[Bug 212323] tests/sys/acl/01:main fails due to changes in NFSv4 ACL behavior on ^/head

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=212323

--- Comment #7 from Harald Schmalzbauer <bugzilla.freebsd at omnilan.de> ---
My ZFS setups suffer from an upstream ACL inheritance bug:
https://www.illumos.org/issues/9722 wich is referring
https://www.illumos.org/issues/8984
The latter is marked closed/solved but it is only partially solved, like the
newer issue describes.

I had to give up using samba for environments where NTFS ACLs are crucial.
I also gave up deploying new NFSv4 ACL setups.  All previous setups were
damaged by the mentioned ZFS inheritance bugs.
I remember many questions to be clarified regarding d and D flags (and in
respect to NTFS conventions also R and W and C), but lost almost all experience
results.

I can't tell anything about the test failure status!
I just can tell that I'm observing issues regading ACL/permission mappings.
Time for me to look into tests...


I'm really interested in polishing our ACL implementation, but I'm lacking a
good portion of standards knowledge (posix) and my lousy C skills require
someone else to fix the ZFS inheritance bug first.

Symlinks are one major issue to discuss regarding inheritance on ZFS – that
was/is another big problem in my setups.

I still have my private ACL setups (partially damaged), which is a collection
of special usage scenarios (e.g. users can add files and directories, but can't
delete anything, even not their own; or shared home directory, which suffers
from chmod(2) fallout due to the ACL).

So it's my pleasure to test any changes and put some light in uncommon but
usefuls corner cases ;-)
And I'm willing to do my best to catch up with posix knowledge, but
unfortunately I can't afford spending much time :-(
My personal estimation was that some very skilled persons would need at least a
week to decide/implement and test a new/improved ACL mapping mode.
My needs aren't covered by the current ACL/permission mappings – not for NFSv4
only environments and additional CIFS/NTFS bridges were mutual destructive.

Thanks,

-harry

-- 
You are receiving this mail because:
You are the assignee for the bug.