Re: Dual display on Blade 2000

From: Lawrence Statton N1GAK/XE2 (lawrence_at_hummer.not-here.net)
Date: 08/30/05


Date: 29 Aug 2005 22:29:18 -0700

dnichols@d-and-d.com (DoN. Nichols) writes:
> >On sun4d machines, each system board has a zs. Anyone want an SS1000
> >w/ three system boards and a mountain of memory and full of SM61s?
> >Come-and-get-it.
>
> Aha! I had forgotten those. Weren't those the ones where the
> CPU trays plugged into the back, and the RAM boards plugged into the
> front?
>

Naw -- the front had a couple of spaces for discs and a pair of
removable media device. One or two M-Bus CPUs, some memory and a few
S-Bus slots fit on "curious L-shaped boards" for the SS1000(E), or
square shaped boards for the SC2000(E). 1000 had one XDBus backplane,
and the 2000 had two. Memory had XDBus affinity, not CPU affinity as
the physical layout would lead you to believe.

You might be thinking of the Enterprise machines that had a midplane
bus, but again, CPUs and memory fit on the same kind of cards, and
could go in any slot (except the one that HAD to be an IO card so the
internal devices could pick up SCSI - I suspect you could violate THAT
rule if you didn't want to use the internal SCSI devices, but I've
never tested.)

Speaking of which: Does anyone have a bare or nearly bare E4x00
chassis they'd like to unload cheap? I want a spare and the
nincompoops on eBay seem to think an E4000 is worth $1300. Pickup in
metro socal.

> Of course -- a mountain of memory then is a drop in the bucket,
> even for the Ultra-2 machines (my current fastest machines).

Heh. My current slowest (operating) machine is a Ultra 1/170. All
of my old sun4c and sun4m stuff was given away/sold long ago. The
Solbourne and Sun4 stuff went years before.

> It might be so. It has been some years since those were some of
> the machines in the machine room at work. I no longer have access to
> them, though I do have a couple of the desktop ones -- one S4000, and
> one S4000DX, IIRC. The DX was for a while the fastest machine that I
> had at home.

I had an S4000DX *BURST INTO FLAME* once. I was away on vacation, and
came home to find its charred remains in the lab. Thank $DEITY it had
been sitting on a relatively-immune-to-fire steel shelving unit, or I
may had lost my entire home. Before the fire, it was the best $33.33
I ever spent (Had to be 1996 that a friend of mine and I bought three
for a hundred bucks.) I had been hosting a web site on it, and all of
the users were all whiny, "Why did the site go down over Christmas
vacation? Why didn't you cancel your trip to visit your family to
reboot it." "Because it caught #!%#@!ing fire, you whining losers."

It was that machine that got me turned onto Solbourne, and soon I had
a mountain of S400 and S700 machines.

>
> ttya and ttyb were of course ZS ports -- even as far back as the
> Sun 2/120. IIRC, zs0 and zs1 were the keyboard and mouse, and zs2 and
> zs3 were the tty ports.

Well, remember the 4/330 also had zs3 and zs4 for TTYs C and D. Maybe
this thread belongs over in a.f.c.

-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- --
        Lawrence Statton - lawrenabae@abaluon.abaom s/aba/c/g
Computer software consists of only two components: ones and
zeros, in roughly equal proportions. All that is required is to
sort them into the correct order.



Relevant Pages

  • Next July 27: boot failure(hang) on x86_64 box.
    ... Freeing unused kernel memory: 1360k freed ... ACPI: PM-Timer IO Port: 0x488 ... CPU: L2 Cache: 1024K ... # AX.25 network device drivers ...
    (Linux-Kernel)
  • [PATCH] Document Linuxs memory barriers [try #3]
    ... The attached patch documents the Linux kernel's memory barriers. ... I've tried to get rid of the concept of memory accesses appearing on the bus; ... barring implicit enforcement by the CPU. ...
    (Linux-Kernel)
  • Oops in 2.6.28-rc9 and -rc8 -- mtrr issues / e1000e
    ... Bios 1.04beta did show correct memory sizing in dmidecode, ... I hope this is as simple as me doing something glaringly wrong in the kernel ... DMI present. ... CPU: L2 cache: 6144K ...
    (Linux-Kernel)
  • Re: read vs. mmap (or io vs. page faults)
    ... not fit in main memory, and there are overheads related to the heuristics ... But because the CPU is underutilized, ... reasonably sized user buffer). ... You have to measure the actual overhead to see what the actual cost is. ...
    (freebsd-questions)
  • Sun Fire v440 hardware problem (cant get ok>)
    ... 0>Init CPU ... 1>Set JBUS config reg ... 0>Probe and Setup Memory ... Could not read diag-level from NVRAM! ...
    (SunManagers)