From: George Michaelson <ggm@algebras.org>
To: Larry McVoy <lm@mcvoy.com>
Cc: TUHS main list <tuhs@minnie.tuhs.org>
Subject: Re: [TUHS] If not Linux, then what?
Date: Wed, 28 Aug 2019 08:30:01 +1000 [thread overview]
Message-ID: <CAKr6gn2V_T_EnYaz3OYassHSpLecoKTkqZe+By8A9kQQ=7jnMA@mail.gmail.com> (raw)
In-Reply-To: <20190827145556.GD13570@mcvoy.com>
BSD, but with the original STREAMS semantics, not sockets.
DARPA did us no favours accepting sockets in place of simple file I/O
semantics for networks.
Newcastle connection put the namespace into
/.../remote-part/path/to/thing which I felt was also good.
So for me, 7 -> BSD -> got worse for some values of worse
On Wed, Aug 28, 2019 at 12:56 AM Larry McVoy <lm@mcvoy.com> wrote:
>
> On Mon, Aug 26, 2019 at 11:14:45PM -0400, Arthur Krewat wrote:
> > On 8/26/2019 10:45 PM, Larry McVoy wrote:
> > > Which was that the page cache is
> > >*the* cache. There is nothing else.
> > Yeah, I re-read what you wrote a few times after I replied, and realized
> > what you meant ... eventually ;)
>
> I might be making too big of a deal about it. mmap semantics mattered
> a lot when SMPs first showed up and main memory was small. It meant
> that you could have multiple CPUs seeing and working on the same chunk
> of data at the same time.
>
> It's very similar to way that IOMMUs are exposed to user space these
> days, enabling virtual machines direct access to the I/O devices.
>
> ZFS breaks that model, the data is all in the ARC and if you mmap
> it they have to bcopy the data out of the ARC, into the page cache
> and now they have a consistency problem, you could modify stuff
> via mmap or write and they have to manage that.
>
> That consistency problem is the main reason that Sun almost completely
> killed the buffer cache (it still was used for inodes and directories
> but that was it). That consistency problem is a pain in the rear,
> all sorts of race conditions and it tended to bit rot.
>
> Jeff and Bill are smart people so I suspect they got it right but I'm
> still stunned that they took such an architecturally bad approach.
> And even more stunned that the oversight people approved it. There
> is zero chance that the Sun I worked at would have allowed that.
>
> --lm
next prev parent reply other threads:[~2019-08-27 22:30 UTC|newest]
Thread overview: 96+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-26 23:13 Arthur Krewat
2019-08-26 23:27 ` Warner Losh
2019-08-26 23:37 ` Larry McVoy
2019-08-26 23:56 ` William Pechter
2019-08-27 0:19 ` Arthur Krewat
2019-08-27 0:30 ` Larry McVoy
2019-08-27 0:58 ` Rob Pike
2019-08-27 1:06 ` Clem Cole
2019-08-27 2:53 ` Larry McVoy
2019-08-27 9:47 ` Rob Pike
2019-08-27 7:47 ` arnold
2019-08-27 16:05 ` [TUHS] Running v10 Angelo Papenhoff
2019-08-27 16:27 ` Henry Bent
2019-08-28 4:22 ` Jason Stevens
2019-08-28 7:34 ` Angelo Papenhoff
2019-08-28 16:46 ` Henry Bent
2019-08-27 0:59 ` [TUHS] If not Linux, then what? Arthur Krewat
2019-08-27 1:26 ` Dan Cross
2019-08-27 2:45 ` Larry McVoy
2019-08-27 3:14 ` Arthur Krewat
2019-08-27 14:55 ` Larry McVoy
2019-08-27 22:30 ` George Michaelson [this message]
2019-08-27 22:40 ` Larry McVoy
2019-08-27 22:46 ` George Michaelson
2019-08-27 22:59 ` [TUHS] [SPAM] " Larry McVoy
2019-08-27 23:10 ` [TUHS] " Clem Cole
2019-08-28 0:07 ` George Michaelson
2019-08-28 3:22 ` [TUHS] [SPAM] " Rob Pike
2019-08-28 3:25 ` Rob Pike
2019-08-28 4:05 ` Larry McVoy
2019-08-28 13:52 ` Clem Cole
2019-08-28 14:31 ` [TUHS] " Larry McVoy
2019-08-28 14:57 ` Clem Cole
2019-08-28 6:19 ` Wesley Parish
2019-08-28 6:30 ` Peter Jeremy
2019-08-28 11:05 ` Jason Stevens
2019-08-28 11:11 ` Arrigo Triulzi
2019-08-28 14:04 ` Clem Cole
2019-08-28 16:34 ` Henry Bent
2019-08-28 17:32 ` Larry McVoy
2019-08-28 17:51 ` Jon Forrest
2019-08-28 18:56 ` Clem Cole
2019-08-28 20:23 ` Arrigo Triulzi
2019-08-29 3:24 ` Lawrence Stewart
2019-08-29 10:55 ` Tony Finch
2019-08-28 13:57 ` Clem Cole
2019-08-28 12:46 ` Warner Losh
2019-08-27 23:16 ` Bakul Shah
2019-08-27 23:33 ` Larry McVoy
2019-08-28 0:21 ` Bakul Shah
2019-08-28 1:21 ` Arthur Krewat
2019-08-28 1:46 ` Larry McVoy
2019-08-27 0:48 ` Clem Cole
2019-08-27 1:25 ` Gregg Levine
2019-08-27 2:16 ` Theodore Y. Ts'o
2019-08-27 2:39 ` Larry McVoy
2019-08-27 5:54 ` Adam Thornton
2019-08-27 6:05 ` Gregg Levine
2019-08-27 1:17 ` Dan Cross
2019-08-28 3:53 ` Charles H. Sauer
2019-08-28 4:30 ` Jason Stevens
2019-08-28 9:36 ` Angus Robinson
2019-08-28 9:50 ` Michael Kjörling
2019-08-28 10:48 ` arnold
2019-08-28 14:10 ` Earl Baugh
2019-08-28 14:55 ` Clem Cole
2019-08-28 14:22 ` Charles H Sauer
2019-08-28 15:00 ` Steve Nickolas
2019-08-28 15:37 ` Richard Salz
2019-08-28 19:54 ` Peter Jeremy
2019-08-28 20:05 ` Christopher Browne
2019-08-28 20:07 ` Christopher Browne
2019-08-28 20:27 ` Adam Thornton
2019-08-28 20:56 ` William Pechter
2019-08-28 22:24 ` Clem cole
2019-08-28 22:27 ` William Pechter
2019-08-28 22:53 ` Arthur Krewat
2019-08-29 18:40 ` Nemo Nusquam
2019-08-29 19:18 ` Steffen Nurpmeso
2019-08-28 22:28 ` Clem cole
2019-08-28 22:48 ` Adam Thornton
2019-08-28 23:01 ` William Pechter
2019-08-28 23:09 ` Adam Thornton
2019-08-29 6:37 ` Wesley Parish
2019-08-28 23:04 ` Gregg Levine
2019-08-29 11:12 ` Tony Finch
2019-08-28 23:19 ` Theodore Y. Ts'o
2019-08-29 13:31 ` A. P. Garcia
2019-08-29 13:55 ` Arthur Krewat
2019-08-29 15:54 ` Thomas Paulsen
2019-08-29 19:19 ` Steffen Nurpmeso
2019-08-31 1:35 ` Dave Horsfall
2019-08-31 15:14 ` Steffen Nurpmeso
2019-08-31 16:58 ` Christopher Browne
2019-08-31 21:20 ` Theodore Y. Ts'o
2019-08-28 21:02 ` Thomas Paulsen
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='CAKr6gn2V_T_EnYaz3OYassHSpLecoKTkqZe+By8A9kQQ=7jnMA@mail.gmail.com' \
--to=ggm@algebras.org \
--cc=lm@mcvoy.com \
--cc=tuhs@minnie.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).