From: Sape Mullender <sape@plan9.bell-labs.com>
To: 9fans@cse.psu.edu
Subject: Re: [9fans] QTCTL?
Date: Thu, 1 Nov 2007 12:58:03 -0400 [thread overview]
Message-ID: <1e3bc7798b6eeadd827686536b41ec68@plan9.bell-labs.com> (raw)
In-Reply-To: <CD011460-455B-44B5-9DF3-73BB13EC37D1@lanl.gov>
> In the case of read cache (which is probably going to be used more
> often than write-cache), the client needs to send two RPC every time
> a writer modifies the cached file. What if Rlease doesn't necessary
> break the lease, but have an option (negotiated in Tcache) to let the
> client know that the file is changed without breaking the lease.
>
> Thanks,
> Lucho
Another point in this discussion:
1. Most files are not shared
2. Some files are read-shared
3. Very, very few files are read-write shared
(Satya did some research on this at CMU — quite some time ago)
Having said that, we do want correct semantics all the time,
especially for read-write sharing.
A file server can use heuristics to decide the time out for leases.
For example, it could always grant 10-minute leases to begin with.
Doesn't cost a thing unless the client refuses to return a lease early
(but clients will be rarely asked to do so).
With updates in the recent past, or with the first occurrence of
read-write sharing, lease times can be drastically reduced.
Note that for files not shared or read-shared, call backs do not happen,
so lease calls will occur at the rate of the lease time, which is
once every few minutes. Big deal.
Sape
next prev parent reply other threads:[~2007-11-01 16:58 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-10-31 18:40 Francisco J Ballesteros
2007-10-31 18:56 ` Eric Van Hensbergen
2007-10-31 19:13 ` Charles Forsyth
2007-10-31 19:33 ` Eric Van Hensbergen
2007-10-31 19:39 ` erik quanstrom
2007-10-31 20:43 ` geoff
2007-10-31 21:32 ` Charles Forsyth
2007-10-31 22:48 ` roger peppe
2007-10-31 23:35 ` erik quanstrom
2007-11-01 9:29 ` roger peppe
2007-11-01 11:03 ` Eric Van Hensbergen
2007-11-01 11:19 ` Charles Forsyth
2007-11-01 12:11 ` erik quanstrom
2007-10-31 19:42 ` erik quanstrom
2007-10-31 19:49 ` Eric Van Hensbergen
2007-10-31 20:03 ` erik quanstrom
2007-10-31 20:10 ` Latchesar Ionkov
2007-10-31 20:12 ` Eric Van Hensbergen
2007-10-31 20:17 ` Russ Cox
2007-10-31 20:29 ` Francisco J Ballesteros
2007-10-31 20:48 ` Charles Forsyth
2007-10-31 21:23 ` Francisco J Ballesteros
2007-10-31 21:40 ` Russ Cox
2007-10-31 22:11 ` Charles Forsyth
2007-10-31 22:26 ` Francisco J Ballesteros
2007-10-31 22:37 ` Charles Forsyth
2007-10-31 22:43 ` Francisco J Ballesteros
2007-10-31 23:32 ` Eric Van Hensbergen
2007-10-31 23:41 ` [V9fs-developer] " Charles Forsyth
[not found] ` <606b6f003ae9f0ed3e8c3c5f90ddc720@terzarima.net>
2007-11-01 1:13 ` Eric Van Hensbergen
2007-10-31 23:54 ` erik quanstrom
2007-11-01 0:03 ` Charles Forsyth
2007-11-01 1:25 ` Eric Van Hensbergen
2007-11-01 1:44 ` erik quanstrom
2007-11-01 2:15 ` Eric Van Hensbergen
2007-11-01 7:34 ` Skip Tavakkolian
2007-11-01 6:21 ` Bakul Shah
2007-11-01 14:28 ` Russ Cox
2007-11-01 14:38 ` erik quanstrom
2007-11-01 14:41 ` Charles Forsyth
2007-11-01 15:26 ` Sape Mullender
2007-11-01 15:51 ` Latchesar Ionkov
2007-11-01 16:04 ` ron minnich
2007-11-01 16:16 ` Latchesar Ionkov
2007-11-01 16:21 ` Sape Mullender
2007-11-01 16:58 ` Francisco J Ballesteros
2007-11-01 17:11 ` Charles Forsyth
2007-11-01 17:11 ` Francisco J Ballesteros
2007-11-01 17:13 ` Sape Mullender
2007-11-01 17:38 ` ron minnich
2007-11-01 17:56 ` Francisco J Ballesteros
2007-11-01 18:01 ` Francisco J Ballesteros
2007-11-01 18:52 ` Eric Van Hensbergen
2007-11-01 19:29 ` Francisco J Ballesteros
2007-11-01 23:24 ` ron minnich
2007-11-01 17:03 ` Russ Cox
2007-11-01 17:12 ` Sape Mullender
2007-11-01 17:35 ` erik quanstrom
2007-11-01 18:36 ` erik quanstrom
2007-11-01 17:13 ` Charles Forsyth
2007-11-01 17:16 ` Charles Forsyth
2007-11-01 17:20 ` Charles Forsyth
2007-11-01 17:52 ` Eric Van Hensbergen
2007-11-01 18:00 ` Latchesar Ionkov
2007-11-01 18:03 ` Francisco J Ballesteros
2007-11-01 18:08 ` Latchesar Ionkov
2007-11-01 18:16 ` erik quanstrom
2007-11-01 18:19 ` Francisco J Ballesteros
2007-11-01 18:35 ` Sape Mullender
2007-11-01 19:09 ` Charles Forsyth
2007-11-01 19:07 ` erik quanstrom
2007-11-01 17:14 ` Bakul Shah
2007-11-01 16:17 ` Sape Mullender
2007-11-01 16:27 ` Sape Mullender
2007-11-01 16:58 ` Sape Mullender [this message]
2007-11-01 16:59 ` Bakul Shah
2007-11-01 4:21 Brian L. Stuart
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=1e3bc7798b6eeadd827686536b41ec68@plan9.bell-labs.com \
--to=sape@plan9.bell-labs.com \
--cc=9fans@cse.psu.edu \
/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).