我可以使用文件来模拟 NVMe 设备吗?我不想使用 qemu,它在我的机器上真的很慢。
答案1
是的,可以,但您需要 NVME 目标支持。
- 确保您有内核模块:
nvme_loop
,nvmet
,nvme_fabrics
- 在文件上设置循环设备:
losetup /dev/loop0 /tmp/mynvmefile
- 获取NVME 目标 CLI,并确保您具有依赖项。
configshell-fb
是主要部门,并且没有正确声明setup.py
examples/loop.json
从 nvmetcli 编辑:device
将示例中的背景更改为/dev/loop0
(默认为/dev/nvme0n1
)。
- 设定目标:
sudo ./nvmetcli restore examples/loop-modified.json
- 内核日志应该只有一行:
nvmet: adding nsid 1 to subsystem testnqn
- 内核日志应该只有一行:
- 使用 nvme-cli 工具连接到目标:
nvme connect -t loop -n testnqn -q hostnqn
- 利润!
创建和连接后的 dmesg 输出示例
nvmet: adding nsid 1 to subsystem testnqn
nvmet: creating controller 1 for subsystem testnqn for NQN hostnqn.
nvme nvme0: creating 8 I/O queues.
nvmet: adding queue 1 to ctrl 1.
nvmet: adding queue 2 to ctrl 1.
nvmet: adding queue 3 to ctrl 1.
nvmet: adding queue 4 to ctrl 1.
nvmet: adding queue 5 to ctrl 1.
nvmet: adding queue 6 to ctrl 1.
nvmet: adding queue 7 to ctrl 1.
nvmet: adding queue 8 to ctrl 1.
nvme nvme0: new ctrl: "testnqn"
NVME 信息:
# nvme list
Node SN Model Namespace Usage Format FW Rev
---------------- -------------------- ---------------------------------------- --------- -------------------------- ---------------- --------
/dev/nvme0n1 191b474c759f6b80 Linux 1 134.22 MB / 134.22 MB 4 KiB + 0 B 4.14.0-r
fio 结果在这个假设备上运行(内存支持,而不是磁盘上的文件):
# fio --filename=/dev/nvme0n1 --rw=write --bs=4k --numjobs=1 \
--iodepth=1 --runtime=60 --time_based --group_reporting \
--name=journal-test
journal-test: (g=0): rw=write, bs=4K-4K/4K-4K/4K-4K, ioengine=psync, iodepth=1
fio-2.16
Starting 1 process
Jobs: 1 (f=1): [W(1)] [100.0% done] [0KB/951.4MB/0KB /s] [0/244K/0 iops] [eta 00m:00s]
journal-test: (groupid=0, jobs=1): err= 0: pid=13352: Thu Oct 19 13:26:18 2017
write: io=110476MB, bw=1840.5MB/s, iops=471152, runt= 60027msec
clat (usec): min=0, max=85222, avg= 1.78, stdev=190.60
lat (usec): min=0, max=85222, avg= 1.84, stdev=190.60
clat percentiles (usec):
| 1.00th=[ 0], 5.00th=[ 0], 10.00th=[ 1], 20.00th=[ 1],
| 30.00th=[ 1], 40.00th=[ 1], 50.00th=[ 1], 60.00th=[ 1],
| 70.00th=[ 1], 80.00th=[ 1], 90.00th=[ 2], 95.00th=[ 2],
| 99.00th=[ 2], 99.50th=[ 3], 99.90th=[ 9], 99.95th=[ 9],
| 99.99th=[ 21]
lat (usec) : 2=88.18%, 4=11.50%, 10=0.27%, 20=0.03%, 50=0.01%
lat (usec) : 100=0.01%, 250=0.01%, 500=0.01%, 750=0.01%
lat (msec) : 2=0.01%, 4=0.01%, 10=0.01%, 20=0.01%, 50=0.01%
lat (msec) : 100=0.01%
cpu : usr=26.90%, sys=39.40%, ctx=3488, majf=0, minf=11
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 : total=r=0/w=28281845/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
latency : target=0, window=0, percentile=100.00%, depth=1
Run status group 0 (all jobs):
WRITE: io=110476MB, aggrb=1840.5MB/s, minb=1840.5MB/s, maxb=1840.5MB/s, mint=60027msec, maxt=60027msec
Disk stats (read/write):
nvme0n1: ios=0/12044, merge=0/3027439, ticks=0/347358, in_queue=318011, util=46.10%