[SAC] [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU Charged (100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)

-------- Forwarded Message --------
Subject: [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU Charged
(100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives (6937
Errors)
Date: Wed, 28 Jan 2015 15:51:51 -0800
From: SRE Team via RT <sre@osuosl.org>
Reply-To: sre@osuosl.org
To: tech@wildintellect.com

Greetings,

This message has been automatically generated in response to the
creation of a support ticket call:

        "CRITICAL: 0:BBU Charged (100%):0:RAID-6:6
drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)",

a summary of which appears below.

There is no need to reply to this message right now. Your ticket has been
assigned an ID of [support.osuosl.org #24790]. Please include this string
in the subject line of all future correspondence about this issue. You may
also catch us on irc (irc.freenode.net) in #osuosl.

                        Thank you.
                        sre@osuosl.org

-------------------------------------------------------------------------
Alex / OSGEO team:

We're getting the following nagios alert:

CRITICAL: 0:BBU Charged (100%):0:RAID-6:6 drives:557.75GB:Partially
Drives:6 1 Bad Drives (6937 Errors)

An excerpt from megacli tells the story

Enclosure Device ID: 32
Slot Number: 5
WWN: 5000C5001D26114C
Raw Size: 279.396 GB [0x22ecb25c Sectors]
Firmware state: Failed
Inquiry Data: SEAGATE ST3300657SS ES623SJ0GNRS

--
Justin Dugger
Senior System Administrator
OSU Open Source Lab

Looks like we need to get a new HD, $52
http://amzn.com/B0035G0J98

Who wants to handle the order? Michael?

I'll restart talks with OSUOSL about putting in a some new machines and
make some fresh quotes based on
http://wiki.osgeo.org/wiki/Infrastructure_Transition_Plan_2014

Seems the idea to borrow some time on OSUOSL hardware just never
materialized.

Thanks,
Alex

On 01/30/2015 11:16 AM, Alex Mandel wrote:

-------- Forwarded Message --------
Subject: [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU Charged
(100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives (6937
Errors)
Date: Wed, 28 Jan 2015 15:51:51 -0800
From: SRE Team via RT <sre@osuosl.org>
Reply-To: sre@osuosl.org
To: tech@wildintellect.com

Greetings,

This message has been automatically generated in response to the
creation of a support ticket call:

        "CRITICAL: 0:BBU Charged (100%):0:RAID-6:6
drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)",

a summary of which appears below.

There is no need to reply to this message right now. Your ticket has been
assigned an ID of [support.osuosl.org #24790]. Please include this string
in the subject line of all future correspondence about this issue. You may
also catch us on irc (irc.freenode.net) in #osuosl.

                        Thank you.
                        sre@osuosl.org

-------------------------------------------------------------------------
Alex / OSGEO team:

We're getting the following nagios alert:

CRITICAL: 0:BBU Charged (100%):0:RAID-6:6 drives:557.75GB:Partially
Drives:6 1 Bad Drives (6937 Errors)

An excerpt from megacli tells the story

Enclosure Device ID: 32
Slot Number: 5
WWN: 5000C5001D26114C
Raw Size: 279.396 GB [0x22ecb25c Sectors]
Firmware state: Failed
Inquiry Data: SEAGATE ST3300657SS ES623SJ0GNRS

Hi

any news here?
I would be glad if a kind of protocol be established to handle this kind of urgent problems rapidly.

Which VMs are affected here?

Thanks
Markus

On Jan 30, 2015 8:23 PM, “Alex Mandel” <tech_dev@wildintellect.com> wrote:

Looks like we need to get a new HD, $52
http://amzn.com/B0035G0J98

Who wants to handle the order? Michael?

I’ll restart talks with OSUOSL about putting in a some new machines and
make some fresh quotes based on
http://wiki.osgeo.org/wiki/Infrastructure_Transition_Plan_2014

Seems the idea to borrow some time on OSUOSL hardware just never
materialized.

