Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fio read pass but --debug=io occurs error when we inject uecc error #1829

Open
vera-ya opened this issue Oct 17, 2024 · 0 comments
Open

fio read pass but --debug=io occurs error when we inject uecc error #1829

vera-ya opened this issue Oct 17, 2024 · 0 comments

Comments

@vera-ya
Copy link

vera-ya commented Oct 17, 2024

Description of the bug:
we inject an uecc error in lba0.
so we just can not read lba0.nvme read will fail everytime.
when i use fio command "fio --name=test --size=10G --filename=/dev/nvme0n1 --rw=read --offset=0 --bs=128K --numjobs=1 --direct=1--ioengine=libaio --iodepth=256 --bs=128K --numjobs=1 --ba=4k" fio will report ioerror
fio: io_u error on file /dev/nvme0n1: Input/output error: read offset=0, buflen=131072
fio: first I/O failed. If /dev/nvme0n1 is a zoned block device, consider --zonemode=zbd
fio: pid=12737, err=5/file:io_u.c:1896, func=io_u error, error=Input/output error

but when I put these parameters in a fio file named read.fio.
fio will pass sometimes.
image
fio read.fio
Full_Drive_Read: (g=0): rw=read, bs=(R) 128KiB-128KiB, (W) 128KiB-128KiB, (T) 128KiB-128KiB, ioengine=libaio, iodepth=256
fio-3.36
Starting 1 process
Jobs: 1 (f=1)
Full_Drive_Read: (groupid=0, jobs=1): err= 0: pid=12854: Wed Oct 16 21:50:30 2024
read: IOPS=49.7k, BW=6214MiB/s (6515MB/s)(10.0GiB/1648msec)
slat (nsec): min=2405, max=59802, avg=4815.50, stdev=1896.31
clat (usec): min=1628, max=11003, avg=5128.46, stdev=515.06
lat (usec): min=1637, max=11007, avg=5133.28, stdev=515.08
clat percentiles (usec):
| 99.0000th=[ 6325], 99.9000th=[ 8848], 99.9900th=[10421],
| 99.9990th=[10945], 99.9999th=[10945]
bw ( MiB/s): min= 6182, max= 6241, per=100.00%, avg=6220.25, stdev=32.59, samples=3
iops : min=49462, max=49934, avg=49762.00, stdev=260.74, samples=3
lat (msec) : 2=0.16%, 4=0.38%, 10=99.43%, 20=0.02%
cpu : usr=4.37%, sys=33.27%, ctx=59651, majf=0, minf=8203
IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=99.9%
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=0.1%
issued rwts: total=81920,0,0,0 short=0,0,0,0 dropped=0,0,0,0
latency : target=0, window=0, percentile=100.00%, depth=256

Run status group 0 (all jobs):
READ: bw=6214MiB/s (6515MB/s), 6214MiB/s-6214MiB/s (6515MB/s-6515MB/s), io=10.0GiB (10.7GB), run=1648-1648msec

Disk stats (read/write):
nvme0n1: ios=69510/0, sectors=17794560/0, merge=0/0, ticks=354344/0, in_queue=275632, util=93.52%

and when i run "fio read.fio --debug=io" it will fail every time.
when i change fiofile bs=4K it will fail everytime.

Environment: Ubuntu 18.04 linux 5.4.0

fio version: 3.26/3.36
Reproduction steps
I dont know if u can inject a uecc error to a SSD. if u can do that, just inject an uecc error to a lba, and read it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant