进程生成管理器

Sure, technically these are processes, and this program should really be called a process spawning manager, but this is only due to the way that BASH works when it forks using the ampersand, it uses the fork() or perhaps clone() system call which clones into a separate memory space, rather than something like pthread_create() which would share memory. If BASH supported the latter, each "sequence of execution" would operate just the same and could be termed to be traditional threads whilst gaining a more efficient memory footprint. Functionally however it works the same, though a bit more difficult since GLOBAL variables are not available in each worker clone hence the use of the inter-process communication file and the rudimentary flock semaphore to manage critical sections. Forking from BASH of course is the basic answer here but I feel as if people know that but are really looking to manage what is spawned rather than just fork it and forget it. This demonstrates a way to manage up to 200 instances of forked processes all accessing a single resource. Clearly this is overkill but I enjoyed writing it so I kept on. Increase the size of your terminal accordingly. I hope you find this useful.

ME=$(basename $0)
IPC="/tmp/$ME.ipc"      #interprocess communication file (global thread accounting stats)
DBG=/tmp/$ME.log
echo 0 > $IPC           #initalize counter
F1=thread
SPAWNED=0
COMPLETE=0
SPAWN=1000              #number of jobs to process
SPEEDFACTOR=1           #dynamically compensates for execution time
THREADLIMIT=50          #maximum concurrent threads
TPS=1                   #threads per second delay
THREADCOUNT=0           #number of running threads
SCALE="scale=5"         #controls bc's precision
START=$(date +%s)       #whence we began
MAXTHREADDUR=6         #maximum thread life span - demo mode

LOWER=$[$THREADLIMIT*100*90/10000]   #90% worker utilization threshold
UPPER=$[$THREADLIMIT*100*95/10000]   #95% worker utilization threshold
DELTA=10                             #initial percent speed change

threadspeed()        #dynamically adjust spawn rate based on worker utilization
{
   #vaguely assumes thread execution average will be consistent
   THREADCOUNT=$(threadcount)
   if [ $THREADCOUNT -ge $LOWER ] && [ $THREADCOUNT -le $UPPER ] ;then
      echo SPEED HOLD >> $DBG
      return
   elif [ $THREADCOUNT -lt $LOWER ] ;then
      #if maxthread is free speed up
      SPEEDFACTOR=$(echo "$SCALE;$SPEEDFACTOR*(1-($DELTA/100))"|bc)
      echo SPEED UP $DELTA%>> $DBG
   elif [ $THREADCOUNT -gt $UPPER ];then
      #if maxthread is active then slow down
      SPEEDFACTOR=$(echo "$SCALE;$SPEEDFACTOR*(1+($DELTA/100))"|bc)
      DELTA=1                            #begin fine grain control
      echo SLOW DOWN $DELTA%>> $DBG
   fi

   echo SPEEDFACTOR $SPEEDFACTOR >> $DBG

   #average thread duration   (total elapsed time / number of threads completed)
   #if threads completed is zero (less than 100), default to maxdelay/2  maxthreads

   COMPLETE=$(cat $IPC)

   if [ -z $COMPLETE ];then
      echo BAD IPC READ ============================================== >> $DBG
      return
   fi

   #echo Threads COMPLETE $COMPLETE >> $DBG
   if [ $COMPLETE -lt 100 ];then
      AVGTHREAD=$(echo "$SCALE;$MAXTHREADDUR/2"|bc)
   else
      ELAPSED=$[$(date +%s)-$START]
      #echo Elapsed Time $ELAPSED >> $DBG
      AVGTHREAD=$(echo "$SCALE;$ELAPSED/$COMPLETE*$THREADLIMIT"|bc)
   fi
   echo AVGTHREAD Duration is $AVGTHREAD >> $DBG

   #calculate timing to achieve spawning each workers fast enough
   # to utilize threadlimit - average time it takes to complete one thread / max number of threads
   TPS=$(echo "$SCALE;($AVGTHREAD/$THREADLIMIT)*$SPEEDFACTOR"|bc)
   #TPS=$(echo "$SCALE;$AVGTHREAD/$THREADLIMIT"|bc)  # maintains pretty good
   #echo TPS $TPS >> $DBG

