grandi@noao.edu (Steve Grandi) (12/12/88)
What follows are some of my impressions of the Sun Users Group meeting held at the Fountainbleau "resort" on Miami Beach between December 5 and 7, 1988. Life is sure tough when one has to go such dreary places for a meeting... Scott McNealy, Sun's President, said the DRAM shortage is incredibly bad for Sun (allocations are based on last year's sales, but Sun has doubled sales and machines are now going out with twice the amount of RAM as before!). Sun is now the third largest consumer of DRAM in the world after IBM and DEC. He said to compare NeXT's machine with the machines Sun will be shipping in July 1989. Sun has been shy of announcements during the last 12 months, but will announce lots of machines during the next 12 months. McNealy said "Sun is no longer benign" in the eyes of the industry and is trying to distance itself from the SPARC chip by the establishment of the SPARC Council. Bernie LaCroute, Sun's executive vice president, was much more specific about product plans. While Sun is committed to the 680X0 and 80X86 architectures, most of their resources will be devoted to SPARC systems. During the next 3 to 6 months, expect 3 new SPARC machines: a low cost desktop model running at 10-13 MIPS and about 2.5 Mflops; a deskside pedestal system at about the same $20K price point as the existing 4/110 running at 10-15 MIPS and about 3 Mflops and a "server" system at about the same $40K price point as the 4/260 running at 15-20 MIPS and about 4 Mflops. Later in 1989, an ECL system running at 35-40 MIPS and about 10 Mflops should be released (since this system requires a completely new memory and I/O system to do justice to such performance, delays might happen; but a "taped" prototype is running now in the lab). For comparison, the 4/280 is benchmarked by Sun at 10 MIPS and about 1 Mflops. Also in the 3 to 6 month timescale are two 68030 machines. A system at the $30K price point of the 3/260 will feature a 33 MHz 68030 and crank out about 7 MIPS. A desktop system at the $10K and under price point of the 3/50 and 3/60 will feature a 68030 at a lower clock rate and run at 3.5 MIPS. For comparison, the current 3/60 is rated at 3 MIPS or so, and the 3/280 is rated at about 5 MIPS. Also in 1989, a "486i" will be released running at about 10 MIPS. The two low-end desktop machines (a 4/50 SPARC machine and a 5/50 68030 machine?) will feature some interesting features. To quote LaCroute, they feature "revolutionary" graphics using new chips that will "redefine" desktop performance levels. The numbers he quoted showed an increase from 2K 3D vectors (per second?) to 130K 3D vectors. I wish I knew what these numbers mean; also, how about resolution? The 4/50 and the 5/50 will also have an expansion bus ("open" of course) capable of supporting expansion cards, will apparently use PS/2 form factor floppies (which Sun expects to be running 4 Mb in capacity in 1989) as a peripheral, will have room for small winchesters in the desktop package (there was a very nice 3.5 inch 100 Mb drive from Fujitsu shown on the exhibit floor, for example) and will feature "telephone quality sound" capability. These are systems that Sun says will stand up quite nicely against the NeXT machine. Expect to buy the low end Suns in computer stores before too long. LaCroute went on to talk about more nebulous product futures. Sun has FDDI running in the lab but is very disappointed in the cost: the system will have to reduced to a couple of chips before it will be economical for all servers to feature a FDDI port. PHIGS and PHIGS+ are definitely the focus of a lot of work as is improved GKS performance. 24 bit color will become the new standard. High end graphics systems will move from 150K 3D vectors and 20K shaded polygons to .8-1M vectors and 150K shaded polygons. Finally, Bill Joy (VP of research and development) gave his traditional closing talk and as usual was opinionated, interesting and quotable. In Joy's words, Sun is trying to accomplish an economic restructuring of the middle part of the computer industry by enabling multiple companies to build binary compatible machines. Sun is not afraid of competition in open systems, says Joy, and he goes on to say that binary compatibility such as exists within the VAX line or in the PC and PC-clone market is the arena in which Sun wants to compete. Joy's comments about the denizens of the OSF (chiefly DEC, IBM, HP and Apollo) are that their support of open systems is a smokescreen hiding their traditional "customer motel" strategy (a customer checks in, but never checks out...). Joy's test for OSF open systems is binary compatible formats: will an executable and data