Re: [PATCH v2 07/14] xprtrdma: Remove logic that constructs RDMA_MSGP type calls

[Chuck Lever <chuck.lever@oracle.com>]

Thanks Devesh, will note that in the next versions of these series.


On Jul 15, 2015, at 2:26 PM, Devesh Sharma <devesh.sharma@avagotech.com> wrote:

> with MAX_IOVS set to 2 iozone passes with ocrdma device. My testing
> includes both the series of svcrdma and xprtrdma.
> 
> On Wed, Jul 15, 2015 at 12:31 AM, Chuck Lever <chuck.lever@oracle.com> wrote:
>> 
>> On Jul 14, 2015, at 3:00 PM, Tom Talpey <tom@talpey.com> wrote:
>> 
>>> On 7/13/2015 12:30 PM, Chuck Lever wrote:
>>>> RDMA_MSGP type calls insert a zero pad in the middle of the RPC
>>>> message to align the RPC request's data payload to the server's
>>>> alignment preferences. A server can then "page flip" the payload
>>>> into place to avoid a data copy in certain circumstances. However:
>>>> ...
>>>> 
>>>> Clean up the marshaling code by removing the logic that constructs
>>>> RDMA_MSGP type calls. This also reduces the maximum send iovec size
>>>> from four to just two elements.
>>>> 
>>> 
>>>> diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
>>>> index 8219011..0b50103 100644
>>>> --- a/net/sunrpc/xprtrdma/xprt_rdma.h
>>>> +++ b/net/sunrpc/xprtrdma/xprt_rdma.h
>>> ...>
>>>> +#define RPCRDMA_MAX_IOVS    (4)
>>>> +
>>> 
>>> So, shouldn't this constant be "2"? The extra 2 iov's were used
>>> only for constructing the pad.
>> 
>> Yes, thanks. I folded a couple of patches together into this
>> one, and forgot to update the constant.
>> 
>> 
>> --
>> Chuck Lever
>> 
>> 
>> 
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
Chuck Lever