Thanks,
Alex

On 01/30/2015 11:16 AM, Alex Mandel wrote:

-------- Forwarded Message --------
Subject: [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU Charged
(100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives (6937
Errors)
Date: Wed, 28 Jan 2015 15:51:51 -0800
From: SRE Team via RT <sre@osuosl.org>
Reply-To: sre@osuosl.org
To: tech@wildintellect.com

Greetings,

This message has been automatically generated in response to the
creation of a support ticket call:

“CRITICAL: 0:BBU Charged (100%):0:RAID-6:6
drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)”,

a summary of which appears below.

There is no need to reply to this message right now. Your ticket has been
assigned an ID of [support.osuosl.org #24790]. Please include this string
in the subject line of all future correspondence about this issue. You may
also catch us on irc (irc.freenode.net) in #osuosl.

Thank you.
sre@osuosl.org


Alex / OSGEO team:

We’re getting the following nagios alert:

CRITICAL: 0:BBU Charged (100%):0:RAID-6:6 drives:557.75GB:Partially
Drives:6 1 Bad Drives (6937 Errors)

An excerpt from megacli tells the story

Enclosure Device ID: 32
Slot Number: 5
WWN: 5000C5001D26114C
Raw Size: 279.396 GB [0x22ecb25c Sectors]
Firmware state: Failed
Inquiry Data: SEAGATE ST3300657SS ES623SJ0GNRS


Sac mailing list
Sac@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/sac

I'm not the email made it to Michael (Treasurer), adding him now.

Generally the protocol is the SAC chair makes the request to the
Treasurer who places the order.

Machine is OSGeo4, so the same machine that's been performing poorer for
a while. Refer to the wiki for the list of VMs. I usually look here
http://wiki.osgeo.org/wiki/Infrastructure_Transition_Plan_2010#osgeo3_.26_osgeo4

Thanks,
Alex

On 02/02/2015 08:49 AM, Markus Neteler wrote:

Hi

any news here?
I would be glad if a kind of protocol be established to handle this kind
of urgent problems rapidly.

Which VMs are affected here?

Thanks
Markus
On Jan 30, 2015 8:23 PM, "Alex Mandel" <tech_dev@wildintellect.com> wrote:

Looks like we need to get a new HD, $52
http://amzn.com/B0035G0J98

Who wants to handle the order? Michael?

I'll restart talks with OSUOSL about putting in a some new machines and
make some fresh quotes based on
http://wiki.osgeo.org/wiki/Infrastructure_Transition_Plan_2014

Seems the idea to borrow some time on OSUOSL hardware just never
materialized.

Thanks,
Alex

On 01/30/2015 11:16 AM, Alex Mandel wrote:

-------- Forwarded Message --------
Subject: [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU Charged
(100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives (6937
Errors)
Date: Wed, 28 Jan 2015 15:51:51 -0800
From: SRE Team via RT <sre@osuosl.org>
Reply-To: sre@osuosl.org
To: tech@wildintellect.com

Greetings,

This message has been automatically generated in response to the
creation of a support ticket call:

        "CRITICAL: 0:BBU Charged (100%):0:RAID-6:6
drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)",

a summary of which appears below.

There is no need to reply to this message right now. Your ticket has been
assigned an ID of [support.osuosl.org #24790]. Please include this

string

in the subject line of all future correspondence about this issue. You

may

also catch us on irc (irc.freenode.net) in #osuosl.

                        Thank you.
                        sre@osuosl.org

-------------------------------------------------------------------------
Alex / OSGEO team:

We're getting the following nagios alert:

CRITICAL: 0:BBU Charged (100%):0:RAID-6:6 drives:557.75GB:Partially
Drives:6 1 Bad Drives (6937 Errors)

An excerpt from megacli tells the story

Enclosure Device ID: 32
Slot Number: 5
WWN: 5000C5001D26114C
Raw Size: 279.396 GB [0x22ecb25c Sectors]
Firmware state: Failed
Inquiry Data: SEAGATE ST3300657SS ES623SJ0GNRS

_______________________________________________
Sac mailing list
Sac@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/sac

On Feb 2, 2015 7:50 PM, “Alex Mandel” <tech_dev@wildintellect.com> wrote:

I’m not the email made it to Michael (Treasurer), adding him now.

