Linux IO性能分析blktrace/blk跟踪器

关键词：blktrace、blk tracer、blkparse、block traceevents、BIO。

本章只做一个记录，关于优化Block层IO性能方法工具。

对Block层没有详细分析，对工作的使用和结果分析也没有展开。

如果有合适的机会补充。

1. blktrace介绍

如下图可知整个Block I/O框架可以分为三层：VFS、Block和I/O设备驱动。

Linux内核中提供了跟踪Block层操作的手段，可以通过blk跟踪器、或者使用blktrace/blkparse/btt工具抓取分析、或者使用block相关trace events记录。

 

2. blk跟踪器分析

blk跟踪器作为Linux ftrace的一个跟踪器，主要跟踪Linux Block层相关操作。

2.1 使用blk跟踪器

执行脚本sh blk_tracer.sh 4k 512 fsync，抓取相关case。

#!/bin/bash

echo $1 $2 $3

#Prepare for the test
echo 1 > /sys/block/mmcblk0/trace/enable
echo 0 > /sys/kernel/debug/tracing/tracing_on
echo 0 > /sys/kernel/debug/tracing/events/enable

echo 10000 > /sys/kernel/debug/tracing/buffer_size_kb
echo blk > /sys/kernel/debug/tracing/current_tracer

echo 1 > /sys/kernel/debug/tracing/tracing_on

#Run the test case
if [ $3 = 'fsync' ]; then
dd bs=$1 count=$2 if=/dev/zero of=out_empty conv=fsync
else
dd bs=$1 count=$2 if=/dev/zero of=out_empty
fi

#Capture the test log
echo 0 > /sys/kernel/debug/tracing/tracing_on
echo 0 > /sys/block/mmcblk0/trace/enable
cat /sys/kernel/debug/tracing/trace > test_$1_$2_$3.txt
echo nop > /sys/kernel/debug/tracing/current_tracer
echo > /sys/kernel/debug/tracing/trace

 

2.2 注册blk跟踪器

首先register_tracer向ftrace注册blk跟踪器，然后打印核心函数是blk_tracer_print_line。

static int __init init_blk_tracer(void)
{
...
    if (register_tracer(&blk_tracer) != 0) {
        pr_warning("Warning: could not register the block tracer\n");
        unregister_ftrace_event(&trace_blk_event);
        return 1;
    }

    return 0;
}

static struct tracer blk_tracer __read_mostly = {
    .name        = "blk",
    .init        = blk_tracer_init,
    .reset        = blk_tracer_reset,
    .start        = blk_tracer_start,
    .stop        = blk_tracer_stop,
    .print_header    = blk_tracer_print_header,
    .print_line    = blk_tracer_print_line,
    .flags        = &blk_tracer_flags,
    .set_flag    = blk_tracer_set_flag,
};

static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
{
    if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
        return TRACE_TYPE_UNHANDLED;

    return print_one_line(iter, true);
}

 

print_one_line是打印的核心，这里最主要是根据当前struct blk_io_trace->action选择合适的打印函数。

 

static enum print_line_t print_one_line(struct trace_iterator *iter,
                    bool classic)
{
    struct trace_seq *s = &iter->seq;
    const struct blk_io_trace *t;
    u16 what;
    int ret;
    bool long_act;
    blk_log_action_t *log_action;

    t       = te_blk_io_trace(iter->ent);
    what       = t->action & ((1 << BLK_TC_SHIFT) - 1);-------------------------------what表示是什么操作类型？
    long_act   = !!(trace_flags & TRACE_ITER_VERBOSE);
    log_action = classic ? &blk_log_action_classic : &blk_log_action;

    if (t->action == BLK_TN_MESSAGE) {
        ret = log_action(iter, long_act ? "message" : "m");
        if (ret)
            ret = blk_log_msg(s, iter->ent);
        goto out;
    }

    if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))---------------------------what为0表示未知操作类型
        ret = trace_seq_printf(s, "Unknown action %x\n", what);
    else {
        ret = log_action(iter, what2act[what].act[long_act]);--------------------------首先调用blk_long_action_classic或者blk_long_action打印
        if (ret)
            ret = what2act[what].print(s, iter->ent);----------------------------------然后在调用具体action对应的但因函数打印细节。
    }
out:
    return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
}

