Andrea Cerrito | 15 Oct 2002 20:35
Picon

What happen when inodes or metadata = 100%?


-----BEGIN PGP SIGNED MESSAGE-----

Hi to list,

what happen when inodes or metadata is equal to 100%?

IE:
Type           Total          Used           Free           use%
- ----------------------------------------------------------------------
- --
inodes         19453          18231          1222           94%
metadata       2312           826            1486           36%
data           4125751        386983         3738768        9%

And, what are the corrective solutions?
Thanks

Andrea Cerrito
IT Manager

+39.  0744.  5441. 1
+39.  348.   4912. 581

www.centromultimediale.tv
www.centromultimediale.it
www.etad.it 

== /history
Due giovani e uno meno giovane si trovano proiettati a causa di una
(Continue reading)

Andrea Cerrito | 15 Oct 2002 20:34
Picon

Preferred way to backup


-----BEGIN PGP SIGNED MESSAGE-----

Hi.

Is there any preferred solution to backup a gfs partition?
Can the "dump" command work without problems?
Maybe tar? Or any other command gfs-specific command?
Thanks

Andrea Cerrito
IT Manager

+39.  0744.  5441. 1
+39.  348.   4912. 581

www.centromultimediale.tv
www.centromultimediale.it
www.etad.it 

== /history
Due giovani e uno meno giovane si trovano proiettati a causa di una
serie di fatalita' in un mondo parallelo dove non esistono le leggi
del business ma solo follia e dolore.

-----BEGIN PGP SIGNATURE-----
Version: PGP 7.0.4

iQEVAwUBPaxfnvo9HK4+yTI3AQEU9Af/W9l43YwtFkb3V5kV4nTSUcu2g0lNEGHM
3tObKVMmPWRvUycNiP44v35GFtNluIghA8LGZ1N0yz1ydU4o/Z79yvlWBvdIZuqy
(Continue reading)

Manuela Fortes | 11 Sep 2002 02:16
Picon
Favicon

recipe for gfs whit parallel scsi and gulm

Hi,

I'm begginer with GFS and i need some helps please.
I've gfs 5.1.0 to evaluate which software license
number is BE-0005-10001015.
I want to set up GFS on cluster of nodes with parallel
SCSI with IP lock server using gulm lock server but
neither of your recipes match with that. Then i'm
attempt create one specific recipe groundoing in yours
recipes in section 5.3(GFS with Fibre Channel and gulm
lock server) and 5.5(GFS with parallel scsi and
LOCK_SWDMEPD) to do why i want, but i have some doubt:
1.Why the pool module is not loaded in recipe 5.5?
2.Using IP-based DMEP, all pooldevices should have a
weight of zero. The same role apply to IP-based GULM?
3.Why the i/o fence daemon are not started in the
nodes in the recipe of section 5.3?

Please, Could you see the file attached with the
description of the recipe and localized questions i'm
trying to create, to give me the feedback if it's
correct.

Other question:
Who is the correct way to stop the gfs before do
reboot or shutdown the nodes?

Thanks for your helps.
Manuela Fortes.

(Continue reading)

Andrea Cerrito | 6 Sep 2002 20:21
Picon

RE: really poor performance on a 2 terabyte gfs


-----BEGIN PGP SIGNED MESSAGE-----

I don't know if it can help but: set the noatime option on the
filesystem.
Regards,

Andrea Cerrito
IT Manager

+39.  0744.  5441. 1
+39.  348.   4912. 581

www.centromultimediale.tv
www.centromultimediale.it
www.etad.it 

== /history
Due giovani e uno meno giovane si trovano proiettati a causa di una
serie di fatalita' in un mondo parallelo dove non esistono le leggi
del business ma solo follia e dolore.

