then
            if [ "$shm" -le 64 ]; then
                echo "  ! /dev/shm   ${shm} MB — postgres puts shared memory here and 64 MB"
                echo "    is docker's default. Raise it with --shm-size when postgres fails."
            else
                echo "  /dev/shm    ${shm} MB"
            fi
        fi
    fi

    echo
    echo "disk"
    local d
    for d in / /tmp /var/lib/docker; do
        [ -d "$d" ] || continue
        df -Pm "$d" 2>/dev/null | awk -v p="$d" 'NR==2{printf "  %-12s %s MB free of %s MB\n", p, $4, $2}'
    done

    # kind and Tilt both watch large trees, and the failure mode is silent:
    # they simply stop noticing file changes. Cheap to report while we are here.
    local w i
    w=$(cat /proc/sys/fs/inotify/max_user_watches 2>/dev/null || echo 0)
    i=$(cat /proc/sys/fs/inotify/max_user_instances 2>/dev/null || echo 0)
    echo
    echo "tooling"
    echo "  inotify     watches=$w instances=$i"
    if [ "$w" -lt 524288 ] || [ "$i" -lt 512 ]; then
        echo "  ! low — anything watching files will silently stop seeing changes"
    fi

    if ! command -v docker >/dev/null 2>&1; then
        if [ -S /var/run/docker.sock ]; then
            echo "  docker      socket present, no cli"
        else
            echo "  docker      not installed"
        fi
    elif docker info >/dev/null 2>&1; then
        local n
        n=$(docker ps -q 2>/dev/null | wc -l)
        echo "  docker      $(docker version --format '{{.Server.Version}}' 2>/dev/null), ${n} container(s) running"
    else
        echo "  ! docker     cli present but the daemon is unreachable"
    fi

    # WSL keeps its cap on the Windows side, in a file this shell can read but
    # not usefully apply — the change costs a full VM restart. Report it, and
    # report the commonest mistake, which is editing it and not restarting.
    if is_wsl; then
        local cfg conf conf_mb n
        cfg=$(wslconfig_path)
        echo
        echo "wsl"
        if [ -z "$cfg" ]; then
            echo "  ! cannot tell which Windows profile owns .wslconfig"
        else
            echo "  config      $cfg"
            conf=$(configured_memory "$cfg")
            if [ -n "$conf" ]; then
                conf_mb=$(to_mb "$conf")
                echo "  configured  $conf  (${conf_mb} MB), booted ${total} MB"
                # The VM reports a little less than allocated; 15% covers the
                # kernel without calling every healthy machine a mismatch.
                if [ -n "$conf_mb" ] && [ "$total" -lt $(( conf_mb * 85 / 100 )) ]; then
                    echo "  ! configured ${conf_mb} MB but booted ${total} MB — not applied yet."
                    echo "    From a WINDOWS terminal:  wsl --shutdown   then start the distro again."
                fi
            else
                echo "  configured  no memory= set (WSL defaults to 50% of host RAM, or 8 GB,"
                echo "              whichever is less). To raise it, add on the Windows side:"
                echo "                  [wsl2]"
                echo "                  memory=8GB"
                echo "              then from a WINDOWS terminal:  wsl --shutdown"
            fi
            n=$(ls "$cfg".*.bak 2>/dev/null | wc -l)
            if [ "$n" -gt 0 ]; then
                echo "  backups     $n  (newest: $(ls -t "$cfg".*.bak 2>/dev/null | head -1))"
            fi
        fi
    else
        echo
        echo "  - native linux: no VM allocation to raise. If memory is tight the levers"
        echo "    are freeing something or adding swap."
    fi

    echo
    echo "effective ceiling  $(effective_ceiling_mb) MB"
    echo "  the lowest of MemTotal, the cgroup cap and ulimit -v. What the box"
    echo "  claims. 'push' measures what it will actually hand over."

    [ "$avail" -lt $(( total / 5 )) ] && { echo; hogs; }
    return 0
}

# ── .wslconfig ─────────────────────────────────────────────────────────────

require_wsl() {
    if ! is_wsl; then
        echo "$1 acts on .wslconfig, which only exists under WSL." >&2
        echo "This is native Linux — there is no VM allocation to save or roll back." >&2
        echo "Use 'status' to see what the machine actually has." >&2
        exit 1
    fi
}

# backup and restore act on the file, so unlike status they must not guess.
wslconfig_required() {
    local cfg; cfg=$(wslconfig_required)
    if [ -z "$cfg" ]; then
        echo "cannot tell which Windows profile owns .wslconfig. Candidates:" >&2
        ls -d /mnt/c/Users/*/ 2>/dev/null \
          | grep -viE "/(All Users|Default|Default User|Public)/$" | sed "s/^/  /" >&2
        exit 1
    fi
    echo "$cfg"
}

configured_memory() {
    [ -r "$1" ] || { echo ""; return; }
    sed -n 's/^[[:space:]]*memory[[:space:]]*=[[:space:]]*//p' "$1" | tail -1 | tr -d '[:space:]'
}

# "9GB" / "8192MB" / "9G" -> MB, so it can be compared with /proc/meminfo.
to_mb() {
    local v="${1^^}" n
    n=$(echo "$v" | tr -dc '0-9')
    [ -n "$n" ] || { echo ""; return; }
    case "$v" in
        *GB|*G) echo $(( n * 1024 )) ;;
        *MB|*M) echo "$n" ;;
        *)      echo $(( n / 1024 / 1024 )) ;;
    esac
}

backup() {
    require_wsl backup
    local cfg dest
    cfg=$(wslconfig_required)
    [ -r "$cfg" ] || { echo "nothing to back up: $cfg does not exist" >&2; exit 1; }
    # Timestamped and never overwritten: a backup that can destroy itself on a
    # second run is not a backup.
    dest="${cfg}.$(date +%Y%m%d-%H%M%S).bak"
    cp "$cfg" "$dest"
    echo "backed up  $dest"
    echo
    echo "Edit $cfg by hand, then from a WINDOWS terminal:  wsl --shutdown"
}

restore() {
    require_wsl restore
    local cfg newest count
    cfg=$(wslconfig_required)
    newest=$(ls -t "$cfg".*.bak 2>/dev/null | head -1 || true)
    [ -n "$newest" ] || { echo "no backups found beside $cfg" >&2; exit 1; }

    echo "restoring  $newest"
    echo "        -> $cfg"
    echo

    # Newest is the right default — undo the last edit — but if you backed up
    # *after* editing, the state you want is older. Show the rest so a no-op
    # restore is obviously a no-op rather than a mystery.
    count=$(ls "$cfg".*.bak 2>/dev/null | wc -l)
    if [ "$count" -gt 1 ]; then
        echo "$count backups exist, newest first:"
        ls -t "$cfg".*.bak | sed 's/^/  /'
        echo "  (restoring the newest; copy another by hand to pick an older one)"
        echo
    fi

    if [ -r "$cfg" ]; then
        echo "what changes:"
        if diff "$cfg" "$newest" > /tmp/mem.diff 2>&1 && [ ! -s /tmp/mem.diff ]; then
            echo "  nothing — that backup is identical to the current config"
        else
            sed 's/^/  /' /tmp/mem.diff
        fi
        rm -f /tmp/mem.diff
        echo
    fi

    printf "proceed? [y/N] "
    read -r reply
    case "$reply" in
        y|Y|yes|Yes) ;;
        *) echo "left alone"; return 0 ;;
    esac
    cp "$newest" "$cfg"
    echo "restored. From a WINDOWS terminal:  wsl --shutdown"
}

# ── push ───────────────────────────────────────────────────────────────────

STATE=""
CHILD=""

cleanup() {
    if [ -n "$CHILD" ] && kill -0 "$CHILD" 2>/dev/null; then
        kill -KILL "$CHILD" 2>/dev/null || true
        wait "$CHILD" 2>/dev/null || true
    fi
    [ -n "$STATE" ] && rm -f "$STATE"
    return 0
}

