[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [List Home]
Subject: Re: [virtio-dev] [PATCH v6 1/2] content: add virtio file system device
On Thu, Aug 22, 2019 at 01:23:45PM +0200, Cornelia Huck wrote: > On Tue, 13 Aug 2019 14:13:19 +0100 > Stefan Hajnoczi <stefanha@redhat.com> wrote: > > +\item[\field{num_queues}] is the total number of request virtqueues exposed by > > + the device. Each virtqueue offers identical functionality and there are no > > + ordering guarantees between requests made available on different queues. > > + Use of multiple queues is intended to increase performance. > > As this came up during review of the qemu implementation of the device: > num_queues is not the number of virtqueues of the device, but rather > the number of request queues -- which is clear from the description, > but not from the field name. Maybe rename this field to > num_request_queues or so? Sounds good. Will fix in the next revision. > > +\subsubsection{Device Operation: Request Queues}\label{sec:Device Types / File System Device / Device Operation / Device Operation: Request Queues} > > + > > +The driver enqueues normal requests on an arbitrary request queue. High > > +priority requests are not placed on request queues. The device processes > > +requests in any order. The driver is responsible for ensuring that ordering > > +constraints are met by making available a dependent request only after its > > +prerequisite request has been used. > > + > > +Requests have the following format with endianness chosen by the driver as > > "chosen by the driver in the FUSE_INIT request used to initiate the > session", maybe? You describe this below, but I think it would be > easier to understand if you mentioned it here already. Thanks, will fix in the next revision.
Attachment:
signature.asc
Description: PGP signature
[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [List Home]