Date: February 22, 1992 To: X3T9.2 Membership From: Lawrence J. Lamers, X3T9.2 Secretary George Penokie, Chair Queuing Working Group Subject: February 17, 1992 Queuing Working Group Meeting Minutes George Penokie called the meeting to order at 6:00 p.m. February 17, 1991. He thanked Carl Zeitler of IBM Corporation for hosting the meeting. The final agenda was as follows: 1. SCSI-3 Queuing [Penokie] (91-098R3) 2. Meeting Schedule 3. Adjournment The following people attended the meeting: Name Status Organization ------------------------------ ------ ------------------------------ Mr. Alan Olson V 3M Company Mr. Thomas Newman P Adaptec, Inc. Mr. Scott Smyers P Apple Computer Mr. Joe Chen P Cirrus Logic Inc. Mr. John Geldman A Cirrus Logic Inc. Mr. Edward Haske O CMD Technology Mr. Stephen R. Cornaby P Conner Peripherals Mr. Charles Monia P Digital Equipment Corp. Mr. Edward A. Gardner A Digital Equipment Corp. Mr. Skip Jones A Emulex Corp. Mr. I. Dal Allan P ENDL Mr. Edward Lappin P Exabyte Corp. Mr. Robert Liu P Fujitsu Computer Products,Am Mr. Jeffrey L. Williams A Hewlett Packard Co. Mr. George Penokie P IBM Corp. Mr. Giles Frazier S IBM Corp. Mr. Lawrence J. Lamers P Maxtor Corp. Mr. Raymond C. Yule O Micropolis Corp. Mr. John Lohmeyer P NCR Corp. Mr. Stephen F. Heil P Panasonic Technologies, Inc Mr. Gene Milligan A Seagate Technology Mr. Robert L. Simpson P Sony Corp. of America Mr. Vit Novak O Sun Microsystems, Inc. Mr. Matthew Tedone R Sun Microsystems, Inc. Mr. Pete Tobias O Tandem 25 People Present Status Key: P - Principal Member A - Alternate Member O - Observer S,V - Visitor One new document was distributed at the meeting: X3T9.2/91-98 R3 G. Penokie SCSI-3 Queuing Model Results of Meeting 1. SCSI-3 Queuing [Penokie] (91-098R3) George Penokie presented a complete re-write of the SCSI-3 Queuing model. This is the third total revamping of the model. This latest model was the result of an queuing architecture meeting and queuing model drafting meeting held in San Jose during the later part of January. The new model eliminates the usage of several terms (e.g. command execution) that are difficult to define in terms of the SCSI bus. The new model defines queuing in terms of observable characteristics of the SCSI bus. This introduces several degrees of freedom in implementation that did not previously exist. It also makes some host side folks a bit nervous because they now have to take more responsibility for their actions. The model was constructed with an interlocked parallel mentality. The automatic extended contingent allegiance feature works well with this mentality and is backward compatible with existing SCSI-2 initiators. However, a serial packetized implementation will need a more explicit method of ending the ECA condition. This is because the time sequencing of events that is intrinsic to an interlocked parallel bus is not guaranteed with a serial packetized bus. The most likely solution is to generate a new command to terminate the ECA condition. Further work is needed on this topic. The new model had changed the HEAD OF QUEUE tag message to PRIORITY tag. The resulting confusion due to peoples' connotations of what priority is caused the label to be changed back to HEAD OF QUEUE. It is possible that a priority may be added because several people saw it is a being useful. A statement may be needed to avoid class three service in the serial environment since the ECA handling must require acknowledges. 2. Meeting Schedule The Queuing Working Group meeting for March is on Tuesday, March 17, 1992 at 9:00 am at Humphrey's Half Moon Inn in San Diego, CA. The Queuing Working Group meeting for April is on Monday, February 17, 1992 at 6:00 pm at the Tradewinds Hotel in St. Petersburg, FL. 3. Adjournment The meeting adjourned at 8:30 pm.