RE: [PATCH V3] svcrdma: refactor marshalling logic

2014-06-02 Thread Steve Wise
: Friday, May 30, 2014 6:32 PM To: Devesh Sharma; bfie...@fieldses.org Cc: linux-...@vger.kernel.org; linux-rdma@vger.kernel.org; t...@opengridcomputing.com Subject: RE: [PATCH V3] svcrdma: refactor marshalling logic Hi Steve I am testing this patch. I have found that when server tries

Re: [PATCH V3] svcrdma: refactor marshalling logic

2014-06-02 Thread J. Bruce Fields
On Mon, Jun 02, 2014 at 11:47:58AM -0500, Steve Wise wrote: Steve I have not checked the code because I am away from my laptop But I assume mlx and mthca is using fmr and cxgb4 is using rdma-read-with-invalidate which has implicit fence. If invalidate is issued before read

RE: [PATCH V3] svcrdma: refactor marshalling logic

2014-06-02 Thread Steve Wise
You're correct. And this bug appears to be in the current upstream code as well. If an IB_WR_LOCAL_INV wr is used, it must include IB_SEND_FENCE to fence it until the prior read completes. Good catch! I'll post V4 soon. Any chance that can be handled as a separate patch

Re: [PATCH V3] svcrdma: refactor marshalling logic

2014-06-02 Thread 'J. Bruce Fields'
On Mon, Jun 02, 2014 at 11:52:47AM -0500, Steve Wise wrote: You're correct. And this bug appears to be in the current upstream code as well. If an IB_WR_LOCAL_INV wr is used, it must include IB_SEND_FENCE to fence it until the prior read completes. Good catch! I'll

RE: [PATCH V3] svcrdma: refactor marshalling logic

2014-06-02 Thread Steve Wise
On Mon, Jun 02, 2014 at 11:52:47AM -0500, Steve Wise wrote: You're correct. And this bug appears to be in the current upstream code as well. If an IB_WR_LOCAL_INV wr is used, it must include IB_SEND_FENCE to fence it until the prior read completes. Good catch!

Re: [PATCH V3] svcrdma: refactor marshalling logic

2014-06-02 Thread 'J. Bruce Fields'
On Mon, Jun 02, 2014 at 12:06:39PM -0500, Steve Wise wrote: On Mon, Jun 02, 2014 at 11:52:47AM -0500, Steve Wise wrote: You're correct. And this bug appears to be in the current upstream code as well. If an IB_WR_LOCAL_INV wr is used, it must include IB_SEND_FENCE to fence

RE: [PATCH V3] svcrdma: refactor marshalling logic

2014-05-30 Thread Steve Wise
; linux-rdma@vger.kernel.org; t...@opengridcomputing.com Subject: [PATCH V3] svcrdma: refactor marshalling logic This patch refactors the NFSRDMA server marshalling logic to remove the intermediary map structures. It also fixes an existing bug where the NFSRDMA server was not minding

RE: [PATCH V3] svcrdma: refactor marshalling logic

2014-05-30 Thread Devesh Sharma
From: Steve Wise [sw...@opengridcomputing.com] Sent: Friday, May 30, 2014 6:32 PM To: Devesh Sharma; bfie...@fieldses.org Cc: linux-...@vger.kernel.org; linux-rdma@vger.kernel.org; t...@opengridcomputing.com Subject: RE: [PATCH V3] svcrdma: refactor marshalling logic Hi Steve I am testing

[PATCH V3] svcrdma: refactor marshalling logic

2014-05-29 Thread Steve Wise
This patch refactors the NFSRDMA server marshalling logic to remove the intermediary map structures. It also fixes an existing bug where the NFSRDMA server was not minding the device fast register page list length limitations. I've also made a git repo available with these patches on top of

Re: [PATCH V3] svcrdma: refactor marshalling logic

2014-05-29 Thread Chuck Lever
Test results: On May 29, 2014, at 12:55 PM, Steve Wise sw...@opengridcomputing.com wrote: This patch refactors the NFSRDMA server marshalling logic to remove the intermediary map structures. It also fixes an existing bug where the NFSRDMA server was not minding the device fast register page