看到邮箱里 HostSlick 通知要对黑五的 1T 的机器 I/O 进行紧急升级，
我这边的机器在今早 4-5点左右下线了40分钟，现在的情况感觉比之前更卡了，你们的目前都还好吗？
dear customer,
to increase the quality of the HostNode I/O again we need to perform a urgent upgrade.
This will take place in the next hours. Our datacenter did not give us a fixed time schedule as we told them to please do it ASAP!
We except a downtime of arround 20minute on all 1TB Storage Black-Friday deals because of high load (everyone migrating data to us).
So we need to make this HostNode upgrade ASAP.
thank you for understanding.
- root@hostslick :~# dd if=/dev/zero of=test_$$ bs=64k count=16k conv=fdatasync && rm -f test_$$
- 16384+0 records in
- 16384+0 records out
- 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 321.17 s, 3.3 MB/s
- fio Disk Speed Tests (Mixed R/W 50/50) (Partition /dev/vda2):
- ---------------------------------
- Block Size | 4k (IOPS) | 64k (IOPS)
- ------ | --- ---- | ---- ----
- Read | 725.00 KB/s (181) | 7.89 MB/s (123)
- Write | 758.00 KB/s (189) | 8.26 MB/s (129)
- Total | 1.48 MB/s (370) | 16.16 MB/s (252)
- | |
- Block Size | 512k (IOPS) | 1m (IOPS)
- ------ | --- ---- | ---- ----
- Read | 20.87 MB/s (40) | 28.97 MB/s (28)
- Write | 22.45 MB/s (43) | 31.70 MB/s (30)
- Total | 43.33 MB/s (83) | 60.67 MB/s (58)
- fio --name=test --ioengine=sync --iodepth=1 --rw=randwrite --bs=4k --size=1G --numjobs=1 --time_based --runtime=5m --ramp_time=5s
- test: (g=0): rw=randwrite, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=sync, iodepth=1
- fio-3.33
- Starting 1 process
- test: Laying out IO file (1 file / 1024MiB)
- Jobs: 1 (f=1): [w(1)][100.0%][w=380KiB/s][w=95 IOPS][eta 00m:00s]
- test: (groupid=0, jobs=1): err= 0: pid=288485: Sun Dec 3 07:05:19 2023
- write: IOPS=213, BW=854KiB/s (874kB/s)(250MiB/300133msec); 0 zone resets
- clat (nsec): min=1994, max=987350k, avg=4683257.68, stdev=28051716.26
- lat (usec): min=2, max=987350, avg=4683.36, stdev=28051.73
- clat percentiles (usec):
- | 1.00th=[ 3], 5.00th=[ 3], 10.00th=[ 3], 20.00th=[ 3],
- | 30.00th=[ 3], 40.00th=[ 3], 50.00th=[ 4], 60.00th=[ 4],
- | 70.00th=[ 4], 80.00th=[ 5], 90.00th=[ 8], 95.00th=[ 31],
- | 99.00th=[204473], 99.50th=[204473], 99.90th=[208667], 99.95th=[208667],
- | 99.99th=[304088]
- bw ( KiB/s): min= 8, max=98560, per=100.00%, avg=857.42, stdev=4097.02, samples=598
- iops : min= 2, max=24640, avg=214.32, stdev=1024.25, samples=598
- lat (usec) : 2=0.01%, 4=71.98%, 10=19.29%, 20=2.05%, 50=2.89%
- lat (usec) : 100=0.26%, 250=0.01%
- lat (msec) : 10=0.01%, 20=0.02%, 50=0.40%, 100=1.17%, 250=1.91%
- lat (msec) : 500=0.01%, 750=0.01%, 1000=0.01%
- cpu : usr=0.03%, sys=0.12%, ctx=2273, majf=0, minf=37
- 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=0,64072,0,0 short=0,0,0,0 dropped=0,0,0,0
- latency : target=0, window=0, percentile=100.00%, depth=1
- Run status group 0 (all jobs):
- WRITE: bw=854KiB/s (874kB/s), 854KiB/s-854KiB/s (874kB/s-874kB/s), io=250MiB (262MB), run=300133-300133msec
- Disk stats (read/write):
- vda: ios=15847/15564, merge=64/729, ticks=2624865/1241903, in_queue=3869497, util=95.46%
|
发表于 2023-12-3 15:11:31
楼主