Generally the protocol is the SAC chair makes the request to the
Treasurer who places the order.

Machine is OSGeo4,

Just curious: can this been seen from their notification?

so the same machine that’s been performing poorer for
a while.

Yes, soon it will be for a year…

The RAID reconstruction took many days last time, will this be again like this?

I just wonder if I’d better move the GRASS GIS server elsewhere.

Thanks
Markus

On 02/02/2015 11:01 AM, Markus Neteler wrote:

On Feb 2, 2015 7:50 PM, "Alex Mandel" <tech_dev@wildintellect.com> wrote:

I'm not the email made it to Michael (Treasurer), adding him now.

Generally the protocol is the SAC chair makes the request to the
Treasurer who places the order.

Machine is OSGeo4,

Just curious: can this been seen from their notification?

I happen to know osgeo4 is raid 6 and the drive are a different size.

so the same machine that's been performing poorer for
a while.

Yes, soon it will be for a year...

The RAID reconstruction took many days last time, will this be again like
this?

I just wonder if I'd better move the GRASS GIS server elsewhere.

Thanks
Markus

Not sure, will need to chat with OSUOSL about it.

Thanks,
Alex

Yes, at $50 we should just order it. Let me know if you need the
shipping details.

Thanks,
Alex

On 02/02/2015 10:53 AM, Michael Smith wrote:

If we are ready to order, I can do this today

Mike

On 2/2/15, 1:49 PM, "Alex Mandel" <tech_dev@wildintellect.com> wrote:

I'm not the email made it to Michael (Treasurer), adding him now.

Generally the protocol is the SAC chair makes the request to the
Treasurer who places the order.

Machine is OSGeo4, so the same machine that's been performing poorer for
a while. Refer to the wiki for the list of VMs. I usually look here
http://wiki.osgeo.org/wiki/Infrastructure_Transition_Plan_2010#osgeo3_.26_
osgeo4

Thanks,
Alex

On 02/02/2015 08:49 AM, Markus Neteler wrote:

Hi

any news here?
I would be glad if a kind of protocol be established to handle this
kind
of urgent problems rapidly.

Which VMs are affected here?

Thanks
Markus
On Jan 30, 2015 8:23 PM, "Alex Mandel" <tech_dev@wildintellect.com>
wrote:

Looks like we need to get a new HD, $52
http://amzn.com/B0035G0J98

Who wants to handle the order? Michael?

I'll restart talks with OSUOSL about putting in a some new machines and
make some fresh quotes based on
http://wiki.osgeo.org/wiki/Infrastructure_Transition_Plan_2014

Seems the idea to borrow some time on OSUOSL hardware just never
materialized.

Thanks,
Alex

On 01/30/2015 11:16 AM, Alex Mandel wrote:

-------- Forwarded Message --------
Subject: [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU
Charged
(100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives
(6937
Errors)
Date: Wed, 28 Jan 2015 15:51:51 -0800
From: SRE Team via RT <sre@osuosl.org>
Reply-To: sre@osuosl.org
To: tech@wildintellect.com

Greetings,

This message has been automatically generated in response to the
creation of a support ticket call:

        "CRITICAL: 0:BBU Charged (100%):0:RAID-6:6
drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)",

a summary of which appears below.

There is no need to reply to this message right now. Your ticket has
been
assigned an ID of [support.osuosl.org #24790]. Please include this

string

in the subject line of all future correspondence about this issue.
You

may

also catch us on irc (irc.freenode.net) in #osuosl.

