Minor optimization: when dealing with write chunk XDR roundup, do
not post a Write WR for the zero bytes in the pad. Simply update
the write segment in the RPC-over-RDMA header to reflect the extra
pad bytes.
The Reply chunk is also a write chunk, but the server does not use
send_write_chunks() to send the Reply chunk. That's OK in this case:
the server Upper Layer typically marshals the Reply chunk contents
in a single contiguous buffer, without a separate tail for the XDR
pad.
The comments and the variable naming refer to "chunks" but what is
really meant is "segments." The existing code sends only one
xdr_write_chunk per RPC reply.
The fix assumes this as well. When the XDR pad in the first write
chunk is reached, the assumption is the Write list is complete and
send_write_chunks() returns.
That will remain a valid assumption until the server Upper Layer can
support multiple bulk payload results per RPC.
Signed-off-by: Chuck Lever <[email protected]>
---
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 7 +++++++
1 files changed, 7 insertions(+), 0 deletions(-)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 1dfae83..6c48901 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -342,6 +342,13 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
arg_ch->rs_handle,
arg_ch->rs_offset,
write_len);
+
+ /* Do not send XDR pad bytes */
+ if (chunk_no && write_len < 4) {
+ chunk_no++;
+ break;
+ }
+
chunk_off = 0;
while (write_len) {
ret = send_write(xprt, rqstp,
> On Oct 16, 2015, at 9:30 AM, Chuck Lever <[email protected]> wrote:
>
> Minor optimization: when dealing with write chunk XDR roundup, do
> not post a Write WR for the zero bytes in the pad. Simply update
> the write segment in the RPC-over-RDMA header to reflect the extra
> pad bytes.
>
> The Reply chunk is also a write chunk, but the server does not use
> send_write_chunks() to send the Reply chunk. That's OK in this case:
> the server Upper Layer typically marshals the Reply chunk contents
> in a single contiguous buffer, without a separate tail for the XDR
> pad.
>
> The comments and the variable naming refer to "chunks" but what is
> really meant is "segments." The existing code sends only one
> xdr_write_chunk per RPC reply.
>
> The fix assumes this as well. When the XDR pad in the first write
> chunk is reached, the assumption is the Write list is complete and
> send_write_chunks() returns.
>
> That will remain a valid assumption until the server Upper Layer can
> support multiple bulk payload results per RPC.
>
> Signed-off-by: Chuck Lever <[email protected]>
> --
Bruce, can you take this for 4.4 ?
> net/sunrpc/xprtrdma/svc_rdma_sendto.c | 7 +++++++
> 1 files changed, 7 insertions(+), 0 deletions(-)
>
> diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> index 1dfae83..6c48901 100644
> --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> @@ -342,6 +342,13 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
> arg_ch->rs_handle,
> arg_ch->rs_offset,
> write_len);
> +
> + /* Do not send XDR pad bytes */
> + if (chunk_no && write_len < 4) {
> + chunk_no++;
> + break;
> + }
> +
> chunk_off = 0;
> while (write_len) {
> ret = send_write(xprt, rqstp,
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
—
Chuck Lever
> On Nov 3, 2015, at 3:10 PM, Chuck Lever <[email protected]> wrote:
>
>
>> On Oct 16, 2015, at 9:30 AM, Chuck Lever <[email protected]> wrote:
>>
>> Minor optimization: when dealing with write chunk XDR roundup, do
>> not post a Write WR for the zero bytes in the pad. Simply update
>> the write segment in the RPC-over-RDMA header to reflect the extra
>> pad bytes.
>>
>> The Reply chunk is also a write chunk, but the server does not use
>> send_write_chunks() to send the Reply chunk. That's OK in this case:
>> the server Upper Layer typically marshals the Reply chunk contents
>> in a single contiguous buffer, without a separate tail for the XDR
>> pad.
>>
>> The comments and the variable naming refer to "chunks" but what is
>> really meant is "segments." The existing code sends only one
>> xdr_write_chunk per RPC reply.
>>
>> The fix assumes this as well. When the XDR pad in the first write
>> chunk is reached, the assumption is the Write list is complete and
>> send_write_chunks() returns.
>>
>> That will remain a valid assumption until the server Upper Layer can
>> support multiple bulk payload results per RPC.
>>
>> Signed-off-by: Chuck Lever <[email protected]>
>> --
>
> Bruce, can you take this for 4.4 ?
Hi Bruce-
Your 4.4 pull request did not include this patch.
>> net/sunrpc/xprtrdma/svc_rdma_sendto.c | 7 +++++++
>> 1 files changed, 7 insertions(+), 0 deletions(-)
>>
>> diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
>> index 1dfae83..6c48901 100644
>> --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
>> +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
>> @@ -342,6 +342,13 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
>> arg_ch->rs_handle,
>> arg_ch->rs_offset,
>> write_len);
>> +
>> + /* Do not send XDR pad bytes */
>> + if (chunk_no && write_len < 4) {
>> + chunk_no++;
>> + break;
>> + }
>> +
>> chunk_off = 0;
>> while (write_len) {
>> ret = send_write(xprt, rqstp,
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
>> the body of a message to [email protected]
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
> —
> Chuck Lever
>
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
—
Chuck Lever
On Wed, Nov 11, 2015 at 03:20:33PM -0500, Chuck Lever wrote:
>
> > On Nov 3, 2015, at 3:10 PM, Chuck Lever <[email protected]> wrote:
> >
> >
> >> On Oct 16, 2015, at 9:30 AM, Chuck Lever <[email protected]> wrote:
> >>
> >> Minor optimization: when dealing with write chunk XDR roundup, do
> >> not post a Write WR for the zero bytes in the pad. Simply update
> >> the write segment in the RPC-over-RDMA header to reflect the extra
> >> pad bytes.
