From: Mike Christie <michaelc@cs.wisc.edu>
To: device-mapper development <dm-devel@redhat.com>
Subject: Re: Block multipathing in an IP-SAN
Date: Wed, 02 Nov 2005 00:56:06 -0600 [thread overview]
Message-ID: <43686306.9030701@cs.wisc.edu> (raw)
In-Reply-To: <C2EEB4E538D3DC48BF57F391F422779321AD90@SRMANNING.eng.emc.com>
goggin, edward wrote:
> I'm wondering about how block device multipathing works in conjunction with
> the high availability
> features of an IP-SAN.
>
> Does the iSCSI initiator's session layer's retransmission capability and the
> IP-takeover capability
> of IP-SAN switches eliminate the need for block device multipathing in an
> IP-SAN?
>
> Does the iSCSI initiator present redundant paths to the SCSI mid-layer?
>
> Do these answers differ with software verses hardware iSCSI initiators?
>
For linux mainline and what some distros carry, software will be similar
to HW iscsi becuase the linux-scsi community has not wanted MCS. For
software iscsi in mainline (open-iscsi/linux-iscsi-5) and RHEL 4
(linux-iscsi-4), you can use bonding or trunking - whatever you know it
as, and hide everything from the iSCSI and SCSI levels, or you can use
dm-multipath. To do the latter for software iscsi, the iscsi driver
creates a session to each portal, scans it, and dm-multipath/multipath
assembles dm devices like it would for FC. The softare drivers drivers
also support login redirect and some vendors use this for failover and
load balancing. I think qlogic also support this.
prev parent reply other threads:[~2005-11-02 6:56 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-11-01 22:19 Block multipathing in an IP-SAN goggin, edward
2005-11-02 6:56 ` Mike Christie [this message]
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=43686306.9030701@cs.wisc.edu \
--to=michaelc@cs.wisc.edu \
--cc=dm-devel@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.