From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f173.google.com ([209.85.212.173]:38491 "EHLO mail-wi0-f173.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753167AbbEGKPk (ORCPT ); Thu, 7 May 2015 06:15:40 -0400 Received: by wiun10 with SMTP id n10so53804517wiu.1 for ; Thu, 07 May 2015 03:15:39 -0700 (PDT) Message-ID: <554B3B56.1010806@dev.mellanox.co.il> Date: Thu, 07 May 2015 13:15:50 +0300 From: Sagi Grimberg MIME-Version: 1.0 To: Chuck Lever , linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org Subject: Re: [PATCH v1 06/14] xprtrdma: Acquire FMRs in rpcrdma_fmr_register_external() References: <20150504174626.3483.97639.stgit@manet.1015granger.net> <20150504175739.3483.46010.stgit@manet.1015granger.net> In-Reply-To: <20150504175739.3483.46010.stgit@manet.1015granger.net> Content-Type: text/plain; charset=utf-8; format=flowed Sender: linux-nfs-owner@vger.kernel.org List-ID: On 5/4/2015 8:57 PM, Chuck Lever wrote: > Acquiring 64 FMRs in rpcrdma_buffer_get() while holding the buffer > pool lock is expensive, and unnecessary because FMR mode can > transfer up to a 1MB payload using just a single ib_fmr. > > Instead, acquire ib_fmrs one-at-a-time as chunks are registered, and > return them to rb_mws immediately during deregistration. > > Transport reset is now unneeded for FMR. Each FMR is recovered > synchronously when its RPC is retransmitted. Does this worth a separate patch? I don't see why the two changes are together. Is there a dependency I'm missing? From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sagi Grimberg Subject: Re: [PATCH v1 06/14] xprtrdma: Acquire FMRs in rpcrdma_fmr_register_external() Date: Thu, 07 May 2015 13:15:50 +0300 Message-ID: <554B3B56.1010806@dev.mellanox.co.il> References: <20150504174626.3483.97639.stgit@manet.1015granger.net> <20150504175739.3483.46010.stgit@manet.1015granger.net> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20150504175739.3483.46010.stgit-FYjufvaPoItvLzlybtyyYzGyq/o6K9yX@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Chuck Lever , linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: linux-rdma@vger.kernel.org On 5/4/2015 8:57 PM, Chuck Lever wrote: > Acquiring 64 FMRs in rpcrdma_buffer_get() while holding the buffer > pool lock is expensive, and unnecessary because FMR mode can > transfer up to a 1MB payload using just a single ib_fmr. > > Instead, acquire ib_fmrs one-at-a-time as chunks are registered, and > return them to rb_mws immediately during deregistration. > > Transport reset is now unneeded for FMR. Each FMR is recovered > synchronously when its RPC is retransmitted. Does this worth a separate patch? I don't see why the two changes are together. Is there a dependency I'm missing? -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html