xargs -Pとバックグラウンドジョブによる並列処理

#!/usr/bin/env bash
# Create sample files
mkdir -p /tmp/xargs_demo
for i in 1 2 3; do
  echo "hello world $i" > /tmp/xargs_demo/file$i.txt
done

# Process files one at a time (sequential)
find /tmp/xargs_demo -name '*.txt' | xargs -I {} sh -c 'tr a-z A-Z < "$1"' _ {}

# Cleanup
rm -rf /tmp/xargs_demo

#!/usr/bin/env bash
# Simulate 8 tasks, each taking ~1 second
# Sequential would take ~8s; parallel with -P 4 takes ~2s

process_item() {
  local item="$1"
  sleep 1
  echo "Done: $item"
}
export -f process_item

time printf '%s\n' task{1..8} | xargs -n 1 -P 4 bash -c 'process_item "$@"' _

#!/usr/bin/env bash
# Create dummy log files
mkdir -p /tmp/logs_demo
for i in $(seq 1 12); do
  dd if=/dev/urandom bs=1K count=64 2>/dev/null > /tmp/logs_demo/app_$i.log
done

echo "Files before: $(ls /tmp/logs_demo | wc -l)"

# Compress all .log files in parallel (up to 8 workers)
find /tmp/logs_demo -name '*.log' -print0 \
  | xargs -0 -n 1 -P 8 gzip --fast

echo "Files after : $(ls /tmp/logs_demo | wc -l)"
rm -rf /tmp/logs_demo

#!/usr/bin/env bash
CORES=$(nproc)
IO_WORKERS=$(( CORES * 4 ))

echo "CPU cores   : $CORES"
echo "CPU-bound -P: $CORES"
echo "I/O-bound -P: $IO_WORKERS"

# Example: parallel curl downloads (I/O-bound)
# printf '%s\n' url1 url2 ... | xargs -n 1 -P "$IO_WORKERS" curl -sSO

#!/usr/bin/env bash
process() {
  local id="$1"
  sleep $(( RANDOM % 3 + 1 ))
  echo "Job $id finished at $(date +%T)"
}

echo "Launching 5 background jobs..."
for id in $(seq 1 5); do
  process "$id" &
done

wait   # Block until every background job completes
echo "All jobs done."

#!/usr/bin/env bash
MAX_JOBS=3

process() {
  local id="$1"
  sleep $(( RANDOM % 3 + 1 ))
  echo "Task $id done"
}

for id in $(seq 1 10); do
  # Throttle: wait for a slot if pool is full
  while (( $(jobs -r | wc -l) >= MAX_JOBS )); do
    wait -n 2>/dev/null || true
  done
  process "$id" &
done

wait
echo "All 10 tasks complete."

#!/usr/bin/env bash
set -euo pipefail

task() {
  local id="$1"
  sleep 1
  if (( id == 3 )); then
    echo "Task $id: FAILED" >&2
    return 1
  fi
  echo "Task $id: ok"
}

pids=()
for id in $(seq 1 5); do
  task "$id" &
  pids+=("$!")
done

failed=0
for pid in "${pids[@]}"; do
  if ! wait "$pid"; then
    echo "PID $pid exited with error" >&2
    (( failed++ ))
  fi
done

(( failed == 0 )) && echo "All OK" || { echo "$failed job(s) failed"; exit 1; }

#!/usr/bin/env bash
# Download several small public files in parallel
URLs=(
  "https://httpbin.org/bytes/1024"
  "https://httpbin.org/bytes/2048"
  "https://httpbin.org/bytes/512"
  "https://httpbin.org/bytes/4096"
)

mkdir -p /tmp/parallel_dl

printf '%s\n' "${URLs[@]}" | xargs -n 1 -P 4 bash -c '
  url="$1"
  out="/tmp/parallel_dl/$(echo "$url" | md5sum | cut -c1-8).bin"
  curl -sSf "$url" -o "$out" && echo "Saved $out"
' _

ls -lh /tmp/parallel_dl/
rm -rf /tmp/parallel_dl

#!/usr/bin/env bash
mkdir -p /tmp/proc_demo
for i in $(seq 1 8); do echo "data $i" > /tmp/proc_demo/item_$i.txt; done

process_file() {
  local f="$1"
  local base
  base=$(basename "$f" .txt)
  # Simulate work: count words and append a timestamp
  local wc
  wc=$(wc -w < "$f")
  echo "[$base] words=$wc processed=$(date +%T)" >> "/tmp/proc_demo/${base}.result"
}
export -f process_file

find /tmp/proc_demo -name '*.txt' -print0 \
  | xargs -0 -n 1 -P "$(nproc)" bash -c 'process_file "$@"' _

grep '' /tmp/proc_demo/*.result
rm -rf /tmp/proc_demo

#!/usr/bin/env bash
work() { sleep 0.2; }   # simulate a 200ms task
export -f work

ITEMS=$(seq 1 16)

echo "=== Sequential ==="
time printf '%s\n' $ITEMS | xargs -n 1 bash -c 'work' _

echo
echo "=== Parallel ($(nproc) workers) ==="
time printf '%s\n' $ITEMS | xargs -n 1 -P "$(nproc)" bash -c 'work' _