> -----Original Message-----
> From: gfs-users-admin <at> sistina.com
> [mailto:gfs-users-admin <at> sistina.com]On Behalf Of Robert Binz
> Sent: Friday, September 06, 2002 7:01 PM
> To: gfs-users <at> sistina.com
> Subject: RE: [gfs-users] really poor performance on a 2 terabyte
> gfs  
> 
(Continue reading)

brown wrap | 6 Sep 2002 18:32
Picon
Favicon

really poor performance on a 2 terabyte gfs


does anybody out there have a configuration with at
least a 2 terabyte filesystem? i am using gfs 5.1 and
in even doing simple things like 'ls -l' it takes
MINUTES to return a result. basically we have a large
ftp site currently running on  an sgi. the same
command
on the same directory structure behaves normally, or
as one would expect it to, on the sgi. on our linux
box, running gfs 5.1, the results take up to two
minutes
to return a listing. thanks.

greg

=====
Sixty miles, three days, one mission.

http://brownwrap.pledgepage.com

http://homepage.bethepeople.com/display/mp_page.php?page_id=53

__________________________________________________
Do You Yahoo!?
Yahoo! Finance - Get real-time stock quotes
http://finance.yahoo.com

_______________________________________________
gfs-users mailing list
gfs-users <at> sistina.com
(Continue reading)

Manuela Fortes | 6 Sep 2002 18:18
Picon
Favicon

install sistina's kernel

Hi,

I'm trying to instal the Kernel
(kernel-smp-2.4.18-4.gfs.i686.rpm) i've purchase with
gfs 5.1.0 to evaluate which software license number is
BE-0005-10001015.
However, something go wrong:
rpm -ivh kernel-smp-2.4.18-4.gfs.i686.rpm
Preparing...
########################################### [100%]
   1:kernel-smp
error: unpacking of archive failed on file
/lib/modules/2.4.18-4.gfssmp/kernel/fs/jbd/jbd.o;3d78d07b:
cpio: read failed - Bad file descriptor

Could You help with any idea?

Thanks
Manuela Fortes.

_______________________________________________________________________
Yahoo! PageBuilder
O super editor para criação de sites: é grátis, fácil e rápido.
http://br.geocities.yahoo.com/v/pb.html

_______________________________________________
gfs-users mailing list
gfs-users <at> sistina.com
http://lists.sistina.com/mailman/listinfo/gfs-users
Read the GFS Howto:  http://www.sistina.com/gfs/Pages/howto.html
(Continue reading)

Andrea Cerrito | 27 Aug 2002 11:52
Picon

Help with error received


-----BEGIN PGP SIGNED MESSAGE-----

Hi to list,
I've had a panic on a machine caused by these errors:

kernmsg:
Aug 27 04:05:01 homer-b kernel: memexp:  slow heartbeat time
(33894889, 33896940, 2051)
Aug 27 04:05:56 homer-b kernel: dmep_tcp:  For pbn:831188 seq:9
<3>dmep_tcp: Error received: Mel_You_are_Banned

messages:
Aug 27 04:05:01 homer-b kernel: memexp:  Warning - delayed heartbeats
Aug 27 04:05:01 homer-b kernel:   last: 33894689, now: 33896938,
diff: 2249, timeout: 15
Aug 27 04:05:01 homer-b kernel: memexp:  slow heartbeat time
(33894889, 33896940, 2051)

But I cannot find the reason for that error (Mel_You_are_Banned).
What does it mean???

The node running memexpd shows:

Aug 27 04:05:26 homer-a kernel: memexp:  Warning - delayed heartbeats
Aug 27 04:05:26 homer-a kernel:   last: 33734170, now: 33736310,
diff: 2140, timeout: 15
Aug 27 04:05:26 homer-a kernel: memexp:  slow heartbeat time
(33734370, 33736312, 1942)
Aug 27 04:05:56 homer-a kernel: memexp:  client recovery stomithing
(Continue reading)

brown wrap | 13 Aug 2002 18:21
Picon
Favicon

how do you use gfs


i will eventually have to justify gfs to people. the
system we have in place was purchased by the system
administrator before. through one person on this, i
received a very detailed description of how he was
using gfs. it got me to think how is everyone else
using gfs, what version, and what hardware. i'd like
to know how big the gfs community is.

