#!/usr/bin/env bash # ubi-runner — run a command on an ephemeral Ubicloud VM. # # UBICLOUD_API_KEY=... scripts/ubicloud/ubi-runner.sh run --setup S.sh -- 'make test' # # UBICLOUD_API_TOKEN is accepted as an alias for UBICLOUD_API_KEY. SSH # connections are multiplexed per VM, and `pack` / `unpack` upload one prebuilt # checkout tarball to many VMs. This is the repo copy the user-scope Capy # `ubicloud` skill and gbrain's scripts/ubicloud/ubi-runner.sh are kept in sync # with (plan E2); `bun run test:ubicloud` drives it through test-free.sh. # # Scratch record: every VM this machine creates is appended to a VM-id file # (UBI_VM_RECORD; default ~/.capy/work/ubi-runner/vms.tsv when ~/.capy/work # exists, else $STATE_ROOT/vms.tsv) as `name location owner created_at pid`, # and removed once `down` confirms it gone. A resumed Capy thread reads that # file to find VMs an earlier turn left behind (docs/TESTING_INTERNALS.md, # "Resuming after a wake"). # # Creates a VM (standard-16 by default), streams the checkout to it (tracked + # untracked-unignored files + .git, so uncommitted edits are included), runs an # optional setup script and the command, copies requested artifacts back, and # destroys the VM on every exit path. Exits with the command's status. # Needs only bash, curl, python3, ssh, ssh-keygen, and tar locally, so it works # from dev boxes, containers, and cloud sandboxes. # # Ownership: VMs are named ubirun---[-t]. is UBI_OWNER # (lowercased, letters and digits only, at most 12 characters, starting with a # letter) or a random per-machine id kept in $STATE_ROOT/owner-id. Ubicloud names # allow 63 characters of [a-z0-9-], so a full name stays under 40. # # Teardown: `up` records each VM's state (location, create status) before it # sends the create request, and `down` destroys and polls until the VM is # confirmed gone or provably never existed, waiting out a create that may still # be in flight. An interrupted `up` or `run` (EXIT, INT, TERM, HUP, QUIT) runs # that `down`; further signals are ignored until it finishes. A create refused # for vCPU quota prints the project's usage per owner. # # Stale-VM sweeps are off by default. With UBI_GC_HOURS set to a positive # number, every `up` first destroys this owner's VMs older than that; `gc HOURS` # runs the same sweep on demand. Neither ever touches another owner's VMs. # # TTL and reaper: a name this script generates ends in -t (UBI_TTL_HOURS, # default 4; 0 omits it), the creator's own declaration of how long the VM may # live. `reap` destroys every VM in the project whose TTL expired more than ten # minutes ago, whichever owner made it, and every `up` runs it first (UBI_REAP=0 # skips it), so a runner killed by a sleeping machine leaves nothing behind for # longer than its TTL. Names without a TTL are never reaped. # # Quota preflight: when the project's vCPU ceiling is known (UBI_QUOTA_VCPUS, or # the maximum a refusal printed, cached in $STATE_ROOT/quota-max), `up` adds the # size's vCPUs to the project's running VMs and refuses before any create when # that exceeds it; UBI_QUOTA_WAIT= waits for room instead. # # Watchdog: `run`, `verify` and `ssh NAME COMMAND` stream the remote output # through a watchdog that logs a heartbeat every UBI_HEARTBEAT seconds (300) # and kills a command silent for UBI_IDLE_TIMEOUT seconds (1800) or older than # UBI_RUN_TIMEOUT seconds (0, unlimited), exiting 124 with the last 40 lines, # so a hung verify fails fast instead of holding the VM until its TTL. # # `verify` is the one entry point for a repository's full remote verify: it # reads .gstack/ubicloud.json (setup, command, size, location, env, pass, pull) # and runs it through `run`, so lanes share one committed definition instead of # per-lane wrappers. set -euo pipefail # Keep heredoc bodies on temp files, not the pipe window (test/heredoc-pipe-deadlock.test.ts). BASH_COMPAT=50 API="${UBICLOUD_API_URL:-https://api.ubicloud.com}" STATE_ROOT="${UBI_RUNNER_STATE:-${XDG_STATE_HOME:-$HOME/.local/state}/ubi-runner}" DEFAULT_SIZE="${UBI_SIZE:-standard-16}" DEFAULT_LOCATION="${UBI_LOCATION:-eu-central-h1}" GC_HOURS="${UBI_GC_HOURS:-0}" API_TIMEOUT="${UBI_API_TIMEOUT:-120}" CREATE_GRACE="${UBI_CREATE_GRACE:-180}" DOWN_TIMEOUT="${UBI_DOWN_TIMEOUT:-900}" POLL="${UBI_POLL_SECONDS:-5}" ALLOWED_STORAGE="${UBI_ALLOWED_STORAGE:-320 640}" TTL_HOURS="${UBI_TTL_HOURS:-4}" REAP="${UBI_REAP:-1}" REAP_GRACE=600 IDLE_TIMEOUT="${UBI_IDLE_TIMEOUT:-1800}" RUN_TIMEOUT="${UBI_RUN_TIMEOUT:-0}" HEARTBEAT="${UBI_HEARTBEAT:-300}" QUOTA_VCPUS="${UBI_QUOTA_VCPUS:-}" QUOTA_WAIT="${UBI_QUOTA_WAIT:-0}" PREFIX="ubirun" if [ -n "${UBI_VM_RECORD:-}" ]; then VM_RECORD="$UBI_VM_RECORD" elif [ -d "$HOME/.capy/work" ]; then VM_RECORD="$HOME/.capy/work/ubi-runner/vms.tsv" else VM_RECORD="$STATE_ROOT/vms.tsv"; fi die() { echo "ubi-runner: $*" >&2; exit 1; } log() { echo "ubi-runner: $*" >&2; } for bin in curl python3 ssh ssh-keygen tar; do command -v "$bin" >/dev/null || die "$bin is required" done