\ From:	HENRY::IN%"linscomb%NGP.UTEXAS.EDU%SRI-KL.ARPA%relay.cs.net@rca.com"  5-NOV-1986 11:43 To:	info-vax@SRI-KL.ARPA Subj:	DECUS trip report      From:     Thomas Linscomb   $ Subject:  Fall DECUS U.S.  Symposium-           San Francisco, October 5 - 10, 1986    Sessions Attended    V102 - VAX System Update V099 - VMS System Update$ V158 - VAX SIG Working Group Meeting< V178 - VAXCluster Working Group Meeting (acting as WG chair) E016 - Printing Across DECNet $ V056 - VAXCluster Extension Overview% V095 - Low end VAXCluster Performance 2 V053 - VAXCluster Internals (Network Interconnect)5 V096 - Managing VAXClusters for Performance (chaired) $ V081 - Using VAXClusters Effectively DA059- ADV-11D Device Driver* V109 - Ins and Outs of VMS Sharable Images V060 - Network File System  V062 - VMS File System Internals* V164 - System Improvement Request Response+ V200 - Licensing Birds of a Feather meeting !        Nashville Planning Meeting ' V161 - VAX Advanced Question and Answer   	 Synopsis:   F      Since Marg has already covered the licensing issues in her reportF I have not repeated the material here.  Most of what follows is purelyC technical VAX/VMS.  Digital did not release any new hardware during B this session (except the VAXMate).  The two software products thatE were new included RSM, a remote system management tool, and a product = for managing the performance on large VAXClusters.  This last D pre-product announcement was made under a cryptically hidden session title.E      I am now co-Chairing the VAXCluster Working Group along with the C previous Chairman.  I intend to exercise the lines of communication D within the working group by having a few newsletters before the next? symposium.  Digital's product direction continues to be heavily F towards the VAXCluster in its various forms and this group needs to beF active in directing that functionality.  Jim Caddick, who is the otherF chairman, will be addressing the problem in VAXClusters of each memberD maintaining a different system time, while I am going to try and get0 the VAXCluster System Journal "QUORUM" improved.     Odds and Ends:  @ VMS v4.5 will be a maintenance release only.  It consists of 150D changes to 110 components.  The kit has been turned over to SDC.  It= includes limited dual porting of TA78 tapes (the tape must be E dismounted/mounted).  VMS v4.6 will probably be a maintenance release  also.   D The next major release (VMS v5.0?) is functionally complete/defined.  E VMS v4.3 has been certified at C2 security level by the Department of A Defense.  An interesting note is that Digital is working on an A1 8 certified machine (not necessarily of VAX architecture).  B Digital made an advance statement informing users of UIS, the WorkF Station software, that future developments in the software may requireC changes to the UIS standard.  Digital is attempting to give a large D warning that they are developing a common windowing interface across7 different computer architectures (PC, VAXStation, etc).     D The general VAXCluster performance session sought to explain some ofD the cluster workings and debunk a few of the myths that have arisen. A few of the MYTHS: 5 - CI bandwidth is often a limiting factor in clusters D - Locally attached disks perform better than globally accessible HSC   disks , - Tuning disk usage isn't terribly important9 - Distributed locking is a major overhead in a VAXCluster D - If the quorum disk holds the majority of the votes in the cluster,?   then the cluster can survive the loss of all but one VAX node ? - Every cluster needs a quorum disk to prevent interruptions in 	   service A - Because the CI is a 70 Mb/s bus, it supports higher performance )   DECnet traffic than a 10 Mb/s Ethernet. 7 - The VAXCluster concept is inseparable from the CI bus   F This session is in the VAX Session Notes (V081).  Anyone who wishes toB see the reason the above ideas are myths can contact me to get the notes.  < Also explained during this session were the VAXCluster stateD transitions.  Many users have complained that a transition will hangE the entire cluster for a very long time (10 minutes).  The developers C have yet to explain how this can occur and appear skeptical that it  does.   D I also brought back a handout from the "Ins and Outs of VMS SharableC Images." This session gave some hints and undocumented information.   E The SUN Network File System (NFS) was discussed under a number of VAX 9 sessions.  The session I attended was very well attended.   E The SIR session addressed the top ten requests of the VAX SIG.  A few  notes:    D - Some of the TOPS-20 MM (mailer) functionality will be incorporated   into VMS MAIL.A - More consideration to allowing privileged users to advise other    terminal users. > - Will implement a function to flush the command recall buffer   (RECALL/ERASE).   @ Overall the answers seemed to be a bit on the light side.  Twice; Digital tried to get away with questioning the need for the F improvements.  The speaker was reminded that the users had voted these items as their top requests.  = The VMS Question and Answer session posed problems to the VMS B developers.  They ranged from the trivial to the unsolvable.  Some interesting points: . - $ SET ACCOUNTING/NEW can turn off accountingA - MicroVMS (v4.2 and v4.3) kitbuild doesn't build a MicroVMS kit. ;   Will not be fixed since MicroVMS will be rolled into VMS. D - April 17, 1987 is a special date.  During a power failure some VAX*   consoles will set the time to that date.C - For the VAX 8600 there is a grounding FCO.  It consists of a half :   inch braid to ground the BA11 Unibus box to the cabinet.F - For three high RA81 cabinets there is an FCO to remove the filter onE   the top RA81.  This relieves a large heat buildup in the top drive. = - XQP (the VMS file system) means eXempt from Quality control    ProceduresC - There is a problem with the XEDRIVER on the 8600 that causes some ?   systems to be REALLY "slow".  A fix exists and Denver has it.    MicroVAX Clusters:  A The VAXCluster Extension Overview more clearly laid out Digital's = implementation of the VAXCluster concept based on the Network F Interconnect (NI or Ethernet).  The MicroVAX Cluster had been shown as? a "technology demonstration", but it should come to market as a @ layered product before the next DECUS meeting.  I attended threeE one-hour sessions covering the technology, performance and internals.   C The MicroVAX Cluster consists of one boot member of any type of VAX F and up to thirteen MicroVAXs or VAXStations as satellites.  Because ofB the booting firmware required, the system is designed to work onlyA with MicroVAXs as the satellites.  The total number of systems is 0 currently limited by the number of system roots.  C The MicroVAX Cluster is based on Ethernet and does not allow any of F the members to have a CI (Computer Interconnect).  This means that the@ MicroVAX Cluster cannot have access to an HSC disk controller orB larger (CI based) VAXCluster.  Undoubtably Digital is working on a? system to integrate both the CI and NI Clusters (maybe by using F hardware).  Creating an ethernet interface for the HSC disk controller has been ruled out.   D An elaborate system has been setup to allow a MicroVAX that does notE have a disk to boot off the Ethernet.  Multiple clusters can run on a D single NI without saturation or interference.  The boot process uses    C the Maintenance Operation Protocol to determine its boot host and a B password system to prevent illegal cluster members or local system@ disks.  The best MicroVAX configuration for the satellite member7 should have a local disk for doing paging and swapping.   C The internals of the NI cluster are very interesting.  For the most F part it consists of replacing the CI port driver (PADRIVER) and the CIE hardware capabilities with a software driver for ethernet (PEDRIVER). F Schematically, if you look at the VMS system the higher functions (RMSD for example) do not know about the lower level communication systemsE or hardware.  Of course, the CI hardware provides many assists to the > software that had to be implemented in the software driver forF ethernet.  Looking at the assists the CI provides, its easy to believe5 that Digital is working on similar NI based hardware.   C The performance data presented indicated that the satellite systems F should perform well, about the same as comparable systems based on theF current local disk technology.  What must be remembered is that remoteE disks only effects I/O.  During heavy compute cycles, there is no I/O  dependency.   E The best boot member in a MicroVAX cluster is a MicroVAX II with RA81 < disks.  It tends to run out of CPU power, ethernet interfaceB throughput and disk throughput at the same time.  The MV II CPU isE faster then the VAX 11/780 (for the instructions used), it has faster B memory, and the VAX 11/780's memory cache doesn't help.  The worstB satellite member would be a VAX 11/750 (not counting the "defunct"; 11/730 and 11/725).  The 11/750 does not provide enough I/O  throughput.   F Avoid a DEUNA interface on the boot member, it does not provide enoughE throughput.  (AGL has recently purchased a DELUA interface to connect  to its MicroVAXs.) --------------------K --Thomas Linscomb aka linscomb@ngp.UTEXAS.EDU aka t.linscomb@agl.UTEXAS.EDU B --Advanced Graphics Lab/Computation Center/The University of Texas5 --Austin, TX 78712               phone:  512/471-3241 C --uucp:   ...seismo!ut-sally!ut-ngp!linscomb   linscomb@ut-ngp.UUCP  --bitnet: cctj001@utadnx