}
function plot()
{
   echo -en \\033[${2}\;${1}H

   if [ -n "$3" ];then
         if [[ $4 = "good" ]];then
            echo -en "\\033[1;32m"
         elif [[ $4 = "warn" ]];then
            echo -en "\\033[1;33m"
         elif [[ $4 = "fail" ]];then
            echo -en "\\033[1;31m"
         elif [[ $4 = "crit" ]];then
            echo -en "\\033[1;31;4m"
         fi
   fi
      echo -n "$3"
      echo -en "\\033[0;39m"
}

trackthread()   #displays thread status
{
   WORKERID=$1
   THREADID=$2
   ACTION=$3    #setactive | setfree | update
   AGE=$4

   TS=$(date +%s)

   COL=$[(($WORKERID-1)/50)*40]
   ROW=$[(($WORKERID-1)%50)+1]

   case $ACTION in
      "setactive" )
         touch /tmp/$ME.$F1$WORKERID  #redundant - see main loop
         #echo created file $ME.$F1$WORKERID >> $DBG
         plot $COL $ROW "Worker$WORKERID: ACTIVE-TID:$THREADID INIT    " good
         ;;
      "update" )
         plot $COL $ROW "Worker$WORKERID: ACTIVE-TID:$THREADID AGE:$AGE" warn
         ;;
      "setfree" )
         plot $COL $ROW "Worker$WORKERID: FREE                         " fail
         rm /tmp/$ME.$F1$WORKERID
         ;;
      * )

      ;;
   esac
}

getfreeworkerid()
{
   for i in $(seq 1 $[$THREADLIMIT+1])
   do
      if [ ! -e /tmp/$ME.$F1$i ];then
         #echo "getfreeworkerid returned $i" >> $DBG
         break
      fi
   done
   if [ $i -eq $[$THREADLIMIT+1] ];then
      #echo "no free threads" >> $DBG
      echo 0
      #exit
   else
      echo $i
   fi
}

updateIPC()
{
   COMPLETE=$(cat $IPC)        #read IPC
   COMPLETE=$[$COMPLETE+1]     #increment IPC
   echo $COMPLETE > $IPC       #write back to IPC
}


worker()
{
   WORKERID=$1
   THREADID=$2
   #echo "new worker WORKERID:$WORKERID THREADID:$THREADID" >> $DBG

   #accessing common terminal requires critical blocking section
   (flock -x -w 10 201
      trackthread $WORKERID $THREADID setactive
   )201>/tmp/$ME.lock

   let "RND = $RANDOM % $MAXTHREADDUR +1"

   for s in $(seq 1 $RND)               #simulate random lifespan
   do
      sleep 1;
      (flock -x -w 10 201
         trackthread $WORKERID $THREADID update $s
      )201>/tmp/$ME.lock
   done

   (flock -x -w 10 201
      trackthread $WORKERID $THREADID setfree
   )201>/tmp/$ME.lock

   (flock -x -w 10 201
      updateIPC
   )201>/tmp/$ME.lock
}

threadcount()
{
   TC=$(ls /tmp/$ME.$F1* 2> /dev/null | wc -l)
   #echo threadcount is $TC >> $DBG
   THREADCOUNT=$TC
   echo $TC
}

status()
{
   #summary status line
   COMPLETE=$(cat $IPC)
   plot 1 $[$THREADLIMIT+2] "WORKERS $(threadcount)/$THREADLIMIT  SPAWNED $SPAWNED/$SPAWN  COMPLETE $COMPLETE/$SPAWN SF=$SPEEDFACTOR TIMING=$TPS"
   echo -en '\033[K'                   #clear to end of line
}