UBICLOUD_API_KEY="${UBICLOUD_API_KEY:-${UBICLOUD_API_TOKEN:-}}" [[ "$GC_HOURS" =~ ^[0-9]+$ ]] || die "UBI_GC_HOURS must be a whole number of hours (unset or 0 disables the sweep)" [[ "$TTL_HOURS" =~ ^(0|[1-9][0-9]{0,2})$ ]] || die "UBI_TTL_HOURS must be a whole number of hours from 0 to 999 with no leading zero (0 names VMs without a TTL)" for v in IDLE_TIMEOUT RUN_TIMEOUT HEARTBEAT QUOTA_WAIT; do [[ "${!v}" =~ ^[0-9]+$ ]] || die "UBI_$v must be a whole number of seconds (0 disables it)" done [ -z "$QUOTA_VCPUS" ] || [[ "$QUOTA_VCPUS" =~ ^[0-9]+$ ]] || die "UBI_QUOTA_VCPUS must be a whole number of vCPUs" owner_id() { local raw=${UBI_OWNER:-} file="$STATE_ROOT/owner-id" tmp if [ -z "$raw" ]; then if [ ! -s "$file" ]; then mkdir -p "$STATE_ROOT" tmp="$file.$$" echo "m$(head -c4 /dev/urandom | od -An -tx1 | tr -d ' \n')" >"$tmp" mv -n "$tmp" "$file" rm -f "$tmp" fi raw=$(cat "$file") fi raw=$(printf %s "$raw" | tr '[:upper:]' '[:lower:]' | tr -cd 'a-z0-9') [ -n "$raw" ] || die "UBI_OWNER must contain letters or digits" [[ "$raw" =~ ^[a-z] ]] || raw="u$raw" echo "${raw:0:12}" } OWNER=$(owner_id) # api OUT ARGS...: send one Ubicloud CLI command, write the body to OUT, and # print the HTTP status (000 when no response arrived). api() { local out=$1 code shift code=$(python3 -c 'import json,sys; print(json.dumps({"argv": sys.argv[1:]}))' "$@" \ | curl -sS -o "$out" -w '%{http_code}' --max-time "$API_TIMEOUT" -X POST \ -H "Authorization: Bearer $UBICLOUD_API_KEY" \ -H 'Accept: text/plain' -H 'Content-Type: application/json' \ -H 'X-Ubi-Version: 1.0.0' --data @- "$API/cli") || true echo "${code:-000}" } cli() { local out code out=$(mktemp) code=$(api "$out" "$@") if [ "$code" = 000 ]; then rm -f "$out" die "request failed: ubi $*" fi if [ "$code" != 200 ]; then cat "$out" >&2 rm -f "$out" return 1 fi cat "$out" rm -f "$out" } state_dir() { echo "$STATE_ROOT/$1"; } load() { local dir dir=$(state_dir "$1") [ -f "$dir/env" ] || die "no local state for VM '$1' (created on another machine?)" # shellcheck disable=SC1091 . "$dir/env" KEY="$dir/key" } ssh_opts() { echo -i "$KEY" -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null \ -o LogLevel=ERROR -o ServerAliveInterval=30 -o ServerAliveCountMax=6 -o ConnectTimeout=10 \ -o ControlMaster=auto -o "ControlPath=$(dirname "$KEY")/ctl" -o ControlPersist=300 } # Ubuntu's default umask (002) leaves new directories group-writable, which # permission-checking code under test rejects; every remote command uses 022. remote() { local name=$1; shift load "$name" # shellcheck disable=SC2046 ssh $(ssh_opts) "ubi@$IP" "umask 022; $*" } mtime() { stat -c %Y "$1" 2>/dev/null || stat -f %m "$1"; } # sq STRING: STRING as one single-quoted shell word. sq() { printf "'%s'" "$(printf %s "$1" | sed "s/'/'\\\\''/g")"; } # remote_cancel NAME SIDFILE: end the session a watched command started on the # VM (its leader pid is in SIDFILE there), bounded to 20 seconds. Killing the # local ssh client alone leaves a silent remote command running until it next # writes to the closed channel. remote_cancel() { local name=$1 sidf=$2 cpid i=0 remote "$name" "sid=\$(cat $sidf 2>/dev/null); rm -f $sidf; [ -z \"\$sid\" ] || { pkill -TERM -s \"\$sid\"; sleep 2; pkill -KILL -s \"\$sid\"; }; true" >/dev/null 2>&1 /dev/null && [ "$i" -lt 20 ]; do sleep 1; i=$(( i + 1 )); done kill "$cpid" 2>/dev/null || true wait "$cpid" 2>/dev/null || true } # watched NAME PHASE COMMAND: run COMMAND on the VM, streaming its output and # keeping a copy of both streams in the VM's state dir, with a heartbeat every HEARTBEAT # seconds and a watchdog that kills it after IDLE_TIMEOUT seconds of silence or # RUN_TIMEOUT seconds in total: exit 124, reason and the last 40 lines on # stderr. The ssh runs in its own session (python3's setsid) so the watchdog # kills it and anything it started, not just the shell that launched it; on # the VM the command runs in its own session too (setsid where the image has # it), whose leader pid is written to ~/.ubirun-PHASE-.sid so # remote_cancel can end it when the client is killed. watched() { local name=$1 phase=$2 cmd=$3 out pid rc=0 start now last_beat idle elapsed why="" old_traps inner sidf sidf="~/.ubirun-$phase-$$.sid" load "$name" out="$(state_dir "$name")/$phase.log" : >"$out" inner=$(sq "printf %s \$\$ >$sidf; $cmd") # The sid file outlives the command on purpose: a background child it left # behind keeps the ssh channel open after the wrapper exits, and remote_cancel # still needs the session id to end it. remote_cancel removes the file. cmd="if command -v setsid >/dev/null 2>&1; then setsid -w bash -c $inner; else bash -c $inner; fi" # The caller's stdin is handed to the background ssh explicitly (a background # job in a non-interactive shell would otherwise read /dev/null), so piped # input reaches the remote command as it did before the watchdog. exec 3<&0 # shellcheck disable=SC2046 ( exec python3 -c 'import os, sys; os.setsid(); os.execvp(sys.argv[1], sys.argv[1:])' \ ssh $(ssh_opts) "ubi@$IP" "umask 