Re: [PATCH] proto: add xNBD command NBD_CMD_CACHE to the spec
Hi,
On Mon, Apr 02, 2018 at 07:47:53AM +0000, 広渕崇宏 wrote:
> Hi,
>
> > +* `NBD_CMD_CACHE` (5)
> > +
> > + Cache request. Implies server to perform some action to speed-up
> > + further read requests to the area specified by *offset* and
> > + *length*. However, performance gain is not guaranteed and depends on
> > + server implementation.
>
> It may also speed up future write requests.
> It depends on how a server program supporting the NBD protocol is implemented.
> For xNBD, a future write request (not aligned to a block-size boundary) will get performance gain.
Okay, so make that "speed up further access to the area specified
by...". We also should make it implementation-defined whether this is a
write-through or a write-back cache, I think, and which algorithm and/or
protocol the server uses to realize that cache (e.g., it may be a proxy
for another disk access protocol).
> > + If an error occurs, the server MUST set the appropriate error code
> > + in the error field. However failure on this operation doesn't mean
> > + that further read requests on this area will fail.
> > +
> > + A client MUST NOT send a cache request unless `NBD_FLAG_SEND_CACHE`
> > + was set in the transmission flags field.
This presumably conflicts with xNBD, which does send out CMD_CACHE
without that flag (at least, the flag is not reserved, so...). However,
I do think that it's better to negotiate the cache command before trying
to use it, so I would just append the following to your proposed wording:
However, implementations already exist that do send out NBD_CMD_CACHE
without negotiating its use through NBD_FLAG_SEND_CACHE; therefore,
implementations desiring maximum portability should allow for this
possibility.
> When receiving an NBD_CMD_CACHE request, a xNBD server running in the
> proxy mode retrieves the disk blocks of the specified area from a
> remote NBD server and saves them in the local storage of the xNBD
> server. The reply message of NBD_CMD_CACHE does not have disk data in
> its payload.
Good point, thanks; we should add that too.
--
Could you people please use IRC like normal people?!?
-- Amaya Rodrigo Sastre, trying to quiet down the buzz in the DebConf 2008
Hacklab
Reply to: