From shay at opensfs.org Thu Mar 1 17:29:53 2012 From: shay at opensfs.org (Shay Seager) Date: Thu, 1 Mar 2012 09:29:53 -0800 Subject: [cdwg] LUG Program Announced Message-ID: Hello Lustre Community! The LUG committee is happy to announce that we have just published the LUG Program. Please follow this link http://www.opensfs.org/lug/program to see what all the excitement is about. Don't forget to register by March 9th to ensure early bird pricing and hotel room discounts! Register here: http://www.opensfs.org/lug/registration. We look forward to seeing you at LUG! - - - Shay Seager Open SFS Secretary www.opensfs.org (925) 290-7641 shay at opensfs.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From pjones at whamcloud.com Fri Mar 2 14:43:52 2012 From: pjones at whamcloud.com (Peter Jones) Date: Fri, 02 Mar 2012 06:43:52 -0800 Subject: [cdwg] Lustre 2.2 update - March 2nd 2012 Message-ID: <4F50DCA8.2070308@whamcloud.com> Hi there Here is an update on the Lustre 2.2 release. Testing ======= -Testing has been ongoing on the 2.1.56 tag -Hyperion scale performance testing has shown favourable results comparing 2.2 vs 2.1.1; apples to applies comparisons with 1.8.7 are harder because RHEL6 servers are not supported on 1.8.x and 2.2 does not support RHEL5 servers but we are exploring options -We were able to use a test cluster onsite at Juelich in order to complete large LUN testing for 2.1.56 Blockers ======== -At the time of writing we are down to 4 blockers - see http://jira.whamcloud.com/secure/IssueNavigator.jspa?mode=hide&requestId=10184 for details Other ===== -Expect to branch b2_2 shortly which will open up master for 2.3 landings We will continue to provide periodic updates on our progress on this release. In the meantime, you can always see the landings as they happen at http://git.whamcloud.com/?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master and follow the patch reviews and testing at http://review.whamcloud.com/#q,status:open+project:fs/lustre-release+branch:master,n,z Regards Peter -- Peter Jones Whamcloud, Inc. www.whamcloud.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From hamilton5 at llnl.gov Wed Mar 7 18:24:51 2012 From: hamilton5 at llnl.gov (Hamilton, Pam) Date: Wed, 7 Mar 2012 10:24:51 -0800 Subject: [cdwg] Agenda items for next OpenSFS CDWG call Message-ID: Hi all, I am planning to hold an OpenSFS Community Development Working Group call next Wednesday, 3/14, at 9am Pacific. Please send me any agenda items you have. Regards, Pam ___________________________________ Pam Hamilton Lawrence Livermore National Lab P.O. Box 808, L-556 Livermore, CA  94551-9900 E-Mail:  pgh at llnl.gov Phone:  925-423-1332          Fax:  925-423-8719 From hamilton5 at llnl.gov Sat Mar 10 03:52:55 2012 From: hamilton5 at llnl.gov (Hamilton, Pam) Date: Fri, 9 Mar 2012 19:52:55 -0800 Subject: [cdwg] OpenSFS Community Development WG call Wednesday, 3/14, at 9am Pacific Message-ID: When: Wednesday, March 14, 2012 9:00 AM-10:00 AM (UTC-08:00) Pacific Time (US & Canada). Where: Call-in: 866-914-3976 (925-424-8105) Passcode: 534986# Note: The GMT offset above does not reflect daylight saving time adjustments. *~*~*~*~*~*~*~*~*~* Hi all, We will have an OpenSFS Community Development Working Group conference call on 3/14 at 9am Pacific. Call-in: 866-914-3976 (925-424-8105) Passcode: 534986# Please send me any agenda items you might have. Here is my list so far: Agenda: * Agenda ideas for the CDWG meeting at LUG which will be held Wednesday, 4/25, in the afternoon * Open discussion Regards, Pam ___________________________________ Pam Hamilton Lawrence Livermore National Lab P.O. Box 808, L-556 Livermore, CA 94551-9900 E-Mail: pgh at llnl.gov Phone: 925-423-1332 Fax: 925-423-8719 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/calendar Size: 2450 bytes Desc: not available URL: From spitzcor at cray.com Wed Mar 14 16:08:38 2012 From: spitzcor at cray.com (Cory Spitz) Date: Wed, 14 Mar 2012 11:08:38 -0500 Subject: [cdwg] Fwd: [Twg] OpenSFS Test Cluster Configuration Message-ID: <4F60C286.1030504@cray.com> FYI: Proposed OpenSFS Test Cluster Configuration -------- Original Message -------- Subject: [Twg] OpenSFS Test Cluster Configuration Date: Thu, 8 Mar 2012 13:04:00 -0500 From: Joshua Walgenbach To: twg at lists.opensfs.org -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 All, Here is all the deliverable items for the OpenSFS test cluster for a discussion of concerns. Thanks, - -Josh - ---------------------------------------------------------------- 6 X Test Client Cluster (Client Nodes; 2U per 4 nodes, blade type) FT-E5620SXi/2UQ, Intel