022; $cmd" ) <&3 > >(tee -a "$out") 2> >(tee -a "$out" >&2) & pid=$! exec 3<&- # A signal to this process takes the ssh session down with it, so Ctrl-C on # `ssh NAME COMMAND` leaves no orphaned client behind. old_traps=$(trap -p INT TERM) trap 'kill -TERM -- "-$pid" 2>/dev/null; exit 130' INT TERM start=$(date +%s) last_beat=$start while :; do sleep 1 kill -0 "$pid" 2>/dev/null || break now=$(date +%s) elapsed=$(( now - start )) idle=$(( now - $(mtime "$out") )) if [ "$IDLE_TIMEOUT" -gt 0 ] && [ "$idle" -ge "$IDLE_TIMEOUT" ]; then why="printed nothing for ${idle}s (UBI_IDLE_TIMEOUT=$IDLE_TIMEOUT)" elif [ "$RUN_TIMEOUT" -gt 0 ] && [ "$elapsed" -ge "$RUN_TIMEOUT" ]; then why="ran ${elapsed}s (UBI_RUN_TIMEOUT=$RUN_TIMEOUT)" fi if [ -n "$why" ]; then # The command may have finished while the clock was read; a finished # command is never reported as a timeout. kill -0 "$pid" 2>/dev/null || break log "watchdog: $phase $why; killing it. Last output:" tail -n 40 "$out" >&2 kill -TERM -- "-$pid" 2>/dev/null || kill "$pid" 2>/dev/null || true wait "$pid" 2>/dev/null || rc=$? trap - INT TERM; eval "$old_traps" # A command killed by the watchdog never exits 0; a 0 here means it # finished in the instant before the kill, and that result stands. if [ "$rc" -eq 0 ]; then log "watchdog: $phase finished before it could be killed; its exit 0 stands" return 0 fi remote_cancel "$name" "$sidf" return 124 fi if [ "$HEARTBEAT" -gt 0 ] && [ $(( now - last_beat )) -ge "$HEARTBEAT" ]; then log "heartbeat: $phase ${elapsed}s elapsed, last output ${idle}s ago" last_beat=$now fi done wait "$pid" || rc=$? trap - INT TERM; eval "$old_traps" return "$rc" } # vm_rows: "location name owner expires" for every VM in the project; owner is # "-" for untagged ubirun--* names and "." for VMs this runner did not # name; expires is the epoch the name's -t TTL ends at, or "-". vm_rows() { local loc name owner created expires cli vm list -N -f location,name | while read -r loc name; do owner=. created="" expires=- if [[ "$name" =~ ^${PREFIX}-([a-z][a-z0-9]{0,11})-([0-9]{10})- ]]; then owner=${BASH_REMATCH[1]} created=${BASH_REMATCH[2]} elif [[ "$name" =~ ^${PREFIX}-([0-9]{10})- ]]; then owner=- created=${BASH_REMATCH[1]} fi if [ -n "$created" ] && [[ "$name" =~ -t([0-9]{1,3})$ ]]; then expires=$(( 10#$created + 10#${BASH_REMATCH[1]} * 3600 )) fi echo "$loc $name $owner $expires" done } # reap: destroy every VM whose name carries a TTL that ended more than # REAP_GRACE seconds ago, whichever owner created it (the TTL is that owner's # own declaration). Names without a TTL are never touched. cmd_reap() { local now rows loc name owner expires n=0 failed=0 now=$(date +%s) rows=$(vm_rows) || { log "reap: could not list the project's VMs; nothing destroyed"; return 1; } while read -r loc name owner expires; do [ -n "$name" ] || continue [ "$expires" != - ] || continue [ "$now" -ge $(( expires + REAP_GRACE )) ] || continue n=$(( n + 1 )) log "reaping expired $loc/$name (owner $owner; its TTL ended $(( (now - expires) / 60 )) min ago)" cmd_down "$name" -l "$loc" || { failed=$(( failed + 1 )); log "failed to reap $loc/$name"; } done <<<"$rows" [ "$n" -gt 0 ] || log "reap: no expired VMs" [ "$failed" -eq 0 ] || { log "reap: $failed of $n expired VMs could not be destroyed"; return 1; } } cmd_gc() { local hours=${1:-$GC_HOURS} now loc name owner [[ "$hours" =~ ^[0-9]+$ ]] || die "gc: HOURS must be a whole number (or set UBI_GC_HOURS)" if [ "$hours" -eq 0 ]; then log "gc: no sweep (give HOURS > 0 or set UBI_GC_HOURS); nothing listed, nothing destroyed"; return 0; fi now=$(date +%s) vm_rows | while read -r loc name owner _; do [ "$owner" = "$OWNER" ] || continue [[ "$name" =~ -([0-9]{10})- ]] || continue if [ $(( (now - BASH_REMATCH[1]) / 3600 )) -ge "$hours" ]; then log "destroying stale $loc/$name (owner $OWNER, older than ${hours}h)" cmd_down "$name" -l "$loc" || log "failed to destroy $loc/$name" fi done } cmd_list() { case ${1:-} in "") cli vm list ;; --mine) vm_rows | awk -v o="$OWNER" '$3==o {print $1 " " $2}' ;; *) die "list: unknown option $1 (use --mine)" ;; esac } # usage: VMs and vCPUs per owner, from each VM's size (standard-16 = 16 vCPUs). cmd_usage() { local tmp loc name owner i=0 tmp=$(mktemp -d) while read -r loc name owner _; do i=$(( i + 1 )) cli vm "$loc/$name" show 2>/dev/null | sed -n "s/^size: /$owner /p" >"$tmp/$i" & [ $(( i % 8 )) -ne 0 ] || wait done < <(vm_rows) wait cat "$tmp"/* 2>/dev/null | awk -v me="$OWNER" ' { n = $2; sub(/^.*-/, "", n); o = $1 == "-" ? "(untagged)" : $1 == "." ? "(other)" : $1 vms[o]++; cpu[o] += n; total += n; count++ } END { printf "%-14s %4s %6s\n", "OWNER", "VMS", "VCPUS" for (o in cpu) printf "%-14s %4d %6d%s\n", o, vms[o], cpu[o], o == me ? " (you)" : "" | "sort -k3,3nr" close("sort -k3,3nr") printf "%-14s %4d %6d\n", "total", count, total }' rm -rf "$tmp" } write_state() { printf 'NAME=%q\nLOCATION=%q\nSIZE=%q\nIP=%q\nCREATED=%q\nCREATE_AT=%q\nCREATE_PID=%q\n' \ "$1" "$2" "$3" "$4" "$5" "$6" "$$" >"$(state_dir "$1")/env" } # record_vm NAME LOCATION: append to the scratch VM-id file (record-before-create). record_vm() { mkdir -p "$(dirname "$VM_RECORD")" 2>/dev/null || return 0 printf '%s\t%s\t%s\t%s\t%s\n' "$1" "$2" "$OWNER" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" "$$" >>"$VM_RECORD" } # forget_vm NAME: drop the VM from the scratch file once it is confirmed gone. forget_vm() { [ -f "$VM_RECORD" ] || return 0 local tmp="$VM_RECORD.