static const struct {
    const char *act[2];
    int       (*print)(struct trace_seq *s, const struct trace_entry *ent);
} what2act[] = {
    [__BLK_TA_QUEUE]    = {{  "Q", "queue" },       blk_log_generic },
    [__BLK_TA_BACKMERGE]    = {{  "M", "backmerge" },  blk_log_generic },
    [__BLK_TA_FRONTMERGE]    = {{  "F", "frontmerge" }, blk_log_generic },
    [__BLK_TA_GETRQ]    = {{  "G", "getrq" },       blk_log_generic },
    [__BLK_TA_SLEEPRQ]    = {{  "S", "sleeprq" },       blk_log_generic },
    [__BLK_TA_REQUEUE]    = {{  "R", "requeue" },       blk_log_with_error },
    [__BLK_TA_ISSUE]    = {{  "D", "issue" },       blk_log_generic },
    [__BLK_TA_COMPLETE]    = {{  "C", "complete" },   blk_log_with_error },
    [__BLK_TA_PLUG]        = {{  "P", "plug" },       blk_log_plug },
    [__BLK_TA_UNPLUG_IO]    = {{  "U", "unplug_io" },  blk_log_unplug },
    [__BLK_TA_UNPLUG_TIMER]    = {{ "UT", "unplug_timer" }, blk_log_unplug },
    [__BLK_TA_INSERT]    = {{  "I", "insert" },       blk_log_generic },
    [__BLK_TA_SPLIT]    = {{  "X", "split" },       blk_log_split },
    [__BLK_TA_BOUNCE]    = {{  "B", "bounce" },       blk_log_generic },
    [__BLK_TA_REMAP]    = {{  "A", "remap" },       blk_log_remap },
}

 

从fill_rwbs()可知，RWBS之类的字符表示读写类型，W-BLK_TC_WRITE、S-BLK_TC_SYNC、R-BLK_TC_READ、N-BLK_TN_MESSAGE等等。

结合what2act可知当前当前打印的确切含义，结合打印函数，可知其大概含义。

              dd-844   [000] ....  1540.751312: 179,0    Q  WS 32800 + 1 [dd]---------------Q-queue操作，WS-写同步，blk_log_generic打印-磁盘偏移量+写sector数目 [进程名]
              dd-844   [000] ....  1540.751312: 179,0    G  WS 32800 + 1 [dd]---------------G-getrq操作
              dd-844   [000] ....  1540.751312: 179,0    I  WS 32800 + 1 [dd]
              dd-844   [000] ....  1540.753937: 179,0    P   N [dd]-------------------------P-plug操作，N-BLK_TN_MESSAGE
              dd-844   [000] ....  1540.753937: 179,0    A  WS 18079 + 1 <- (179,1) 18047
              dd-844   [000] ....  1540.753937: 179,0    Q  WS 18079 + 1 [dd]
              dd-844   [000] ....  1540.753967: 179,0    G  WS 18079 + 1 [dd]
              dd-844   [000] ....  1540.753967: 179,0    I  WS 2863 + 1 [dd]
              dd-844   [000] ....  1540.753967: 179,0    I  WS 18079 + 1 [dd]
              dd-844   [000] ....  1540.753967: 179,0    U   N [dd] 2------------------------U-unplug_io操作，
         mmcqd/0-673   [000] ....  1540.753967: 179,0    D  WS 2863 + 1 [mmcqd/0]
         mmcqd/0-673   [000] ....  1540.753998: 179,0    D  WS 18079 + 1 [mmcqd/0]
         mmcqd/0-673   [000] ....  1540.757690: 179,0    C  WS 2863 + 1 [0]
         mmcqd/0-673   [000] ....  1540.760681: 179,0    C  WS 18079 + 1 [0]
              dd-844   [000] ....  1540.760742: 179,0    A   R 2864 + 1 <- (179,1) 2832------A-remap操作，读取偏移量+读取sect数 <-源设备主从设备号 源设备偏移量

 

 

 

3.blktrace使用及原理

blktrace是针对Linux内核中Block I/O的跟踪工具，属于内核Block Layer。

通过这个工具可以获得I/O请求队列的详细情况，包括读写进程名、进程号、执行时间、读写物理块号、块大小等等。

 PS：代码是LInux 3.4.110，但是试验在Ubuntu Kernel 4.4.0-31进行。

3.1 blktrace的使用

安装blktrace

sudo apt-get install blktrace

blktrace用于抓取Block I/O相关的log，blkparse用于分析blktrace抓取的二进制log。通过btt也可以用blktrace抓取的二进制log。

sudo blktrace -d /dev/sda6 -o - | blkparse -i -

或者分开使用

sudo blktrace -d /dev/sda6 -o sda6 #生成sda6.blktrace.x文件

blkparse -i sda6.blktrace.* -o sda6.txt

btt -i sda6.blktrace.*

 

 

 

3.2 blktrace原理

1. blktrace在运行的时候会在/sys/kernel/debug/block下面设备名称对应的目录，并生成四个文件droppeed/msg/trace0/trace2。

2. blktrace通过ioctl对内核进行设置，从而抓取log。

3. blktrace针对系统每个CPU绑定一个线程来收集相应数据。

3.2.1 Block设备blktrace相关节点

使用strace跟中blktrace执行流程可以看出：打开/dev/sda6设备，然后通过ioctl发送BLKTRACESETUP和BLKTRACESTART。

open("/dev/sda6", O_RDONLY|O_NONBLOCK)  = 3
statfs("/sys/kernel/debug", {f_type=0x64626720, f_bsize=4096, f_blocks=0, f_bfree=0, f_bavail=0, f_files=0, f_ffree=0, f_fsid={0, 0}, f_namelen=255, f_frsize=4096}) = 0...
ioctl(3, BLKTRACESETUP, {act_mask=65535, buf_size=524288, buf_nr=4, start_lba=0, end_lba=0, pid=0}, {name="sda6"}) = 0...
ioctl(3, BLKTRACESTART, 0x608c20)       = 0

 

下面通过走查代码简单分析流程。

add_disk()
  ->blk_register_queue()
    ->blk_trace_init_sysfs()
      ->blk_trace_attr_group
        ->blk_trace_attrs

 

如果定义了CONFIG_BLK_DEV_IO_TRACE，会在/sys/block/sda/sda6下创建一个trace目录。执行blktrace可以打开enable。

3.2.2 Block设备ioctl相关命令

ioctl通过/dev/sda6设置进去，可以看一下ioctl代码流程。

def_blk_fops
  ->unlocked_ioctl    = block_ioctl
    ->blkdev_ioctl
      ->BLKTRACESTART/BLKTRACESTOP/BLKTRACESETUPBLKTRACETEARDOWN
        ->blk_trace_ioctl

 

blk_trace_ioctl处理BLKTRACESETUP/BLKTRACESTART/BLKTRACESTOP/BLKTRACETEARDOWN四种情况，分别表示配置、开始、停止、释放资源。

int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
{
    struct request_queue *q;
    int ret, start = 0;
    char b[BDEVNAME_SIZE];

    q = bdev_get_queue(bdev);
    if (!q)
        return -ENXIO;

    mutex_lock(&bdev->bd_mutex);

    switch (cmd) {
    case BLKTRACESETUP:
        bdevname(bdev, b);
        ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
        break;
#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
    case BLKTRACESETUP32:
        bdevname(bdev, b);
        ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
        break;
#endif
    case BLKTRACESTART:
        start = 1;
    case BLKTRACESTOP:
        ret = blk_trace_startstop(q, start);
        break;
    case BLKTRACETEARDOWN:
        ret = blk_trace_remove(q);
        break;
    default:
        ret = -ENOTTY;
        break;
    }

    mutex_unlock(&bdev->bd_mutex);
    return ret;
}

 

 

int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
            struct block_device *bdev,
            char __user *arg)
{
    struct blk_user_trace_setup buts;
    int ret;

    ret = copy_from_user(&buts, arg, sizeof(buts));
    if (ret)
        return -EFAULT;

    ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
    if (ret)
        return ret;

    if (copy_to_user(arg, &buts, sizeof(buts))) {
        blk_trace_remove(q);
        return -EFAULT;
    }
    return 0;
}

int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
               struct block_device *bdev,
               struct blk_user_trace_setup *buts)
{
    struct blk_trace *old_bt, *bt = NULL;
    struct dentry *dir = NULL;
    int ret, i;
...
    bt = kzalloc(sizeof(*bt), GFP_KERNEL);
    if (!bt)
        return -ENOMEM;

    ret = -ENOMEM;
    bt->sequence = alloc_percpu(unsigned long);
    if (!bt->sequence)
        goto err;

    bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
    if (!bt->msg_data)
        goto err;

    ret = -ENOENT;

    mutex_lock(&blk_tree_mutex);
    if (!blk_tree_root) {
        blk_tree_root = debugfs_create_dir("block", NULL);-------------------创建/sys/kernel/debug/block目录
        if (!blk_tree_root) {
            mutex_unlock(&blk_tree_mutex);
            goto err;
        }
    }
    mutex_unlock(&blk_tree_mutex);

    dir = debugfs_create_dir(buts->name, blk_tree_root);---------------------在/sys/kernel/debug/block目录下创建设备名称对应目录

    if (!dir)
        goto err;

    bt->dir = dir;
    bt->dev = dev;
    atomic_set(&bt->dropped, 0);

    ret = -EIO;
    bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
                           &blk_dropped_fops);--------------------------------在/sys/kernel/debug/block/sda6下创建dropped节点
    if (!bt->dropped_file)
        goto err;

    bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
    if (!bt->msg_file)
        goto err;

    bt->rchan = relay_open("trace", dir, buts->buf_size,
                buts->buf_nr, &blk_relay_callbacks, bt);----------------------为每个CPU创建/sys/kernel/debug/block/sda6/tracex对应额relay channel
...
    if (atomic_inc_return(&blk_probes_ref) == 1)
        blk_register_tracepoints();-------------------------------------------注册和/sys/kernel/debug/tracing/events/block下同样的trace events。

    return 0;
err:
    blk_trace_free(bt);
    return ret;
}

 

blk_trace_startstop执行blktrace的开关操作，停止过后将per cpu的relay chanel强制flush出来。

int blk_trace_startstop(struct request_queue *q, int start)
{
    int ret;
    struct blk_trace *bt = q->blk_trace;
...
    ret = -EINVAL;
    if (start) {
        if (bt->trace_state == Blktrace_setup ||
            bt->trace_state == Blktrace_stopped) {
            blktrace_seq++;
            smp_mb();
            bt->trace_state = Blktrace_running;

            trace_note_time(bt);
            ret = 0;
        }
    } else {
        if (bt->trace_state == Blktrace_running) {
            bt->trace_state = Blktrace_stopped;
            relay_flush(bt->rchan);
            ret = 0;
        }
    }

    return ret;
}

 

释放blktrace设置创建的buffer、删除相关文件节点，并去注册trace events。

int blk_trace_remove(struct request_queue *q)
{
    struct blk_trace *bt;

    bt = xchg(&q->blk_trace, NULL);
    if (!bt)
        return -EINVAL;

    if (bt->trace_state != Blktrace_running)
        blk_trace_cleanup(bt);

    return 0;
}

static void blk_trace_cleanup(struct blk_trace *bt)
{
    blk_trace_free(bt);
    if (atomic_dec_and_test(&blk_probes_ref))
        blk_unregister_tracepoints();
}

 

 

这里的print_one_line和blk跟踪器的打印稍有不同，此处调用blk_log_action打印公共部分信息。

static int __init init_blk_tracer(void)
{
    if (!register_ftrace_event(&trace_blk_event)) {
        pr_warning("Warning: could not register block events\n");
        return 1;
    }

...
}

static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
                           int flags, struct trace_event *event)
{
    return print_one_line(iter, false);
}

 

blk跟踪器使用blk_log_action_classic()打印，两者区别在于blk跟踪器

static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
{
    char rwbs[RWBS_LEN];
    unsigned long long ts  = iter->ts;
    unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
    unsigned secs           = (unsigned long)ts;
    const struct blk_io_trace *t = te_blk_io_trace(iter->ent);

    fill_rwbs(rwbs, t);

    return trace_seq_printf(&iter->seq,
                "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ",
                MAJOR(t->device), MINOR(t->device), iter->cpu,
                secs, nsec_rem, iter->ent->pid, act, rwbs);
}

static int blk_log_action(struct trace_iterator *iter, const char *act)
{
    char rwbs[RWBS_LEN];
    const struct blk_io_trace *t = te_blk_io_trace(iter->ent);

    fill_rwbs(rwbs, t);
    return trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
                MAJOR(t->device), MINOR(t->device), act, rwbs);
}

