Re: [PATCH 04/10] xen/blkfront: separate ring information to an new struct

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
To: Felipe Franciosi <felipe.franciosi@citrix.com>
Cc: "hch@infradead.org" <hch@infradead.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>,
	"axboe@fb.com" <axboe@fb.com>,
	David Vrabel <david.vrabel@citrix.com>,
	"avanzini.arianna@gmail.com" <avanzini.arianna@gmail.com>,
	Roger Pau Monne <roger.pau@citrix.com>
Subject: Re: [PATCH 04/10] xen/blkfront: separate ring information to an new struct
Date: Wed, 18 Feb 2015 13:29:23 -0500	[thread overview]
Message-ID: <20150218182923.GA12845__47057.7611857609$1424284323$gmane$org@l.oracle.com> (raw)
In-Reply-To: <9F2C4E7DFB7839489C89757A66C5AD629EB997@AMSPEX01CL03.citrite.net>

> > > AFAICT you seem to have a list of persistent grants, indirect pages
> > > and a grant table callback for each ring, isn't this supposed to be
> > > shared between all rings?
> > >
> > > I don't think we should be going down that route, or else we can hoard
> > > a large amount of memory and grants.
> > 
> > It does remove the lock that would have to be accessed by each ring thread to
> > access those. Those values (grants) can be limited to be a smaller value such
> > that the overall number is the same as it was with the previous version. As in:
> > each ring has = MAX_GRANTS / nr_online_cpus().
> > >
> 
> We should definitely be concerned with the amount of memory consumed on the backend for each plugged virtual disk. We have faced several problems in XenServer around this area before; it drastically affects VBD scalability per host.
> 
> This makes me think that all the persistent grants work was done as a workaround while we were facing several performance problems around concurrent grant un/mapping operations. Given all the recent submissions made around this (grant ops) area, is this something we should perhaps revisit and discuss whether we want to continue offering persistent grants as a feature?
> 

Certainly. Perhaps as a talking point at XenHackathon?

> Thanks,
> Felipe