# The child allocates and stops itself; the parent only watches. That split is
# the point: under --to-oom the allocating process is expected to be killed, and
# something has to survive to say how far it got.
allocator() {
    # Raise our own OOM score to the maximum so the kernel picks THIS process
    # first. Raising needs no privilege (only lowering does). Without it, the
    # kernel is free to choose your shell, your ssh session or dockerd — on a
    # box you are still using, that is not an acceptable coin toss.
    echo 1000 > "/proc/$BASHPID/oom_score_adj" 2>/dev/null || true

    local arr=() held=0 i=0 rss swapped avail first_swap=0
    local bytes=$((STEP_MB * 1024 * 1024))
    local swap_used_start
    swap_used_start=$(( $(mb SwapTotal) - $(mb SwapFree) ))

    while :; do
        # Written STRAIGHT INTO the array element. The obvious spelling —
        # build one chunk and `arr+=("$chunk")` — costs three copies per step,
        # not one: the template stays resident, expanding "$chunk" makes a
        # temporary word, and the append makes the element. A 128 MB step then
        # needs 384 MB transiently, and on a small box it is killed on the
        # first append while reporting a third of the true ceiling.
        #
        # printf -v into a subscript also means every page is written, so it is
        # resident rather than merely promised — the only kind of allocation
        # that measures anything under heuristic overcommit.
        printf -v "arr[$i]" '%*s' "$bytes" ''
        i=$((i + 1)); held=$((held + STEP_MB))

        rss=$(awk '/^VmRSS:/{print int($2/1024)}' "/proc/$BASHPID/status" 2>/dev/null || echo 0)
        avail=$(headroom_mb)
        swapped=$(( $(mb SwapTotal) - $(mb SwapFree) - swap_used_start ))
        [ "$swapped" -lt 0 ] && swapped=0

        printf '%8s MB held   rss %7s MB   headroom %7s MB   swap +%s MB\n' \
            "$held" "$rss" "$avail" "$swapped"
        printf '%s %s %s %s\n' "$held" "$rss" "$avail" "$swapped" >> "$STATE"

        # Worth calling out separately from the ceiling: this is where the box
        # stops being fast and starts being unusable, which for a scheduler is
        # a different and earlier problem than being killed.
        if [ "$swapped" -gt 0 ] && [ "$first_swap" -eq 0 ]; then
            first_swap=$held
            echo "  - first swap page at ${held} MB — past here it works but crawls"
            echo "swapat $held" >> "$STATE"
        fi

        if [ -n "$TO_MB" ] && [ "$held" -ge "$TO_MB" ]; then
            echo "stop reached-the-cap" >> "$STATE"; return 0
        fi
        if [ "$TO_OOM" = no ] && [ "$avail" -lt "$FLOOR_MB" ]; then
            echo "stop floor" >> "$STATE"; return 0
        fi
    done
}

push() {
    local total ceiling rc=0 last held rss swapat stop
    total=$(mb MemTotal)
    ceiling=$(effective_ceiling_mb)

    # A step is worth about a sixty-fourth of the ceiling: enough resolution to
    # find the edge, few enough lines to read, and small enough that the
    # transient cost of one allocation never dominates a small box. A fixed
    # size cannot do all three — 128 MB is fine on 16 GB and absurd on 512 MB.
    if [ "$STEP_EXPLICIT" = no ]; then
        STEP_MB=$(( ceiling / 64 ))
        [ "$STEP_MB" -lt 4 ] && STEP_MB=4
        [ "$STEP_MB" -gt 256 ] && STEP_MB=256
    fi

    # Stop with a cushion rather than riding it to the kill. How big a cushion
    # depends on what it is protecting. Under a cgroup cap, running out kills
    # only this container's own processes, so it need cover no more than the
    # shell that prints the result — and a 512 MB cushion on a 1 GB box would
    # halve the answer. On a host there is everything else to protect, and the
    # OOM killer does not promise to pick the process that caused the problem.
    if [ -n "$(cgroup_cap_mb)" ]; then FLOOR_MB=64; else FLOOR_MB=512; fi
    [ $(( ceiling / 20 )) -gt "$FLOOR_MB" ] && FLOOR_MB=$(( ceiling / 20 ))

