Add job timeout

README.md

@@ -7,6 +7,7 @@ Configuration happens via environment variables:
 * `HTTP2IRC_GET_URL` and `HTTP2IRC_POST_URL`: GET/POST URLs for IRC channel interaction
 * `IA_S3_ACCESS` and `IA_S3_SECRET`: authentication for IA
 * `CODEARCHIVER_BOT_TEST` (optional): enables test mode when set to any non-empty value, with uploads going into items prefixed with `test_` and placed into `test_collection`.
+* `CODEARCHIVER_BOT_TIMEOUT` (optional): number of seconds how long a `codearchiver` command may run. Default: unlimited (0)
 
 The data produced by `codearchiver-bot` must be kept in its working directory for correct deduplication. However, there's nothing unique there; all data is uploaded to IA continuously, and operation can be restored from there by downloading all `*_codearchiver_metadata.txt` files and creating placeholders (e.g. symlinks to `.uploaded` as the script does by default) for everything else.
 

codearchiver-bot

@@ -9,6 +9,9 @@ for envvar in "${envvars[@]}"; do
 	fi
 done
 
+# Optional env variables
+declare -i timeout="${CODEARCHIVER_BOT_TIMEOUT:-0}"
+
 for dep in awk codearchiver curl ia-upload-stream python3 sha256sum tee zstd; do
 	if ! command -v "${dep}" &>/dev/null; then
 		printf 'Error: %s not found\n' "${dep}" >&2
@@ -155,7 +158,8 @@ function respond {
 
 			# Run codearchiver, duplicating WARNINGs and higher in the bot output
 			log "Running ${url} (${singlejobid}), logging into ${logname}"
-			codearchiver --verbose --write-artefacts-fd-3 "${url}" \
+			timeout --signal=INT "${timeout}" \
+				codearchiver --verbose --write-artefacts-fd-3 "${url}" \
 				2> >(tee "${logname}" | grep -Fv -e '  INFO  ' | log_loop "From codearchiver ${singlejobid}: ") \
 				3> >(tee "${artefactsname}" | log_loop "New artefacts from codearchiver ${singlejobid}: ")
 			status="$?"