$$" awk -F'\t' -v n="$1" '$1!=n' "$VM_RECORD" >"$tmp" && mv "$tmp" "$VM_RECORD" } # records: print the scratch file (VMs this machine created and has not confirmed gone). cmd_records() { echo "record: $VM_RECORD" [ -s "$VM_RECORD" ] || { echo "(no VMs recorded)"; return 0; } printf '%-40s %-14s %-12s %-20s %s\n' NAME LOCATION OWNER CREATED_AT PID awk -F'\t' '{ printf "%-40s %-14s %-12s %-20s %s\n", $1, $2, $3, $4, $5 }' "$VM_RECORD" } new_name() { local ttl="" [ "$TTL_HOURS" -eq 0 ] || ttl="-t$TTL_HOURS" echo "$PREFIX-$OWNER-$(date +%s)-$(head -c4 /dev/urandom | od -An -tx1 | tr -d ' \n')$ttl" } # vcpus SIZE: the vCPU count a Ubicloud size name carries (standard-16 -> 16). vcpus() { [[ "$1" =~ -([0-9]+)$ ]] && echo "${BASH_REMATCH[1]}"; } # quota_preflight LOCATION NAME SIZE: refuse (or wait UBI_QUOTA_WAIT seconds) # before the create request when the project's running VMs plus this size # exceed the known vCPU ceiling. The ceiling comes from UBI_QUOTA_VCPUS or the # maximum the last refusal printed; without either the API's own refusal rules. QUOTA_CACHE_MAX_AGE=86400 quota_preflight() { local location=$1 name=$2 size=$3 need max used remaining step source="UBI_QUOTA_VCPUS" cache="$STATE_ROOT/quota-max" need=$(vcpus "$size") || return 0 max=$QUOTA_VCPUS if [ -z "$max" ] && [ -f "$cache" ]; then # A refusal's maximum is remembered for a day: after that (a raised quota, # another project's key) the API's own answer decides again. if [ $(( $(date +%s) - $(mtime "$cache") )) -lt "$QUOTA_CACHE_MAX_AGE" ]; then max=$(cat "$cache" 2>/dev/null || true); source="the last refusal, cached in $cache" else rm -f "$cache" fi fi [[ "$max" =~ ^[0-9]+$ ]] || return 0 # The budget counts seconds spent waiting for room, not the usage calls # between them: a slow first usage read must not shave the printed budget. remaining=$QUOTA_WAIT while :; do used=$(cmd_usage 2>/dev/null | awk '$1=="total" {print $3}') [[ "$used" =~ ^[0-9]+$ ]] || return 0 [ $(( used + need )) -gt "$max" ] || return 0 if [ "$remaining" -le 0 ]; then log "quota preflight refused $location/$name ($size): it needs $need vCPUs and the project's VMs already use $used of $max (ceiling from $source; other usage such as managed runners counts on top)" cmd_usage >&2 || true die "create refused before any request: vCPU quota exhausted (quota full); wait for running VMs to finish (UBI_QUOTA_WAIT= waits here), run $0 reap, use a smaller size, or set UBI_QUOTA_VCPUS to the project's real ceiling" fi log "quota: $used of $max vCPUs in use and $need needed; waiting up to ${remaining}s more for room" step=$(( remaining < 30 ? remaining : 30 )) sleep "$step" remaining=$(( remaining - step )) done } valid_name() { [[ "$1" =~ ^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$ ]]; } # check_storage GIB: Ubicloud accepts only these disk sizes; refuse before any API call. check_storage() { case " $ALLOWED_STORAGE " in *" $1 "*) [ -n "$1" ] && return 0 ;; esac die "invalid storage '$1' GiB (allowed: $ALLOWED_STORAGE; set UBI_ALLOWED_STORAGE when Ubicloud adds sizes)" } UP_NAME="" UP_READY="" cmd_up() { local size=$DEFAULT_SIZE location=$DEFAULT_LOCATION name="" storage="" image=ubuntu-noble while [ $# -gt 0 ]; do case $1 in -s|--size) size=$2; shift 2 ;; -l|--location) location=$2; shift 2 ;; -n|--name) name=$2; shift 2 ;; -S|--storage) check_storage "$2"; storage=$2; shift 2 ;; -b|--image) image=$2; shift 2 ;; *) die "up: unknown option $1" ;; esac done [ -n "$name" ] || name=$(new_name) valid_name "$name" || die "invalid VM name '$name' (Ubicloud allows 1-63 of a-z, 0-9 and '-', starting and ending with a letter or digit)" if [ "$REAP" != 0 ]; then cmd_reap || log "reap failed; continuing" fi if [ "$GC_HOURS" -gt 0 ]; then cmd_gc "$GC_HOURS" || log "stale-VM cleanup failed; continuing" fi quota_preflight "$location" "$name" "$size" local dir create_at dir=$(state_dir "$name") mkdir -p "$dir" chmod 700 "$dir" ssh-keygen -q -t ed25519 -N '' -C "$name" -f "$dir/key" local args=(vm "$location/$name" create -s "$size" -b "$image") [ -z "$storage" ] || args+=(-S "$storage") args+=("$(cat "$dir/key.pub")") create_at=$(date +%s) write_state "$name" "$location" "$size" "" unknown "$create_at" record_vm "$name" "$location" UP_NAME=$name log "creating $location/$name ($size)" # Hold signals until the create answer is recorded, so teardown knows # whether the VM exists instead of waiting out UBI_CREATE_GRACE. local interrupted="" created=yes refusal need used max trap 'interrupted=1' INT TERM HUP QUIT cli "${args[@]}" >/dev/null 2>"$dir/create.err" || created=no write_state "$name" "$location" "$size" "" "$created" "$create_at" trap 'exit 130' INT TERM HUP QUIT [ -z "$interrupted" ] || exit 130 if [ "$created" = no ]; then refusal=$(sed -n 's/.