From owner-freebsd-scsi@FreeBSD.ORG Mon Dec 9 05:50:46 2013 Return-Path: Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 905448BA; Mon, 9 Dec 2013 05:50:46 +0000 (UTC) Received: from na01-bn1-obe.outbound.protection.outlook.com (mail-bn1lp0150.outbound.protection.outlook.com [207.46.163.150]) (using TLSv1 with cipher AES128-SHA (128/128 bits)) (No client certificate requested) by mx1.freebsd.org (Postfix) with ESMTPS id 17CF415D4; Mon, 9 Dec 2013 05:50:45 +0000 (UTC) Received: from BN1PR07MB247.namprd07.prod.outlook.com (10.141.64.146) by BN1PR07MB358.namprd07.prod.outlook.com (10.141.60.144) with Microsoft SMTP Server (TLS) id 15.0.837.10; Mon, 9 Dec 2013 05:50:36 +0000 Received: from BN1PR07MB247.namprd07.prod.outlook.com ([169.254.7.70]) by BN1PR07MB247.namprd07.prod.outlook.com ([169.254.7.17]) with mapi id 15.00.0837.004; Mon, 9 Dec 2013 05:50:36 +0000 From: "Desai, Kashyap" To: Doug Ambrisko Subject: RE: LSI - MR-Fusion controller driver patch and man page Thread-Topic: LSI - MR-Fusion controller driver patch and man page Thread-Index: Ac7ykKZzGPABTpK8R3+D5UAv3TD3WQADqpeAAICPhOA= Date: Mon, 9 Dec 2013 05:50:35 +0000 Message-ID: <4ebf0c915b784464827c30858a42d54f@BN1PR07MB247.namprd07.prod.outlook.com> References: <08ba2a262fba45f687cdd3225f325110@BN1PR07MB247.namprd07.prod.outlook.com> <20131206162211.GB14280@cisco.com> In-Reply-To: <20131206162211.GB14280@cisco.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [192.19.239.250] x-forefront-prvs: 00550ABE1F x-forefront-antispam-report: SFV:NSPM; SFS:(199002)(189002)(24454002)(13464003)(164054003)(51704005)(377454003)(81686001)(90146001)(56816005)(87936001)(2656002)(85306002)(80976001)(47976001)(74706001)(76482001)(74316001)(87266001)(74366001)(85852002)(19580405001)(83322001)(81342001)(74876001)(49866001)(19580395003)(81816001)(74662001)(81542001)(59766001)(77982001)(54356001)(66066001)(51856001)(4396001)(80022001)(46102001)(65816001)(79102001)(76576001)(47446002)(54316002)(56776001)(50986001)(47736001)(74502001)(53806001)(83072001)(76786001)(33646001)(63696002)(77096001)(69226001)(31966008)(76796001)(24736002); DIR:OUT; SFP:; SCL:1; SRVR:BN1PR07MB358; H:BN1PR07MB247.namprd07.prod.outlook.com; CLIP:192.19.239.250; FPR:; RD:InfoNoRecords; A:1; MX:1; LANG:en; Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: lsi.com X-Mailman-Approved-At: Mon, 09 Dec 2013 16:23:14 +0000 Cc: "scottl@netflix.com" , "Radford, Adam" , "Kenneth D. Merry" , "sean_bruno@yahoo.com" , "Mankani, Krishnaraddi" , "dwhite@ixsystems.com" , "Maloy, Joe" , "jpaetzel@freebsd.org" , "freebsd-scsi@freebsd.org" , "McConnell, Stephen" X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 09 Dec 2013 05:50:46 -0000 > -----Original Message----- > From: Doug Ambrisko [mailto:ambrisko@cisco.com] > Sent: Friday, December 06, 2013 9:52 PM > To: Desai, Kashyap > Cc: freebsd-scsi@freebsd.org; scottl@netflix.com; sean_bruno@yahoo.com; > dwhite@ixsystems.com; jpaetzel@freebsd.org; Maloy, Joe; Mankani, > Krishnaraddi; McConnell, Stephen; Saxena, Sumit; Radford, Adam; Kenneth > D. Merry > Subject: Re: LSI - MR-Fusion controller driver patch and man page >=20 > Sounds like good progress. I'll need to play with it a bit. One questio= n I have > with fast path, is how does LSI determine if they should use that method > versus the RAID firmware? The problem I've seen with fast path is that i= t > skips the NVRAM cache which is a huge performance boost for us. Is there= a > sysctl to control it?