greg

=====
Sixty miles, three days, one mission.

http://brownwrap.pledgepage.com

http://homepage.bethepeople.com/display/mp_page.php?page_id=53

__________________________________________________
Do You Yahoo!?
HotJobs - Search Thousands of New Jobs
http://www.hotjobs.com

_______________________________________________
gfs-users mailing list
gfs-users <at> sistina.com
http://lists.sistina.com/mailman/listinfo/gfs-users
Read the GFS Howto:  http://www.sistina.com/gfs/Pages/howto.html

(Continue reading)

Robert Binz | 6 Aug 2002 18:59

RE: Any experience with GFS on U*IX?

Ken,
Currently GFS is only for Linux with a port possibility to BSD.  I am
currently deploying a large Linux cluster on IBM XSeries hardware.  I would
jump for joy if Sistina would port to Solaris.

Robert Binz

-----Original Message-----
From: Miller, Ken (Federal-Engineering) [mailto:Kenny.Miller <at> hp.com]
Sent: Tuesday, August 06, 2002 8:35 AM
To: gfs-users <at> sistina.com
Subject: [gfs-users] Any experience with GFS on U*IX?

Hi,

This is probably a dumb question, but I'm new to GFS and trying to cobble
together an Open Systems alternative to SANergy and GFS.

Does anyone have experience using GFS with the following clients:

	Sun Solaris
	HP Tru64 UNIX
	SGI IRIX
	IBM AIX
	Cray UNICOS
	HP UX

Thanks in advance,

	== ken miller ==
(Continue reading)

Picon
Favicon

Any experience with GFS on U*IX?

Hi,

This is probably a dumb question, but I'm new to GFS and trying to cobble together an Open Systems
alternative to SANergy and GFS.

Does anyone have experience using GFS with the following clients:

	Sun Solaris
	HP Tru64 UNIX
	SGI IRIX
	IBM AIX
	Cray UNICOS
	HP UX

Thanks in advance,

	== ken miller ==

_______________________________________________
gfs-users mailing list
gfs-users <at> sistina.com
http://lists.sistina.com/mailman/listinfo/gfs-users
Read the GFS Howto:  http://www.sistina.com/gfs/Pages/howto.html

Peglar, Robert | 30 Jul 2002 22:45
Favicon

RE: gfs 5.1, rh 7.3, qlogic 2200, and a brocade

Just some follow-up...

Some storage subsystems insist on having and/or starting at LUN 0, even
though their is no such requirement in the SCSI standards (SAM-2).  Others
do not.

Also, some subsystems require a complete 0..N LUN scheme, i.e. if LUN N
exists, all LUNs 0..N-1 must also exist.  Once again, this is a non-standard
but is (all too) typical of proprietary controllers.

Rob

-----Original Message-----
From: Jordi Floriach [mailto:jordi.floriach <at> ibernettelematica.es]
Sent: Wednesday, July 24, 2002 3:55 AM
To: gfs-users <at> sistina.com
Cc: Xavier Arandes; Jordi Herrero; Santi Casas
Subject: RE: [gfs-users] gfs 5.1, rh 7.3, qlogic 2200, and a brocade

Hi

I've experienced the same problem with SuSE 7.3 and RH 7.3 with my qla2200
connecting to a Compaq HGS80.
At qlogic web site I found SANsurfer, an HBA administration software from
which I can see my LUNs. This tells me that HSG80 and qla2200 are working
well. But, cat /proc/partitions does not show the logical units and
/var/log/messages only shows that qla2200 has discovered the HSG80
controller (LUN 0) but not the other LUNs.
Just yesterday I discovered where the error is: at SCSI support module. It
seems like each LUN discovered tells the kernel wether it needs to continue
(Continue reading)


Gmane