  

 

3.3 blkparse结果分析

使用blkparse分析blktrace后，得出的结果和blk跟踪器大概类似。

可见实验结果多了第2列CPU序号，和第4列执行的时间戳。

  8,6    1        1     0.000000000   173  P   N [jbd2/sda1-8]
  8,6    1        2     0.000011134   173  U   N [jbd2/sda1-8] 1
  8,0    1        3     4.000017080   570  A  WS 528813240 + 8 <- (8,6) 440921272
  8,6    1        4     4.000018315   570  Q  WS 528813240 + 8 [jbd2/sda6-8]
  8,6    1        5     4.000024476   570  G  WS 528813240 + 8 [jbd2/sda6-8]
  8,6    1        6     4.000025282   570  P   N [jbd2/sda6-8]
  8,0    1        7     4.000026610   570  A  WS 528813248 + 8 <- (8,6) 440921280
  8,6    1        8     4.000026935   570  Q  WS 528813248 + 8 [jbd2/sda6-8]
  8,6    1        9     4.000028253   570  M  WS 528813248 + 8 [jbd2/sda6-8]
  8,0    1       10     4.000028895   570  A  WS 528813256 + 8 <- (8,6) 440921288
  8,6    1       11     4.000029180   570  Q  WS 528813256 + 8 [jbd2/sda6-8]
  8,6    1       12     4.000029585   570  M  WS 528813256 + 8 [jbd2/sda6-8]
  8,0    1       13     4.000030182   570  A  WS 528813264 + 8 <- (8,6) 440921296
  8,6    1       14     4.000030463   570  Q  WS 528813264 + 8 [jbd2/sda6-8]
  8,6    1       15     4.000030845   570  M  WS 528813264 + 8 [jbd2/sda6-8]
  8,0    1       16     4.000031406   570  A  WS 528813272 + 8 <- (8,6) 440921304
  8,6    1       17     4.000031687   570  Q  WS 528813272 + 8 [jbd2/sda6-8]
  8,6    1       18     4.000032066   570  M  WS 528813272 + 8 [jbd2/sda6-8]
...
CPU0 (sda6):
 Reads Queued:        2375,    16816KiB     Writes Queued:         909,     4648KiB
 Read Dispatches:     2329,    16632KiB     Write Dispatches:      310,     3876KiB
 Reads Requeued:         0         Writes Requeued:        15
 Reads Completed:       23,      132KiB     Writes Completed:        0,        0KiB
 Read Merges:           27,      108KiB     Write Merges:          489,     1960KiB
 Read depth:            32             Write depth:            31
 IO unplugs:           379             Timer unplugs:           0
CPU1 (sda6):
 Reads Queued:        2737,    12724KiB     Writes Queued:        1152,     5080KiB
 Read Dispatches:     2755,    12908KiB     Write Dispatches:      759,     5852KiB
 Reads Requeued:         0         Writes Requeued:       249
 Reads Completed:     5061,    29408KiB     Writes Completed:      945,     9728KiB
 Read Merges:            0,        0KiB     Write Merges:          759,     3044KiB
 Read depth:            32             Write depth:            31
 IO unplugs:           212             Timer unplugs:           1

Total (sda6):
 Reads Queued:        5112,    29540KiB     Writes Queued:        2061,     9728KiB
 Read Dispatches:     5084,    29540KiB     Write Dispatches:     1069,     9728KiB
 Reads Requeued:         0         Writes Requeued:       264
 Reads Completed:     5084,    29540KiB     Writes Completed:      945,     9728KiB
 Read Merges:           27,      108KiB     Write Merges:         1248,     5004KiB
 IO unplugs:           591             Timer unplugs:           1

Throughput (R/W): 2KiB/s / 0KiB/s
Events (sda6): 41303 entries
Skips: 0 forward (0 -   0.0%)

 

 

