[LUAU] recommended reading

[Jim Thompson]

http://www.coss.fi/openmind/presentations
http://www.paulgraham.com/web20.html

[LUAU] ZFS (Zettabyte File System) blogfest....

[Jim Thompson]

So the code for ZFS has been released and is "Open", but not "Free" (its 
licensed under the SCDL).
For those of you wondering what ZFS is, here's a collection of links.  
Its all pro-Sun, of course.


http://blogs.sun.com/roller/page/bmc?entry=welcome_to_zfs

A port to linux is "being investigated":
http://www.sun.com/emrkt/campaign_docs/expertexchange/knowledge/solaris_zfs_gen.html#10

ZFS was primarily designed for deployment in an enterprise environment 
where performance and scalability are extremely critical. It was 
engineered with a totally different set of assumptions focused on 
managing a huge amount of storage, so comparing it to other contemporary 
filesystems like Reiser would probably not be a good use of time.


That said, a lot of the 'features' found in ZFS are not innovative 
per-se, and the kernel-userland interface is a bit gross (but who reads 
the source these days?)   Not sure how to define a good interface to LVM 
for dynamically sizing partitions ... no problem, just hack the entire 
LVM into the FS. Not sure how to put checksumming in the block layer to 
give reliable storage ... no problem, just hack parts of the block layer 
into the FS.   Parts of ZFS appear to be a huge layering hack to me, but 
as I said, who reads the source these days?


For the true hardcore linux user, most of what ZFS and Solaris provide 
in terms of innovation can be replicated in Linux with a bit of 
fiddling: a lot of what ZFS does can be done with md and lvm, zones are 
like vserver  (plus Linux also has UML and Xen, though Xen should be 
coming to Solaris too).


Still, ZFS is a package that is advertised to work well. With its 
self-healing capabilities and support for a new high-reliability data 
replication model called RAID-Z, a Linux port of ZFS could potentially 
become a very popular choice for commodity file servers in Enterprise 
environments, but the benefits of ZFS on a desktop Linux system are 
debatable.

Re: [LUAU] SMP kernel wierdness

[Brian Chee]

hmmmhard to answer...I just downloaded the network install for debian 64
and it just worked. Same for RHEL 64.

Default bios config using the onboard tyan SATA controller to a single
drive. More detail once I can boot up the machine...everything is torn apart
in my lab as I move.

/brian chee

University of Hawai'i at Manoa
School of Ocean & Earth Science & Technology
Advanced Network Computing Lab
1680 East West Road, POST rm 311
Honolulu, HI  96822
808-956-5797 voice, 877-284-1934 fax
- Original Message - 
From: "Jim Thompson" <[EMAIL PROTECTED]>
To: "LUAU" 
Sent: Monday, November 21, 2005 3:38 PM
Subject: Re: [LUAU] SMP kernel wierdness


> *which* smp kernel?  The "one that comes with centos"?   centos4? (which
> comes with a patched 2.6.9 kernel)
> *what* are the h/w configs?
>
> maybe some bootlog love?
>
> Does Monarch (or the mobo vendor) have a BIOS upgrade, by chance?
>
> jim
>
> Charles Lockhart wrote:
>
> >My workplace just got a bunch of dual athlon 64 x2 machines that we're
loading centos 4.x on and using to replace our older Sun machines.
Unfortunately, we get wierd behaviors when running the SMP kernels.  Bursty
keyboard interrupts (you can be typing just fine when suddenly the system
speeds up and iit'l look like ttthhhis)
and timing issues (the system clock seems to gain 7 minutes every hour).
> >
> >Switch to the single processor kernel and all the problems go away.
> >
> >Some of them are from Monarch Computer Systems, which supposedly puts out
pretty reliable Linux boxes.  Others are from other vendors, but the same
hardware configs.  All have wierd behaviors with the SMP kernel.
> >
> >Any recommendations?  Computer related I mean.  Right now considering how
much we have going on we're thinking of just punting and hoping it'll go
away with a later kernel update.
> >
> >-Charles
> >___
> >LUAU@lists.hosef.org mailing list
> >http://lists.hosef.org/cgi-bin/mailman/listinfo/luau
> >
> >
> ___
> LUAU@lists.hosef.org mailing list
> http://lists.hosef.org/cgi-bin/mailman/listinfo/luau

Re: [LUAU] SMP kernel wierdness

[Jim Thompson]

*which* smp kernel?  The "one that comes with centos"?   centos4? (which 
comes with a patched 2.6.9 kernel)
*what* are the h/w configs? 


maybe some bootlog love?

Does Monarch (or the mobo vendor) have a BIOS upgrade, by chance?

jim

Charles Lockhart wrote:


My workplace just got a bunch of dual athlon 64 x2 machines that we're loading 
centos 4.x on and using to replace our older Sun machines.  Unfortunately, we 
get wierd behaviors when running the SMP kernels.  Bursty keyboard interrupts 
(you can be typing just fine when suddenly the system speeds up and 
iit'l look like ttthhhis) and timing issues 
(the system clock seems to gain 7 minutes every hour).

Switch to the single processor kernel and all the problems go away.

Some of them are from Monarch Computer Systems, which supposedly puts out 
pretty reliable Linux boxes.  Others are from other vendors, but the same 
hardware configs.  All have wierd behaviors with the SMP kernel.