*Requested vCPU count: \([0-9]*\), currently used vCPU count: \([0-9]*\), maximum allowed vCPU count: \([0-9]*\).*/\1 \2 \3/p' "$dir/create.err") if [ -z "$refusal" ]; then cat "$dir/create.err" >&2 die "create failed" fi read -r need used max <<<"$refusal" echo "$max" >"$STATE_ROOT/quota-max" log "quota refused $location/$name ($size): it needs $need vCPUs and the project already uses $used of $max" log "VMs in the project by owner (the rest of the used count is other usage, such as managed GitHub runners):" cmd_usage >&2 || true die "create failed: vCPU quota exhausted; wait for running VMs to finish, or use fewer or smaller VMs (ci:ubicloud --vms N)" fi local deadline=$(( $(date +%s) + 600 )) show state ip while :; do show=$(cli vm "$location/$name" show 2>/dev/null || true) state=$(sed -n 's/^state: //p' <<<"$show") ip=$(sed -n 's/^ip4: //p' <<<"$show") [ "$state" = running ] && [ -n "$ip" ] && break [ "$(date +%s)" -lt "$deadline" ] || die "VM did not reach running in 10 minutes (last state: ${state:-unknown})" sleep "$POLL" done write_state "$name" "$location" "$size" "$ip" yes "$create_at" load "$name" deadline=$(( $(date +%s) + 300 )) # shellcheck disable=SC2046 until ssh $(ssh_opts) "ubi@$IP" true 2>/dev/null; do [ "$(date +%s)" -lt "$deadline" ] || die "SSH did not come up on $IP" sleep "$POLL" done remote "$name" 'cloud-init status --wait >/dev/null 2>&1 || true' UP_READY=1 log "ready: $name ($IP)" echo "$name" } # down NAME [-l LOCATION]: destroy NAME and return 0 only once it is confirmed # gone or never existed. While this machine's create request for NAME may # still be in flight (its `up` process is alive, or the create was sent less # than UBI_CREATE_GRACE seconds ago with no answer), "not found" is not final. cmd_down() { local name=${1:-} loc="" dir [ -n "$name" ] || die "down: missing NAME" shift while [ $# -gt 0 ]; do case $1 in -l|--location) loc=$2; shift 2 ;; *) die "down: unknown option $1" ;; esac done valid_name "$name" || die "invalid VM name '$name'" dir=$(state_dir "$name") local CREATED=none CREATE_AT=0 CREATE_PID="" IP="" LOCATION="" KEY="" if [ -f "$dir/env" ]; then load "$name" loc=$LOCATION if [ -S "$dir/ctl" ] && [ -n "$IP" ]; then # shellcheck disable=SC2046 ssh $(ssh_opts) -O exit "ubi@$IP" >/dev/null 2>&1 || true fi fi local deadline=$(( $(date +%s) + DOWN_TIMEOUT )) seen=0 asked=0 out code now out=$(mktemp) while :; do now=$(date +%s) if [ -z "$loc" ]; then loc=$(vm_rows 2>/dev/null | awk -v n="$name" '$2==n {print $1}') || loc="" code=404 [ -z "$loc" ] || code=$(api "$out" vm "$loc/$name" show) else code=$(api "$out" vm "$loc/$name" show) fi if [ "$code" = 200 ]; then seen=1 if [ $(( now - asked )) -ge 60 ]; then code=$(api "$out" vm "$loc/$name" destroy -f) if [ "$code" != 200 ]; then cat "$out" >&2 rm -f "$out" log "FAILED to destroy $loc/$name (HTTP $code); retry: $0 down $name" return 1 fi asked=$now log "destroy requested: $loc/$name" fi elif [ "$code" = 404 ]; then if [ "$seen" = 1 ] || [ "$CREATED" != unknown ] || { [ $(( now - CREATE_AT )) -ge "$CREATE_GRACE" ] \ && { [ "$CREATE_PID" = "$$" ] || ! kill -0 "$CREATE_PID" 2>/dev/null; }; }; then rm -f "$out" rm -rf "$dir" forget_vm "$name" if [ "$seen" = 1 ]; then log "destroyed ${loc:-?}/$name"; else log "gone: ${loc:-?}/$name (never existed or already destroyed)"; fi return 0 fi log "waiting for an in-flight create of $name to resolve" fi if [ "$now" -ge "$deadline" ]; then rm -f "$out" log "WARNING: could not confirm ${loc:-?}/$name is gone after ${DOWN_TIMEOUT}s; rerun: $0 down $name" return 1 fi sleep "$POLL" done } # pack SRC: write a gzipped checkout tarball to stdout (tracked + untracked # files that are not ignored, plus a .git snapshot; a non-git directory is # taken whole). The live .git is never tarred: another process running git in # the checkout (a review subagent's diff, a trial merge's worktree add) writes # index.lock, packed-refs and objects while tar reads, and GNU tar exits 1 # on a file that changed under it (GSTA-121's PREGATE_REMOTE_INFRA). Instead # the refs are fetched into a fresh repository through git's own transport, # which reads a consistent view, the remote.* config is replayed so # origin/ still resolves, and the index is copied (git writes it # atomically through a rename). A linked worktree's .git is a one-line # pointer into the main repository, useless on the VM; the same snapshot # replaces it, on the worktree's own branch and index. Not carried: submodule # repositories (.git/modules) and a partial clone's promisor (the fetch pulls # every missing blob first); gstack has neither. cmd_pack() { local src tmp gitdir branch head entry src=$(cd "${1:-.