Closed theverytak closed 6 years ago
Hi HyeongTak,
Have you initialized pblk on top, before running the fio workload?
You may also want to switch to the latest qemu (https://github.com/OpenChannelSSD/qemu-nvme) and use something like the following for the device parameters.
-device nvme,drive=mynvme,serial=deadbeef,lnum_pu=4,lstrict=1,meta=0,mc=0,lsecs_per_chk=4096,lws_min=4,lws_opt=8
If you do want to run raw fio on top of the drive, you should make sure to use the for-4.19/zoned kernel branch, and couple it with Bart's fio.
https://github.com/bvanassche/fio
Make sure to install the latest libzbc (https://github.com/hgst/libzbc) as well. You can take a look at t/zbc/ scripts to see how to make the fio scripts.
I was to use qemu-nvme version1.2 for some reasons, but now it seems like I need to use 2.0. Thank you for your kind reply!
Hello nvme developers,
I am trying to make a custom kernel to do some experiments over ocssd. But before that, I wanted to get some benchmark result on the current kernel that I was using in qemu-nvme(kernel version 4.16)
However, whenever I tried to run fio or ezfio on my qemu-nvme, on host Ubuntu(17.10), this message comes out and halts,
double free or corruption ( !prev) Aborted (core dumped)
This is my option for qemu :
-drive file=blknvme,if=none,id=mydevice -device nvme,drive=mydevice,serial=deadbeef,namespaces=1,lver=1,lmetasize=16,ll2pmode=0,nlbaf=5,lba_index=3,mdts=10,lnum_lun=4,lnum_pln=2,lsec_size=4096,lsecs_per_pg=4,lpgs_per_blk=512,lbbtable=bbtable.qemu,lmetadata=meta.qemu,ldebug=1
Thank you, HyeongTak Ji