Single Xeon E5620 2.4GHz 2U-Quad Nodes Including: * (1) SM 2U 6026TT-HiBQRF 2U Quad Nodes * (4) sets of 1 x Intel E5620 2.4GHz Westmere (Total 4 Cores) * (4) sets of 1 x Copper Base CP0217 CPU Cooler 1U with Heat Pipe * (4) sets of 32GB DDRIII 1333MHz ECC/REG - (4x8GB Modules Installed) * (4) sets of On Board Dual 10/100/1000T Ports * (4) sets of On Board VGA * (4) sets of On Board IPMI 2.0 Via 3rd. Lan * (4) sets of 1 x 500GB SATA Enterprises 24x7 * (4) sets of 3 x Hot Swap Drive Bays for SATA/SAS * (4) sets of PCi-e Slots 8X * (4) sets of QDR 40GB QSFP to QSFP iB Cables * (4) sets of Mellanox QDR 40GB QSFP Port - Embedded * (1) Platinum level 1400W redundant Power * (1) UL (NRTL) Certified Power Supply/System * 3 years Warranty Parts and Labor Fully Warranty - ---------------------------------------------------------------- 4 X Test Server Nodes (MDS server nodes) FT-E5620DXi/2U, Intel Single Xeon E5620 2.4GHz 2U Including: * (1) SM X8DTH-iF Motherboard * (2) Intel E5620 2.4GHz Westmere (Total 8 Cores) * (2) Copper Base CP0217 CPU Cooler 1U with Heat Pipe * (1) 64GB DDRIII 1333MHz ECC/REG - (8x8GB Modules Installed) * (1) On Board Dual 10/100/1000T Ports * (1) On Board VGA * (1) On Board IPMI 2.0 Via 3rd. Lan * (1) 500GB SATA Enterprises 24x7 * (1) 40GB SSD OCZ SATA * (8) Hot Swap Drive Bays for SATA/SAS * (6) PCi-e Slots 8X * (1) QDR 40GB QSFP to QSFP iB Cables * (1) Mellanox QDR 40GB QSFP Single Port * (2) LCI 9200-8E 2xSAS External Ports to Storage * (4) SAS Cables for Storage * (1) Platinum level 720W redundant Power * (1) Set of Screw Free Drop-in Rails * (1) UL (NRTL) Certified Power Supply/System * 3 years Warranty Parts and Labor Fully Warranty - ---------------------------------------------------------------- 4 X Shared Storage Devices for MDS (1 per MDS server node, and by Pair) Including: * (1) Infortrend DSS12SR2240MB-0A30 SAS-to-SAS/SATA 2U/12-bay Redundant RAID, Data Service Option, 4 x SAS-6G ports, SAS-6G Exp, ASIC667, 4GB, BBU * (2) Intel 710 Enterprises 100GB SSD * (10) Toshiba 2TB SAS II 6GB/s 24x7 Enterprises * 3 years Warranty Parts and Labor Fully Warranty - ---------------------------------------------------------------- 4 X OSS server ndoes FT-E5620DXi/2U, Intel Single Xeon E5620 2.4GHz 2U Including: * (1) SM X8DTH-iF Motherboard * (2) Intel E5620 2.4GHz Westmere (Total 8 Cores) * (2) Copper Base CP0217 CPU Cooler 1U with Heat Pipe * (1) 64GB DDRIII 1333MHz ECC/REG - (8x8GB Modules Installed) * (1) On Board Dual 10/100/1000T Ports * (1) On Board VGA * (1) On Board IPMI 2.0 Via 3rd. Lan * (1) 500GB SATA Enterprises 24x7 * (1) 40GB SSD OCZ SATA * (8) Hot Swap Drive Bays for SATA/SAS * (6) PCi-e Slots 8X * (1) QDR 40GB QSFP to QSFP iB Cables * (1) Mellanox QDR 40GB QSFP Single Port * (2) LCI 9200-8E 2xSAS External Ports to Storage * (4) SAS Cables for Storage * (1) Platinum level 720W redundant Power * (1) Set of Screw Free Drop-in Rails * (1) UL (NRTL) Certified Power Supply/System * 3 years Warranty Parts and Labor Fully Warranty - ---------------------------------------------------------------- 4 X Shared Storage Devices for MDS (1 per OSS server node) Including: Including: * (1) Infortrend DSS12SR2240MB-0A30 SAS-to-SAS/SATA 2U/12-bay Redundant RAID, Data Service Option, 4 x SAS-6G ports, SAS-6G Exp, ASIC667, 4GB, BBU * (1) DSS12SJ2000R-0A32 SAS-to-SAS/SATA 2U/12-bay Redundant JBOD for EonStor DS, 4 x SAS-6G ports. * (4) Intel 710 Enterprises 100GB SSD * (20) Toshiba 2TB SAS II 6GB/s 24x7 Enterprises * 3 years Warranty Parts and Labor Fully Warranty - ---------------------------------------------------------------- 1 X Head Node FT-E5620SXi/1U, Intel Single Xeon E5620 2.4GHz 1U Including: * (1) Intel E5620 2.4GHz Westmere (Total 4 Cores) * (1) Copper Base CP0217 CPU Cooler 1U with Heat Pipe * (1) 24GB DDRIII 1333MHz ECC - (6x4GB Modules Installed) * (1) On Board Dual 10/100/1000T Ports * (1) On Board VGA * (1) On Board IPMI 2.0 Via 3rd. Lan * (1) 500GB SATA Enterprises 24x7 * (2) Hot Swap Drive Bays for SATA/SAS * (1) PCi-e Slots 8X * (1) Platinum level 450W redundant Power * (1) Set of Screw Free Drop-in Rails * (1) UL (NRTL) Certified Power Supply/System * 3 years Warranty Parts and Labor Fully Warranty - ---------------------------------------------------------------- 1 X Avocent 6048AC, 48 Ports Console 1U Server with 48 DB9 to RJ45 Adapter and Cat5e Cables - ---------------------------------------------------------------- 2 X NetGear 48 Ports 10/100/1000T Gige Switch with 48 Cat5e cables - ---------------------------------------------------------------- 1 X InfiniScale IV QDR InfiniBand Switch, 1U, 36 