From: Clem Cole <clemc@ccc.com>
To: Bakul Shah <bakul@iitbombay.org>
Cc: Noel Chiappa <jnc@mercury.lcs.mit.edu>,
The Unix Heritage Society mailing list <tuhs@tuhs.org>
Subject: [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' The Register
Date: Mon, 17 Jun 2024 12:00:13 -0400 [thread overview]
Message-ID: <CAC20D2OLExWuHYM67XMumPevaZuL6WmSCsJ6X0w80pjn15kNsw@mail.gmail.com> (raw)
In-Reply-To: <CAC20D2PdHFM9A7mBMZZ0cfVYXmYRBrVUKMYfzP5fbSSmge4sKg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 5716 bytes --]
typo... like the VFS layer (not CFS layer)
ᐧ
On Mon, Jun 17, 2024 at 11:56 AM Clem Cole <clemc@ccc.com> wrote:
>
>
> On Mon, Jun 17, 2024 at 1:51 AM Bakul Shah via TUHS <tuhs@tuhs.org> wrote:
>
>> Forgot to mention LOCUS, which was the only distributed Unix compatible
>> OS I am aware of. To anyone who has user/implementer experience, I would
>> love to hear what worked well, what didn't, what was easy to implement,
>> what was very hard and what you wished was added to it.
>>
> Jerry and Bruce's book is the complete reference:
> https://www.amazon.com/Distributed-System-Architecture-Computer-Systems/dp/0262161028
>
> There were basically 3/4 versions... the original version of the PDP 11
> which is the SOSP paper, which morphed to include a VAX at UCLA; IBM's
> AIX/370 and AIX/PS2 which included TCF (Transparent Computing Facility),
> and LCC's TNC Transparent Networking Computing "product" which were the 14
> core technologies used to built it. Part of them landed in other systems
> from Tru64, HPUX, the Paragon and even a later a Linux implementation
> (which sadly was done on the V2 kernel so was lost when Linus did not
> understand it).
>
> What worked well was different flavors of the DFS and the later core idea
> of the VPROCS layer which I sorely miss, which allowed process migration -
> which w worked well and boy did I miss later in my career. Admin of a
> Locus based system was a dream because it was just one system for up to
> 4096 nodes in a Paragon. It also means you could migrate processes off a
> node, take the node down, reboot/change and bring it back. Very cool.
> After the first system was installed, adding a node was trivial, by the
> way. You booted the node, "joined" the cluster, and were up. AIX used file
> replication to then build the local disks as needed. BTW:
> "checkpointing" was a freebie -- you just migrated the file to a disk.
>
> Mixing ISA like the 370 and PS/2 was a mixed bag -- I'll let Charlie
> comment. With TNC we redid that model a bit, I'm not sure we ever got it
> 100% right. The HP-UX version was probably the best.
>
> The biggest implementation issue is that UNIX has too many different
> namespaces with all sorts of rules that are particular to each. For all of
> the concept of "everything is a file," - when you start to try to bring it
> together, you discover new and werid^H^H^H^H^Hintersting name spaces from
> System V IPC to signals to FIFOs and Name Pipes (similar but different).
> It seemed like everything we looked, we would find another NS we needed to
> handle, and when we started to try to look at non-UNIX process layers, it
> got even stranger. The original UNIX protection model is a tad weak, but
> most people had started to add ACLs, and POSIX was in the throughs of
> standardizing them -- so we based it on an early POSIX proposal (mostly
> based on HP-UX since they had them before the others did).
>
> To be more specific, the virtual process layer (VPROC) attempted to do
> what VFS had done for the FS layer to the core kernel. If you look at
> both the original 2 Locus schemes, process control was ad hoc and thus very
> messy. LCC realized if we were going to succeed, we needed to make that
> cleaner. But that still took major surgery - although, like the CFS layer,
> things were a lot clearer once done. Bruce, Roman, and I came up with
> VPROCs. BTW: one of the cool parts of VPROC is like VFS. It conceptually
> made it possible to have other process models. We did a prototype for OS/2
> running inside of the OSF uK and were trying to get a contract from DEC to
> do it to Tru64 and adding VMS before we got sold (we had already developed
> CFS for DEC as part of Tru64 - which TNC's Cluster File System). Truth is,
> cheap VMs killed the need for this idea, but it worked fairly well.
>
> After the core VPROCs layer, the hardest thing was distributed
> shared memory (DSM) and the distributed lock manager (DLM). DSM was an
> example that offered pure transparency in operation, *i.e.,* test and set
> worked (operationally) correctly across the DSM, but it was not "speed
> transparent." But if you rewrote to use DLM, then you could get full
> transparency and speed. The DLM is one of the TNC technology which lives
> on today. It ended up in a number of systems - Oracle wrote their own
> based on the specs for the DEC DLM we built for the CFS for Tru64 (which is
> from TNC). I believe a few other folks used it. It was in OSF's DCE, and
> ISTR Microsoft picked it up.