}" && pwd) if git -C "$src" rev-parse --is-inside-work-tree >/dev/null 2>&1; then head=$(git -C "$src" rev-parse --verify -q HEAD) || die "pack: $src has no commits; the VM needs a HEAD to fingerprint" branch=$(git -C "$src" symbolic-ref -q --short HEAD || true) tmp=$(mktemp -d) # The path is baked in: a set -e failure unwinds the function before the trap runs, and a local $tmp is unset there. trap "rm -rf $(printf %q "$tmp")" EXIT # No template hooks from a global init.templateDir, and no auto-gc under the tar. git -c gc.auto=0 init -q --bare --template= "$tmp/.git" git -C "$tmp/.git" -c gc.auto=0 fetch -q --no-tags --update-shallow "$src" '+refs/*:refs/*' \ || die "pack: could not snapshot the refs of $src" if [ -z "$branch" ]; then branch="detached-${head:0:12}" git -C "$tmp/.git" fetch -q --no-tags --update-shallow "$src" "+HEAD:refs/heads/$branch" fi git -C "$tmp/.git" symbolic-ref HEAD "refs/heads/$branch" git -C "$tmp/.git" config core.bare false gitdir=$(cd "$src" && cd "$(git rev-parse --git-common-dir)" && pwd) while IFS= read -r -d '' entry; do # A key with no value (`[remote "x"] mirror`) is boolean true. case $entry in *$'\n'*) ;; *) entry="$entry"$'\n'true ;; esac git -C "$tmp/.git" config --add "${entry%%$'\n'*}" "${entry#*$'\n'}" done < <(git -C "$gitdir" config --local --null --get-regexp '^(remote|branch)\.' 2>/dev/null || true) # The checkout's index rides along so the VM's status matches, except a # split index, whose shared half lives only in the original git dir. The # index's blobs that HEAD's tree lacks (staged, intent-to-add, the stages # of an unmerged entry) are behind no ref, so they travel as a pack of # their own; without them the VM's write-tree (gstack-wtree) cannot read a # staged file. if [ "$(git -C "$src" config --bool core.splitIndex 2>/dev/null)" != true ]; then cp "$(cd "$src" && cd "$(dirname "$(git rev-parse --git-path index)")" && pwd)/index" "$tmp/.git/index" # Read the copy, not the live index, so the pack matches it; a gitlink's # sha (mode 160000) is a submodule commit this object store lacks. GIT_INDEX_FILE="$tmp/.git/index" git -C "$src" ls-files -s | awk '$1 != "160000" {print $2}' | sort -u \ | comm -23 - <(git -C "$src" ls-tree -r HEAD | awk '{print $3}' | sort -u) \ | git -C "$src" pack-objects -q --stdout \ | git -C "$tmp/.git" unpack-objects -q \ || die "pack: could not snapshot the staged blobs of $src" fi ( cd "$src" git ls-files -z -co --exclude-standard \ | while IFS= read -r -d '' f; do if [ -e "$f" ] || [ -L "$f" ]; then printf '%s\0' "$f"; fi done \ | tar --null -T - -c -C "$tmp" .git -zf - ) rm -rf "$tmp"; trap - EXIT else tar -C "$src" -czf - . fi } # unpack NAME DEST: extract a tarball read from stdin into DEST on the VM. cmd_unpack() { local qdest qdest=$(printf %q "$2") remote "$1" "mkdir -p $qdest && tar -xzf - -C $qdest" } cmd_sync() { local name=$1 src=${2:-.} dest=${3:-} src=$(cd "$src" && pwd) [ -n "$dest" ] || dest="work/$(basename "$src")" cmd_pack "$src" | cmd_unpack "$name" "$dest" log "synced $src -> $name:$dest" } # pull NAME REMOTE_GLOB LOCAL_DIR: copy matching remote entries into LOCAL_DIR. # Relative remote paths start at /home/ubi. A glob that matches nothing (for # example an optional flake ledger) is reported and skipped, not a failure. cmd_pull() { local name=$1 from=$2 to=$3 dir dir=$(printf %q "$(dirname "$from")") if ! remote "$name" "cd $dir 2>/dev/null && ls -d -- $(basename "$from") >/dev/null 2>&1"; then log "pull: nothing matches $from" return 0 fi mkdir -p "$to" remote "$name" "cd $dir && tar -czf - $(basename "$from")" | tar -xzf - -C "$to" } # pass_name NAME: a variable this runner may forward to a VM. Its own # credentials (UBICLOUD_*) never leave this machine, whoever asks. pass_name() { [[ "$1" =~ ^[A-Za-z_][A-Za-z0-9_]*$ ]] || die "--pass $1: not a variable name" case $1 in UBICLOUD_*) die "--pass $1: the runner never forwards its own Ubicloud credentials to a VM" ;; esac } # inside_dir DIR ROOT: DIR resolves, symlinks followed, to ROOT or below it. # Its nearest existing ancestor is checked first, so a refused destination # creates nothing (not even outside the root); only then is DIR created and # checked again. inside_dir() { local a b near=$1 b=$(cd "$2" 2>/dev/null && pwd -P) || return 1 while [ ! -d "$near" ]; do [ "$near" != "$(dirname "$near")" ] || return 1 near=$(dirname "$near") done a=$(cd "$near" 2>/dev/null && pwd -P) || return 1 [ "$a" = "$b" ] || [[ "$a" = "$b"/* ]] || return 1 mkdir -p "$1" 2>/dev/null || return 1 a=$(cd "$1" 2>/dev/null && pwd -P) || return 1 [ "$a" = "$b" ] || [[ "$a" = "$b"/* ]] } # PULL_ROOT: set by verify; every pull destination must resolve inside it at # pull time (an earlier pull may have placed a symlink where a later one lands). PULL_ROOT="" cmd_run() { local up_args=() src=. dest="" setup="" keep=0 pulls=() envs=() while [ $# -gt 0 ]; do case $1 in -S|--storage) check_storage "$2"; up_args+=("$1" "$2"); shift 2 ;; -s|--size|-l|--location|-n|--name|-b|--image) up_args+=("$1" "$2"); shift 2 ;; --src) src=$2; shift 2 ;; --dest) dest=$2; shift 2 ;; --setup) setup=$2; shift 2 ;; --env) envs+=("$2"); shift 