I'm the author of the presentation. I'll bow to Tomer's knowledge about how the internals of Spectrum Scale (GPFS) work.
I've been working with GPFS since V1.3 so it was a bit of a shock to think I had a fundamental misunderstanding. In this case both viewpoints are actually equivalent because of the way Spectrum Scale works. Both ways of visualising what happens work in exactly the same way from a "user perspective". The 2 actions of allocating an NSD into a filesystem, and also allocating it into a storage pool occur as part of the same single atomic transaction. An NSD is either in both a filesystem and a storage pool, or it is in neither. You can visualise one part of the operation first- "allocate NSD into filesystem"- and then second part of the operation is"allocate into System storage pool within the filesystem" (Stephen's perspective). Or you can visualise the actions happening the other way around "allocate NSD into System storage pool within the cluster", then "allocate into filesystem" (Indulis' perspective). The output of mmdf always made me think of it in this way. Because the 2 transactions on the NSD- allocate to filesystem and allocate to storage pool- are atomic, and there is a 1:1 mapping in each operation, who cares? I can take the viewpoint that the NSD goes into a cluster-wide System pool, or someone else can take the view that there is a System pool per filesystem. There is no external way to distinguish which is right or wrong. The "visual and mental models" are different but it makes no nevermind in terms of how things work. Though now that I have had to think about it, it is simpler to visualise each filesystem having its own System pool, and the fact that Tomer says this is how it works internally is a good reason to change the visualisation as well :-D Regards, Indulis Bernsteins Systems Architect IBM New Generation Storage Unless stated otherwise above: IBM United Kingdom Limited - Registered in England and Wales with number 741598. Registered office: PO Box 41, North Harbour, Portsmouth, Hampshire PO6 3AU
_______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at spectrumscale.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss
