From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?ISO-8859-15?Q?Stefan_H=FCbner?= Subject: Re: Good SAS adapters for 6 Gb/s SATA SSD's (with TRIM)? Date: Sun, 14 Aug 2011 21:59:55 +0200 Message-ID: <4E48293B.5050209@stud.tu-ilmenau.de> References: <4E43F2C3.9000808@computerix.info> <4E4434A4.7010808@interlog.com> <4E449BB1.3060300@interlog.com> <4E44D348.30003@stud.tu-ilmenau.de> <4E452DC7.7060004@interlog.com> Reply-To: stefan.huebner@stud.tu-ilmenau.de Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from wega.rz.tu-ilmenau.de ([141.24.4.159]:36701 "EHLO wega.rz.tu-ilmenau.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755139Ab1HNUAb (ORCPT ); Sun, 14 Aug 2011 16:00:31 -0400 In-Reply-To: <4E452DC7.7060004@interlog.com> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: dgilbert@interlog.com Cc: "Prof. Dr. Klaus Kusche" , linux-scsi@vger.kernel.org Hi Doug, that indeed is right - it's kind of a pita and took me some time to mak= e a well-suited DOS-bootstick for basic hardware initialization... But actually Supermicro.nl at least provides good support and how-to's (via mail if you ask support@supermicro.nl). And there should have bee a correct script for flashing from IR to IT (including the erase-option= , if you took the Supermicro-package). Cheers, Stefan Am 12.08.2011 15:42, schrieb Douglas Gilbert: > Stefan, > My test was done with IT firmware. >=20 > Actually I switched from IR (initiator raid?) to IT > (initiator target) firmware in the process of upgrading > from 9 to 10. [Wouldn't it be great if someone would > hookup these controllers in target mode to the Linux > kernel's new target infrastructure.] >=20 > As far as I have seen, most LSI SAS HBAs come with IR > firmware on them. Switching IR to IT firmware with > their sas2flash tool is a bit of a pain. First sas2flash > didn't work on a AMD 64 bit platform (DOS to the rescue), > then it refuses to load IT over IR firmware. The latter > problem is solved by clearing the flash ("-o -e 6" was > the magic for the clear (in the past when I did > "-o -e 7" I had to program the controller's SAS address > back in by hand)). >=20 > Doug Gilbert >=20 >=20 > On 11-08-12 03:16 AM, Stefan /*St0fF*/ H=FCbner wrote: >> Douglas, >> >> have you double-checked to use the IT (Initiator Mode) Firmware from >> LSI? I mean we build up systems based on the X8SI6-F mainboard from >> Supermicro which has a LSI SAS2008 with 8 Lanes on-board. If using >> HW-RAID (Modes 0, 1, 1E, ...) on those, we have to flash the "IR" >> firmware. If using the chip as HBA for Linux software RAID, we flas= h >> the "IT" firmware, and if the customer needs HW-RAID5-Support, they = get >> an extra chip onto the board and we have to flash "iMR" firmware... >> >> So you have 3 different firmware versions. IT would be the way to g= o >> here... >> >> Greets, >> Stefan >> >> Am 12.08.2011 05:19, schrieb Douglas Gilbert: >>> On 11-08-11 03:59 PM, Douglas Gilbert wrote: >>>> On 11-08-11 11:18 AM, Prof. Dr. Klaus Kusche wrote: >>>>> I'm looking for ways to hook up fast 6 Gb/s SATA SSD's (non-RAID!= ) >>>>> to (server or i-X58) mainboards which do not have native 6 Gb/s S= ATA. >>>>> >>>>> From the reviews I've read so far, two things became obvious: >>>>> * The SSD's I'm looking at really want a working SATA TRIM comman= d. >>>>> * All the onboard Marvell 88SE9128 (or ASmedia) solutions >>>>> seriuosly lack performance, as do PCIe cards based on those chips= =2E >>>>> >>>>> So basically, there seem to be two choices: >>>>> 1.) LSI 2008 >>>>> 2.) Marvell 9485 >>>>> >>>>> 1.) seems to be fast, reliable and well-supported, >>>>> but as far as I can tell, it doesn't support TRIM at all: >>>>> It neither maps SCSI unmap to SATA TRIM, >>>>> nor accepts TRIM as a SATA passthrough command. >>>>> >>>>> Is that true? >>>> >>>> What counts in Linux for "trim" support on a SSD (SATA, >>>> SAS or FC) is correctly processing the SCSI WRITE SAME (16) >>>> with the UNMAP bit set. In the case of a SATA SSD, a SCSI >>>> to ATA Translation Layer (SATL) should map that SCSI WRITE >>>> SAME (16) with the UNMAP bit set to the ATA DATA SET >>>> MANAGEMENT command with the TRIM attribute set. >>>> >>>> Many Linux SATA low level drivers use libata which >>>> implements the above mapping. However some SAS HBAs >>>> (e.g. LSI MPT Fusion 3 and 6 Gbps) implement the SATL >>>> in their own HBA firmware. >>>> >>>> I tested a LSI SAS 9212-4i4e HBA running its most recent >>>> firmware (9.0 from Feb 26, 2011) with a Intel SSDSA2M080 >>>> which does support trim. I used my ddpt utility and the >>>> SCSI WRITE SAME (16) with the UNMAP bit set was rejected >>>> as an "illegal request". With the UNMAP bit clear it >>>> accepted the command. I also checked the SCSI UNMAP >>>> command and it was also rejected. >>>> >>>> LSI have some more work to do on their firmware. >>> >>> I did check the LSI support page for my HBA just before sending >>> my original reply. And the version 9 firmware was showing at the >>> top of the list. Alas, that page had been alpha sorted on the >>> file names so that version 10 of the firmware (May 2011) was >>> hiding further down the page :-) >>> >>> So I installed the newest firmware and redid the above tests. >>> Now the SCSI WRITE SAME (16) with the UNMAP bit set works on >>> that SSD. The SCSI UNMAP command was rejected and I did not >>> test sending the ATA DATA SET MANAGEMENT command through >>> the pass-through (but I expect that would work). >>> >>> So Linux file systems will be able "discard" (=3D"unmap"(SCSI); >>> =3D"trim"(ATA)) data using LSI HBAs based the LSI 2008 chip >>> which are running recent firmware. >>> >>> Doug Gilbert >>> >>>>> I didn't find much about 2.) >>>>> * The only cards based on this chip are the HighPoint 27xx, >>>>> or did I miss something? >>>>> * Running a 27xx with the mvsas driver was reported to have stabi= lity >>>>> problems or random errors. Are these problems solved? >>>>> * Is the 27xx fast (with SATA SSD's& mvsas driver), >>>>> i.e. significantly faster than onboard SATA 3 Gb/s ports? >>>>> * Does the 27xx+mvsas support TRIM when connected to SATA drives? >>>>> >>>>> Are there any other solutions? >>> >>> --=20 >>> To unsubscribe from this list: send the line "unsubscribe linux-scs= i" in >>> the body of a message to majordomo@vger.kernel.org >>> More majordomo info at http://vger.kernel.org/majordomo-info.html >> >> >=20 -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html