Return-Path: Received: from mail-lf0-f47.google.com ([209.85.215.47]:35460 "EHLO mail-lf0-f47.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753538AbbLPOAS (ORCPT ); Wed, 16 Dec 2015 09:00:18 -0500 Received: by mail-lf0-f47.google.com with SMTP id l133so29576228lfd.2 for ; Wed, 16 Dec 2015 06:00:17 -0800 (PST) Subject: Re: [PATCH v3 04/11] xprtrdma: Move struct ib_send_wr off the stack To: Chuck Lever , anna.schumaker@netapp.com References: <20151214211317.16295.70115.stgit@manet.1015granger.net> <20151214211811.16295.47695.stgit@manet.1015granger.net> Cc: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org From: Sagi Grimberg Message-ID: <56716E6C.4020604@dev.mellanox.co.il> Date: Wed, 16 Dec 2015 16:00:12 +0200 MIME-Version: 1.0 In-Reply-To: <20151214211811.16295.47695.stgit@manet.1015granger.net> Content-Type: text/plain; charset=utf-8; format=flowed Sender: linux-nfs-owner@vger.kernel.org List-ID: > diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h > index 4197191..e60d817 100644 > --- a/net/sunrpc/xprtrdma/xprt_rdma.h > +++ b/net/sunrpc/xprtrdma/xprt_rdma.h > @@ -206,6 +206,8 @@ struct rpcrdma_frmr { > enum rpcrdma_frmr_state fr_state; > struct work_struct fr_work; > struct rpcrdma_xprt *fr_xprt; > + struct ib_reg_wr fr_regwr; > + struct ib_send_wr fr_invwr; Would it make sense to unionize these as they are guaranteed not to execute together? Some people don't like this sort of savings.