From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga07.intel.com (mga07.intel.com [134.134.136.100]) by dpdk.org (Postfix) with ESMTP id 53A261B3A3 for ; Mon, 15 Apr 2019 19:39:11 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by orsmga105.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 15 Apr 2019 10:39:10 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.60,354,1549958400"; d="scan'208";a="164936207" Received: from irsmsx104.ger.corp.intel.com ([163.33.3.159]) by fmsmga001.fm.intel.com with ESMTP; 15 Apr 2019 10:39:08 -0700 Received: from irsmsx105.ger.corp.intel.com ([169.254.7.31]) by IRSMSX104.ger.corp.intel.com ([169.254.5.44]) with mapi id 14.03.0415.000; Mon, 15 Apr 2019 18:39:07 +0100 From: "Ananyev, Konstantin" To: Stephen Hemminger CC: Honnappa Nagarahalli , "paulmck@linux.ibm.com" , "Kovacevic, Marko" , "dev@dpdk.org" , "Gavin Hu (Arm Technology China)" , Dharmik Thakkar , Malvika Gupta , nd Thread-Topic: [PATCH v5 1/3] rcu: add RCU library supporting QSBR mechanism Thread-Index: AQHU8W09YQlYNBQMIUeythDpmiY2L6Y5BHAAgAAFAYCAAAupgIAEE9RggAAmBQCAACqAYA== Date: Mon, 15 Apr 2019 17:39:07 +0000 Message-ID: <2601191342CEEE43887BDE71AB9772580148A98064@irsmsx105.ger.corp.intel.com> References: <20181122033055.3431-1-honnappa.nagarahalli@arm.com> <20190412202039.46902-1-honnappa.nagarahalli@arm.com> <20190412202039.46902-2-honnappa.nagarahalli@arm.com> <20190412150650.3709358e@shemminger-XPS-13-9360> <20190412160629.670eacd1@shemminger-XPS-13-9360> <2601191342CEEE43887BDE71AB9772580148A97E53@irsmsx105.ger.corp.intel.com> <20190415083834.31b38ed3@shemminger-XPS-13-9360> In-Reply-To: <20190415083834.31b38ed3@shemminger-XPS-13-9360> Accept-Language: en-IE, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-titus-metadata-40: eyJDYXRlZ29yeUxhYmVscyI6IiIsIk1ldGFkYXRhIjp7Im5zIjoiaHR0cDpcL1wvd3d3LnRpdHVzLmNvbVwvbnNcL0ludGVsMyIsImlkIjoiMGM2NGIyZDktYTQ4OC00MTE5LTlkYTktYzZhNWMxZDc5ZWE5IiwicHJvcHMiOlt7Im4iOiJDVFBDbGFzc2lmaWNhdGlvbiIsInZhbHMiOlt7InZhbHVlIjoiQ1RQX05UIn1dfV19LCJTdWJqZWN0TGFiZWxzIjpbXSwiVE1DVmVyc2lvbiI6IjE3LjEwLjE4MDQuNDkiLCJUcnVzdGVkTGFiZWxIYXNoIjoiaVMzZFQrNTdMREJDS2dsczU0YjU3THh1eElBcXRxU1ZvZnRxcWdHbFNcL09wQkM3NTU0RnNDSWFLVXBzdGNxWU4ifQ== x-ctpclassification: CTP_NT dlp-product: dlpe-windows dlp-version: 11.0.600.7 dlp-reaction: no-action x-originating-ip: [163.33.239.182] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v5 1/3] rcu: add RCU library supporting QSBR mechanism X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 15 Apr 2019 17:39:11 -0000 > -----Original Message----- > From: Stephen Hemminger [mailto:stephen@networkplumber.org] > Sent: Monday, April 15, 2019 4:39 PM > To: Ananyev, Konstantin > Cc: Honnappa Nagarahalli ; paulmck@linux.ib= m.com; Kovacevic, Marko > ; dev@dpdk.org; Gavin Hu (Arm Technology China= ) ; Dharmik Thakkar > ; Malvika Gupta ; nd > Subject: Re: [PATCH v5 1/3] rcu: add RCU library supporting QSBR mechanis= m >=20 > On Mon, 15 Apr 2019 12:24:47 +0000 > "Ananyev, Konstantin" wrote: >=20 > > > -----Original Message----- > > > From: Stephen Hemminger [mailto:stephen@networkplumber.org] > > > Sent: Saturday, April 13, 2019 12:06 AM > > > To: Honnappa Nagarahalli > > > Cc: Ananyev, Konstantin ; paulmck@linux= .ibm.com; Kovacevic, Marko ; > > > dev@dpdk.org; Gavin Hu (Arm Technology China) ; Dha= rmik Thakkar ; Malvika > Gupta > > > ; nd > > > Subject: Re: [PATCH v5 1/3] rcu: add RCU library supporting QSBR mech= anism > > > > > > On Fri, 12 Apr 2019 22:24:45 +0000 > > > Honnappa Nagarahalli wrote: > > > > > > > > > > > > > On Fri, 12 Apr 2019 15:20:37 -0500 > > > > > Honnappa Nagarahalli wrote: > > > > > > > > > > > Add RCU library supporting quiescent state based memory reclama= tion > > > > > method. > > > > > > This library helps identify the quiescent state of the reader t= hreads > > > > > > so that the writers can free the memory associated with the loc= k less > > > > > > data structures. > > > > > > > > > > > > Signed-off-by: Honnappa Nagarahalli > > > > > > Reviewed-by: Steve Capper > > > > > > Reviewed-by: Gavin Hu > > > > > > Reviewed-by: Ola Liljedahl > > > > > > Acked-by: Konstantin Ananyev > > > > > > > > > > After evaluating long term API/ABI issues, I think you need to ge= t rid of almost > > > > > all use of inline and visible structures. Yes it might be margina= lly slower, but > > > > > you thank me the first time you have to fix something. > > > > > > > > > Agree, I was planning on another version to address this (I am yet = to take a look at your patch addressing the ABI). > > > > The structure visibility definitely needs to be addressed. > > > > For the inline functions, is the plan to convert all the inline fun= ctions in DPDK? If yes, I think we need to consider the performance > > > difference. May be consider L3-fwd application, change all the inline= functions in its path and run a test? > > > > > > Every function that is not in the direct datapath should not be inlin= e. > > > Exceptions or things like rx/tx burst, ring enqueue/dequeue, and pack= et alloc/free > > > > Plus synchronization routines: spin/rwlock/barrier, etc. > > I think rcu should be one of such exceptions - it is just another synch= ronization mechanism after all > > (just a bit more sophisticated). > > Konstantin >=20 > If you look at the other userspace RCU, you wil see that the only inlines > are the rcu_read_lock,rcu_read_unlock and rcu_reference/rcu_assign_pointe= r. >=20 > The synchronization logic is all real functions. In fact, I think urcu provides both flavors: https://github.com/urcu/userspace-rcu/blob/master/include/urcu/static/urcu-= qsbr.h I still don't understand why we have to treat it differently then let say s= pin-lock/ticket-lock or rwlock. If we gone all the way to create our own version of rcu, we probably want i= t to be as fast as possible (I know that main speedup should come from the fact that readers don't have= to wait for writer to finish, but still...) Konstantin From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by dpdk.space (Postfix) with ESMTP id 83FB5A00E6 for ; Mon, 15 Apr 2019 19:39:14 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id A14221B3A4; Mon, 15 Apr 2019 19:39:12 +0200 (CEST) Received: from mga07.intel.com (mga07.intel.com [134.134.136.100]) by dpdk.org (Postfix) with ESMTP id 53A261B3A3 for ; Mon, 15 Apr 2019 19:39:11 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by orsmga105.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 15 Apr 2019 10:39:10 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.60,354,1549958400"; d="scan'208";a="164936207" Received: from irsmsx104.ger.corp.intel.com ([163.33.3.159]) by fmsmga001.fm.intel.com with ESMTP; 15 Apr 2019 10:39:08 -0700 Received: from irsmsx105.ger.corp.intel.com ([169.254.7.31]) by IRSMSX104.ger.corp.intel.com ([169.254.5.44]) with mapi id 14.03.0415.000; Mon, 15 Apr 2019 18:39:07 +0100 From: "Ananyev, Konstantin" To: Stephen Hemminger CC: Honnappa Nagarahalli , "paulmck@linux.ibm.com" , "Kovacevic, Marko" , "dev@dpdk.org" , "Gavin Hu (Arm Technology China)" , Dharmik Thakkar , Malvika Gupta , nd Thread-Topic: [PATCH v5 1/3] rcu: add RCU library supporting QSBR mechanism Thread-Index: AQHU8W09YQlYNBQMIUeythDpmiY2L6Y5BHAAgAAFAYCAAAupgIAEE9RggAAmBQCAACqAYA== Date: Mon, 15 Apr 2019 17:39:07 +0000 Message-ID: <2601191342CEEE43887BDE71AB9772580148A98064@irsmsx105.ger.corp.intel.com> References: <20181122033055.3431-1-honnappa.nagarahalli@arm.com> <20190412202039.46902-1-honnappa.nagarahalli@arm.com> <20190412202039.46902-2-honnappa.nagarahalli@arm.com> <20190412150650.3709358e@shemminger-XPS-13-9360> <20190412160629.670eacd1@shemminger-XPS-13-9360> <2601191342CEEE43887BDE71AB9772580148A97E53@irsmsx105.ger.corp.intel.com> <20190415083834.31b38ed3@shemminger-XPS-13-9360> In-Reply-To: <20190415083834.31b38ed3@shemminger-XPS-13-9360> Accept-Language: en-IE, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-titus-metadata-40: eyJDYXRlZ29yeUxhYmVscyI6IiIsIk1ldGFkYXRhIjp7Im5zIjoiaHR0cDpcL1wvd3d3LnRpdHVzLmNvbVwvbnNcL0ludGVsMyIsImlkIjoiMGM2NGIyZDktYTQ4OC00MTE5LTlkYTktYzZhNWMxZDc5ZWE5IiwicHJvcHMiOlt7Im4iOiJDVFBDbGFzc2lmaWNhdGlvbiIsInZhbHMiOlt7InZhbHVlIjoiQ1RQX05UIn1dfV19LCJTdWJqZWN0TGFiZWxzIjpbXSwiVE1DVmVyc2lvbiI6IjE3LjEwLjE4MDQuNDkiLCJUcnVzdGVkTGFiZWxIYXNoIjoiaVMzZFQrNTdMREJDS2dsczU0YjU3THh1eElBcXRxU1ZvZnRxcWdHbFNcL09wQkM3NTU0RnNDSWFLVXBzdGNxWU4ifQ== x-ctpclassification: CTP_NT dlp-product: dlpe-windows dlp-version: 11.0.600.7 dlp-reaction: no-action x-originating-ip: [163.33.239.182] Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v5 1/3] rcu: add RCU library supporting QSBR mechanism X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Message-ID: <20190415173907.IxE0rvm1XmxEivi3NjVwtcaz61Q1GMQwE8qSLZ9GDhg@z> > -----Original Message----- > From: Stephen Hemminger [mailto:stephen@networkplumber.org] > Sent: Monday, April 15, 2019 4:39 PM > To: Ananyev, Konstantin > Cc: Honnappa Nagarahalli ; paulmck@linux.ib= m.com; Kovacevic, Marko > ; dev@dpdk.org; Gavin Hu (Arm Technology China= ) ; Dharmik Thakkar > ; Malvika Gupta ; nd > Subject: Re: [PATCH v5 1/3] rcu: add RCU library supporting QSBR mechanis= m >=20 > On Mon, 15 Apr 2019 12:24:47 +0000 > "Ananyev, Konstantin" wrote: >=20 > > > -----Original Message----- > > > From: Stephen Hemminger [mailto:stephen@networkplumber.org] > > > Sent: Saturday, April 13, 2019 12:06 AM > > > To: Honnappa Nagarahalli > > > Cc: Ananyev, Konstantin ; paulmck@linux= .ibm.com; Kovacevic, Marko ; > > > dev@dpdk.org; Gavin Hu (Arm Technology China) ; Dha= rmik Thakkar ; Malvika > Gupta > > > ; nd > > > Subject: Re: [PATCH v5 1/3] rcu: add RCU library supporting QSBR mech= anism > > > > > > On Fri, 12 Apr 2019 22:24:45 +0000 > > > Honnappa Nagarahalli wrote: > > > > > > > > > > > > > On Fri, 12 Apr 2019 15:20:37 -0500 > > > > > Honnappa Nagarahalli wrote: > > > > > > > > > > > Add RCU library supporting quiescent state based memory reclama= tion > > > > > method. > > > > > > This library helps identify the quiescent state of the reader t= hreads > > > > > > so that the writers can free the memory associated with the loc= k less > > > > > > data structures. > > > > > > > > > > > > Signed-off-by: Honnappa Nagarahalli > > > > > > Reviewed-by: Steve Capper > > > > > > Reviewed-by: Gavin Hu > > > > > > Reviewed-by: Ola Liljedahl > > > > > > Acked-by: Konstantin Ananyev > > > > > > > > > > After evaluating long term API/ABI issues, I think you need to ge= t rid of almost > > > > > all use of inline and visible structures. Yes it might be margina= lly slower, but > > > > > you thank me the first time you have to fix something. > > > > > > > > > Agree, I was planning on another version to address this (I am yet = to take a look at your patch addressing the ABI). > > > > The structure visibility definitely needs to be addressed. > > > > For the inline functions, is the plan to convert all the inline fun= ctions in DPDK? If yes, I think we need to consider the performance > > > difference. May be consider L3-fwd application, change all the inline= functions in its path and run a test? > > > > > > Every function that is not in the direct datapath should not be inlin= e. > > > Exceptions or things like rx/tx burst, ring enqueue/dequeue, and pack= et alloc/free > > > > Plus synchronization routines: spin/rwlock/barrier, etc. > > I think rcu should be one of such exceptions - it is just another synch= ronization mechanism after all > > (just a bit more sophisticated). > > Konstantin >=20 > If you look at the other userspace RCU, you wil see that the only inlines > are the rcu_read_lock,rcu_read_unlock and rcu_reference/rcu_assign_pointe= r. >=20 > The synchronization logic is all real functions. In fact, I think urcu provides both flavors: https://github.com/urcu/userspace-rcu/blob/master/include/urcu/static/urcu-= qsbr.h I still don't understand why we have to treat it differently then let say s= pin-lock/ticket-lock or rwlock. If we gone all the way to create our own version of rcu, we probably want i= t to be as fast as possible (I know that main speedup should come from the fact that readers don't have= to wait for writer to finish, but still...) Konstantin