file running on a DEC system using the MIPS chip run on anybody else's system using MIPS chips? Joy gave several examples of how Suns are becoming more open: the internal bus ("as good as being on the CPU card") which will appear on many systems, SIMM memory (Joy expected SIMMS to be in baggies at Radio Shack before the DRAM crisis hit; it probably will still happen), X11/NeWS and PHIGS and the upcoming plans to make the processor portion of systems modular so a new faster SPARC chip can be inserted without changing the rest of the system. Even Sun has its limits, Joy conceded when confronted with the newly closed boot PROMS on Suns, but said the code in the boot sequence was far too "crufty" to let out. Speaking of SPARC, Joy says Sun expects to stay on the "performance doubling" curve through a pipelined GaAs implementation running at 250 MIPS in 1991 or so, but doesn't see a way beyond that performance level in a uniprocessor level so Sun is exploring multiprocessor systems. Joy says that floating point and graphics performance should now be bundled into the doubling curve instead of just MIPS. Phase 3 of Unix development (Joy and friends rekernelizing and rewriting Unix in C++) is now in limbo pending direction from Unix International, but Joy expects something like it to happen before long. Joy said he actually wants to use C++++-= (a subset providing "safety" of a superset of C++ providing multiple processor and system implementation extensions). Joy had several pithy comments on the NeXT machine. Basically he said it is "wrong, wrong, wrong!" Aside from being very "pre-announced", he said that Mach is not a production quality OS, Objective C is a veneer of a object-oriented language, that the interface builder stuff is done better in existing Smalltalk systems, that the box is big and ugly, the 68030 is old technology and the magneto-optical disk doesn't yet work. Joy conceded he might be wrong (!), but said that Jobs had $100M to develop his system with, whereas he has about $300M per year in R&D money... Here is the scoop on release dates for SunOS. SunOS 4.0.1 for the Sun-2, 3 and 4 architectures is out now (79 bug fixes!). SunOS 4.0.1 for the 386i will be out real soon with bug fixes and performance improvements. SunOS 4.0.2 out Q1/Q2 1989 with new hardware support (including unannounced machines!) plus bug fixes (you will have to to ask for this release from Sun). SunOS 4.0.3 out Q2/Q3 1989 with bug fixes, performance improvements and hardware support. Source will be available and 4.0.3 will be distributed to everyone. 4.0.3 will be the last release to support Sun-2s. The implication is that 4.0.3 is the stable, final release of 4.0. SunOS 4.1 will be out around Summer 1989. 4.1 will pass SVVS edition 2 (implying the addition of RFS, TLI, mandatory file and record locking) and be POSIX compatible (but one would need to turn on some options to meet these standards). 4.1 also has internationalization features. In terms of performance, the kernel has been put on a diet to make more pages available to applications. The windowing system "repaint/damage propagation algorithm" is improved to eliminate thrashing (front windows get repainted first and windows are done sequentially rather than all at once; this change will show up first in the 386i 4.0.1 release). The C optimizer has been made faster and the default optimization level (cc -O) for Sun-3s has been upped to level 2. There will be an option to allocate /tmp out of swap space (no disk I/O for small files!). NFS will now do dynamic retransmission time and buffer size calculation and "mount point hangup" has been avoided to a greater degree. Finally, context switch performance on 3/2X0 and 4/2X0 systems has been vastly improved. Functional enhancements included in 4.1 include asynchronous I/O, even more than 64 file descriptors per process, memory locking of pages (including processes; one will be able to lock down a process from an external process as well) and much more use of loadable modules. HoneyDanBer UUCP, new AWK, a simple programmer's interface to the dynamic binding system and a parallel make are all included in 4.1. So called "Ease of Use" features such as the Organizer, the color editor and the help system now included in the 386i versions of SunOS will be part of 4.1 for all architectures. Sun will also bundle some "personal productivity" software with SunOS such as a low-end word processor and a paint/draw program since "people expect them" (both McNealy and LaCroute emphasized that Sun wasn't getting into the application business, just that folks expected such tools in the same way a previous generation expected a text editor). Beyond 4.1, and