QSFP ports, 1 Power Supply, Managed (PPC405EXR), PSU side to connector side airflow, Standard depth, Rail Kit - ---------------------------------------------------------------- 1 X 1U 17" LCD Rack Mount with KB and Mouse PS/2 or USB- connect to Head node - ---------------------------------------------------------------- 2 X APC NetShelter SX AR3347 Enclosure Rack Cabinet NETSHELTER SX 48U 750X1200MM NETWORKING ENCLOSURE W/ SIDES BLACK - ---------------------------------------------------------------- 8 X PDU: CS-24VD-L30M; Smart CDU, 0U, 24 x IEC C13 Outlets, 3 x LED amp meters, 208V 3-Phase Delta input w/ NEMA L15-30P connector & cord, 10ft (3m), (2) Temperature/Humidity Sensor Capable, with retractable fuses -----BEGIN PGP SIGNATURE----- Version: GnuPG/MacGPG2 v2.0.16 (Darwin) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk9Y9JAACgkQcqyJPuRTYp/IaACfXxu/DTke4dW4vaWL0Zhk6A+l 5HIAnicphwoOAAlKhi0MyfUCq97O77jL =uyvN -----END PGP SIGNATURE----- _______________________________________________ twg mailing list twg at lists.opensfs.org http://lists.opensfs.org/listinfo.cgi/twg-opensfs.org From pjones at whamcloud.com Fri Mar 16 14:29:52 2012 From: pjones at whamcloud.com (Peter Jones) Date: Fri, 16 Mar 2012 07:29:52 -0700 Subject: [cdwg] Lustre 2.2 update - March 16th 2012 Message-ID: <4F634E60.9000203@whamcloud.com> Hi there Here is an update on the Lustre 2.2 release. Testing ======= -RC1 was tagged this week and release testing has commenced on Toro, Hyperion, IU and Juelich test clusters -Further test automation work was completed since the last update; the results of this work should be viewable early next week at https://maloo.whamcloud.com/reports/show_pass_rate_report?only_tagged_versions%3F=true&source_code_branch=13dc103e-6786-11e1-bd1c-5254004bbbd3 when the first of the full test runs on RC1 complete -As per the discussion on the CDWG call this week I have attached the 2.2 test plan for interested parties to review; please note that this document was originally created for internal use only so there are some internal wiki links referenced; these links are largely now redundant as the scripts to run the tests have been landed to the tree (or will be soon for the test automation still under development) Blockers ======== -At the time of writing we are investigating 1 test failure on Hyperion (LU-1222) which may or may not end up being a blocker - see http://jira.whamcloud.com/secure/IssueNavigator.jspa?mode=hide&requestId=10184 for details Other ===== We will continue to provide periodic updates on our progress on this release. In the meantime, you can always see the landings as they happen at http://git.whamcloud.com/?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b2_2 and follow the patch reviews and testing at http://review.whamcloud.com/#q,status:open+project:fs/lustre-release+branch:master,n,z Regards Peter -- Peter Jones Whamcloud, Inc. www.whamcloud.com -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Lustre2.2TestPlan.pdf Type: application/pdf Size: 152008 bytes Desc: not available URL: From hamilton5 at llnl.gov Fri Mar 23 20:07:01 2012 From: hamilton5 at llnl.gov (Hamilton, Pam) Date: Fri, 23 Mar 2012 13:07:01 -0700 Subject: [cdwg] Canceled: OpenSFS Community Development WG call Message-ID: When: Wednesday, March 28, 2012 9:00 AM-10:00 AM (UTC-08:00) Pacific Time (US & Canada). Where: Call-in: 866-914-3976 (925-424-8105) Passcode: 534986# Note: The GMT offset above does not reflect daylight saving time adjustments. *~*~*~*~*~*~*~*~*~* Hi all, This is the bi-weekly conference call of the OpenSFS Community Development Working Group. This working group was formed to facilitate a discussion about a community development model for Lustre, taking into consideration the needs/concerns of Lustre vendors. For this to be successful, it's important to have vendor participation. Regards, Pam -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/calendar Size: 2887 bytes Desc: not available URL: From shay at opensfs.org Tue Mar 27 19:02:50 2012 From: shay at opensfs.org (Shay Seager) Date: Tue, 27 Mar 2012 09:02:50 -1000 Subject: [cdwg] LUG is just around the corner, are you ready? Message-ID: Hello All, LUG 2012 is less than a month away; April 23rd-April 25th. We recommend you fly in Sunday April 22nd in the morning because we have some great events for you on Sunday: April 22, 2012 2:00-5:00pm the Benchmarking Work Group will be holding our first face to face meeting. The “Benchmarking Work Group” will focus on identifying and defining I/O workloads for the various Lustre markets, and then define IO generation benchmarking