2 ;; --pass) pass_name "$2"; [ -n "${!2+x}" ] || die "--pass $2: not set locally"; envs+=("$2=${!2}"); shift 2 ;; --pull) pulls+=("$2"); shift 2 ;; --keep) keep=1; shift ;; --) shift; break ;; *) die "run: unknown option $1" ;; esac done [ $# -gt 0 ] || die "run: missing command after --" [ -z "$setup" ] || [ -f "$setup" ] || die "setup script not found: $setup" src=$(cd "$src" && pwd) [ -n "$dest" ] || dest="work/$(basename "$src")" local i name="" for (( i = 0; i < ${#up_args[@]}; i += 2 )); do case ${up_args[i]} in -n|--name) name=${up_args[i+1]} ;; esac done [ -n "$name" ] || { name=$(new_name); up_args+=(-n "$name"); } RUN_VM=$name # Armed before the create request: an interrupted `up` still destroys its VM. # A second signal must not cut teardown short, so the EXIT handler ignores them. trap 'trap "" INT TERM HUP QUIT; cmd_down "$RUN_VM" || log "WARNING: failed to destroy $RUN_VM; run: $0 down $RUN_VM"' EXIT trap 'exit 130' INT TERM HUP QUIT cmd_up "${up_args[@]}" >/dev/null if [[ "$name" =~ -t([0-9]+)$ ]]; then log "$name carries a ${BASH_REMATCH[1]}h TTL (any later run of this script reaps it); if this process dies first: $0 down $name" else log "$name has no TTL; if this process dies before its teardown line, destroy it with: $0 down $name" fi if [ "$keep" = 1 ]; then trap - EXIT log "--keep: leaving $name running; destroy with: $0 down $name" fi local e for e in ${envs[@]+"${envs[@]}"}; do printf 'export %s=%q\n' "${e%%=*}" "${e#*=}"; done \ | remote "$name" 'umask 077 && cat > ~/.ubirun-env' cmd_sync "$name" "$src" "$dest" local qdest rc=0 qdest=$(printf %q "$dest") if [ -n "$setup" ]; then remote "$name" 'cat > ~/.ubirun-setup.sh' <"$setup" log "running setup $(basename "$setup")" watched "$name" setup "cd $qdest && . ~/.ubirun-env && bash -l ~/.ubirun-setup.sh" || { rc=$?; log "setup failed (exit $rc)"; exit "$rc"; } fi local start start=$(date +%s) log "running on $name: $*" watched "$name" command "cd $qdest && . ~/.ubirun-env && bash -lc $(printf %q "$*")" || rc=$? log "command exited $rc after $(( $(date +%s) - start ))s" local p for p in ${pulls[@]+"${pulls[@]}"}; do if [ -n "$PULL_ROOT" ] && ! inside_dir "${p#*:}" "$PULL_ROOT"; then log "pull refused: ${p#*:} resolves outside $PULL_ROOT" [ "$rc" -ne 0 ] || rc=1 continue fi cmd_pull "$name" "${p%%:*}" "${p#*:}" || log "pull failed: $p" done return "$rc" } # verify [run opts] [--trust-config] [-- COMMAND]: run the repository's # committed remote verify. .gstack/ubicloud.json under --src (default .) # supplies setup, command, size, location, storage, image, env, pass and pull; # flags given here and a trailing -- COMMAND override it. Without the file it # refuses, so every lane runs the one committed definition instead of its own # wrapper. # # The file is repository content and gets no reach beyond the checkout on its # own: its setup script and pull destinations must resolve inside --src, and a # local variable it lists under pass is forwarded only when this command line # also names it (--pass NAME) or grants every listed name (--trust-config). cmd_verify() { local src=. i j g n cfg cfg_setup cfg_cmd parsed err rc=0 trust=0 cfg_args=() cfg_pass=() user_pre=() user_cmd=() granted=() missing=() for (( i = 1; i <= $#; i++ )); do [ "${!i}" = -- ] && break if [ "${!i}" = --src ]; then j=$(( i + 1 )); src=${!j}; fi done cfg="$src/.gstack/ubicloud.json" [ -f "$cfg" ] || die "verify: no $cfg; commit one ({\"setup\": \"scripts/ubicloud/bootstrap.sh\", \"command\": \"bash scripts/ubicloud/verify.sh\"}) so every lane runs the same verify instead of its own wrapper" err=$(mktemp) parsed=$(python3 -c ' import json, os, shlex, sys cfg, src = sys.argv[1], sys.argv[2] try: c = json.load(open(cfg)) except ValueError: sys.exit(3) if not isinstance(c, dict): sys.exit(3) base, root = os.path.abspath(src), os.path.realpath(src) def inside(rel, what): if not isinstance(rel, str) or not rel or os.path.isabs(rel) or rel.startswith("~") or ".." in rel.replace("\\", "/").split("/"): print("%s %r must be a relative path inside the checkout" % (what, rel), file=sys.stderr); sys.exit(2) full = os.path.realpath(os.path.join(root, rel)) if full != root and not full.startswith(root + os.sep): print("%s %r resolves outside the checkout (%s)" % (what, rel, full), file=sys.stderr); sys.exit(2) return os.path.join(base, rel) q = lambda s: shlex.quote(str(s)) args = [] for key, flag in (("size", "-s"), ("location", "-l"), ("storage", "-S"), ("image", "-b")): if key in c: args += [flag, q(c[key])] for item in c.get("env", []): args += ["--env", q(item)] for item in c.get("pull", []): remote, sep, local = str(item).partition(":") if not sep or not remote: print("pull entry %r must be REMOTE_GLOB:LOCAL_DIR" % (item,), file=sys.stderr); sys.exit(2) args += ["--pull", q(remote + ":" + inside(local, "pull destination"))] setup = c.get("setup", "") print("cfg_args=(" + " ".join(args) + ")") print("cfg_pass=(" + " ".join(q(x) for x in c.get("pass", [])) + ")") print("cfg_setup=" + q(inside(setup, "setup") if