=20 Fast Path will not be enabled for Cached VDs. Driver choose Fast Path provi= ded information from firmware. You can find out those bits (fpCapable) in Raid Map. > I could probably read through the code to figure it out but > thought it would be good to get an idea of how LSI plans to use it since = you > guys are the experts on this feature. I understand from Adam that LSI us= es > this to increase the IOPS. I can see it potentially used if an SSD is in= the > system so then LD or PD access could be improved to that type of device. = In > past experience fast path was slower and created a bunch of SCSI sense > errors reported by the RAID firmware. That is one reason why I removed > support of fastpath in mfi. I also didn't want to introduce potential bu= gs if > the RAID firmware and driver got out of sync. due to bugs. Recently we > found with SW RAID that trying to load balance IOs across drives can defe= at > read ahead caches of disks. LSI have never heard anything like above in linux Driver or = any other OS driver for MR controllers. If there is really such a case, we can correct it or provide user option to= bypass load balancing, but as I mentioned, we have never hear anything lik= e that from customer. Thanks, Kashyap >=20 > Thanks, >=20 > Doug A. >=20 > On Fri, Dec 06, 2013 at 02:37:21PM +0000, Desai, Kashyap wrote: > | Hi, > | > | Please consider attached patch for FreeBSD upstream check-in. > | > | Please find attached patch for driver for LSI's MegaRaid > Controllers. This driver supports Thunderbolt onwards Device IDs of MR > controllers. > | Currently it supports 0x005B and 0x005D Device IDs. > | > | NOTE : This driver will not eliminate or by pass any functionality of <= mfi> > driver which already support above to Device IDs to keep existing user > experience unchanged. > | > | Driver will be always given priority over driver and > | only if customer/user wants to use/migrate from to , it > | will hook up into kernel via device.hint rules. (Attached is mrsas man > | page for more info.) > | > | LSI will continue to update driver in future in timely bases. > | We have another set of patch in pipeline to be submitted for , > | but need first go ahead for attached patch and later we will continue > | to keep up-to-date (In sync with LSI released driver which is > | available at lsi's external site) > | > | Apply patch with "patch -p0 < patchname.patch" from head directory. > | > | -- Few notes for user-- > | LSI recommends using fusion_force bit In hint settings at start of the = day, if > they want to use . ( will be a default choice for MR-Fusion > HBA), if will be changed only with fusion_force hint settings. (See mrsas= man > page) Changing any default behavior is well tested for most of the condit= ion. > | Switching from to for MR-Fusion options is designed to > allow user as one time choice, though multiple time switch from to > is possible, it is not recommended. So, user needs to decide from > start of the day, which driver they want to use for MR-Fusion card. > | > | -- Implementation details -- > | To support this feature, we have modify code to change default > return type from probe. Currently driver return > "BUS_PROBE_DEFAULT". driver has been be changed to return > "BUS_PROBE_LOW_PRIORITY" if fusion_force hint from device.hints is set. > | Please notice, above mentioned implementation in driver is only > applicable in case of MR-Fusion controller detection. For any other > controllers, supported by driver, the behavior of probe return will > remain same as before. > | > | > | -- High level feature list of -- 1. Supports Fast Path feature > | of LSI controllers. > | 2. Supports 4K sector Drives. > | 3. CAM layer based interface. All VDs will be attached to CAM layer > | (Expected storage will be visible in "camcontroll") 4. Complete > | support of Online Controller Reset. (OCR) 5. OCR on Fimrware fault and= IO > timeout case. > | 6. Work well with management application which is generic > application provided by LSI for all other Operating system. > | 7. Supporst DIF enabled VDs (Same support as provided in Linux and > | other OSes in FreeBSD) 8. Fast Path Load balance support. > | > | - In summary, this driver is in part with Linux based MR drivers and > | all other features will be available to as planned activity > | from LSI > | > | This code is well tested by LSI Q/A team on 32 bit and 64 bit FreeBSD > Released OSes. > | > | > | Thanks, Kashyap > | >=20 >=20 >=20