function main()
{
   while [ $SPAWNED -lt $SPAWN ]
   do
      while [ $(threadcount) -lt $THREADLIMIT ] && [ $SPAWNED -lt $SPAWN ]
      do
         WID=$(getfreeworkerid)
         worker $WID $SPAWNED &
         touch /tmp/$ME.$F1$WID    #if this loops faster than file creation in the worker thread it steps on itself, thread tracking is best in main loop
         SPAWNED=$[$SPAWNED+1]
         (flock -x -w 10 201
            status
         )201>/tmp/$ME.lock
         sleep $TPS
        if ((! $[$SPAWNED%100]));then
           #rethink thread timing every 100 threads
           threadspeed
        fi
      done
      sleep $TPS
   done

   while [ "$(threadcount)" -gt 0 ]
   do
      (flock -x -w 10 201
         status
      )201>/tmp/$ME.lock
      sleep 1;
   done

   status
}

clear
threadspeed
main
wait
status
echo

有一个非常有用的程序调用nohup。

     nohup - run a command immune to hangups, with output to a non-tty

你可以使用wait:

some_command &
P1=$!
other_command &
P2=$!
wait $P1 $P2

它将后台程序pid分配给变量($!是最后启动进程的PID)，然后wait命令等待它们。这很好，因为如果您终止了脚本，它也会终止进程!

进程生成管理器

Sure, technically these are processes, and this program should really be called a process spawning manager, but this is only due to the way that BASH works when it forks using the ampersand, it uses the fork() or perhaps clone() system call which clones into a separate memory space, rather than something like pthread_create() which would share memory. If BASH supported the latter, each "sequence of execution" would operate just the same and could be termed to be traditional threads whilst gaining a more efficient memory footprint. Functionally however it works the same, though a bit more difficult since GLOBAL variables are not available in each worker clone hence the use of the inter-process communication file and the rudimentary flock semaphore to manage critical sections. Forking from BASH of course is the basic answer here but I feel as if people know that but are really looking to manage what is spawned rather than just fork it and forget it. This demonstrates a way to manage up to 200 instances of forked processes all accessing a single resource. Clearly this is overkill but I enjoyed writing it so I kept on. Increase the size of your terminal accordingly. I hope you find this useful.

ME=$(basename $0)
IPC="/tmp/$ME.ipc"      #interprocess communication file (global thread accounting stats)
DBG=/tmp/$ME.log
echo 0 > $IPC           #initalize counter
F1=thread
SPAWNED=0
COMPLETE=0
SPAWN=1000              #number of jobs to process
SPEEDFACTOR=1           #dynamically compensates for execution time
THREADLIMIT=50          #maximum concurrent threads
TPS=1                   #threads per second delay
THREADCOUNT=0           #number of running threads
SCALE="scale=5"         #controls bc's precision
START=$(date +%s)       #whence we began
MAXTHREADDUR=6         #maximum thread life span - demo mode

LOWER=$[$THREADLIMIT*100*90/10000]   #90% worker utilization threshold
UPPER=$[$THREADLIMIT*100*95/10000]   #95% worker utilization threshold
DELTA=10                             #initial percent speed change

threadspeed()        #dynamically adjust spawn rate based on worker utilization
{
   #vaguely assumes thread execution average will be consistent
   THREADCOUNT=$(threadcount)
   if [ $THREADCOUNT -ge $LOWER ] && [ $THREADCOUNT -le $UPPER ] ;then
      echo SPEED HOLD >> $DBG
      return
   elif [ $THREADCOUNT -lt $LOWER ] ;then
      #if maxthread is free speed up
      SPEEDFACTOR=$(echo "$SCALE;$SPEEDFACTOR*(1-($DELTA/100))"|bc)
      echo SPEED UP $DELTA%>> $DBG
   elif [ $THREADCOUNT -gt $UPPER ];then
      #if maxthread is active then slow down
      SPEEDFACTOR=$(echo "$SCALE;$SPEEDFACTOR*(1+($DELTA/100))"|bc)
      DELTA=1                            #begin fine grain control
      echo SLOW DOWN $DELTA%>> $DBG
   fi

   echo SPEEDFACTOR $SPEEDFACTOR >> $DBG

   #average thread duration   (total elapsed time / number of threads completed)
   #if threads completed is zero (less than 100), default to maxdelay/2  maxthreads

   COMPLETE=$(cat $IPC)

   if [ -z $COMPLETE ];then
      echo BAD IPC READ ============================================== >> $DBG
      return
   fi

   #echo Threads COMPLETE $COMPLETE >> $DBG
   if [ $COMPLETE -lt 100 ];then
      AVGTHREAD=$(echo "$SCALE;$MAXTHREADDUR/2"|bc)
   else
      ELAPSED=$[$(date +%s)-$START]
      #echo Elapsed Time $ELAPSED >> $DBG
      AVGTHREAD=$(echo "$SCALE;$ELAPSED/$COMPLETE*$THREADLIMIT"|bc)
   fi
   echo AVGTHREAD Duration is $AVGTHREAD >> $DBG

   #calculate timing to achieve spawning each workers fast enough
   # to utilize threadlimit - average time it takes to complete one thread / max number of threads
   TPS=$(echo "$SCALE;($AVGTHREAD/$THREADLIMIT)*$SPEEDFACTOR"|bc)
   #TPS=$(echo "$SCALE;$AVGTHREAD/$THREADLIMIT"|bc)  # maintains pretty good
   #echo TPS $TPS >> $DBG

}
function plot()
{
   echo -en \\033[${2}\;${1}H

   if [ -n "$3" ];then
         if [[ $4 = "good" ]];then
            echo -en "\\033[1;32m"
         elif [[ $4 = "warn" ]];then
            echo -en "\\033[1;33m"
         elif [[ $4 = "fail" ]];then
            echo -en "\\033[1;31m"
         elif [[ $4 = "crit" ]];then
            echo -en "\\033[1;31;4m"
         fi
   fi
      echo -n "$3"
      echo -en "\\033[0;39m"
}

trackthread()   #displays thread status
{
   WORKERID=$1
   THREADID=$2
   ACTION=$3    #setactive | setfree | update
   AGE=$4

   TS=$(date +%s)

   COL=$[(($WORKERID-1)/50)*40]
   ROW=$[(($WORKERID-1)%50)+1]

   case $ACTION in
      "setactive" )
         touch /tmp/$ME.$F1$WORKERID  #redundant - see main loop
         #echo created file $ME.$F1$WORKERID >> $DBG
         plot $COL $ROW "Worker$WORKERID: ACTIVE-TID:$THREADID INIT    " good
         ;;
      "update" )
         plot $COL $ROW "Worker$WORKERID: ACTIVE-TID:$THREADID AGE:$AGE" warn
         ;;
      "setfree" )
         plot $COL $ROW "Worker$WORKERID: FREE                         " fail
         rm /tmp/$ME.$F1$WORKERID
         ;;
      * )

      ;;
   esac
}

getfreeworkerid()
{
   for i in $(seq 1 $[$THREADLIMIT+1])
   do
      if [ ! -e /tmp/$ME.$F1$i ];then
         #echo "getfreeworkerid returned $i" >> $DBG
         break
      fi
   done
   if [ $i -eq $[$THREADLIMIT+1] ];then
      #echo "no free threads" >> $DBG
      echo 0
      #exit
   else
      echo $i
   fi
}

updateIPC()
{
   COMPLETE=$(cat $IPC)        #read IPC
   COMPLETE=$[$COMPLETE+1]     #increment IPC
   echo $COMPLETE > $IPC       #write back to IPC
}


worker()
{
   WORKERID=$1
   THREADID=$2
   #echo "new worker WORKERID:$WORKERID THREADID:$THREADID" >> $DBG

   #accessing common terminal requires critical blocking section
   (flock -x -w 10 201
      trackthread $WORKERID $THREADID setactive
   )201>/tmp/$ME.lock

   let "RND = $RANDOM % $MAXTHREADDUR +1"

   for s in $(seq 1 $RND)               #simulate random lifespan
   do
      sleep 1;
      (flock -x -w 10 201
         trackthread $WORKERID $THREADID update $s
      )201>/tmp/$ME.lock
   done

   (flock -x -w 10 201
      trackthread $WORKERID $THREADID setfree
   )201>/tmp/$ME.lock

   (flock -x -w 10 201
      updateIPC
   )201>/tmp/$ME.lock
}

threadcount()
{
   TC=$(ls /tmp/$ME.$F1* 2> /dev/null | wc -l)
   #echo threadcount is $TC >> $DBG
   THREADCOUNT=$TC
   echo $TC
}

status()
{
   #summary status line
   COMPLETE=$(cat $IPC)
   plot 1 $[$THREADLIMIT+2] "WORKERS $(threadcount)/$THREADLIMIT  SPAWNED $SPAWNED/$SPAWN  COMPLETE $COMPLETE/$SPAWN SF=$SPEEDFACTOR TIMING=$TPS"
   echo -en '\033[K'                   #clear to end of line
}

function main()
{
   while [ $SPAWNED -lt $SPAWN ]
   do
      while [ $(threadcount) -lt $THREADLIMIT ] && [ $SPAWNED -lt $SPAWN ]
      do
         WID=$(getfreeworkerid)
         worker $WID $SPAWNED &
         touch /tmp/$ME.$F1$WID    #if this loops faster than file creation in the worker thread it steps on itself, thread tracking is best in main loop
         SPAWNED=$[$SPAWNED+1]
         (flock -x -w 10 201
            status
         )201>/tmp/$ME.lock
         sleep $TPS
        if ((! $[$SPAWNED%100]));then
           #rethink thread timing every 100 threads
           threadspeed
        fi
      done
      sleep $TPS
   done

   while [ "$(threadcount)" -gt 0 ]
   do
      (flock -x -w 10 201
         status
      )201>/tmp/$ME.lock
      sleep 1;
   done

   status
}

clear
threadspeed
main
wait
status
echo

这对我来说非常有用(在这里找到):

sh -c 'command1 & command2 & command3 & wait'

它混合输出每个命令的所有日志(这是我想要的)，并使用ctrl+c杀死所有日志。

xargs -P <n>允许并行运行<n个>命令。

虽然-P是一个非标准选项，但是GNU (Linux)和macOS/BSD实现都支持它。

示例如下:

最多同时运行3个命令， 只有在先前启动的进程终止时才启动附加命令。

time xargs -P 3 -I {} sh -c 'eval "$1"' - {} <<'EOF'
sleep 1; echo 1
sleep 2; echo 2
sleep 3; echo 3
echo 4
EOF

输出如下所示:

1   # output from 1st command 
4   # output from *last* command, which started as soon as the count dropped below 3
2   # output from 2nd command
3   # output from 3rd command

real    0m3.012s
user    0m0.011s
sys 0m0.008s

计时显示这些命令是并行运行的(最后一个命令仅在最初3个命令中的第一个命令终止后启动，但执行得非常快)。

xargs命令本身在所有命令完成之前不会返回，但是您可以在后台执行它，使用控制操作符&终止它，然后使用内置的wait等待整个xargs命令完成。

{
  xargs -P 3 -I {} sh -c 'eval "$1"' - {} <<'EOF'
sleep 1; echo 1
sleep 2; echo 2
sleep 3; echo 3
echo 4
EOF
} &

# Script execution continues here while `xargs` is running 
# in the background.
echo "Waiting for commands to finish..."

# Wait for `xargs` to finish, via special variable $!, which contains
# the PID of the most recently started background process.
wait $!

注意:

BSD/macOS xargs要求您显式地指定并行运行的命令的数量，而GNU xargs允许您指定-P 0以并行运行尽可能多的命令。 并行运行的进程的输出在生成时到达，因此它将不可预测地交错。 正如Ole的回答中所提到的(大多数平台都不是标准的)，GNU并行在每个进程的基础上方便地序列化(分组)输出，并提供了许多更高级的特性。