not counting the S5r4 release, the SunOS guys are working on better support for large heterogeneous networks (following the lead of the automounter and such), an expanded storage hierarchy (tertiary storage on tape or whatever integrated into the backup system), better resource management (improved scheduling and page replacement algorithms), using newer facilities such as VM in other pieces of the system (use file mapping in stdio, for example) and improving the programming environment by providing improved interfaces and support for lightweight processes, dynamic linking and distributed applications. Sun's version of System V, release 4 (S5r4) will not see release until well into 1990. Sun is basically a subcontractor to AT&T (serving as the protector of the BSD flame as well!) for certain portions of S5r4, but will not have the final system to port until Q3 1989. There are some features of SunOS (lightweight processes, for example) that will have to included in Sun's release. Sun will provide "switches" to provide "SunOSish" or "S5ish" behavior (but S5 will be the out-of-the-box default). Software developers could ease their burden by installing the S5 compatibility package in SunOS 4.0 and making sure their software will install with either /usr/ucb or /usr/5bin in the $PATH. The folks from Sun involved in setting the specifications for S5r4 talked a good game and claim that it will neither be a bloated mess (greatest common factor) nor a stripped system requiring huge add-ons (least common denominator). SunOS 4.1 will NOT include X11/NeWS or View 2 as a bundled part of the system. Both these packages will be released about the same time as 4.1, but will be unbundled (available for "distribution costs"). X11/NeWS is a merged server/window system supporting stock X and stock NeWS (Sun's image Postscript system) applications in a common window system (implementing Open Look window frames and such). X and NeWS windows can overlap and text can be cut and pasted between them. Politics decree that multiple toolkits must be supported, so several will be part of S5r4, all implementing the Open Look "look and feel". View2 is an X toolkit providing SunView, NDE is a NeWS toolkit (with all the Postscript goodies) and Xt+ is AT&T's X toolkit with an emphasis on widgets. View2 is a reporting of SunView to X and "should" be an easy transition for old applications into the Open Look world. X11/NeWS plus View2 will not be supported on 4 Mb machines in their 1989 release. Finally, as a "transition aid" SunView 1.X will still be supported in SunOS even when X11/NeWS plus View2/Open Look is integrated. One highlight of the conference was a showing of the "final" version of Pixar's "Tin Toy" video. The winner of the "Sex, Drugs and UNIX!" button award goes to the derivative, but still funny "(Safe) Sex, Drugs and SPARC!" Best performance by a vendor was by Software Associates and their suite featuring Hagen Dazs ice cream sundaes and a balcony with a spectacular view of the beach and ocean. I visited the suite all 3 days. Finally, the 1989 Sun Users Group conference will be at the Anaheim Hilton and Towers between December 6 and 9. Isn't that where they hold DECUS meetings? Steve Grandi, National Optical Astronomy Observatories, Tucson AZ, 602-325-9228 UUCP: {arizona,decvax,ncar}!noao!grandi or uunet!noao.edu!grandi Internet: grandi@noao.edu SPAN/HEPNET: 5355::GRANDI or NOAO::GRANDI
henry@uunet.uu.net (12/22/88)
>... Sun is trying to accomplish an economic restructuring of the >middle part of the computer industry by enabling multiple companies to >build binary compatible machines. Sun is not afraid of competition in >open systems, says Joy, and he goes on to say that binary compatibility >such as exists within the VAX line or in the PC and PC-clone market is the >arena in which Sun wants to compete. Considering that Sun is the company that refuses to supply hardware documentation, and that Sun source tapes omit things like the kernel memory management because it would give away how the Sun MMU works, Joy must be thinking of some other company. MIPS maybe? Henry Spencer at U of Toronto Zoology uunet!attcan!utzoo!henry henry@zoo.toronto.edu
grandi@noao.edu (Steve Grandi) (12/13/89)
