9fans - fans of the OS Plan 9 from Bell Labs
 help / color / mirror / Atom feed
From: Bakul Shah <bakul@bitblocks.com>
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Subject: Re: [9fans] Q: moving directories? hard links?
Date: Fri, 22 Apr 2011 01:03:52 -0700	[thread overview]
Message-ID: <20110422080352.DF703B835@mail.bitblocks.com> (raw)
In-Reply-To: Your message of "Thu, 21 Apr 2011 18:41:25 EDT." <9482032322d5daaadceace1f6875dad3@coraid.com>

On Thu, 21 Apr 2011 18:41:25 EDT erik quanstrom <quanstro@labs.coraid.com>  wrote:
> > IIRC companies such as Panasas separate file names and other
> > metadata from file storage. One way to get a single FS
> > namespace that spans multiple disks or nodes for increasing
> > data redundancy, file size beyond the largest disk size,
> > throughput (and yes, complexity).
>
> that certainly does seem like the hard way to do things.
> why should the structure of the data depend on where it's
> located?  certainly ken's fs doesn't change the format of
> the worm if you concatinate several devices for the worm
> or use just one.

?

It all boils down to having to cope with individual units'
limits and failures.

If a file needs to be larger than the capacity of the largest
disk, you stripe data across multiple disks.  To handle disk
failures you use mirroring or parity across multiple disks.
To increase performance beyond what a single controller can
do, you add multiple disk controllers.  When you want higher
capacity and throughput than is possible on a single node, you
use a set of nodes, and stripe data across them. To handle a
single node failure you mirror data across multiple nodes. To
support increased lookups & metadata operations, you separate
metadata storage  & nodes from file storage & nodes as lookups
+ metadata have a different access pattern from file data
access. To handle more concurrent access you add more net
bandwidth and balance it across nodes.

>From an adminstrative point of view a single global namespace
is much easier to manage. One should be able to add or replace
individual units (disks, nodes, network capacity) quickly as
and when needed without taking the FS down (to reduce
administrative costs and to avoid any downtime). Then you have
to worry about backups (on and offsite). In such a complex
system, the concept of a single `volume' doesn't work well.
In any case, users don't care about what data layout is used
as long as the system can grow to fill their needs.



  parent reply	other threads:[~2011-04-22  8:03 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-04-16  2:36 smiley
2011-04-16  2:40 ` Jacob Todd
2011-04-16  4:22 ` ron minnich
2011-04-16 16:53   ` erik quanstrom
2011-04-16 17:33   ` smiley
2011-04-16 17:51     ` erik quanstrom
2011-04-21 15:32       ` smiley
2011-04-21 15:43         ` ron minnich
2011-04-16 18:22     ` Bakul Shah
2011-04-21 15:44       ` smiley
2011-04-21 15:49         ` ron minnich
2011-04-21 16:54         ` Bakul Shah
2011-04-21 20:17           ` Richard Miller
2011-04-21 21:10             ` Bakul Shah
2011-04-21 22:41               ` erik quanstrom
2011-04-21 23:17                 ` ron minnich
2011-04-21 23:54                   ` Bakul Shah
2011-04-21 23:55                   ` erik quanstrom
2011-04-22  0:01                     ` ron minnich
2011-04-22  0:04                       ` erik quanstrom
2011-04-22  8:03                 ` Bakul Shah [this message]
2011-04-22  8:27                   ` dexen deVries
2011-04-22 13:05                   ` erik quanstrom
2011-04-22 17:47                     ` Bakul Shah
2011-04-24 18:58                       ` erik quanstrom
2011-04-16 18:03   ` Richard Miller
2011-04-16 18:17     ` Skip Tavakkolian
2011-04-16 18:56       ` Rob Pike
2011-04-18  9:08         ` Aharon Robbins
2011-04-18 12:41           ` erik quanstrom
2011-04-18 12:59             ` Lucio De Re
2011-04-18 13:00               ` erik quanstrom
2011-04-18 13:11                 ` Lucio De Re
2011-04-23  3:48                   ` Ethan Grammatikidis
2011-04-21  9:22       ` Balwinder S Dheeman
2011-04-16 16:58 ` erik quanstrom
2011-04-19 15:36 ` Charles Forsyth

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=20110422080352.DF703B835@mail.bitblocks.com \
    --to=bakul@bitblocks.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).