Any recommendations?  Computer related I mean.  Right now considering how much 
we have going on we're thinking of just punting and hoping it'll go away with a 
later kernel update.

-Charles
___
LUAU@lists.hosef.org mailing list
http://lists.hosef.org/cgi-bin/mailman/listinfo/luau
 

[LUAU] SMP kernel wierdness

[Charles Lockhart]

My workplace just got a bunch of dual athlon 64 x2 machines that we're loading 
centos 4.x on and using to replace our older Sun machines.  Unfortunately, we 
get wierd behaviors when running the SMP kernels.  Bursty keyboard interrupts 
(you can be typing just fine when suddenly the system speeds up and 
iit'l look like ttthhhis) and timing issues 
(the system clock seems to gain 7 minutes every hour).

Switch to the single processor kernel and all the problems go away.

Some of them are from Monarch Computer Systems, which supposedly puts out 
pretty reliable Linux boxes.  Others are from other vendors, but the same 
hardware configs.  All have wierd behaviors with the SMP kernel.

Any recommendations?  Computer related I mean.  Right now considering how much 
we have going on we're thinking of just punting and hoping it'll go away with a 
later kernel update.

-Charles
From [EMAIL PROTECTED]  Mon Nov 21 13:07:54 2005
Return-Path: <[EMAIL PROTECTED]>
X-Original-To: luau@lists.hosef.org
Delivered-To: luau@lists.hosef.org
Received: from jem01.its.hawaii.edu (jem01.its.hawaii.edu [128.171.224.23])
by lists.hosef.org (Postfix) with ESMTP id 96AFB1B002E
for ; Mon, 21 Nov 2005 13:07:19 -1000 (HST)
Received: from pmxchannel-daemon.jem01.its.hawaii.edu by jem01.its.hawaii.edu
(Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005))
id <[EMAIL PROTECTED]>; Mon,
21 Nov 2005 13:06:54 -1000 (HST)
Received: from briandell ([128.171.104.187])
by jem01.its.hawaii.edu (Sun Java System Messaging Server 6.2-3.04
(built Jul
15 2005)) with ESMTPSA id <[EMAIL PROTECTED]>; Mon,
21 Nov 2005 13:06:34 -1000 (HST)
Date: Mon, 21 Nov 2005 13:04:36 -1000
From: Brian Chee <[EMAIL PROTECTED]>
Subject: Re: [LUAU] SMP kernel wierdness
To: LUAU 
Message-id: <[EMAIL PROTECTED]>
Organization: University of Hawaii SOEST
MIME-version: 1.0
X-MIMEOLE: Produced By Microsoft MimeOLE V6.00.2800.1506
X-Mailer: Microsoft Outlook Express 6.00.2800.1506
Content-type: text/plain; charset=iso-8859-1
Content-transfer-encoding: 7BIT
X-Priority: 3
X-MSMail-priority: Normal
X-PMX-Version: 5.1.0.207369, Antispam-Engine: 2.1.0.0,
Antispam-Data: 2005.11.21.28
References: <[EMAIL PROTECTED]>
X-BeenThere: luau@lists.hosef.org
X-Mailman-Version: 2.1.5
Precedence: list
Reply-To: LUAU 
List-Id: LUAU 
List-Unsubscribe: ,

List-Archive: 
List-Post: 
List-Help: 
List-Subscribe: ,

X-List-Received-Date: Mon, 21 Nov 2005 23:07:54 -

hmmmmy tyan based Opterons (64x2) work great on both debian and
rhel...no keyboard problems to report hereit even behaves when running 8
VMWare images...this was also using a Raritan KX-232 IP KVM using the CAT5
dongles...which traditionally had keyboard wake up problems...but that went
away once the OHCI drivers got updated.

Sorry I was not of help...but those two distros are not giving me
problemsthey also behaved on the 8-way Opterons from HP also with
VMWare...but we got that up to 16 images...without breathing hard...both
were 2.6 kernels.

/brian chee

University of Hawai'i at Manoa
School of Ocean & Earth Science & Technology
Advanced Network Computing Lab
1680 East West Road, POST rm 311
Honolulu, HI  96822
808-956-5797 voice, 877-284-1934 fax
- Original Message -
From: "Charles Lockhart" <[EMAIL PROTECTED]>
To: "LUAU" 
Sent: Monday, November 21, 2005 11:24 AM
Subject: [LUAU] SMP kernel wierdness


My workplace just got a bunch of dual athlon 64 x2 machines that we're
loading centos 4.x on and using to replace our older Sun machines.
Unfortunately, we get wierd behaviors when running the SMP kernels.  Bursty
keyboard interrupts (you can be typing just fine when suddenly the system
speeds up and iit'l look like ttthhhis)
and timing issues (the system clock seems to gain 7 minutes every hour).

Switch to the single processor kernel and all the problems go away.

Some of them are from Monarch Computer Systems, which supposedly puts out
pretty reliable Linux boxes.  Others are from other vendors, but the same
hardware configs.  All have wierd behaviors with the SMP kernel.

Any recommendations?  Computer related I mean.  Right now considering how
much we have going on we're thinking of just punting and hoping it'll go
away with a later kernel update.

-Charles
___
LUAU@lists.hosef.org mailing list
http://lists.hosef.org/cgi-bin/mailman/listinfo/luau