    STATE=$(mktemp "${TMPDIR:-/tmp}/rigmini.XXXXXX")
    trap cleanup EXIT
    # INT kills the child and lets the summary below print anyway, so an
    # impatient Ctrl-C still tells you how far it got — and, more importantly,
    # still gives the memory back.
    trap 'echo; echo "  interrupted"; echo "stop interrupted" >> "$STATE"; [ -n "$CHILD" ] && kill -KILL "$CHILD" 2>/dev/null || true' INT

    echo "push"
    echo "  step        ${STEP_MB} MB per allocation, every page touched"
    echo "  ceiling     ${ceiling} MB claimed"
    if [ -n "$TO_MB" ]; then
        echo "  stopping    at ${TO_MB} MB (--to)"
    elif [ "$TO_OOM" = yes ]; then
        echo "  ! stopping   only when the kernel stops it (--to-oom)"
        echo "    the allocating child is marked as the preferred OOM victim,"
        echo "    but nothing about an OOM kill is entirely polite. Not on a box"
        echo "    running anything you mind losing."
    else
        echo "  stopping    when headroom drops below ${FLOOR_MB} MB"
    fi
    echo

    allocator &
    CHILD=$!
    wait "$CHILD" || rc=$?
    CHILD=""
    trap - INT

    last=$(grep -E '^[0-9]' "$STATE" 2>/dev/null | tail -1 || true)
    held=$(echo "$last" | awk '{print $1}')
    rss=$(echo "$last"  | awk '{print $2}')
    swapat=$(awk '/^swapat/{print $2}' "$STATE" 2>/dev/null | head -1 || true)
    stop=$(awk '/^stop/{print $2}' "$STATE" 2>/dev/null | head -1 || true)

    echo
    if [ -z "$held" ]; then
        echo "  ! nothing was allocated. Even one ${STEP_MB} MB chunk failed —"
        echo "    try a smaller --step, or check ulimit -v in 'status'."
        return 1
    fi

    echo "  reached     ${rss:-$held} MB resident"
    [ -n "$swapat" ] && echo "  swapping    from ${swapat} MB"

    case "$stop" in
        reached-the-cap)
            echo "  outcome     stopped at the --to cap, not at a limit."
            echo "              The box held ${TO_MB} MB without complaint; there is more." ;;
        floor)
            echo "  outcome     stopped with a cushion intact, by choice."
            echo "              The real ceiling is higher — --to-oom finds it, at the"
            echo "              cost of an actual OOM kill." ;;
        interrupted)
            echo "  outcome     interrupted at ${rss:-$held} MB — where you stopped it,"
            echo "              not where the box did." ;;
        *)
            # No stop line means the child did not decide to stop: it was ended.
            if [ "$rc" -ge 128 ]; then
                echo "  outcome     the child was killed (signal $((rc - 128))) at ${rss:-$held} MB."
            elif [ "$rc" -ne 0 ]; then
                echo "  outcome     the allocation failed at ${rss:-$held} MB (exit ${rc})."
                echo "              bash could not get the next chunk — an honest malloc"
                echo "              failure rather than a kill. That is the strict-overcommit"
                echo "              or ulimit path."
            else
                echo "  outcome     ended at ${rss:-$held} MB."
            fi
            local ev
            ev=$(dmesg 2>/dev/null | tail -80 | grep -iE 'oom-kill|killed process' | tail -1 || true)
            if [ -n "$ev" ]; then
                echo "  kernel      ${ev#*] }"
            else
                echo "  - dmesg is unreadable here (dmesg_restrict, or no privilege),"
                echo "    so the kill cannot be confirmed from this side. The number stands."
            fi ;;
    esac

