That is an interesting point. On the protocol level, the client opens a directory and then issues a QUERY_INFO to ask for the available space. In Samba, we then check the available space and applicable quotas on that path and return the requested information.
The main question is probably on which directory the client asks for the available space. That can be seen in a network or smb trace.
Regards,
Christof Schmitt || IBM || Spectrum Scale Development || Tucson, AZ
[email protected] || +1-520-799-2469 (T/L: 321-2469)
----- Original message -----
From: "Sobey, Richard A" <[email protected]>
Sent by: [email protected]
To: gpfsug main discussion list <[email protected]>
Cc:
Subject: Re: [gpfsug-discuss] SMB quotas query
Date: Mon, May 14, 2018 4:54 AM
Thanks Jonathan. What I failed to mention in my OP was that MacOS clients DO report the correct size of each mounted folder. Not sure how that changes anything except to reinforce the idea that it's Windows at fault.
Richard
-----Original Message-----
From: [email protected] <[email protected]> On Behalf Of Jonathan Buzzard
Sent: 14 May 2018 11:45
To: gpfsug main discussion list <[email protected]>
Subject: Re: [gpfsug-discuss] SMB quotas query
On Mon, 2018-05-14 at 10:09 +0000, Sobey, Richard A wrote:
[SNIP]
>
> I am worried that IBM may tell us we’re doing it wrong (humm) and to
> create individual exports for each fileset but this will quickly
> become tiresome!
>
Worst case scenario you could fall back to using the dfree option in smb.conf and then use a program to get the file quota. I have the ~100 lines of C that you need it. Though it has been ~5 years since I last used it.
In fact the whole reporting the fileset quota as the disk size is my idea, and the dfree config option is how I implemented it prior to IBM adding it to the vfs_gpfs module.
A quick check shows a commit from Jeremy Allison on June 18th last year to use const stuct smb_filename, the comment on the commit is
…instead of const char *.
We need to migrate all pathname based VFS calls to use a struct to finish modernising the VFS with extra timestamp and flags parameters.
I suspect this change has broken the behaviour.
JAB.
--
Jonathan A. Buzzard Tel: +44141-5483420 HPC System Administrator, ARCHIE-WeSt.
University of Strathclyde, John Anderson Building, Glasgow. G4 0NG
_______________________________________________
gpfsug-discuss mailing list
gpfsug-discuss at spectrumscale.org
http://gpfsug.org/mailman/listinfo/gpfsug-discuss
_______________________________________________
gpfsug-discuss mailing list
gpfsug-discuss at spectrumscale.org
http://gpfsug.org/mailman/listinfo/gpfsug-discuss
_______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at spectrumscale.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss
