Accredited Standards Committee X3, Information Processing Systems Doc. No.: X3T9.2/92-223 R0 Date: November 13, 1992 Project: Ref. Doc.: Reply to: L. Lamers To: Membership of X3T9.2 From: Lawrence J. Lamers, Secretary X3T9.2 George Penokie Chair RAID Study Group Subject: Minutes of RAID November 9, '92 Study Group Meeting Agenda 1. Opening Remarks 2. Attendance and Membership 3. Approval of Agenda 4. Scope 5. New Folks Concerns 6. Existence 7. Call For Paper 8. Meeting Schedule 9. Adjournment Results of Meeting 1. Opening Remarks George Penokie the Chair, called the meeting to order at 5:00 pm, Monday November 9, 1992. He thanked Rich Taborek of Amdahl for hosting the meeting. As is customary, the people attending introduced themselves. A copy of the attendance list was circulated for attendance and corrections. It was stated that the meeting had been authorized by X3T9.2 and would be conducted under the X3 rules. Ad hoc meetings take no final actions, but prepare recommendations for approval by the X3T9.2 task group. The voting rules for the meeting are those of the parent committee, X3T9.2. These rules are: one vote per company; and any participating company member may vote. The minutes of this meeting will be posted to the SCSI BBS and the SCSI Reflector and will be included in the next committee mailing. George stated that this is the first meeting of the RAID study group. The purpose of the group is to deal with interface issues related to using RAIDs. The study group will assess the issues and then formulate a strategy for dealing with them. 2. Attendance and Membership Attendance at working group meetings does not count toward minimum attendance requirements for X3T9.2 membership. Working group meetings are open to any person or company to attend and to express their opinion on the subjects being discussed. The following people attended the meeting: Name Status Organization Phone Number ------------------------- ------ ------------------------------ -------------- Mr. Douglas Fields V Adaptec, Inc. (408) 957-6694 Mr. Shahnad Nadershahi P Amdahl Corp. (408) 944-3767 Mr. Dennis Pak O Apple Computer (408) 974-4874 Mr. Clifford E. Strang P BusLogic (408) 492-9090 Jr. Mr. Charles Monia P Digital Equipment Corp. (508) 841-6757 Mr. Ralph Weber A Digital Equipment Corp. (603) 881-1497 Mr. Edward A. Gardner A Digital Equipment Corp. (719) 548-2247 Mr. William Dallas A Digital Equipment Corp. (603) 881-2508 Mr. I. Dal Allan P ENDL (408) 867-6630 Mr. Howard Grill V Formation (609) 234-5020 x2247 Mr. Jeffrey L. Williams P Hewlett Packard Co. (208) 323-5030 Mr. Paul Boulay O Hitachi Computer Prod Amer (408) 986-9770 x205 Mr. Howard Wang O Hitachi Computer Products (408) 986-9770 x207 Mr. Larry Chen V Hitachi Computer Products (408) 986-9770 Mr. Ebrahim Hashemi V Hitachi Computer Products (408) 986-9770 x122 Mr. John P. Scheible O IBM Corp. (408) 284-7719 Mr. Giles Frazier S IBM Corp. (512) 838-1802 Mr. Tom Taetsch O Intellistor, Inc. (303) 682-6651 Mr. Russ Tuck V MasPar Computer Corp. (408) 736-3300 Mr. Lawrence J. Lamers P Maxtor Corp. (408) 432-3889 Mr. Ron Roberts V Maxtor Corp. (408) 432-3875 Mr. Robbie Shergill P National Semiconductor (408) 721-7959 Mr. John Lohmeyer P NCR Corp. (719) 596-5795 x362 Mr. Rod DeKoning S NCR Corp. (316) 636-8842 Mr. Stephen F. Heil P Panasonic Technologies, Inc (201) 348-7064 Mr. Gene Milligan A Seagate Technology (405) 324-3070 Mr. Forrest Crowell P SGS-Thomson Microelectronics (714) 957-6018 Mr. Robert N. Snively P Sun Microsystems, Inc. (415) 336-5332 Mr. Alan Ebright P Toshiba America, Inc. (408) 428-4831 Mr. Jeff Stai P Western Digital (714) 932-7644 Mr. Shishir Shah A Western Digital (714) 932-7235 Mr. Roger Nixon V Zitel Corp. (408) 321-9600 32 people present Status Key: P - Principal Member A - Alternate Member L - Liaison Member O - Observer S,V - Visitor 3. Approval of Agenda The draft agenda was approved. 4. Scope Larry Lamers raised a question of the scope of work. Will it be limited to RAIDs or will it encompass all parallel disk arrays? George stated that the scope is open; that RAID is a convinient term but the activity is not restricted to devices claiming to be RAIDs. There is a new model needed of compound devices. Bob Snively stated that compound devices are described within the IEEE Mass Storage Model. He suggested that the order of business should be first on existing RAID devices, second to make a generic expansion of RAID possible. There is a need to standardize the terminology of RAIDs. Dal Allan stated that the RAID Advisory Board is working on such a project. There are front end and back end issues. There needs to be a command set for devices attached to the RAID controller and another for the RAID. These may turn out to be two different views of the same set. There are maintenance issues related to physical configuration and configuration issues related to the logical configuration. The issues with RAID is availability not reliability. John Lohmeyer stated that much of the functional needs could be addressed in the SCSI-3 Block Device command set document. This document is a natural evolution and part of that is accomodating RAID. Bob Snively stated that a hierarchecal approach is likely to be needed in dealing with the use of RAIDs. Mixed device types behave well in the IEEE Mass Storage model but do not behave well in the RAID environment. 5. New Folks Concerns The approach espoused seems to bottoms up. Need to look at all the possiblities. The different topologies for RAIDs need to be defined. The RAID Advisory Board is attempting to also define the RAID hybrids that go beyond the Berkley definition. John Scheible stated that folks doing implementations bring in their lists of problems encountered and solutions. This approach received a fair amount of support. Is the approach to look for generic solutions or are there pre-conditions on the solution? The solution is aimed at SCSI based devices, but a generic solution should emerge. A generic solution is highly desirable. Do we want to do a RAID architecture? The top level part could be defined such that the RAID box could contain any device interfaces. The need is to stay focused on the appropriate level of interface. The model is that of a disk array and should be generic. It was suggested that the work be divided into device level and box level to limit the politics. 6. Existence The consensus is to recommend that the RAID study group exist as a SWIG under the SBC project. 7. Call For Paper George Penokie requested that all interested parties submit documentation on the issues and problems related to implementing RAID devices. These documents should be sent to George so that he can develop an agenda for the subsequent meetings. 8. Meeting Schedule The next meeting of the RAID Study Group is planned for December 7, 1992 from 5:00 pm to 8:00 pm at the Catamaran Hotel (800-288-0770) in San Diego, CA. The following meeting of the RAID Study Group is planned for January 11, 1993 from 5:00 pm to 8:00 pm at the Sheraton Hotel in Sunnyvale, CA. 9. Adjournment The meeting was adjourned at 7:00 p.m. on Monday November 9, 1992.