The annual meeting of the Sun Users Group took place in Anaheim from December 6 to 8. Announced at the meeting were two new systems: the SPARCserver 1 and the SPARCserver 490. As you might expect, the SPARCserver 1 is a SPARCstation 1 without a monitor packaged with several disks. For a list price of $18,900, one can get a SPARCserver 1 with 8 Mb, two 327 Mb disks and a 150 Mb cartridge tape. The interesting machine is the SPARCserver 490. The 490 is the cabinet of a SPARCserver 390 with a new cpu/memory system. The buzz word was "balanced:" I/O capacity commensurate with cpu capacity. The 490 uses the same Cypress/TI SPARC/FP chip set as used in the 4/300 series but running at 33 MHz instead of 25 MHz. The memory system features ECC error correction instead of the parity error detection used in the 4/300 series. The memory bus (64 bit) runs synchronously at 120 Mb/sec (fast enough to handle full I/O throughput plus full memory traffic even assuming 100% cache misses). With 1 Mb RAM chips, the 4/390 supports up to 160 MB; multiply the capacity by 4 when 4 Mb chips are available (soon). The 4/490 does have a P4 bus for a video adapter. The 4/490 also features a 128 KB write-back cache and a 4 KB I/O cache. A similar I/O cache was first used by Sun on the 3/400 cpu: it buffers DMA traffic from the Ethernet and disks and provides word instead of byte transfers of such data to memory. The 4/390's MMU supports 4 GB per process and 64 contexts in hardware (as compared to 16 for the 4/300) and features hardware flush. The VME bus runs at 22 MB/sec and the claim is that VME throughput is not saturated even by 4 IPI disk controllers each running 8 drives and two 1/2-inch tape drives. Sun's IPI-2 disk controller is their own design featuring a 68020 (20 MHz) and 1 MB dynamically segmented read-ahead cache. The ISP-80 controller will support 6 MB/sec drives, but the drives they are selling with the 390 and 490 are 3 MB/sec CDC drives. The controller can run as a VME master at 30 MB/sec. IPI disk cabling is much simpler than SMD cabling. Sun's benchmarks compared Unix sequential reads (through the file system) comparing a 4/330 with one SCSI controller and 2 disks, a 4/370 with 4 SMD-4 controllers supporting one disk each and a 4/490 with 4 ISP-80 IPI controllers supporting one disk each. Relative performance for these configurations are 1.5, 1.9 and 5.4. The Sun guys said disk striping is not seen as a win on their high-end IPI systems given projected upgrades in IPI performance. Sun now officially sells and supports 8 mm Exabyte tape drives on 390 and 490 systems. Sun folks claimed that these drives are fully qualified (requiring microcode changes in the drives) and supported by a Sun driver. Unlike the case of the SMD-4 controller card where the microcode changes are reserved to Sun alone, Exabyte is free to incorporate the fixes for one and all. Sun's driver will initially be only available on the 390 and 490 feature tapes; but will be available to all with the 4.1 distribution. The 4/490 racks up the following numbers on the various benchmark scales: 22 Dhrystone MIPS, 3.8 double precision Linpack MFLOPS, 16.8 SPECmarks and 47 TP1 tps. Other benchmarks of interest mentioned in passing are 11.3 SPECmarks for the 4/300, 8.3 for the 4/60 and 8.1 for the 4/260. The SPARCserver 490 has a list price of $99,900 for a system with 32 MB and 1 Gb of disk. The increment over a 390 is around $25,000. Sun claims this is lower than the MIPS M/2000, about 1/2 of the price of a DECsystem 5810 and 1/4 the price of a VAX 6430. There are upgrade paths for all rackmounted Sun servers (3/180, 3/280, 4/280, 4/390). Also, Sun has lowered the price for additional IPI disks for the 390 and 490 (and a good thing, too, the previous incremental cost for this disk -- a CDC SABRE-1230 with an IPI interface -- was outrageous even by Sun's standards!) Sun also announced DeskSet 1.0, a suite of Open Look applications which are apparently unbundled from OpenWindows but are similarly available for only a media charge. DeskSet is "based on Open Look and on SunView" and features a "drag and drop" desktop metaphor. The programs included in DeskSet are File Manager ("a better way to manage your Unix files"), Calendar Manager ("instant appointment and resource scheduling"), Mail Tool, Print Tool, Tape Tool, Text Editor, Calculator, Icon Editor, Snapshot Tool, Performance Meters, Clock and Binder ("a developer's tool for defining work methods"). The DeskSet bundled with the first release of OpenWindows lacks several of these tools. Sun executives were much less forthcoming about product plans than they were at last year's SUG meeting. All they did was hint: multi-processor servers are coming, multi-bus servers are coming, the pizza box, the 330 and 370 pedestals and the 390/490 rack will be the shape of any new products to come. Sun will not leave the market to the low priced SPARC clones expected in mid 1990; expect Sun to have both much cheaper and much faster desktop SPARCstations than the current SS-1. It is unclear whether Sun is talking about one (both cheaper AND faster) or two products. Rob Gingell and Pat Harding gave their annual "state of Sun-OS" presentation. SunOS 4.1 is in Beta test and will be released when it is qualified; probably in the spring. 