From: Jamie Lokier <jamie@shareable.org>
To: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
Cc: Sage Weil <sage@newdream.net>, Jeff Garzik <jeff@garzik.org>,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
linux-fsdevel@vger.kernel.org
Subject: Re: POHMELFS high performance network filesystem. Transactions, failover, performance.
Date: Wed, 14 May 2008 22:32:51 +0100 [thread overview]
Message-ID: <20080514213251.GB23758@shareable.org> (raw)
In-Reply-To: <20080514150052.GA15826@2ka.mipt.ru>
Evgeniy Polyakov wrote:
> If I understood that, client has to connect to all servers and send data
> there, so that after single reply things got committed. That is
> definitely not the issue, when there are lots of servers.
>
> That can be the case if client connects to some gate server, which in
> turn broadcasts data further, that is how I plan to implement things at
> first.
Look up Bittorrent, and bandwidth diffusion generally. Also look up
multicast trees.
Sometimes it's faster for a client to send to many servers; sometimes
it's faster to send fewer and have them relayed by intermediaries -
because every packet takes time to transmit, and network topologies
aren't always homogenous or symmetric.
There is no simple answer which is optimal for all networks.
> Another approach, which seems also intersting is leader election (per
> client), so that leader would broadcast all the data.
Leader election is part of standard Paxos too :-)
If you have a single data forwarder elected per client, then if one
client generates a lot of traffic, you concentrate a lot of traffic to
one network link and one CPU. Sometimes it's better to elect several
leaders per client, and hash requests onto them. You diffuse CPU and
traffic, but reduce opportunities to aggregate transactions into fewer
message. It's an interesting problem, again probably with different
optimal results for different networks.
-- Jamie
next prev parent reply other threads:[~2008-05-14 21:33 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-05-13 17:45 POHMELFS high performance network filesystem. Transactions, failover, performance Evgeniy Polyakov
2008-05-13 19:09 ` Jeff Garzik
2008-05-13 20:51 ` Evgeniy Polyakov
2008-05-14 0:52 ` Jamie Lokier
2008-05-14 1:16 ` Florian Wiessner
2008-05-14 8:10 ` Evgeniy Polyakov
2008-05-14 7:57 ` Evgeniy Polyakov
2008-05-14 13:35 ` Sage Weil
2008-05-14 13:52 ` Evgeniy Polyakov
2008-05-14 14:31 ` Jamie Lokier
2008-05-14 15:00 ` Evgeniy Polyakov
2008-05-14 19:08 ` Jeff Garzik
2008-05-14 19:32 ` Evgeniy Polyakov
2008-05-14 20:37 ` Jeff Garzik
2008-05-14 21:19 ` Evgeniy Polyakov
2008-05-14 21:34 ` Jeff Garzik
2008-05-14 21:32 ` Jamie Lokier [this message]
2008-05-14 21:37 ` Jeff Garzik
2008-05-14 21:43 ` Jamie Lokier
2008-05-14 22:02 ` Evgeniy Polyakov
2008-05-14 22:28 ` Jamie Lokier
2008-05-14 22:45 ` Evgeniy Polyakov
2008-05-15 1:10 ` Jamie Lokier
2008-05-15 7:34 ` Evgeniy Polyakov
2008-05-14 19:05 ` Jeff Garzik
2008-05-14 21:38 ` Jamie Lokier
2008-05-14 19:03 ` Jeff Garzik
2008-05-14 19:38 ` Evgeniy Polyakov
2008-05-14 21:57 ` Jamie Lokier
2008-05-14 22:06 ` Jeff Garzik
2008-05-14 22:41 ` Evgeniy Polyakov
2008-05-14 22:50 ` Evgeniy Polyakov
2008-05-14 22:32 ` Evgeniy Polyakov
2008-05-14 14:09 ` Jamie Lokier
2008-05-14 16:09 ` Sage Weil
2008-05-14 19:11 ` Jeff Garzik
2008-05-14 21:19 ` Jamie Lokier
2008-05-14 18:24 ` Jeff Garzik
2008-05-14 20:00 ` Sage Weil
2008-05-14 21:49 ` Jeff Garzik
2008-05-14 22:26 ` Sage Weil
2008-05-14 22:35 ` Jamie Lokier
2008-05-14 6:33 ` Andrew Morton
2008-05-14 7:40 ` Evgeniy Polyakov
2008-05-14 8:01 ` Andrew Morton
2008-05-14 8:31 ` Evgeniy Polyakov
2008-05-14 8:08 ` Evgeniy Polyakov
2008-05-14 13:41 ` Sage Weil
2008-05-14 13:56 ` Evgeniy Polyakov
2008-05-14 17:56 ` Andrew Morton
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=20080514213251.GB23758@shareable.org \
--to=jamie@shareable.org \
--cc=jeff@garzik.org \
--cc=johnpol@2ka.mipt.ru \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=sage@newdream.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).