set -e
fail () {
    touch .failure
}
expect () {
    wait
    if [ -f .failure ]; then
        rm -f .failure
        exit 1
    fi
}

sleep 2 || fail &
sleep 2 && false || fail &
sleep 2 || fail
expect

顶部的set -e使脚本在失败时停止。

如果任何子作业失败，Expect将返回1。

下面是我的版本，适用于多个pid，如果执行时间过长，则记录警告，如果执行时间超过给定值，则停止子进程。

[编辑]我已经在https://github.com/deajan/ofunctions上传了我的WaitForTaskCompletion的新实现，称为ExecTasks。 还有一个用于WaitForTaskCompletion的compat层 (/编辑)

function WaitForTaskCompletion {
    local pids="${1}" # pids to wait for, separated by semi-colon
    local soft_max_time="${2}" # If execution takes longer than $soft_max_time seconds, will log a warning, unless $soft_max_time equals 0.
    local hard_max_time="${3}" # If execution takes longer than $hard_max_time seconds, will stop execution, unless $hard_max_time equals 0.
    local caller_name="${4}" # Who called this function
    local exit_on_error="${5:-false}" # Should the function exit program on subprocess errors       

    Logger "${FUNCNAME[0]} called by [$caller_name]."

    local soft_alert=0 # Does a soft alert need to be triggered, if yes, send an alert once 
    local log_ttime=0 # local time instance for comparaison

    local seconds_begin=$SECONDS # Seconds since the beginning of the script
    local exec_time=0 # Seconds since the beginning of this function

    local retval=0 # return value of monitored pid process
    local errorcount=0 # Number of pids that finished with errors

    local pidCount # number of given pids

    IFS=';' read -a pidsArray <<< "$pids"
    pidCount=${#pidsArray[@]}

    while [ ${#pidsArray[@]} -gt 0 ]; do
        newPidsArray=()
        for pid in "${pidsArray[@]}"; do
            if kill -0 $pid > /dev/null 2>&1; then
                newPidsArray+=($pid)
            else
                wait $pid
                result=$?
                if [ $result -ne 0 ]; then
                    errorcount=$((errorcount+1))
                    Logger "${FUNCNAME[0]} called by [$caller_name] finished monitoring [$pid] with exitcode [$result]."
                fi
            fi
        done

        ## Log a standby message every hour
        exec_time=$(($SECONDS - $seconds_begin))
        if [ $((($exec_time + 1) % 3600)) -eq 0 ]; then
            if [ $log_ttime -ne $exec_time ]; then
                log_ttime=$exec_time
                Logger "Current tasks still running with pids [${pidsArray[@]}]."
            fi
        fi

        if [ $exec_time -gt $soft_max_time ]; then
            if [ $soft_alert -eq 0 ] && [ $soft_max_time -ne 0 ]; then
                Logger "Max soft execution time exceeded for task [$caller_name] with pids [${pidsArray[@]}]."
                soft_alert=1
                SendAlert

            fi
            if [ $exec_time -gt $hard_max_time ] && [ $hard_max_time -ne 0 ]; then
                Logger "Max hard execution time exceeded for task [$caller_name] with pids [${pidsArray[@]}]. Stopping task execution."
                kill -SIGTERM $pid
                if [ $? == 0 ]; then
                    Logger "Task stopped successfully"
                else
                    errrorcount=$((errorcount+1))
                fi
            fi
        fi

        pidsArray=("${newPidsArray[@]}")
        sleep 1
    done

    Logger "${FUNCNAME[0]} ended for [$caller_name] using [$pidCount] subprocesses with [$errorcount] errors."
    if [ $exit_on_error == true ] && [ $errorcount -gt 0 ]; then
        Logger "Stopping execution."
        exit 1337
    else
        return $errorcount
    fi
}

# Just a plain stupid logging function to be replaced by yours
function Logger {
    local value="${1}"

    echo $value
}

例如，等待所有三个进程完成，如果执行时间超过5秒，则记录警告，如果执行时间超过120秒，则停止所有进程。不要在失败时退出程序。

function something {

    sleep 10 &
    pids="$!"
    sleep 12 &
    pids="$pids;$!"
    sleep 9 &
    pids="$pids;$!"

    WaitForTaskCompletion $pids 5 120 ${FUNCNAME[0]} false
}
# Launch the function
someting
    

这是我目前想到的。我想了解如何在子进程终止时中断sleep命令，这样就不必根据使用情况调优WAITALL_DELAY。

waitall() { # PID...
  ## Wait for children to exit and indicate whether all exited with 0 status.
  local errors=0
  while :; do
    debug "Processes remaining: $*"
    for pid in "$@"; do
      shift
      if kill -0 "$pid" 2>/dev/null; then
        debug "$pid is still alive."
        set -- "$@" "$pid"
      elif wait "$pid"; then
        debug "$pid exited with zero exit status."
      else
        debug "$pid exited with non-zero exit status."
        ((++errors))
      fi
    done
    (("$#" > 0)) || break
    # TODO: how to interrupt this sleep when a child terminates?
    sleep ${WAITALL_DELAY:-1}
   done
  ((errors == 0))
}

debug() { echo "DEBUG: $*" >&2; }

pids=""
for t in 3 5 4; do 
  sleep "$t" &
  pids="$pids $!"
done
waitall $pids

wait还(可选地)接受要等待的进程的PID，并且使用$!你会得到最后一个命令的PID在后台启动。 修改循环，将每个衍生子进程的PID存储到一个数组中，然后再次循环等待每个PID。

# run processes and store pids in array
for i in $n_procs; do
    ./procs[${i}] &
    pids[${i}]=$!
done

# wait for all pids
for pid in ${pids[*]}; do
    wait $pid
done

等待所有作业并返回最后一个失败作业的退出码。与上面的解决方案不同，这不需要保存pid，也不需要修改脚本的内部循环。走开，等着吧。

function wait_ex {
    # this waits for all jobs and returns the exit code of the last failing job
    ecode=0
    while true; do
        [ -z "$(jobs)" ] && break
        wait -n
        err="$?"
        [ "$err" != "0" ] && ecode="$err"
    done
    return $ecode
}

编辑:修正了脚本运行不存在的命令时可能被愚弄的错误。

我需要这个，但目标进程不是当前shell的子进程，在这种情况下，等待$PID不起作用。我确实找到了以下替代方案:

while [ -e /proc/$PID ]; do sleep 0.1 ; done

这依赖于procfs的存在，它可能不可用(例如Mac不提供它)。所以对于可移植性，你可以用这个代替:

while ps -p $PID >/dev/null ; do sleep 0.1 ; done