[8987] in linux-scsi channel archive

home help back first fref pref prev next nref lref last post

multi-initiator?

daemon@ATHENA.MIT.EDU (Ralston, Steve)
Wed Jun 14 21:59:34 2000

Message-Id: <B2B3C90E45AED111B7B40001FA7E520A0383424F@exw-kansas.ks.lsil.com>
From: "Ralston, Steve" <sralston@lsil.com>
To: linux-scsi@vger.rutgers.edu
Date:	Wed, 14 Jun 2000 20:49:22 -0500
MIME-Version: 1.0
Content-Type: multipart/alternative;
	boundary="----_=_NextPart_001_01BFD66B.EFA89BB4"

This message is in MIME format. Since your mail reader does not understand
this format, some or all of this message may not be legible.

------_=_NextPart_001_01BFD66B.EFA89BB4
Content-Type: text/plain

Sorry if this has been covered here in the past.  Searches of
various linux mlists for "multi|initiator|reserve|release" failed to
turn up anything (recent) that looked particularly related, so here goes...

There's been some recent discussion and questions 'round here
about multi-initiator setups on linux.  From what I can determine,
the linux scsi mid-layer doesn't do any sort of RESERVE / RELEASE
stuff.  (RESERVE_10, RELEASE_10 weren't even defined in
<scsi/scsi.h> until very recently).

So with two or three linux systems attached to the same fibre channel
(loop in this case:-), I can mount the same target (ext2 f.s.) from
any+all the systems and (blindly+) merrily work away...
while eventual multiple writes clobber the file system, right?

Or is this handled via some other mechanism?
 + Driver(s) responsible for handling any+all multi-initiator issues.
 + LVM, clustering, or somesuch?

Thanks,
-SteveR


------_=_NextPart_001_01BFD66B.EFA89BB4
Content-Type: text/html

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=US-ASCII">
<META NAME="Generator" CONTENT="MS Exchange Server version 5.5.2650.12">
<TITLE>multi-initiator?</TITLE>
</HEAD>
<BODY>

<P><FONT SIZE=2 FACE="Arial">Sorry if this has been covered here in the past.&nbsp; Searches of</FONT>
<BR><FONT SIZE=2 FACE="Arial">various linux mlists for &quot;multi|initiator|reserve|release&quot; failed to</FONT>
<BR><FONT SIZE=2 FACE="Arial">turn up anything (recent) that looked particularly related, so here goes...</FONT>
</P>

<P><FONT SIZE=2 FACE="Arial">There's been some recent discussion and questions 'round here</FONT>
<BR><FONT SIZE=2 FACE="Arial">about multi-initiator setups on linux.&nbsp; From what I can determine,</FONT>
<BR><FONT SIZE=2 FACE="Arial">the linux scsi mid-layer doesn't do any sort of RESERVE / RELEASE</FONT>
<BR><FONT SIZE=2 FACE="Arial">stuff.&nbsp; (RESERVE_10, RELEASE_10 weren't even defined in</FONT>
<BR><FONT SIZE=2 FACE="Arial">&lt;scsi/scsi.h&gt; until very recently).</FONT>
</P>

<P><FONT SIZE=2 FACE="Arial">So with two or three linux systems attached to the same fibre channel</FONT>
<BR><FONT SIZE=2 FACE="Arial">(loop in this case:-), I can mount the same target (ext2 f.s.) from</FONT>
<BR><FONT SIZE=2 FACE="Arial">any+all the systems and (blindly+) merrily work away...</FONT>
<BR><FONT SIZE=2 FACE="Arial">while eventual multiple writes clobber the file system, right?</FONT>
</P>

<P><FONT SIZE=2 FACE="Arial">Or is this handled via some other mechanism?</FONT>
<BR><FONT SIZE=2 FACE="Arial">&nbsp;+ Driver(s) responsible for handling any+all multi-initiator issues.</FONT>
<BR><FONT SIZE=2 FACE="Arial">&nbsp;+ LVM, clustering, or somesuch?</FONT>
</P>

<P><FONT SIZE=2 FACE="Arial">Thanks,</FONT>
<BR><FONT SIZE=2 FACE="Arial">-SteveR</FONT>
</P>

</BODY>
</HTML>
------_=_NextPart_001_01BFD66B.EFA89BB4--

-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@vger.rutgers.edu

home help back first fref pref prev next nref lref last post