setup else "")) print("cfg_cmd=" + q(c.get("command", ""))) ' "$cfg" "$src" 2>"$err") || rc=$? case $rc in 0) ;; 2) local why; why=$(cat "$err"); rm -f "$err"; die "verify: $cfg: $why" ;; *) rm -f "$err"; die "verify: $cfg is not valid JSON" ;; esac rm -f "$err" eval "$parsed" while [ $# -gt 0 ]; do case $1 in --) shift; user_cmd=("$@"); break ;; --trust-config) trust=1; shift ;; --keep) user_pre+=("$1"); shift ;; --pass|-S|--storage|-s|--size|-l|--location|-n|--name|-b|--image|--src|--dest|--setup|--env|--pull) [ $# -ge 2 ] || die "verify: $1 needs a value" [ "$1" != --pass ] || granted+=("$2") user_pre+=("$1" "$2"); shift 2 ;; *) die "verify: unknown option $1" ;; esac done for n in ${cfg_pass[@]+"${cfg_pass[@]}"}; do pass_name "$n" if [ "$trust" = 1 ]; then cfg_args+=(--pass "$n"); continue; fi for g in ${granted[@]+"${granted[@]}"}; do [ "$g" = "$n" ] && continue 2; done missing+=("$n") done [ ${#missing[@]} -eq 0 ] || die "verify: $cfg asks to forward local ${missing[*]}; grant each on this command line with --pass NAME, or every name it lists with --trust-config" [ ${#user_cmd[@]} -gt 0 ] || [ -n "$cfg_cmd" ] || die "verify: $cfg names no command and none was given after --" [ ${#user_cmd[@]} -gt 0 ] || user_cmd=("$cfg_cmd") log "verify: $cfg" PULL_ROOT=$(cd "$src" && pwd) cmd_run ${cfg_args[@]+"${cfg_args[@]}"} ${cfg_setup:+--setup "$cfg_setup"} --src "$src" ${user_pre[@]+"${user_pre[@]}"} -- "${user_cmd[@]}" } usage() { cat < [args] run [up opts] [--src DIR] [--dest PATH] [--setup FILE] [--env K=V]... [--pass NAME]... [--pull REMOTE_GLOB:LOCAL_DIR]... [--keep] -- COMMAND up + sync + setup + command + pull + destroy; exits with COMMAND's status verify [run opts] [--trust-config] [-- COMMAND] run the repository's committed verify (.gstack/ubicloud.json under --src); its setup script and every pull destination stay inside --src (checked again at pull time), and its pass names are forwarded only when granted here (--pass NAME, or all: --trust-config) up [-s SIZE] [-l LOCATION] [-n NAME] [-S STORAGE_GIB] [-b IMAGE] create a VM and wait for SSH; prints its name (STORAGE_GIB: one of $ALLOWED_STORAGE) ssh NAME [COMMAND] shell or login-shell command on the VM (user ubi, passwordless sudo) sync NAME [SRC] [DEST] stream a checkout (tracked + untracked-unignored + .git) pack [SRC] write that checkout tarball to stdout unpack NAME DEST extract a tarball from stdin into DEST on the VM pull NAME REMOTE_GLOB LOCAL_DIR copy matching remote entries into LOCAL_DIR down NAME [-l LOC] destroy the VM; returns once it is confirmed gone or never existed list [--mine] list all VMs in the project, or only this owner's usage VMs and vCPUs per owner across the project owner print this caller's owner tag ($OWNER) records VMs this machine created and has not confirmed gone ($VM_RECORD) gc HOURS destroy this owner's VMs older than HOURS (never other owners') reap destroy every VM whose -t TTL has ended (any owner; TTL-less names never) cli ARGS... raw Ubicloud CLI passthrough (e.g. cli vm list) VMs are named $PREFIX----t; set UBI_OWNER (e.g. your thread code) to tag them, otherwise a per-machine id is used. defaults: size=$DEFAULT_SIZE location=$DEFAULT_LOCATION (env UBI_SIZE, UBI_LOCATION) env: UBI_TTL_HOURS (${TTL_HOURS}h in the name; 0 omits it), UBI_REAP (0: up skips the reap), UBI_IDLE_TIMEOUT (${IDLE_TIMEOUT}s of silence kills the remote command, exit 124; 0 disables), UBI_RUN_TIMEOUT (${RUN_TIMEOUT}s wall clock; 0 unlimited), UBI_HEARTBEAT (${HEARTBEAT}s between heartbeat lines), UBI_QUOTA_VCPUS (project vCPU ceiling for the preflight; else the last refusal's maximum), UBI_QUOTA_WAIT (${QUOTA_WAIT}s to wait for quota room instead of refusing), UBI_GC_HOURS (unset/0: no sweep on up), UBI_CREATE_GRACE (${CREATE_GRACE}s), UBI_DOWN_TIMEOUT (${DOWN_TIMEOUT}s), UBI_API_TIMEOUT (${API_TIMEOUT}s), UBI_VM_RECORD (scratch VM-id file), UBI_ALLOWED_STORAGE (the -S sizes Ubicloud accepts; default "320 640") EOF } cmd=${1:-help} [ $# -eq 0 ] || shift case $cmd in owner|pack|records|help|-h|--help) ;; *) [ -n "${UBICLOUD_API_KEY:-}" ] || die "UBICLOUD_API_KEY is not set (create a token under your Ubicloud project's Tokens page)" ;; esac case $cmd in run) cmd_run "$@" ;; verify) cmd_verify "$@" ;; up) trap 'trap "" INT TERM HUP QUIT; [ -z "$UP_NAME" ] || [ -n "$UP_READY" ] || cmd_down "$UP_NAME" || log "WARNING: failed to destroy $UP_NAME; run: $0 down $UP_NAME"' EXIT trap 'exit 130' INT TERM HUP QUIT cmd_up "$@" ;; ssh) name=$1; shift; load "$name" # shellcheck disable=SC2046 if [ $# -eq 0 ]; then exec ssh -t $(ssh_opts) "ubi@$IP"; else watched "$name" ssh "bash -lc $(printf %q "$*")"; fi ;; sync) cmd_sync "$@" ;; pack) cmd_pack "$@" ;; unpack) cmd_unpack "$@" ;; pull) cmd_pull "$@" ;; down) cmd_down "$@" ;; list) cmd_list "$@" ;; usage) cmd_usage ;; owner) echo "$OWNER" ;; records) cmd_records ;; gc) cmd_gc "$@" ;; reap) cmd_reap ;; cli) cli "$@" ;; help|-h|--help) usage ;; *) usage >&2; exit 2 ;; esac