tools that best emulates those workloads. You are invited to help contribute to this important initiative. Pre LUG 2012 Party Sponsored by DataDirect Networks and Whamcloud The annual Lustre User Group is being held in Austin, TX, this year, with all the great Lustre developers, users and vendors in attendance. If you’re coming, you know some of the best connections are made outside of the talks. DDN and Whamcloud are providing beers & wine to help get it started. Come to Zax Restaurant & Bar, right next to the Hyatt Regency where LUG will be held, to kick off the week in a relaxed atmosphere. No hype, no pressure, just lots of local beers, wine and Lustre superstars. We’re closing the restaurant down, it’s just us from 7pm – 10pm. Hope to see you there! Location: Zax Restaurant & Bar 312 Barton Springs Rd, Austin, TX 78704 (across from the Hyatt Regency) Date/Time: Sun, April 22, 7-10pm RSVP: Are you kidding? Just come on by. On Wednesday we will also have 3 events hosted by OpenSFS, everyone is encouraged to attend, we recommend that you set your flights for Wednesday evening or Thursday morning (note, there are government rate rooms on Wednesday night, so book them now before they are all gone): 1pm – 2pm OpenSFS General Meeting 2pm-3pm OpenSFS Technical Working Group Meeting 3pm-4pm OpenSFS Community Development Working Group Meeting Check out our website for the whole program http://www.opensfs.org/lug/program If you have not registered your ticket, your hotel room, or your shuttle follow this link http://www.opensfs.org/lug/registration for all the resources you need to get discounted room rates and shuttle services. At LUG we will have 2 break out rooms that will be available 24-7 throughout the event and are available for private meetings and break-out sessions. Each room holds 20-30 people. If you would like to reserve room space, please reply to this e-mail (Shay Seager) with your preferred time/date. We want to make sure that this is the best LUG you have experienced, so please reply to this e-mail (to Shay Seager) to let us know if you have any dietary or special needs. (note - our menu already accommodates special diets such as vegan, vegetarian, paleo, and atkins) We also want to thank our generous sponsors: Bright Computing, Bull, Cray, DDN, Dell, EMC, Intel, Net App, RAID Inc., SGI, Terascala, Whamcloud, Xyratex. Best, Shay - - - Shay Seager Open SFS Secretary www.opensfs.org (925) 290-7641 shay at opensfs.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From pjones at whamcloud.com Fri Mar 30 14:31:36 2012 From: pjones at whamcloud.com (Peter Jones) Date: Fri, 30 Mar 2012 07:31:36 -0700 Subject: [cdwg] Lustre 2.2.0 released Message-ID: <4F75C3C8.8000207@whamcloud.com> Hi there I am pleased to announce that Lustre 2.2.0 has been declared GA and is available for download at http://downloads.whamcloud.com/public/lustre/lustre-2.2.0/. Release Highlights -Asynchronous Glimpse Lock/Statahead (LU925/LU389) Improved performance accessing object attributes (file sizes/xtime etc) -Client Parallel Checksums (LU884) Improved support for mmap and better performance using checksums -Imperative Recovery (LU580) Faster recovery -Large Xattrs (LU80) Maximum stripe size raised from 160 to 2000 -Parallel Directory Operations (LU50) Improved performance when multiple processes access the same directory in parallel Changelog details available at *http://wiki.whamcloud.com/display/PUB/Changelog+2.2* Please log any issues found at http://jira.whamcloud.com Regards Peter -- Peter Jones Whamcloud, Inc. www.whamcloud.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From pjones at whamcloud.com Fri Mar 30 15:38:11 2012 From: pjones at whamcloud.com (Peter Jones) Date: Fri, 30 Mar 2012 08:38:11 -0700 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> References: <4F75C3C8.8000207@whamcloud.com> <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> Message-ID: <4F75D363.20008@whamcloud.com> Hi Alexey Thanks for your interest in the 2.2 release. The issue that you mention was of course reviewed and, despite being reported after the code freeze with testing at an advanced stage we would have included a fix for it if it was relevant for production systems but it is only possible to hit this issue when running with kernel debug options on so we decided it was ok to defer it until after 2.2 was GA. Please note that this issue has been marked as low priority rather than a blocker and was not mentioned as a possible blocker in my last update two weeks ago. If you ever see something that you think should be urgent then I encourage you to speak up