    # The gap between the claim and the measurement is the finding — but only
    # when the BOX chose where to stop. An empty $stop means the child was ended
    # rather than deciding to end; anything else (--to, the floor) is a stop we
    # asked for, and flagging those as short of the ceiling would put a warning
    # on every deliberately small run.
    local got="${rss:-$held}"
    echo
    if [ -z "$stop" ] && [ "$got" -lt $(( ceiling * 70 / 100 )) ]; then
        echo "  ! claimed ${ceiling} MB, gave up ${got} MB — under 70% of it."
        echo "    Something is taking the difference. 'status' names the candidates:"
        echo "    a cgroup cap, ulimit -v, or memory already resident."
    fi
    return 0
}

# ── all ────────────────────────────────────────────────────────────────────

all() {
    status
    echo
    echo "────────────────────────────────────────────────────────────"
    echo
    push

    local got budget_mb ceiling
    load_config
    if [ -n "$BUDGET_GB" ]; then
        budget_mb=$(( BUDGET_GB * 1024 ))
    else
        budget_mb=$(( NODES * NODE_MB ))
    fi
    ceiling=$(effective_ceiling_mb)
    got=$(grep -E '^[0-9]' "$STATE" 2>/dev/null | tail -1 | awk '{print $2}' || true)
    [ -n "$got" ] || got=0

    echo
    echo "verdict"
    if [ -n "$BUDGET_GB" ]; then
        echo "  budget      ${budget_mb} MB  (--budget)"
    else
        # rig's own figure for this profile: nodes times what one node costs.
        # Addons carry no memory figure in rig yet, so this is the cluster alone
        # and whatever you deploy comes on top. --budget once you know that too.
        echo "  budget      ${budget_mb} MB — profile ${PROFILE_NAME}: ${NODES} node(s) x ${NODE_MB} MB,"
        echo "              the cluster alone; your workload comes on top (--budget GB)"
    fi
    echo "  measured    ${got} MB handed over"

    if [ "$got" -ge "$budget_mb" ]; then
        echo "  fits, with $(( got - budget_mb )) MB spare."
        if [ "$got" -lt $(( budget_mb * 130 / 100 )) ]; then
            echo "  - under 30% spare is thin once a workload runs on top: memory use"
            echo "    is spiky, and the spikes are what get killed."
        fi
    else
        echo "  ! short by $(( budget_mb - got )) MB."
        if [ "$ceiling" -ge "$budget_mb" ]; then
            echo "    The box CLAIMS enough (${ceiling} MB) but did not deliver it."
            echo "    Free something, or read the caps section again."
        else
            echo "    The box does not have it to give. A bigger machine, or a profile"
            echo "    with fewer nodes."
        fi
    fi
    return 0
}

# ── main ───────────────────────────────────────────────────────────────────

parse_flags() {
    while [ $# -gt 0 ]; do
        case "$1" in
            --to)      TO_MB=$(( ${2:?--to needs a value in GB} * 1024 )); shift 2 ;;
            --to-mb)   TO_MB="${2:?--to-mb needs a value in MB}"; shift 2 ;;
            --step)    STEP_MB="${2:?--step needs a value in MB}"; STEP_EXPLICIT=yes; shift 2 ;;
            --to-oom)  TO_OOM=yes; shift ;;
            --budget)  BUDGET_GB="${2:?--budget needs a value in GB}"; BUDGET_EXPLICIT=yes; shift 2 ;;
            *) echo "unknown argument: $1" >&2; exit 1 ;;
        esac
    done
    if [ "$TO_OOM" = yes ] && [ -n "$TO_MB" ]; then
        echo "--to and --to-oom contradict each other: one stops early, the other" >&2
        echo "refuses to stop at all. Pick one." >&2
        exit 1
    fi
    return 0
}

require_linux
find_cgroup

cmd="${1:-status}"
[ $# -gt 0 ] && shift

case "$cmd" in
    status) parse_flags "$@"; status ;;
    push)   parse_flags "$@"; push ;;
    all)    parse_flags "$@"; all ;;
    backup)  backup ;;
    restore) restore ;;
    *)      echo "usage: $0 [status|push|all|backup|restore]" >&2
            echo "       push [--to GB] [--to-mb MB] [--step MB] [--to-oom]" >&2
            echo "       all  [--budget GB]" >&2
            exit 1 ;;
esac