Re: [Nbd] maximum size of a read/write request
- To: Paolo Bonzini <pbonzini@...696...>
- Cc: nbd-general@lists.sourceforge.net
- Subject: Re: [Nbd] maximum size of a read/write request
- From: Wouter Verhelst <w@...112...>
- Date: Mon, 10 Oct 2011 18:32:28 +0200
- Message-id: <20111010163228.GF4548@...3...>
- In-reply-to: <4E92ED86.10106@...696...>
- References: <CAFDOyVA=n4uBO9NyGeb6SP5fGc-zSkx81KBuMHskYW8qqf5R3Q@...18...> <4E9057E5.30806@...696...> <CAFDOyVCQ3ZnS+Y8pu8evLUCEtGN2dYEvr4_xC00R1WqF-U5Dew@...18...> <4E92ED86.10106@...696...>
On Mon, Oct 10, 2011 at 03:05:10PM +0200, Paolo Bonzini wrote:
> > That is too tricky: a new kernel version might show differnt
> > behaviour. Imho we should specify a limit or make it configurable or
> > put it in the protocol. We have 124 bytes of handshake left, we can
> > use 8 of them for a maximum blocksize.
>
> O_DIRECT bypasses everything clever that the kernel might do.
More to the point, O_DIRECT is _defined_ as "don't try to be clever
about this request, just do it". If a new kernel version were to show
different behaviour, that would be a bug in the kernel.
--
The volume of a pizza of thickness a and radius z can be described by
the following formula:
pi zz a
Reply to: