On Fri, Dec 17, 2010 at 1:37 AM, Benny Halevy <bhalevy@xxxxxxxxxxx> wrote: > On 2010-12-16 19:21, Peng Tao wrote: >> Hi, Benny, >> >> On Thu, Dec 16, 2010 at 3:26 PM, Benny Halevy <bhalevy@xxxxxxxxxxx> wrote: >>> On 2010-12-15 22:24, Trond Myklebust wrote: >>>> On Wed, 2010-12-15 at 14:31 -0500, Trond Myklebust wrote: >>>>> On Wed, 2010-12-15 at 20:51 +0200, Benny Halevy wrote: >>>> >>>>>> Eventually, when CB_LAYOUTRECALL is clear to go sending the LAYOUTRETURN >>>>>> or replying with CB_NOMATCHING_LAYOUT (assuming no I/O error to report >>>>>> for pnfs-obj) should be equivalent [note: need errata to clarify the >>>>>> resulting stateid after NOMATCHING_LAYOUT]. >>>>>> Is this the serialization "crap" you're talking about? >>>>>> What makes checking the conditions for returning NFS4ERR_DELAY to >>>>>> CB_LAYOUTRECALL so different from implementing a barrier and doing the >>>>>> returns asynchronously with the CB_LAYOUTRECALL? >>>>> >>>>> "CB_LAYOUTRECALL request processing MUST be processed in "seqid" order >>>>> at all times." (section 12.5.3). >>>>> >>>>> In other words, you cannot just 'do the returns asynchronously': the >>>>> CB_LAYOUTRECALL requests are required by the protocol to be processed in >>>>> order, which means that you must serialise those LAYOUTRETURN calls to >>>>> ensure that they all happen in the order the wretched server expects. >>>> >>>> BTW: one consequence of the way the protocol was written is that you >>>> can't just throw out a LAYOUTRETURN for the entire file if the server >>>> just recalls a segment. Instead, you have to first return the segment, >>>> then send the LAYOUTRETURN for the entire file. >>>> >>> >>> It is true that the protocol requires the return of the exact recalled range >>> but why can't the client do return the whole file before returning the recalled >>> range? >> Just for clarification, do you mean that after client returns more >> than server recalls, clients still has to do an echoing LAYOUTRETURN? >> It is barely overhead... >> Why would server require some behavior like that? >> > > The reason for that in the protocol was to provide a simple way to > complete a CB_LAYOUTRECALL "meta operation" when the client returns > the layout in smaller ranges than recalled. We overlooked this case > of the client returning a range containing the returned range. > which is easier to deal with, with further stateid related functionality > we introduced after specifying how layout recall initially worked... I see it. Thanks. The behavior is clearly defined in section 18.44.3. And only in the subset returning case, client has to do a matching layoutreturn to complete CB_LAYOUTRECALL. > > Benny > >>> >>>> That part of the protocol is just one insane idea after another... >>>> >>> >>> This was done to ensure that the server and client are in-sync after a >>> CB_LAYOUTRECALL. ÂI agree that returning the whole layout thus resetting >>> the layout state achieves the same goal and we should consider allowing it >>> in the next version. >>> >>> Benny >>> -- >>> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in >>> the body of a message to majordomo@xxxxxxxxxxxxxxx >>> More majordomo info at Âhttp://vger.kernel.org/majordomo-info.html >>> >> >> >> > -- Thanks, -Bergwolf -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
