使用 PHP 处理十亿行数据，如何极致提升处理速度？

<?php

$stations = [];

$fp = fopen('measurements.txt', 'r');

while ($data = fgetcsv($fp, null, ';')) {
    if (!isset($stations[$data[0]])) {
        $stations[$data[0]] = [
            $data[1],
            $data[1],
            $data[1],
            1
        ];
    } else {
        $stations[$data[0]][3]++;
        $stations[$data[0]][2] += $data[1];
        if ($data[1] < $stations[$data[0]][0]) {
            $stations[$data[0]][0] = $data[1];
        }
        if ($data[1] > $stations[$data[0]][1]) {
            $stations[$data[0]][1] = $data[1];
        }
    }
}

ksort($stations);

echo '{';
foreach ($stations as $k => &$station) {
    $station[2] = $station[2] / $station[3];
    echo $k, '=', $station[0], '/', $station[2], '/', $station[1], ', ';
}
echo '}';

// ...
while ($data = fgets($fp, 999)) {
    $pos = strpos($data, ';');
    $city = substr($data, 0, $pos);
    $temp = substr($data, $pos + 1, -1);
// ...

18 | $stations[$city][3]++;
   | // ...
23 | if ($temp > $stations[$city][1]) {

$station = &$stations[$city];
$station[3]++;
$station[2] += $temp;
// 替代原有的
$stations[$city][3]++;
$stations[$city][2] += $temp;

if ($temp < $station[0]) {
    $station[0] = $temp;
} elseif ($temp > $station[1]) {
    $station[1] = $temp;
}

$temp = (float)substr($data, $pos + 1, -1);

18 | $station = &$stations[$city];
   | // ...
23 | } elseif ($temp > $station[1]) {

while ($data = fgets($fp)) {
// 替代之前的
while ($data = fgets($fp, 999)) {

<?php

$file = 'measurements.txt';

$threads_cnt = 16;

/**
 * 计算并返回每个线程应处理的文件块的起始和结束位置。
 * 这些位置将基于 \n 字符进行对齐，因为我们使用 `fgets()` 进行读取，
 * 它会读取直到遇到 \n 字符为止。
 *
 * @return array<int, array{0: int, 1: int}>
 */
function get_file_chunks(string $file, int $cpu_count): array {
    $size = filesize($file);

    if ($cpu_count == 1) {
        $chunk_size = $size;
    } else {
        $chunk_size = (int) ($size / $cpu_count);
    }

    $fp = fopen($file, 'rb');

    $chunks = [];
    $chunk_start = 0;
    while ($chunk_start < $size) {
        $chunk_end = min($size, $chunk_start + $chunk_size);

        if ($chunk_end < $size) {
            fseek($fp, $chunk_end);
            fgets($fp); // 将文件指针移动到下一个 \n 字符
            $chunk_end = ftell($fp);
        }

        $chunks[] = [
            $chunk_start,
            $chunk_end
        ];

        $chunk_start = $chunk_end;
    }

    fclose($fp);
    return $chunks;
}

/**
 * 该函数负责打开指定的 `$file` 文件，并从 `$chunk_start` 开始读取处理数据，
 * 直到达到 `$chunk_end`。
 *
 * 返回的结果数组以城市名作为键，其值为一个数组，包含最低温度（键 0）、最高温度（键 1）、
 * 温度总和（键 2）及温度计数（键 3）。
 *
 * @return array<string, array{0: float, 1: float, 2: float, 3: int}>
 */
$process_chunk = function (string $file, int $chunk_start, int $chunk_end): array {
    $stations = [];
    $fp = fopen($file, 'rb');
    fseek($fp, $chunk_start);
    while ($data = fgets($fp)) {
        $chunk_start += strlen($data);
        if ($chunk_start > $chunk_end) {
            break;
        }
        $pos2 = strpos($data, ';');
        $city = substr($data, 0, $pos2);
        $temp = (float)substr($data, $pos2 + 1, -1);
        if (isset($stations[$city])) {
            $station = &$stations[$city];
            $station[3]++;
            $station[2] += $temp;
            if ($temp < $station[0]) {
                $station[0] = $temp;
            } elseif ($temp > $station[1]) {
                $station[1] = $temp;
            }
        } else {
            $stations[$city] = [
                $temp,
                $temp,
                $temp,
                1
            ];
        }
    }
    return $stations;
};

$chunks = get_file_chunks($file, $threads_cnt);

$futures = [];

for ($i = 0; $i < $threads_cnt; $i++) {
    $runtime = new \parallel\Runtime();
    $futures[$i] = $runtime->run(
        $process_chunk,
        [
            $file,
            $chunks[$i][0],
            $chunks[$i][1]
        ]
    );
}

$results = [];

for ($i = 0; $i < $threads_cnt; $i++) {
    // 等待线程结果，主线程在此处阻塞直至获取结果
    $chunk_result = $futures[$i]->value();
    foreach ($chunk_result as $city => $measurement) {
        if (isset($results[$city])) {
            $result = &$results[$city];
            $result[2] += $measurement[2];
            $result[3] += $measurement[3];
            if ($measurement[0] < $result[0]) {
                $result[0] = $measurement[0];
            }
            if ($measurement[1] > $result[1]) {
                $result[1] = $measurement[1];
            }
        } else {
            $results[$city] = $measurement;
        }
    }
}

ksort($results);

echo '{', PHP_EOL;
foreach ($results as $k => &$station) {
    echo "\t", $k, '=', $station[0], '/', ($station[2] / $station[3]), '/', $station[1], ',', PHP_EOL;
}
echo '}', PHP_EOL;