in the way of
his air, one of the three central fan pairs should have got triggered to
high speed too, and the second fan of the same PSU too.
So the heat source (if ever, may be a failing sensor only) seems for me to
be a local defect in one of the two PSUs.
Viele Gruesse
Eberhard Moenke
s one inside the power supplies, with little effect
on CPU temperatueres.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551
--
ks with
PERC5/i.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551
-
Gesellschaft fuer wissenschaftli
5"?
>
> Well if the platters are smaller the heads have less distance to move,
> so seeking from the start of the disk to the end would be quicker...
>
>> The opposite is fact.
>>
>>> [1]
>>> http://www.latestpcnews.com/western-digital-launches-new-backplane-
ted out, an SSD would be even better in this respect.
How do you see an effort of 2.5" against 3.5"?
The opposite is fact.
> [1]
> http://www.latestpcnews.com/western-digital-launches-new-backplane-compatible-wdvelociraptor-hard-drive/
Only advertising, sorry.
Viele Gruess
5"
side.
More iops per physical server volume is the only benefit of 2.5".
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551
-
rives, the "used surface" starts at the outer corner and does
not reach to the inner corner. So 3.5" drives have in any case the bits
sliding faster under the heads at a given rpm.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeits
Hi,
On Tue, 29 Jun 2010, Jefferson Ogata wrote:
> On 2010-06-29 19:44, Eberhard Moenkeberg wrote:
>> On Tue, 29 Jun 2010, J. Epperson wrote:
>>> Arrived home very tired and in a lapse of judgement tried to configure a
>>> new USB backup drive on my PERC3 based home ser
n table change.
If you do not have a backup of the master boot record (LILO would have
one), you can use the df output to estimate the right cylinder numbers.
If you need trial and error to find the boundaries, "tune2fs -l /dev/sdaX"
is a non-destructive test.
Viele Gruesse
Hi,
On Thu, 1 Apr 2010, Matt Domsch wrote:
> On Thu, Apr 01, 2010 at 11:58:15PM +0200, Eberhard Moenkeberg wrote:
>> would it be possible to offer http://linux.dell.com/files/ via rsync?
>
> It's possible; we need to do some pruning there before I'd open it up
> thou
mine have the same size (and maybe timestamp)
> (poorman's checksum)? If not, get it.
Good that (or if) you do it, but a crazy way I won't go.
I will only mirror it if I get access via rsync.
> On 04/01/2010 02:58 PM, Eberhard Moenkeberg wrote:
>> Hi,
>>
>>
Hi,
would it be possible to offer http://linux.dell.com/files/ via rsync?
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551
Hi,
On Thu, 1 Apr 2010, Robin Bowes wrote:
> On 01/04/10 00:59, Eberhard Moenkeberg wrote:
>>> If you don't mention that the failed drive is a "one-year item" from Dell,
>>> it is covered by your 3-year warranty.
>
> Er, I wouldn't think so - al
Hi,
On Thu, 1 Apr 2010, Eberhard Moenkeberg wrote:
> On Thu, 1 Apr 2010, Robin Bowes wrote:
>> We have 32 x PE1950, plus 34 x R410, and have another 42 R410 on order.
>> All servers have (the balance of) a 3-year warranty.
>>
>> Each server has 4 x 146GB 2.5"
e failed drive is a "one-year item" from Dell,
it is covered by your 3-year warranty.
Maybe too if you buy Seagate drives at second source.
But my question is: why didn't you choose originally the 5-year warranty
from Dell?
You can get it, even if not choosable in the web interface.
URL?
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail: emoe...@gwdg.de Tel.: +49 (0)551 201-1551
-
Gesellschaft fuer wissenschaftliche Daten
v/sda. But if the external array is down then
> we've got issues anyway. :-)
The real matter is the sequence of drivers within the initrd file.
I can't tell about RH, but with SUSE you have /etc/sysconfig/kernel with a
line like
INITRD_MODULES="amd74xx megaraid_mbox process
t disks.
Raid1 can have a double throughput advantage during read - just using
disk1 AND disk2 - if the controller supports it.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail: emoe...@gwdg.de Tel.: +4
it:// today.
>
> I hope you enjoy this new way to participate.
ftp://ftp5.gwdg.de/pub/linux/dell/
http://ftp5.gwdg.de/pub/linux/dell/
rsync://ftp5.gwdg.de/pub/linux/dell/
will be a mirror of both repo/ and git/.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
y formed a proper signal against
his marketing collegues, and I guess he has the power to place it right.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail:
loss could waste the buffer cache.
The battery backuped controller cache would keep the data and write back
after the next power-on (if it happens within the battery lifetime).
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.o
sting to see speed and reliability if
> the OS changed to, say, Linux.
Seconded very much.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhard Moenkeberg
Arbeitsgruppe IT-Infrastruktur
E-Mail: emoe...@gwdg.de Tel.: +49
Hi,
On Wed, 9 Dec 2009, Howard, Chris wrote:
> You guys are a lifesaver.
>
> This says I have two 512MB DIMMs in bank1_A and bank1_B
> and speed is 266 Mhz.
As I remember it is DDR-1 reg ECC.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de, e...@kki.org)
--
Eberhar
gt;
> I still haven't figured out how to get a proper console though...
Many thanks for this, really many.
Too much vendors do not see the efforts they can gain thru open-sourcing
their software, by binding the brains of their users.
Viele Gruesse
Eberhard Moenkeberg (emoe...@gwdg.de,
Hi,
On Sat, 31 Oct 2009, Eberhard Moenkeberg wrote:
> On Mon, 26 Oct 2009, Rainer Traut wrote:
>> Eberhard Moenkeberg schrieb:
>>> On Sat, 24 Oct 2009, Steve Thompson wrote:
>>>> I have just taken delivery of a T710 w/BCM5709's, and can confirm that the
Hi,
On Mon, 26 Oct 2009, Rainer Traut wrote:
> Eberhard Moenkeberg schrieb:
>> On Sat, 24 Oct 2009, Steve Thompson wrote:
>>> I have just taken delivery of a T710 w/BCM5709's, and can confirm that the
>>> disable_msi=1 trick does *not* resolve this problem; I ha
the Slony backlog.
>
> Good luck and let me know if you have any questions (or where to
> find some slick SFF-8087 cables with a 90deg angle connector)
>
> You can see a dmesg(8) for the r710 w/ areca for NetBSD/amd64
> -current from last month at:
>
> http://www.nycb
hile idle, 5 minutes after a cold start. Installing the netxtreme
> driver *does* fix the issue. Not very clever, guys.
No Problems here with SUSE SLES10.
Works just out of the box, no tricks necessary.
BTW: My guess is since long (i.e. almost ever, about 15 years) that SUSE
has the be
28 matches
Mail list logo