 4. block的Traceevents

关于block Traceevents和blk跟踪器的关联，可以通过blk_register_tracepoints()和include/trace/events/block.h中定义的时间关联起来，两者是一一对应的。

block事件打印的信息多了一个字符串，可读性更强一点。比blk跟踪器和blktrace更容易了解含义。

在/sys/kernel/debug/tracing/events/block下，可以分别打开相关事件：

block_bio_backmerge
block_bio_bounce
block_bio_complete
block_bio_frontmerge
block_bio_queue
block_bio_remap
block_getrq
block_plug
block_rq_abort
block_rq_complete
block_rq_insert
block_rq_issue
block_rq_remap
block_rq_requeue
block_sleeprq
block_split
block_unplug

 

同时根据这些字符串，也容易找出内核中代码位置。

也只有明白了block层流程，以及这些关键事件的log，才能知道问题点在哪里？然后再去进行优化。

# tracer: nop
#
# entries-in-buffer/entries-written: 14856/14856   #P:1
#
#                              _-----=> irqs-off
#                             / _----=> need-resched
#                            | / _---=> hardirq/softirq
#                            || / _--=> preempt-depth
#                            ||| /     delay
#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
#              | |       |   ||||       |         |
              dd-955   [000] ....  3287.902618: block_bio_remap: 179,0 W 472280 + 16 <- (179,1) 472248
              dd-955   [000] ....  3287.902618: block_bio_queue: 179,0 W 472280 + 16 [dd]
              dd-955   [000] ....  3287.902649: block_getrq: 179,0 W 472280 + 16 [dd]
              dd-955   [000] ....  3287.902649: block_plug: [dd]
              dd-955   [000] d...  3287.902649: block_rq_insert: 179,0 W 0 () 472280 + 16 [dd]
              dd-955   [000] d...  3287.902679: block_unplug: [dd] 1
         mmcqd/0-673   [000] d...  3287.902679: block_rq_issue: 179,0 W 0 () 472280 + 16 [mmcqd/0]
         mmcqd/0-673   [000] d...  3287.907440: block_rq_complete: 179,0 W () 472280 + 16 [0]
              dd-955   [000] ....  3287.907501: block_bio_remap: 179,0 WS 32800 + 1 <- (179,1) 32768
              dd-955   [000] ....  3287.907501: block_bio_queue: 179,0 WS 32800 + 1 [dd]
              dd-955   [000] ....  3287.907501: block_getrq: 179,0 WS 32800 + 1 [dd]
              dd-955   [000] d...  3287.907501: block_rq_insert: 179,0 WS 0 () 32800 + 1 [dd]
         mmcqd/0-673   [000] d...  3287.907532: block_rq_issue: 179,0 WS 0 () 32800 + 1 [mmcqd/0]
         mmcqd/0-673   [000] d...  3287.921631: block_rq_complete: 179,0 WS () 32800 + 1 [0]
              dd-955   [000] ....  3287.921631: block_bio_remap: 179,0 WS 2794 + 1 <- (179,1) 2762
              dd-955   [000] ....  3287.921631: block_bio_queue: 179,0 WS 2794 + 1 [dd]
              dd-955   [000] ....  3287.921631: block_getrq: 179,0 WS 2794 + 1 [dd]
              dd-955   [000] ....  3287.921661: block_plug: [dd]
              dd-955   [000] ....  3287.921661: block_bio_remap: 179,0 WS 18010 + 1 <- (179,1) 17978
              dd-955   [000] ....  3287.921661: block_bio_queue: 179,0 WS 18010 + 1 [dd]
              dd-955   [000] ....  3287.921661: block_getrq: 179,0 WS 18010 + 1 [dd]
              dd-955   [000] ....  3287.921661: block_bio_remap: 179,0 WS 2792 + 1 <- (179,1) 2760
              dd-955   [000] ....  3287.921661: block_bio_queue: 179,0 WS 2792 + 1 [dd]
              dd-955   [000] ....  3287.921661: block_getrq: 179,0 WS 2792 + 1 [dd]
              dd-955   [000] ....  3287.921661: block_bio_remap: 179,0 WS 18008 + 1 <- (179,1) 17976
              dd-955   [000] ....  3287.921661: block_bio_queue: 179,0 WS 18008 + 1 [dd]
              dd-955   [000] ....  3287.921692: block_getrq: 179,0 WS 18008 + 1 [dd]
              dd-955   [000] ....  3287.921692: block_bio_remap: 179,0 WS 2797 + 1 <- (179,1) 2765
              dd-955   [000] ....  3287.921692: block_bio_queue: 179,0 WS 2797 + 1 [dd]
              dd-955   [000] ....  3287.921692: block_getrq: 179,0 WS 2797 + 1 [dd]
              dd-955   [000] ....  3287.921692: block_bio_remap: 179,0 WS 18013 + 1 <- (179,1) 17981
              dd-955   [000] ....  3287.921692: block_bio_queue: 179,0 WS 18013 + 1 [dd]

