9fans - fans of the OS Plan 9 from Bell Labs
 help / color / mirror / Atom feed
From: ron minnich <rminnich@gmail.com>
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Subject: [9fans] simple venti demo:
Date: Wed, 10 Aug 2011 13:53:49 -0700	[thread overview]
Message-ID: <CAP6exYKWeCLRiUUjMr88ByWZbubxvvHsqqOKad0Mvk+wycSbDg@mail.gmail.com> (raw)

I've been working with people who anticipate that big flash that looks
like ram will be available mid/end of the decade. By big, I mean big
as your disk. By RAM, yep, I mean RAM. Reboot, it's all still there.

Needless to say, this changes things a bit. I also noticed the venti
stats: many of the ventis I've seen don't have more than about 30G
used. 30G? I can get a 1U with 512G for 18K nowadays. 1TB for 36K.

Finally, it's always bothered me that to most people, Plan 9 file
systems are a black box. Plan9ports has a very nice "devnull" venti
that seemed like it could be used for a real system.

I thought it might be fun to have a very simple venti that uses an
mmapped backing store and a common hash library (posix hash, available
everywhere) as a demo and to maybe get people wanting to hack in this
area. So on the long boring flight to Spain, I threw one together.

So, see it here: http://pastebin.com/47aC2XGv

To use, just drop into src/cmd/venti, fix mkfile, mk all

to make an arena, the usual dd from /dev/zero

To run, you can, e.g.:
./o.devram -s 2   -a 'tcp!*!6666' /tmp/arenas
the '2' here means two GB. To grow the arena, tack zeros onto the end,
and restart.

To test, used randtest. Or vac. Or whatever.

I've set -s to 32 and had a 32GB venti. Sync is a no-op; it always
syncs on each write. Performance: well, you try it :-)

Mistakes and bugs and things to be done better? Of course! Lucho
pointed out some to me already. You can find more. Hack away!

And, there's going to be a better version soon. I think. But the more
versions floating around, the better.

have fun.

ron



             reply	other threads:[~2011-08-10 20:53 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-08-10 20:53 ron minnich [this message]
2011-08-10 21:36 ` Lyndon Nerenberg (VE6BBM/VE7TFX)
2011-08-10 21:47   ` ron minnich
2011-08-10 21:54     ` Lyndon Nerenberg (VE6BBM/VE7TFX)
2011-08-10 21:57       ` erik quanstrom
2011-08-10 22:04       ` Bakul Shah
2011-08-10 22:07         ` Lyndon Nerenberg (VE6BBM/VE7TFX)
2011-08-10 22:12           ` ron minnich
2011-08-11 16:15             ` ron minnich
2011-08-11 16:49               ` David Leimbach
2011-08-11 17:18                 ` Latchesar Ionkov
2011-08-11 19:20               ` Bakul Shah
2011-08-11 19:54               ` Bakul Shah
2011-08-11 20:03                 ` erik quanstrom
2011-08-11 20:07                   ` ron minnich
2011-08-11 20:50                     ` David Leimbach
2011-08-11 21:03                       ` ron minnich
2011-08-11 21:19                       ` Fazlul Shahriar
2011-08-11 21:42                         ` David Leimbach
2011-08-11 21:54                           ` ron minnich
2011-08-11 22:00                             ` David Leimbach
2011-08-11 21:59                           ` Fazlul Shahriar
2011-08-11 20:04                 ` ron minnich
2011-08-11 20:20                   ` Bakul Shah
     [not found]                 ` <CAP6exYK9pwpRctLeuehEMdmVVW73sC7VOxujRq-Gwu9=gCDQQQ@mail.gmail.c>
2011-08-11 20:19                   ` erik quanstrom
2011-08-12  7:50               ` dexen deVries
2011-08-12 15:45                 ` ron minnich
     [not found]             ` <CAP6exYLmZXLCgBsczjR5e87B095R231WLp3hi0VZOtxgmBd5kw@mail.gmail.c>
2011-08-11 16:49               ` erik quanstrom
2011-08-11 16:55                 ` David Leimbach
2011-08-11 16:56                 ` ron minnich
     [not found]                 ` <CAP6exYJEgJ=KbAtiQR5+qPzYPwWgPU0xtxV1wDY4H_BN_5pWTg@mail.gmail.c>
2011-08-11 17:28                   ` erik quanstrom
2011-08-11 17:37                     ` ron minnich
2011-08-11 18:45                       ` David Leimbach
     [not found]                     ` <CAP6exY+0wGYT2ojbmm+8F1R48w0tycgRTR3KGTm_yki9A7cmSw@mail.gmail.c>
2011-08-11 17:58                       ` erik quanstrom
2011-08-11  3:05           ` David Leimbach
2011-08-11  6:21             ` ron minnich
2011-08-11 13:21               ` Eric Van Hensbergen
2011-08-11 15:09               ` Charles Forsyth
2011-08-11 15:16                 ` Eric Van Hensbergen
2011-08-11 17:06                 ` Salman Aljammaz
2011-08-11 18:33             ` Lyndon Nerenberg (VE6BBM/VE7TFX)
2011-08-11 18:46               ` David Leimbach
2011-08-12 16:18 ` Russ Cox
2011-08-12 18:29   ` Wes Kussmaul

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=CAP6exYKWeCLRiUUjMr88ByWZbubxvvHsqqOKad0Mvk+wycSbDg@mail.gmail.com \
    --to=rminnich@gmail.com \
    --cc=9fans@9fans.net \
    /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).