zfs on nvme: gnop breaks pool, zfs gets stuck

[Karli Sjöberg]

On Thu, 2016-04-28 at 07:48 +0200, Gerrit Kühn wrote:
> On Wed, 27 Apr 2016 15:14:36 +0100 Gary Palmer <gpalmer at freebsd.org>
> wrote
> about Re: zfs on nvme: gnop breaks pool, zfs gets stuck:
> 
> GP> vfs.zfs.min_auto_ashift
> GP> 
> GP> which lets you manage the ashift on a new pool without having to
> try
> GP> the gnop trick
> 
> I just tried this, and it appears to work fine:
> 
> ---
> root at storage:~ # sysctl vfs.zfs.min_auto_ashift
> vfs.zfs.min_auto_ashift: 12
> 
> root at storage:~ # zpool status
>   pool: data
>  state: ONLINE
>   scan: none requested
> config:
> 
> 	NAME            STATE     READ WRITE CKSUM
> 	data            ONLINE       0     0     0
> 	  raidz2-0      ONLINE       0     0     0
> 	    gpt/disk0   ONLINE       0     0     0
> 	    gpt/disk1   ONLINE       0     0     0
> 	    gpt/disk2   ONLINE       0     0     0
> 	    gpt/disk3   ONLINE       0     0     0
> 	    gpt/disk4   ONLINE       0     0     0
> 	    gpt/disk5   ONLINE       0     0     0
> 	    gpt/disk6   ONLINE       0     0     0
> 	    gpt/disk7   ONLINE       0     0     0
> 	    gpt/disk8   ONLINE       0     0     0
> 	    gpt/disk9   ONLINE       0     0     0
> 	    gpt/disk10  ONLINE       0     0     0
> 	    gpt/disk11  ONLINE       0     0     0
> 
> errors: No known data errors
> 
>   pool: flash
>  state: ONLINE
>   scan: none requested
> config:
> 
> 	NAME            STATE     READ WRITE CKSUM
> 	flash           ONLINE       0     0     0
> 	  raidz1-0      ONLINE       0     0     0
> 	    gpt/flash0  ONLINE       0     0     0
> 	    gpt/flash1  ONLINE       0     0     0
> 	    gpt/flash2  ONLINE       0     0     0
> 
> errors: No known data errors
> 
> root at storage:~ # zdb | grep ashift
>             ashift: 12
>             ashift: 12
> 
> root at storage:~ # zpool list
> NAME    SIZE  ALLOC   FREE  EXPANDSZ   FRAG    CAP  DEDUP  HEALTH  AL
> TROOT
> data     65T  1.88M  65.0T         -     0%     0%  1.00x  ONLINE  -
> flash  1.39T   800K  1.39T         -     0%     0%  1.00x  ONLINE  -
> 
> ---
> 
> 
> I still wonder why the gnop workaround went so terribly wrong. 

Again, because you need to tell zfs where the providers are:

# zpool import -d /dev/gpt flash

/K

> Anyway,
> thanks again for pointing out this new sysctl to me!
> 
> And for the record: this is what I get with a simple linear write
> test:
> 
> ---
> root at storage:~ # dd if=/dev/zero of=/flash/Z bs=1024k count=10000
> 10000+0 records in
> 10000+0 records out
> 10485760000 bytes transferred in 3.912829 secs (2679840997 bytes/sec)
> ---
> 
> 
> I guess I won't complain...
> 
> 
> cu
>   Gerrit
> _______________________________________________
> freebsd-fs at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-fs
> To unsubscribe, send any mail to "freebsd-fs-unsubscribe at freebsd.org"