 

 

 

 

 5. 优化尝试

对文件系统性能的调优，主要通过两个目录下节点：/proc/sys/vm和/sys/block/sda/queue。

5.1 更改IO调度算法

echo cfq > /sys/block/sda/queue/scheduler

5.2 修改磁盘相关内核参数

/sys/block/sda/queue/scheduler

/sys/block/sda/queue/nr_requests 磁盘队列长度。默认只有 128 个队列,可以提高到 512 个.会更加占用内存,但能更加多的合并读写操作,速度变慢,但能读写更加多的量

/sys/block/sda/queue/iosched/antic_expire 等待时间 。读取附近产生的新请时等待多长时间

 

/sys/block/sda/queue/read_ahead_kb

这个参数对顺序读非常有用,意思是,一次提前读多少内容,无论实际需要多少.默认一次读 128kb 远小于要读的,设置大些对读大文件非常有用,可以有效的减少读 seek 的次数,这个参数可以使用 blockdev –setra 来设置,setra 设置的是多少个扇区,所以实际的字节是除以2,比如设置 512 ,实际是读 256 个字节.

 

/proc/sys/vm/dirty_ratio

  这个参数控制文件系统的文件系统写缓冲区的大小,单位是百分比,表示系统内存的百分比,表示当写缓冲使用到系统内存多少的时候,开始向磁盘写出数 据.增大之会使用更多系统内存用于磁盘写缓冲,也可以极大提高系统的写性能.但是,当你需要持续、恒定的写入场合时,应该降低其数值,一般启动上缺省是 10.下面是增大的方法： echo ’40’> 

 

/proc/sys/vm/dirty_background_ratio

这个参数控制文件系统的pdflush进程,在何时刷新磁盘.单位是百分比,表示系统内存的百分比,意思是当写缓冲使用到系统内存多少的时候, pdflush开始向磁盘写出数据.增大之会使用更多系统内存用于磁盘写缓冲,也可以极大提高系统的写性能.但是,当你需要持续、恒定的写入场合时,应该降低其数值,一般启动上缺省是 5.下面是增大的方法： echo ’20’ >

 

 /proc/sys/vm/dirty_writeback_centisecs

这个参数控制内核的脏数据刷新进程pdflush的运行间隔.单位是 1/100 秒.缺省数值是500,也就是 5 秒.如果你的系统是持续地写入动作,那么实际上还是降低这个数值比较好,这样可以把尖峰的写操作削平成多次写操作.设置方法如下： echo ‘200’ > /proc/sys/vm/dirty_writeback_centisecs 如果你的系统是短期地尖峰式的写操作,并且写入数据不大（几十M/次）且内存有比较多富裕,那么应该增大此数值： echo ‘1000’ > /proc/sys/vm/dirty_writeback_centisecs

 

/proc/sys/vm/dirty_expire_centisecs

这个参数声明Linux内核写缓冲区里面的数据多“旧”了之后,pdflush进程就开始考虑写到磁盘中去.单位是 1/100秒.缺省是 30000,也就是 30 秒的数据就算旧了,将会刷新磁盘.对于特别重载的写操作来说,这个值适当缩小也是好的,但也不能缩小太多,因为缩小太多也会导致IO提高太快.建议设置为 1500,也就是15秒算旧. echo ‘1500’ > /proc/sys/vm/dirty_expire_centisecs 当然,如果你的系统内存比较大,并且写入模式是间歇式的,并且每次写入的数据不大（比如几十M）,那么这个值还是大些的好.

 

参考文档

1. Linux IO Scheduler（Linux IO 调度器）

2. Linux文件系统性能优化 

3. Linux 性能优化之 IO 子系统