4.1 is the same for all "real" Suns (i.e., there is no 4.1c release) but there will be 4 distributions (Sun-3, 3x, 4 and 4c). "There are no plans for a 4.1 release for the 386i" (but a 4.0.3 was mentioned). Thought is being given to only two distributions (Sun-3 and Sun-4) for future releases; but what the folks REALLY want to do is bundle all releases on one CD-ROM. 4.1 complies with POSIX 1003.1, FIPS 151-1, XPG2 and most of XPG3 (through /usr/xpg2bin), and SVID issue 2 -- including RFS and mandatory file and record locking (not guaranteed for other than local files!) -- and most SVID 89 interfaces (through /usr/5bin). The C compiler has been ANSIfied enough to meet POSIX 1003.1; but no function prototypes. 4.1 supports "8-bit clean" utilities to go along with the 8-bit clean kernel of 4.0. The international features of the type-4 keyboard are supported. 4.1 supports memory locking in the memory management facility. Pages may be locked through mlock(addr,len) and address spaces may be locked with mlockall(flag). SV compatible locking is available with plock(region). These three calls are restricted to the super-user. General applications may influence the system's page replacement policy through madvise (addr, len, advice) where the advice can be normal, sequential, random, or will/won't be seeking. The system can now utilize a /tmp file system built from swap space which has no "forced-write" semantics. I/O to disk occurs only if memory demand requires it; otherwise files exist only in main memory. On reboot, these files are GONE! SunOS utilities have been doctored to put files that should survive reboots into /usr/tmp instead of /tmp; users should be similarly careful! Asynchronous I/O is included in 4.1 through variants of read and write that are conceptually similar to process handling. aioreas and aiowrite are like fork, aiowait is like wait and aiocancel is like kill. This I/O is truly asynchronous and not "not-blocking". Asynchronous I/O is a kernel configuration option and available only to dynamically linked programs (this is the wave of the future: in this case it preserves the implementor's freedom to pull the 4.1 kernel based implementation of asynchronous I/O out of the kernel in later releases). 4.1 includes the promised programmer's interface to dynamic linking, loadable modules (which aren't integrated into the usual autoconfigure process, unfortunately), HoneyDanBer uucp, new AWK, an ISO 9660 (CD-ROM High Sierra) file system, compressed kernel crash dumps (thus the requirement that swap space must be greater than physical memory is removed), up to 256 file descriptors (watch your select calls again!), up to 256 pseudo-terminals, more flexible configuration options (no software limit on number of Ethernet interfaces!), adaptive NFS retransmission (automatic setting of timeo, rsize and wsize based on round-trip times), mount table enhancements (providing enough information that stating a mount point of a dead server will not hang the process), Berkeley "Fat Fast File System," much improved interaction between YP and named, decreased kernel residency requirements (may actually decrease behavior of large memory systems in favor of 4 MB machines), some reworked algorithms to minimize thrashing (such as the way the "window damage signal" is propagated to processes), a changed default optimization level for the 680x0 C compiler (to -O2) and much improved context-switch performance on 3/200 and 4/200 systems. 4.1 will include all the pieces necessary to reconstruct the shared system libraries and construct libraries that bypass YP to go directly to named. 4.1 requires a full install (but installation speed-ups have been made and the Installing SunOS manual has been extensively revised). The directory structure has been once more revised to include the concept of release levels for 4.1 and subsequent versions (e.g., /export/exec/sun3.sunos.4.1). There are no longer any distinction between domestic and international SunOS; encryption now is included as an add-on tape. 4.0[.x] sources, binaries and objects are OK under 4.1 excluding "invasive and many libkvm programs." As usual, one cannot go backwards -- do NOT build on 4.1 for execution on previous releases. Also, the "Fat Fast File System" file system changes mean that a file system, once converted to 4.1, cannot go back. Drivers (or anything referencing the user or proc structures) must be recompiled (probably no conversion). Sun-2 systems are no longer supported. 