> >>
> >> The Reply chunk is also a write chunk, but the server does not use
> >> send_write_chunks() to send the Reply chunk. That's OK in this case:
> >> the server Upper Layer typically marshals the Reply chunk contents
> >> in a single contiguous buffer, without a separate tail for the XDR
> >> pad.
> >>
> >> The comments and the variable naming refer to "chunks" but what is
> >> really meant is "segments." The existing code sends only one
> >> xdr_write_chunk per RPC reply.
> >>
> >> The fix assumes this as well. When the XDR pad in the first write
> >> chunk is reached, the assumption is the Write list is complete and
> >> send_write_chunks() returns.
> >>
> >> That will remain a valid assumption until the server Upper Layer can
> >> support multiple bulk payload results per RPC.
> >>
> >> Signed-off-by: Chuck Lever <[email protected]>
> >> --
> >
> > Bruce, can you take this for 4.4 ?
>
> Hi Bruce-
>
> Your 4.4 pull request did not include this patch.
Whoops, sorry.
For some reason I don't have the original email, though I do see your
first followup. Would you mind resending?
Also, it looks like that wasn't actually sent to me? I really want
submitted patches to have my address on the To: line. Obviously I also
try to pick up stuff sent only to the mailing list, but I'm a little
more likely to miss those.
But my fault either way, apologies.
--b.
>
>
> >> net/sunrpc/xprtrdma/svc_rdma_sendto.c | 7 +++++++
> >> 1 files changed, 7 insertions(+), 0 deletions(-)
> >>
> >> diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> >> index 1dfae83..6c48901 100644
> >> --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> >> +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> >> @@ -342,6 +342,13 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
> >> arg_ch->rs_handle,
> >> arg_ch->rs_offset,
> >> write_len);
> >> +
> >> + /* Do not send XDR pad bytes */
> >> + if (chunk_no && write_len < 4) {
> >> + chunk_no++;
> >> + break;
> >> + }
> >> +
> >> chunk_off = 0;
> >> while (write_len) {
> >> ret = send_write(xprt, rqstp,
> >>
> >> --
> >> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> >> the body of a message to [email protected]
> >> More majordomo info at http://vger.kernel.org/majordomo-info.html
> >
> > —
> > Chuck Lever
> >
> >
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> > the body of a message to [email protected]
> > More majordomo info at http://vger.kernel.org/majordomo-info.html
>
> —
> Chuck Lever
>
>
> On Nov 12, 2015, at 9:19 AM, J. Bruce Fields <[email protected]> wrote:
>
> On Wed, Nov 11, 2015 at 03:20:33PM -0500, Chuck Lever wrote:
>>
>>> On Nov 3, 2015, at 3:10 PM, Chuck Lever <[email protected]> wrote:
>>>
>>>
>>>> On Oct 16, 2015, at 9:30 AM, Chuck Lever <[email protected]> wrote:
>>>>
>>>> Minor optimization: when dealing with write chunk XDR roundup, do
>>>> not post a Write WR for the zero bytes in the pad. Simply update
>>>> the write segment in the RPC-over-RDMA header to reflect the extra
>>>> pad bytes.
>>>>
>>>> The Reply chunk is also a write chunk, but the server does not use
>>>> send_write_chunks() to send the Reply chunk. That's OK in this case:
>>>> the server Upper Layer typically marshals the Reply chunk contents
>>>> in a single contiguous buffer, without a separate tail for the XDR
>>>> pad.
>>>>
>>>> The comments and the variable naming refer to "chunks" but what is
>>>> really meant is "segments." The existing code sends only one
>>>> xdr_write_chunk per RPC reply.
>>>>
>>>> The fix assumes this as well. When the XDR pad in the first write
>>>> chunk is reached, the assumption is the Write list is complete and
>>>> send_write_chunks() returns.
>>>>
>>>> That will remain a valid assumption until the server Upper Layer can
>>>> support multiple bulk payload results per RPC.
>>>>
>>>> Signed-off-by: Chuck Lever <[email protected]>
>>>> --
>>>
>>> Bruce, can you take this for 4.4 ?
>>
>> Hi Bruce-
>>
>> Your 4.4 pull request did not include this patch.
>
> Whoops, sorry.
>
> For some reason I don't have the original email, though I do see your
> first followup. Would you mind resending?
>
> Also, it looks like that wasn't actually sent to me? I really want
> submitted patches to have my address on the To: line. Obviously I also
> try to pick up stuff sent only to the mailing list, but I'm a little
> more likely to miss those.
Yep, my bad, I meant to address that To: you. Will repost.
> But my fault either way, apologies.
>
> --b.
>
>>
>>
>>>> net/sunrpc/xprtrdma/svc_rdma_sendto.c | 7 +++++++
>>>> 1 files changed, 7 insertions(+), 0 deletions(-)
>>>>
>>>> diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
>>>> index 1dfae83..6c48901 100644
>>>> --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
>>>> +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
>>>> @@ -342,6 +342,13 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
>>>> arg_ch->rs_handle,
>>>> arg_ch->rs_offset,
>>>> write_len);
>>>> +
>>>> + /* Do not send XDR pad bytes */
>>>> + if (chunk_no && write_len < 4) {
>>>> + chunk_no++;
>>>> + break;
>>>> + }
>>>> +
>>>> chunk_off = 0;
>>>> while (write_len) {
>>>> ret = send_write(xprt, rqstp,
>>>>
>>>> --
>>>> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
>>>> the body of a message to [email protected]
>>>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>>
>>> —
>>> Chuck Lever
>>>
>>>
>>>
>>> --
>>> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
>>> the body of a message to [email protected]
>>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>
>> —
>> Chuck Lever
>>
>>
—
Chuck Lever