>
> So a good question is if TNC was so cool, why did Beowulf (a real hack in
> comparison) stick around and TNC die? Well, a few things. LCC/HP did not
> open-source the code until it was too late. So Beowulf, which was around,
> was what folks (like me) used to build big scientific clusters. And while
> Popek was "right," -- it takes something like Locus/TNC to make a cluster
> fully transparent. Beowulf ignored the seams and i the end, that was "good
> enough." But it makes setup and admin a PITA, and the program needs to be
> careful -- the dragons are all over the place. So, when I went to Intel, I
> was the Architect of Cluster Ready, which defined away many of those seams
> and then provided tools to test for them and help you admin.
>
> Tools like the Cluster Checker and the whole ClusterReady program would
> not be needed if TNC had "stuck," and I think clusters, in general, a
> cluster of small computers on a LAN, not just clusters on a
> high-speed/special interconnect like a supercomputer, would be more
> available today.
>
>
> Clem
>
> ᐧ
>
[-- Attachment #2: Type: text/html, Size: 8553 bytes --]
next prev parent reply other threads:[~2024-06-17 16:00 UTC|newest]
Thread overview: 142+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-17 0:48 Noel Chiappa
2024-06-17 1:02 ` Clem Cole
2024-06-17 1:05 ` Larry McVoy
2024-06-17 3:56 ` ron minnich
2024-06-17 3:57 ` ron minnich
2024-06-17 5:41 ` Bakul Shah via TUHS
2024-06-17 5:51 ` Bakul Shah via TUHS
2024-06-17 15:56 ` Clem Cole
2024-06-17 16:00 ` Clem Cole [this message]
2024-06-17 16:59 ` Charles H Sauer (he/him)
2024-06-17 16:43 ` Larry McVoy
2024-06-17 22:49 ` Steffen Nurpmeso
-- strict thread matches above, loose matches on Subject: below --
2024-06-20 16:45 Lyndon Nerenberg (VE7TFX/VE6BBM)
2024-06-20 18:32 ` Kevin Bowling
2024-06-13 14:56 [TUHS] Version 256 of systemd boasts '42% less Unix philosophy' • " Charles H Sauer (he/him)
2024-06-13 15:33 ` [TUHS] " Dan Cross
2024-06-13 15:35 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' ??? " Larry McVoy
2024-06-13 15:41 ` Alan D. Salewski
2024-06-13 15:55 ` Steve Nickolas
2024-06-13 15:39 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' • " Clem Cole
2024-06-13 16:47 ` Arrigo Triulzi via TUHS
2024-06-13 18:39 ` segaloco via TUHS
2024-06-13 18:45 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' ??? " Mychaela Falconia
2024-06-14 8:59 ` Ralph Corderoy
2024-06-13 18:54 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' • " Dan Cross
2024-06-12 19:29 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' " Greg A. Woods
2024-06-13 20:03 ` Dan Cross
2024-06-13 17:07 ` Greg A. Woods
2024-06-14 14:17 ` Grant Taylor via TUHS
2024-06-16 5:48 ` Alexis
2024-06-15 8:48 ` Greg A. Woods
2024-06-16 19:44 ` Clem Cole
2024-06-17 0:10 ` Peter Yardley
2024-06-17 0:29 ` Clem Cole
2024-06-17 1:01 ` Alexis
2024-06-17 1:21 ` Warner Losh
2024-06-17 1:25 ` Larry McVoy
2024-06-17 1:32 ` Warner Losh
2024-06-17 19:21 ` Stuff Received
2024-06-17 19:28 ` Larry McVoy
2024-06-17 22:34 ` Steve Nickolas
2024-06-16 7:57 ` Greg A. Woods
2024-06-17 23:44 ` Warner Losh
2024-06-18 0:06 ` Larry McVoy
2024-06-18 22:44 ` Greg A. Woods
2024-06-19 2:33 ` David Arnold
2024-06-18 1:52 ` Steve Nickolas
2024-06-18 4:52 ` segaloco via TUHS
2024-06-18 22:50 ` Greg A. Woods
2024-06-18 23:03 ` Warner Losh
2024-06-18 23:27 ` ron minnich
2024-06-19 1:38 ` Greg 'groggy' Lehey
2024-06-19 1:42 ` Warner Losh
2024-06-19 23:28 ` Greg A. Woods