promptly so that we have time to fix it before the release goes out (if need be). Regards Peter On 12-03-30 7:54 AM, Alexey Lyashkov wrote: > Peter, > > that is good work but why released with know panics in new code? > what about http://jira.whamcloud.com/browse/LU-1188 ? > it's isn't fixed but produce a panic on each sanity run. > > > On Mar 30, 2012, at 18:31, Peter Jones wrote: > >> Hi there >> >> I am pleased to announce that Lustre 2.2.0 has been declared GA and >> is available for download at >> http://downloads.whamcloud.com/public/lustre/lustre-2.2.0/. >> >> >> Release Highlights >> >> -Asynchronous Glimpse Lock/Statahead (LU925/LU389) Improved >> performance accessing object attributes (file sizes/xtime etc) >> -Client Parallel Checksums (LU884) Improved support for mmap and >> better performance using checksums >> -Imperative Recovery (LU580) Faster recovery >> -Large Xattrs (LU80) Maximum stripe size raised from 160 to 2000 >> -Parallel Directory Operations (LU50) Improved performance when >> multiple processes access the same directory in parallel >> >> Changelog details available at >> *http://wiki.whamcloud.com/display/PUB/Changelog+2.2* >> >> Please log any issues found at http://jira.whamcloud.com >> >> Regards >> >> Peter >> -- >> Peter Jones >> Whamcloud, Inc. >> www.whamcloud.com > -- Peter Jones Whamcloud, Inc. www.whamcloud.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From pjones at whamcloud.com Fri Mar 30 16:13:52 2012 From: pjones at whamcloud.com (Peter Jones) Date: Fri, 30 Mar 2012 09:13:52 -0700 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: References: <4F75C3C8.8000207@whamcloud.com> Message-ID: <4F75DBC0.6010304@whamcloud.com> Ah yes - thanks for the reminder. I have updated this now. On 12-03-30 8:52 AM, Pawel Dziekonski wrote: > 2012/3/30 Peter Jones: >> Hi there >> >> I am pleased to announce that Lustre 2.2.0 has been declared GA and is > Hi, > > could you please update > http://wiki.whamcloud.com/display/PUB/Lustre+Releases > ? > > thanks in advance, Pawel > -- Peter Jones Whamcloud, Inc. www.whamcloud.com From pjones at whamcloud.com Fri Mar 30 16:42:44 2012 From: pjones at whamcloud.com (Peter Jones) Date: Fri, 30 Mar 2012 09:42:44 -0700 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <368A62A6-7E32-41E2-B8B7-894E07A4F26D@xyratex.com> References: <4F75C3C8.8000207@whamcloud.com> <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> <4F75D363.20008@whamcloud.com> <368A62A6-7E32-41E2-B8B7-894E07A4F26D@xyratex.com> Message-ID: <4F75E284.8070003@whamcloud.com> Alexey I am sorry if my explanation was not clear enough. The decision was taken to not classify this as a blocker because the issue only occurs when running kernel debug options. The engineers in the triage process considered this not to be a common scenario for production usage. As such it was decided it would be better to have the release be on time for the majority and know that anyone needing to run kernel debug options would be able to apply a simple patch to do so. The kind of logic applied to determining blockers for Lustre releases has been unchanged for many years. Regards Peter On 12-03-30 8:46 AM, Alexey Lyashkov wrote: > Peter, > > you don't answer to the question - why WC make a reese with know panic? > make a stable release with know panics was unacceptable situation in past. > any new code which isn't fixed before release and have a know panic > was reverted from a release in past.. > but it's looks changed now? > so We need to assume WC able name as release a code with know panic? > Anyway - 2.2.0 isn't acceptable to run for me until that panic isn't > fixed because i hit it panic on each run. > > On Mar 30, 2012, at 19:38, Peter Jones wrote: > >> Hi Alexey >> >> Thanks for your interest in the 2.2 release. >> >> The issue that you mention was of course reviewed and, despite being >> reported after the code freeze with testing at an advanced stage we >> would have included a fix for it if it was relevant for production >> systems but it is only possible to hit this issue when running with >> kernel debug options on so we decided it was ok to defer it until >> after 2.2 was GA. >> >> Please note that this issue has been marked as low priority rather >> than a blocker and was not mentioned as a possible blocker in my last >> update two weeks ago. If you ever see something that you think should >> be urgent then I encourage you to speak up promptly so that we have >> time to fix it before the release goes out (if need be). >> >> Regards >> >> Peter >> >> On 12-03-30 7:54 AM, Alexey Lyashkov wrote: >>> Peter, >>> >>> that