铠侠 KIOXIA CD6 7.6T 企业级固态读写测试

原创文章，转载请注明出处
https://qiedd.com/

0. 简介

4 月份在闲鱼买的全新 CD6, 价格 2.1K, 该固态温度较高, 请注意散热

1. 测试环境

格式 ntfs

Disk /dev/nvme2n1：6.99 TiB，7681501126656 字节，15002931888 个扇区
磁盘型号：KCD61LUL7T68                            
单元：扇区 / 1 * 512 = 512 字节
扇区大小(逻辑/物理)：512 字节 / 4096 字节
I/O 大小(最小/最佳)：4096 字节 / 4096 字节
磁盘标签类型：gpt

2. 测试

Linux 下使用 FIO 进行测试

写入

seqwrite: (g=0): rw=write, bs=(R) 128KiB-128KiB, (W) 128KiB-128KiB, (T) 128KiB-128KiB, ioengine=psync, iodepth=32
...
fio-3.34
Starting 10 processes
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
seqwrite: Laying out IO file (1 file / 10240MiB)
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
Jobs: 10 (f=10): [W(10)][100.0%][w=2878MiB/s][w=23.0k IOPS][eta 00m:00s]
seqwrite: (groupid=0, jobs=10): err= 0: pid=2655: Mon Jul 17 15:52:58 2023
  write: IOPS=23.1k, BW=2882MiB/s (3022MB/s)(100GiB/35529msec); 0 zone resets
    clat (usec): min=49, max=2925, avg=432.86, stdev=30.83
     lat (usec): min=49, max=2926, avg=433.37, stdev=30.84
    clat percentiles (usec):
     |  1.00th=[  367],  5.00th=[  371], 10.00th=[  396], 20.00th=[  416],
     | 30.00th=[  424], 40.00th=[  433], 50.00th=[  437], 60.00th=[  441],
     | 70.00th=[  445], 80.00th=[  453], 90.00th=[  461], 95.00th=[  474],
     | 99.00th=[  498], 99.50th=[  502], 99.90th=[  562], 99.95th=[  627],
     | 99.99th=[  734]
   bw (  MiB/s): min= 2550, max= 3390, per=100.00%, avg=2883.29, stdev=16.45, samples=710
   iops        : min=20404, max=27122, avg=23066.34, stdev=131.57, samples=710
  lat (usec)   : 50=0.01%, 100=0.01%, 250=0.01%, 500=99.29%, 750=0.69%
  lat (usec)   : 1000=0.01%
  lat (msec)   : 2=0.01%, 4=0.01%
  cpu          : usr=0.26%, sys=0.83%, ctx=1638525, majf=0, minf=108
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwts: total=0,819200,0,0 short=0,0,0,0 dropped=0,0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=32

Run status group 0 (all jobs):
  WRITE: bw=2882MiB/s (3022MB/s), 2882MiB/s-2882MiB/s (3022MB/s-3022MB/s), io=100GiB (107GB), run=35529-35529msec

Disk stats (read/write):
  nvme2n1: ios=141/746154, merge=0/23113395, ticks=44/4458910, in_queue=4458955, util=68.74%

读取

seqread: (g=0): rw=read, bs=(R) 128KiB-128KiB, (W) 128KiB-128KiB, (T) 128KiB-128KiB, ioengine=psync, iodepth=32
...
fio-3.34
Starting 10 processes
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
seqread: Laying out IO file (1 file / 10240MiB)
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
note: both iodepth >= 1 and synchronous I/O engine are selected, queue depth will be capped at 1
Jobs: 10 (f=10): [R(10)][100.0%][r=8407MiB/s][r=67.3k IOPS][eta 00m:00s]
seqread: (groupid=0, jobs=10): err= 0: pid=2778: Mon Jul 17 15:58:56 2023
  read: IOPS=70.2k, BW=8778MiB/s (9204MB/s)(100GiB/11666msec)
    clat (usec): min=25, max=1317, avg=142.18, stdev= 9.45
     lat (usec): min=25, max=1318, avg=142.20, stdev= 9.45
    clat percentiles (usec):
     |  1.00th=[  130],  5.00th=[  131], 10.00th=[  133], 20.00th=[  139],
     | 30.00th=[  143], 40.00th=[  143], 50.00th=[  145], 60.00th=[  145],
     | 70.00th=[  145], 80.00th=[  145], 90.00th=[  147], 95.00th=[  149],
     | 99.00th=[  157], 99.50th=[  167], 99.90th=[  208], 99.95th=[  265],
     | 99.99th=[  478]
   bw (  MiB/s): min= 8176, max= 9517, per=100.00%, avg=8783.72, stdev=30.62, samples=230
   iops        : min=65412, max=76138, avg=70269.74, stdev=244.93, samples=230
  lat (usec)   : 50=0.01%, 100=0.01%, 250=99.94%, 500=0.05%, 750=0.01%
  lat (usec)   : 1000=0.01%
  lat (msec)   : 2=0.01%
  cpu          : usr=0.43%, sys=1.21%, ctx=819270, majf=0, minf=105
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwts: total=819200,0,0,0 short=0,0,0,0 dropped=0,0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=32

Run status group 0 (all jobs):
   READ: bw=8778MiB/s (9204MB/s), 8778MiB/s-8778MiB/s (9204MB/s-9204MB/s), io=100GiB (107GB), run=11666-11666msec

Disk stats (read/write):
  nvme2n1: ios=0/8, merge=0/3, ticks=0/1, in_queue=0, util=0.03%