2024-06-20 5:01 ` Scot Jenkins via TUHS
2024-06-20 5:09 ` Luther Johnson
2024-06-20 5:18 ` Luther Johnson
2024-06-20 18:34 ` Greg A. Woods
2024-06-20 18:41 ` Adam Thornton
2024-06-20 19:59 ` Warner Losh
2024-06-20 20:12 ` ron minnich
2024-06-20 20:22 ` Adam Thornton
2024-06-20 20:29 ` ron minnich
2024-06-21 15:46 ` Chet Ramey via TUHS
2024-06-21 16:06 ` Henry Bent
2024-06-21 16:24 ` Chet Ramey via TUHS
2024-06-21 16:40 ` Henry Bent
2024-06-21 16:52 ` Warner Losh
2024-06-21 17:25 ` Chet Ramey via TUHS
2024-06-21 17:31 ` Phil Budne
2024-06-21 17:55 ` Chet Ramey via TUHS
2024-06-20 20:19 ` Clem Cole
2024-06-20 20:34 ` Luther Johnson
2024-06-20 21:00 ` ron minnich
2024-06-20 21:53 ` David Arnold
2024-06-20 22:00 ` ron minnich
2024-06-20 22:11 ` Larry McVoy
2024-06-20 22:35 ` Luther Johnson
2024-06-21 13:57 ` Stuff Received
2024-06-20 8:05 ` Steve Nickolas
2024-06-19 2:38 ` David Arnold
2024-06-19 22:52 ` Greg A. Woods
2024-06-19 0:08 ` Luther Johnson
2024-06-19 0:46 ` Nevin Liber
2024-06-19 1:00 ` segaloco via TUHS
2024-06-19 3:07 ` Luther Johnson
2024-06-19 3:14 ` Luther Johnson
2024-06-19 3:36 ` Luther Johnson
2024-06-19 6:50 ` arnold
2024-06-19 11:28 ` sjenkin
2024-06-19 9:00 ` Ralph Corderoy
2024-06-19 13:28 ` Larry McVoy
2024-06-19 14:44 ` Warner Losh
2024-06-19 14:53 ` Larry McVoy
2024-06-19 15:08 ` Warner Losh
2024-06-19 15:11 ` G. Branden Robinson
2024-06-19 15:16 ` ron minnich
2024-06-19 15:59 ` Theodore Ts'o
2024-06-19 22:48 ` Kevin Bowling
2024-06-20 5:14 ` David Arnold
2024-06-20 5:32 ` George Michaelson
2024-06-20 6:37 ` Alexis
2024-06-20 7:07 ` David Arnold
2024-06-21 15:41 ` Chet Ramey via TUHS
2024-06-21 15:38 ` Chet Ramey via TUHS
2024-06-20 20:14 ` Alexander Schreiber
2024-06-16 6:43 ` Wesley Parish
2024-06-16 21:56 ` David Arnold
2024-06-16 23:34 ` Luther Johnson
2024-06-16 23:46 ` Larry McVoy
2024-06-17 21:40 ` Steffen Nurpmeso
2024-06-17 0:54 ` Åke Nordin
2024-06-18 5:55 ` Alexis
2024-06-18 6:39 ` Michael Kjörling
2024-06-13 19:37 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' • " Alan D. Salewski
2024-06-13 20:05 ` Clem Cole
2024-06-13 20:31 ` Bakul Shah via TUHS
2024-06-13 20:06 ` A. P. Garcia
2024-06-13 20:26 ` Jim Capp
2024-06-13 21:35 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' ??? " Larry McVoy
2024-06-14 0:27 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' • " Alexis
2024-06-14 0:59 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' ??? " Larry McVoy
2024-06-14 1:11 ` Luther Johnson
2024-06-14 1:42 ` Alexis
2024-06-14 4:22 ` ron minnich
2024-06-14 6:54 ` Angel M Alganza
2024-06-14 7:04 ` Dave Horsfall
2024-06-14 7:33 ` arnold
2024-06-14 7:34 ` Andy Kosela
2024-06-14 7:44 ` Dave Horsfall
2024-06-14 11:31 ` Vincenzo Nicosia
2024-06-13 20:26 ` [TUHS] Re: Version 256 of systemd boasts '42% less Unix philosophy' • " Dave Horsfall
2024-06-14 11:32 ` Michael Kjörling
2024-06-14 12:21 ` A. P. Garcia
2024-06-18 12:02 ` Arrigo Triulzi via TUHS
2024-06-23 0:13 ` Dave Horsfall
2024-06-23 1:47 ` Alexis
2024-06-23 19:00 ` Theodore Ts'o
2024-06-23 20:04 ` Alexander Schreiber
2024-06-24 13:50 ` Theodore Ts'o
2024-06-24 14:21 ` Dan Cross
2024-06-26 7:39 ` Kevin Bowling
2024-06-24 15:03 ` Steffen Nurpmeso
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAC20D2OLExWuHYM67XMumPevaZuL6WmSCsJ6X0w80pjn15kNsw@mail.gmail.com \
--to=clemc@ccc.com \
--cc=bakul@iitbombay.org \
--cc=jnc@mercury.lcs.mit.edu \
--cc=tuhs@tuhs.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).