is good work but why released with know panics in new code? >>> what about http://jira.whamcloud.com/browse/LU-1188 ? >>> it's isn't fixed but produce a panic on each sanity run. >>> >>> >>> On Mar 30, 2012, at 18:31, Peter Jones wrote: >>> >>>> Hi there >>>> >>>> I am pleased to announce that Lustre 2.2.0 has been declared GA and >>>> is available for download at >>>> http://downloads.whamcloud.com/public/lustre/lustre-2.2.0/. >>>> >>>> >>>> Release Highlights >>>> >>>> -Asynchronous Glimpse Lock/Statahead (LU925/LU389) Improved >>>> performance accessing object attributes (file sizes/xtime etc) >>>> -Client Parallel Checksums (LU884) Improved support for mmap and >>>> better performance using checksums >>>> -Imperative Recovery (LU580) Faster recovery >>>> -Large Xattrs (LU80) Maximum stripe size raised from 160 to 2000 >>>> -Parallel Directory Operations (LU50) Improved performance when >>>> multiple processes access the same directory in parallel >>>> >>>> Changelog details available at >>>> *http://wiki.whamcloud.com/display/PUB/Changelog+2.2* >>>> >>>> Please log any issues found at http://jira.whamcloud.com >>>> >>>> Regards >>>> >>>> Peter >>>> -- >>>> Peter Jones >>>> Whamcloud, Inc. >>>> www.whamcloud.com >>> >> >> -- >> Peter Jones >> Whamcloud, Inc. >> www.whamcloud.com > -- Peter Jones Whamcloud, Inc. www.whamcloud.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From morrone2 at llnl.gov Fri Mar 30 18:44:33 2012 From: morrone2 at llnl.gov (Christopher J. Morrone) Date: Fri, 30 Mar 2012 11:44:33 -0700 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <4F75E284.8070003@whamcloud.com> References: <4F75C3C8.8000207@whamcloud.com> <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> <4F75D363.20008@whamcloud.com> <368A62A6-7E32-41E2-B8B7-894E07A4F26D@xyratex.com> <4F75E284.8070003@whamcloud.com> Message-ID: <4F75FF11.80000@llnl.gov> It sounds to me like the decision to not mark the issue a blocker is reasonable give the information I have seen (i.e., only and issue with debug kernels). While a panic is more likely to be a blocker, it should not necessarily be a guarantee. We do need to consider other factors, and holding to our release schedule is important. It would be fairly easy to delay releases for untold months if a panic automatically blocked releases. A panic that will effect all production users should obviously be a blocker. A panic that only effects a development environment with a debug kernel is not automatically a blocker. I think that it would have been helpful to record that decision in the ticket. Otherwise the Alexey and the rest of us have little visibility into the process, which can lead to unnecessary frustration. Chris On 03/30/2012 09:42 AM, Peter Jones wrote: > Alexey > > I am sorry if my explanation was not clear enough. > > The decision was taken to not classify this as a blocker because the issue only occurs when running kernel debug options. > > The engineers in the triage process considered this not to be a common scenario for production usage. > > As such it was decided it would be better to have the release be on time for the majority and know that anyone needing to run kernel debug options would be able to apply a simple patch to do so. > > The kind of logic applied to determining blockers for Lustre releases has been unchanged for many years. > > Regards > > Peter From pjones at whamcloud.com Fri Mar 30 22:35:53 2012 From: pjones at whamcloud.com (Peter Jones) Date: Fri, 30 Mar 2012 15:35:53 -0700 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <4F75FF11.80000@llnl.gov> References: <4F75C3C8.8000207@whamcloud.com> <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> <4F75D363.20008@whamcloud.com> <368A62A6-7E32-41E2-B8B7-894E07A4F26D@xyratex.com> <4F75E284.8070003@whamcloud.com> <4F75FF11.80000@llnl.gov> Message-ID: <4F763549.9090507@whamcloud.com> Hi Chris I think that this thread is going to turn rather process-oriented. Perhaps we should discuss this on the next CDWG call. Peter On 12-03-30 11:44 AM, Christopher J. Morrone wrote: > It sounds to me like the decision to not mark the issue a blocker is > reasonable give the information I have seen (i.e., only and issue with > debug kernels). While a panic is more likely to be a blocker, it > should not necessarily be a guarantee. We do need to consider other > factors, and holding to our release schedule is important. > > It would be fairly easy to delay releases for untold months if a panic > automatically blocked releases. A panic that will effect all > production users should obviously be a blocker. A panic that only > effects