4.1 has been subjected to increased regression and automated testing including external validation suites. Interactive performance on 4 MB diskless machines (with configured kernels, of course) is about halfway between 3.5 and 4.0; the Sun folks are declaring victory. For diskful 4 MB machines and machines with more than 4 MB, performance is approximately that obtained with 4.0. 4.1 is touted as being the "bridge to SVr4." Sun's SunOS/SVr4 (not the final name!) will be the next major release of SunOS after 4.1 and is at least a year away. Sun has to add some features such as async I/O and lightweight processes back into the SVr4 base and include compatibility and migration support. Remember, this release will default to the SV "look and feel." SunOS 4.x binaries WILL run (assuming one uses shared libraries and doesn't depend on the layout of mem, kmem or a.out). Expect a 10% performance hit. Sources for 4.x applications can be recompiled unchanged on SunOS/SVr4 through a "compatibility feature" and will run with perhaps a 2% performance hit. A set of lint-like tolls will help application writers port their 4.x applications to the new release. A new compiler release will take place early next year. f77 v1.3 and related compilers will feature a new commandline option, -fast, which invokes a set of "favorite" optimizations assuming one is compiling and executing on the same machine. Good stuff! Apparently, Sun will soon start distributing (for not too many $) an "up to date" C compiler that tracks the rest of the languages. The usual system C compiler must be frozen far earlier than other compilers to provide a stable base for OS development. Thus, for customers who want the latest version of the C compiler (bugs fixed and optimizations improved), Sun will provide it just like Sun provides Fortran and Pascal. With the new compiler release, all language pieces will occupy a new hierarchy under /usr/lang. Keith Bierman gave a wonderful talk on compilers and how to tune your code for fun and profit. This talk and the handout that accompanied it were worth the price of the trip to the meeting. For the first time in the 4 years I've been going to SUG meetings , Bill Joy did not give a talk; he was missed. Sun VPs Andy Bechtolsheim and Eric Schmidt both talked about how successful the SPARCstation 1 has been ("the single bestselling workstation in history"): 40,000 units have been shipped so far and the rate of shipment has risen to 10,000 units per month. According to Sun SPARC now has 2/3 of the RISC marketplace: "SPARC has won." Sun's own business has changed as well: whereas a year ago, 80% of Sun's sales were CISC systems (Sun-3 and 386i) and 20% SPARC, these fractions are now reversed. The lack of demand for the 68030 line Sun announced in April was a surprise. "The Motorola line must be considered an endangered species." A panel of Sun execs had to respond to some rather rude questions from the audience. Asked if OpenWindows would ship in our lifetimes, Sun's response was that shipments were "ramping up" so that the answer center wouldn't be swamped by questions. First shipments are only in the 100s and are preferentially going to developers. In other words, the lead time for delivery is still semi-infinite. Asked about the 386i line (the lack of commitment to a 4.1 port seemed ominous to the questioner), Scott McNealy responded that tripling performance in 18 months with the recent announcement of the 486i upgrade didn't seem to him like they were killing off the product. In fact, 386i systems are priced with a lower markup than SPARC systems. Asked why a Wren IV disk costs about three times more from Sun than third party vendors, McNealy responded that Sun's margins are the lowest in the industry. However, he continued, he thinks Sun's prices SHOULD be restructured to charge more for items such as computers and software and lowered for items such as memory and disks that Sun adds little if any value to. The vendor show was full of the usual suspects: database and publishing vendors, peddlers of third party peripherals and Sun itself showing off a 4/490. Items that caught my eye were a S-bus card from Danford Corp. with 4 serial ports plus a parallel port, 4 MB SIMMS (made out of 4 Mb chips!) for 4/60s from several vendors (still quite expensive!) and a 9U SCSI card from Ciprico that emulates Sun's controllers for system booting. The next SUG meeting and vendor show will take place in San Jose on December 2-5, 1990. In 1991 and beyond, SUG will host two get-togethers per year. The 1991 dates are june 16-19 in Atlanta and December 8-11 in San Jose. Steve Grandi, National Optical Astronomy Observatories, Tucson AZ, 602-325-9228 Internet: grandi@noao.edu SPAN/HEPNET: 5355::GRANDI or NOAO::GRANDI