Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-15 Thread Sowmini Varadhan
On (02/15/18 11:35), Willem de Bruijn wrote: > > The flag is a hint, so on its own it does not require a respin. > > There are by now four small items to patch up. I would respin so that the > patchset that is recorded can be read later as a single correct solution. Agreed, I'll genenrate V3

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-15 Thread Willem de Bruijn
On Thu, Feb 15, 2018 at 7:03 AM, Sowmini Varadhan wrote: > On (02/14/18 19:41), Willem de Bruijn wrote: >> >> One more thing: this code notifies that the operation succeeded, but >> the data was copied in the process. It does not have to be set otherwise. > > I see.

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-15 Thread Sowmini Varadhan
On (02/14/18 19:41), Willem de Bruijn wrote: > > One more thing: this code notifies that the operation succeeded, but > the data was copied in the process. It does not have to be set otherwise. I see. this one was a bit confusing for me (hence the copy/paste) - maybe because the TCP/UDP/PACKET

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Willem de Bruijn
On Wed, Feb 14, 2018 at 5:28 AM, Sowmini Varadhan wrote: > RDS removes a datagram (rds_message) from the retransmit queue when > an ACK is received. The ACK indicates that the receiver has queued > the RDS datagram, so that the sender can safely forget the datagram. >

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Santosh Shilimkar
On 2/14/2018 2:26 PM, Willem de Bruijn wrote: On Wed, Feb 14, 2018 at 1:50 PM, Santosh Shilimkar [...] This error change might need to go though other subsystem tree. May be you can seperate it and also copy "linux-...@vger.kernel.org" Previous changes to this file also went in through

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Willem de Bruijn
On Wed, Feb 14, 2018 at 5:28 AM, Sowmini Varadhan wrote: > RDS removes a datagram (rds_message) from the retransmit queue when > an ACK is received. The ACK indicates that the receiver has queued > the RDS datagram, so that the sender can safely forget the datagram. >

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Willem de Bruijn
On Wed, Feb 14, 2018 at 1:50 PM, Santosh Shilimkar wrote: > On 2/14/2018 2:28 AM, Sowmini Varadhan wrote: >> >> RDS removes a datagram (rds_message) from the retransmit queue when >> an ACK is received. The ACK indicates that the receiver has queued >> the RDS

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Santosh Shilimkar
On 2/14/2018 1:25 PM, Sowmini Varadhan wrote: On (02/14/18 13:10), Santosh Shilimkar wrote: RDS support true zero copy already with RDMA transport so some of this code can easily get confused. btw, another way to solve this is to have the RDMA code use the suffix "rdma" (which is what it

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Santosh Shilimkar
On 2/14/2018 1:25 PM, Sowmini Varadhan wrote: On (02/14/18 13:10), Santosh Shilimkar wrote: RDS support true zero copy already with RDMA transport so some of this code can easily get confused. btw, another way to solve this is to have the RDMA code use the suffix "rdma" (which is what it

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Sowmini Varadhan
On (02/14/18 13:10), Santosh Shilimkar wrote: > >>>RDS support true zero copy already with RDMA transport so some of > >>>this code can easily get confused. btw, another way to solve this is to have the RDMA code use the suffix "rdma" (which is what it really is) as needed. --Sowmini

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Santosh Shilimkar
On 2/14/2018 11:02 AM, David Miller wrote: From: Sowmini Varadhan Date: Wed, 14 Feb 2018 14:01:10 -0500 On (02/14/18 10:50), Santosh Shilimkar wrote: generic comment and please update it where it is applicable in terms of variable names, notifiers etc. RDS

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Santosh Shilimkar
On 2/14/2018 11:01 AM, Sowmini Varadhan wrote: On (02/14/18 10:50), Santosh Shilimkar wrote: generic comment and please update it where it is applicable in terms of variable names, notifiers etc. RDS support true zero copy already with RDMA transport so some of this code can easily get

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread David Miller
From: Sowmini Varadhan Date: Wed, 14 Feb 2018 14:01:10 -0500 > On (02/14/18 10:50), Santosh Shilimkar wrote: >> generic comment and please update it where it is applicable >> in terms of variable names, notifiers etc. >> >> RDS support true zero copy already with

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Sowmini Varadhan
On (02/14/18 10:50), Santosh Shilimkar wrote: > generic comment and please update it where it is applicable > in terms of variable names, notifiers etc. > > RDS support true zero copy already with RDMA transport so some of > this code can easily get confused. > > So I suggest something like

Re: [PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Santosh Shilimkar
On 2/14/2018 2:28 AM, Sowmini Varadhan wrote: RDS removes a datagram (rds_message) from the retransmit queue when an ACK is received. The ACK indicates that the receiver has queued the RDS datagram, so that the sender can safely forget the datagram. When all references to the rds_message are

[PATCH V2 net-next 4/7] rds: support for zcopy completion notification

2018-02-14 Thread Sowmini Varadhan
RDS removes a datagram (rds_message) from the retransmit queue when an ACK is received. The ACK indicates that the receiver has queued the RDS datagram, so that the sender can safely forget the datagram. When all references to the rds_message are quiesced, rds_message_purge is called to release