a development environment with a debug kernel is not > automatically a blocker. > > I think that it would have been helpful to record that decision in the > ticket. Otherwise the Alexey and the rest of us have little > visibility into the process, which can lead to unnecessary frustration. > > Chris > > On 03/30/2012 09:42 AM, Peter Jones wrote: >> Alexey >> >> I am sorry if my explanation was not clear enough. >> >> The decision was taken to not classify this as a blocker because the >> issue only occurs when running kernel debug options. >> >> The engineers in the triage process considered this not to be a >> common scenario for production usage. >> >> As such it was decided it would be better to have the release be on >> time for the majority and know that anyone needing to run kernel >> debug options would be able to apply a simple patch to do so. >> >> The kind of logic applied to determining blockers for Lustre releases >> has been unchanged for many years. >> >> Regards >> >> Peter > _______________________________________________ > cdwg mailing list > cdwg at lists.opensfs.org > http://lists.opensfs.org/listinfo.cgi/cdwg-opensfs.org > -- Peter Jones Whamcloud, Inc. www.whamcloud.com From carrier at cray.com Fri Mar 30 22:57:56 2012 From: carrier at cray.com (John Carrier) Date: Fri, 30 Mar 2012 22:57:56 +0000 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <4F763549.9090507@whamcloud.com> References: <4F75C3C8.8000207@whamcloud.com> <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> <4F75D363.20008@whamcloud.com> <368A62A6-7E32-41E2-B8B7-894E07A4F26D@xyratex.com> <4F75E284.8070003@whamcloud.com> <4F75FF11.80000@llnl.gov> <4F763549.9090507@whamcloud.com> Message-ID: Peter, I think that is a great suggestion. Thanks, --jc -----Original Message----- From: cdwg-bounces at lists.opensfs.org [mailto:cdwg-bounces at lists.opensfs.org] On Behalf Of Peter Jones Sent: Friday, March 30, 2012 3:36 PM To: cdwg at lists.opensfs.org; wc-discuss at whamcloud.com Subject: Re: [cdwg] [wc-discuss] Lustre 2.2.0 released Hi Chris I think that this thread is going to turn rather process-oriented. Perhaps we should discuss this on the next CDWG call. Peter On 12-03-30 11:44 AM, Christopher J. Morrone wrote: > It sounds to me like the decision to not mark the issue a blocker is > reasonable give the information I have seen (i.e., only and issue with > debug kernels). While a panic is more likely to be a blocker, it > should not necessarily be a guarantee. We do need to consider other > factors, and holding to our release schedule is important. > > It would be fairly easy to delay releases for untold months if a panic > automatically blocked releases. A panic that will effect all > production users should obviously be a blocker. A panic that only > effects a development environment with a debug kernel is not > automatically a blocker. > > I think that it would have been helpful to record that decision in the > ticket. Otherwise the Alexey and the rest of us have little > visibility into the process, which can lead to unnecessary frustration. > > Chris > > On 03/30/2012 09:42 AM, Peter Jones wrote: >> Alexey >> >> I am sorry if my explanation was not clear enough. >> >> The decision was taken to not classify this as a blocker because the >> issue only occurs when running kernel debug options. >> >> The engineers in the triage process considered this not to be a >> common scenario for production usage. >> >> As such it was decided it would be better to have the release be on >> time for the majority and know that anyone needing to run kernel >> debug options would be able to apply a simple patch to do so. >> >> The kind of logic applied to determining blockers for Lustre releases >> has been unchanged for many years. >> >> Regards >> >> Peter > _______________________________________________ > cdwg mailing list > cdwg at lists.opensfs.org > http://lists.opensfs.org/listinfo.cgi/cdwg-opensfs.org > -- Peter Jones Whamcloud, Inc. www.whamcloud.com _______________________________________________ cdwg mailing list cdwg at lists.opensfs.org http://lists.opensfs.org/listinfo.cgi/cdwg-opensfs.org From alexey_lyashkov at xyratex.com Fri Mar 30 15:46:24 2012 From: alexey_lyashkov at xyratex.com (Alexey Lyashkov) Date: Fri, 30 Mar 2012 19:46:24 +0400 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <4F75D363.20008@whamcloud.com> References: <4F75C3C8.8000207@whamcloud.com> <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> <4F75D363.20008@whamcloud.com> Message-ID: <368A62A6-7E32-41E2-B8B7-894E07A4F26D@xyratex.com> Peter, you don't answer to the question - why WC make a reese with know panic? make a stable release with know panics was unacceptable situation in past. any new code which isn't fixed before release and have a know panic was reverted from a release in past.. but it's looks changed now? so We need to assume WC able name as release a code with know panic? Anyway - 2.2.0 isn't acceptable to run for me until that panic isn't fixed because i hit it panic on each run. On Mar 30, 2012, at 19:38, Peter Jones wrote: > Hi Alexey > > Thanks for your interest in the 2.2 release. > > The issue that you mention was of course reviewed and, despite being reported after the code freeze with testing at an advanced stage we would have included a fix for it if it was relevant for production systems but it is only possible to hit this issue when running with kernel debug options on so we decided it was ok to defer it until after 2.2 was GA. > > Please note that this issue has been marked as low priority rather than a blocker and was not mentioned as a possible blocker in my last update two weeks ago. If you ever see something that you think should be urgent then I encourage you to speak up promptly so that we have time to fix it before the release goes out (if need be). > > Regards > > Peter > > On 12-03-30 7:54 AM, Alexey Lyashkov wrote: >> >> Peter, >> >> that is good work but why released with know panics in new code? >> what about http://jira.whamcloud.com/browse/LU-1188 ? >> it's isn't fixed but produce a panic on each sanity run. >> >> >> On Mar 30, 2012, at 18:31, Peter Jones wrote: >> >>> Hi there >>> >>> I am pleased to announce that Lustre 2.2.0 has been declared GA and is available for download at http://downloads.whamcloud.com/public/lustre/lustre-2.2.0/. >>> >>> Release Highlights >>> >>> -Asynchronous Glimpse Lock/Statahead (LU925/LU389) Improved performance accessing object attributes (file sizes/xtime etc) >>> -Client Parallel Checksums (LU884) Improved support for mmap and better performance using checksums >>> -Imperative Recovery (LU580) Faster recovery >>> -Large Xattrs (LU80) Maximum stripe size raised from 160 to 2000 >>> -Parallel Directory Operations (LU50) Improved performance when multiple processes access the same directory in parallel >>> >>> Changelog details available at http://wiki.whamcloud.com/display/PUB/Changelog+2.2 >>> >>> Please log any issues found at http://jira.whamcloud.com >>> >>> Regards >>> >>> Peter >>> -- >>> Peter Jones >>> Whamcloud, Inc. >>> www.whamcloud.com >> > > -- > Peter Jones > Whamcloud, Inc. > www.whamcloud.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From alexey_lyashkov at xyratex.com Fri Mar 30 14:54:05 2012 From: alexey_lyashkov at xyratex.com (Alexey Lyashkov) Date: Fri, 30 Mar 2012 18:54:05 +0400 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <4F75C3C8.8000207@whamcloud.com> References: <4F75C3C8.8000207@whamcloud.com> Message-ID: <1310D04D-1D5D-432C-841E-792CBB1CFE64@xyratex.com> Peter, that is good work but why released with know panics in new code? what about http://jira.whamcloud.com/browse/LU-1188 ? it's isn't fixed but produce a panic on each sanity run. On Mar 30, 2012, at 18:31, Peter Jones wrote: > Hi there > > I am pleased to announce that Lustre 2.2.0 has been declared GA and is available for download at http://downloads.whamcloud.com/public/lustre/lustre-2.2.0/. > > Release Highlights > > -Asynchronous Glimpse Lock/Statahead (LU925/LU389) Improved performance accessing object attributes (file sizes/xtime etc) > -Client Parallel Checksums (LU884) Improved support for mmap and better performance using checksums > -Imperative Recovery (LU580) Faster recovery > -Large Xattrs (LU80) Maximum stripe size raised from 160 to 2000 > -Parallel Directory Operations (LU50) Improved performance when multiple processes access the same directory in parallel > > Changelog details available at http://wiki.whamcloud.com/display/PUB/Changelog+2.2 > > Please log any issues found at http://jira.whamcloud.com > > Regards > > Peter > -- > Peter Jones > Whamcloud, Inc. > www.whamcloud.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From dzieko at gmail.com Fri Mar 30 15:52:45 2012 From: dzieko at gmail.com (Pawel Dziekonski) Date: Fri, 30 Mar 2012 17:52:45 +0200 Subject: [cdwg] [wc-discuss] Lustre 2.2.0 released In-Reply-To: <4F75C3C8.8000207@whamcloud.com> References: <4F75C3C8.8000207@whamcloud.com> Message-ID: 2012/3/30 Peter Jones : > Hi there > > I am pleased to announce that Lustre 2.2.0 has been declared GA and is Hi, could you please update http://wiki.whamcloud.com/display/PUB/Lustre+Releases ? thanks in advance, Pawel