                        Thank you.
                        sre@osuosl.org

-----------------------------------------------------------------------
--
Alex / OSGEO team:

We're getting the following nagios alert:

CRITICAL: 0:BBU Charged (100%):0:RAID-6:6 drives:557.75GB:Partially
Drives:6 1 Bad Drives (6937 Errors)

An excerpt from megacli tells the story

Enclosure Device ID: 32
Slot Number: 5
WWN: 5000C5001D26114C
Raw Size: 279.396 GB [0x22ecb25c Sectors]
Firmware state: Failed
Inquiry Data: SEAGATE ST3300657SS ES623SJ0GNRS

_______________________________________________
Sac mailing list
Sac@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/sac

New drive is on it's way. Please wait to schedule a good time to put it in.

Do you know if the RAID card allows for speed limiting the rebuild in
exchange for better performance during rebuild?

Thanks,
Alex

On 01/30/2015 11:16 AM, Alex Mandel wrote:

-------- Forwarded Message --------
Subject: [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU Charged
(100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives (6937
Errors)
Date: Wed, 28 Jan 2015 15:51:51 -0800
From: SRE Team via RT <sre@osuosl.org>
Reply-To: sre@osuosl.org
To: tech@wildintellect.com

Greetings,

This message has been automatically generated in response to the
creation of a support ticket call:

        "CRITICAL: 0:BBU Charged (100%):0:RAID-6:6
drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)",

a summary of which appears below.

There is no need to reply to this message right now. Your ticket has been
assigned an ID of [support.osuosl.org #24790]. Please include this string
in the subject line of all future correspondence about this issue. You may
also catch us on irc (irc.freenode.net) in #osuosl.

                        Thank you.
                        sre@osuosl.org

-------------------------------------------------------------------------
Alex / OSGEO team:

We're getting the following nagios alert:

CRITICAL: 0:BBU Charged (100%):0:RAID-6:6 drives:557.75GB:Partially
Drives:6 1 Bad Drives (6937 Errors)

An excerpt from megacli tells the story

Enclosure Device ID: 32
Slot Number: 5
WWN: 5000C5001D26114C
Raw Size: 279.396 GB [0x22ecb25c Sectors]
Firmware state: Failed
Inquiry Data: SEAGATE ST3300657SS ES623SJ0GNRS

On Feb 4, 2015 5:16 PM, “Alex Mandel” <tech_dev@wildintellect.com> wrote:

New drive is on it’s way. Please wait to schedule a good time to put it in.

Do you know if the RAID card allows for speed limiting the rebuild in
exchange for better performance during rebuild?

Hi Alex

did the disk arrive?

Thanks
Markus

On 02/13/2015 09:55 AM, Markus Neteler wrote:

On Feb 4, 2015 5:16 PM, "Alex Mandel" <tech_dev@wildintellect.com> wrote:

New drive is on it's way. Please wait to schedule a good time to put it

in.

Do you know if the RAID card allows for speed limiting the rebuild in
exchange for better performance during rebuild?

Hi Alex

did the disk arrive?

Thanks
Markus

Yes it did. But I haven't talked with the person they assigned to handle
the replacement. They are researching if they can allow the rebuild
speed to be slowed intentionally so that performance is less effected.

PS: I'm negotiating with OSUOSL on a plan to install a new machine and
retire osgeo4. Will post when I have all the details. New machine will
be better configured for our performance needs.

Thanks,
Alex

Justin,

Can we do Friday? I think that will coincide with lower load on our end.

Thanks,
Alex

On 02/18/2015 05:19 PM, Justin Dugger via RT wrote:

Alex wrote:

Since I doubt we can slow the rebuild, we should probably shoot for a
Friday afternoon/evening or Saturday PST. Hmm, Adhoc is in use heavily
until end of next weekend. So something the week of Feb 23 might work
that way we can turn off Adhoc like we did last time.

I'll need to check-in with QGIS too since they are about to do a release
and that might add considerable traffic too."

That's next week, do we have a specific date / time in mind yet?

On Tue Feb 10 16:04:07 2015, jldugger wrote:

I received the drive yesterday. I'll let one of the students
coordinate this and see about reducing the build rate to favor host
I/O requests.

Justin

On Wed Feb 04 08:16:34 2015, tech@wildintellect.com wrote:

New drive is on it's way. Please wait to schedule a good time to put
it in.

Do you know if the RAID card allows for speed limiting the rebuild

in

exchange for better performance during rebuild?

Thanks,
Alex

On 01/30/2015 11:16 AM, Alex Mandel wrote:

-------- Forwarded Message --------
Subject: [support.osuosl.org #24790] AutoReply: CRITICAL: 0:BBU

Charged

(100%):0:RAID-6:6 drives:557.75GB:Partially Drives:6 1 Bad Drives

(6937

Errors)
Date: Wed, 28 Jan 2015 15:51:51 -0800
From: SRE Team via RT <sre@osuosl.org>
Reply-To: sre@osuosl.org
To: tech@wildintellect.com

Greetings,

This message has been automatically generated in response to the
creation of a support ticket call:

        "CRITICAL: 0:BBU Charged (100%):0:RAID-6:6
drives:557.75GB:Partially Drives:6 1 Bad Drives (6937 Errors)",

a summary of which appears below.

There is no need to reply to this message right now. Your ticket

has

been

assigned an ID of [support.osuosl.org #24790]. Please include

this

string

in the subject line of all future correspondence about this issue.

You may

also catch us on irc (irc.freenode.net) in #osuosl.

                        Thank you.
                        sre@osuosl.org

-------------------------------------------------------------------------

Alex / OSGEO team:

We're getting the following nagios alert:

CRITICAL: 0:BBU Charged (100%):0:RAID-6:6

drives:557.75GB:Partially

Drives:6 1 Bad Drives (6937 Errors)

An excerpt from megacli tells the story

Enclosure Device ID: 32
Slot Number: 5
WWN: 5000C5001D26114C
Raw Size: 279.396 GB [0x22ecb25c Sectors]
Firmware state: Failed
Inquiry Data: SEAGATE ST3300657SS ES623SJ0GNRS

On Feb 13, 2015 6:58 PM, “Alex Mandel” <tech_dev@wildintellect.com> wrote:

PS: I’m negotiating with OSUOSL on a plan to install a new machine and
retire osgeo4. Will post when I have all the details. New machine will
be better configured for our performance needs.

Got the new machine ordered?

Thanks
Markus

On 03/12/2015 01:01 AM, Markus Neteler wrote:

On Feb 13, 2015 6:58 PM, "Alex Mandel" <tech_dev@wildintellect.com> wrote:

PS: I'm negotiating with OSUOSL on a plan to install a new machine and
retire osgeo4. Will post when I have all the details. New machine will
be better configured for our performance needs.

Got the new machine ordered?

Thanks
Markus

We have rack space approved. I need to finalize the quote for SAC to
vote on.

Rebuild finished and adhoc was turned back on the monday after we started.

--
Alex Mandel
http://wildintellect.com

On Thu, Mar 12, 2015 at 08:33:42AM -0700, Alex Mandel wrote:

Rebuild finished and adhoc was turned back on the monday after we started.

So I may re-activate the missing backups ?

  Martin.
--
Unix _IS_ user friendly - it's just selective about who its friends are !
--------------------------------------------------------------------------

On 03/12/2015 08:47 AM, Martin Spott wrote:

On Thu, Mar 12, 2015 at 08:33:42AM -0700, Alex Mandel wrote:

Rebuild finished and adhoc was turned back on the monday after we started.

So I may re-activate the missing backups ?

  Martin.

Sure, any chance we can reduce the frequency of the adhoc backup to
every other day or twice a week?

Thanks,
Alex

On Thu, Mar 12, 2015 at 08:49:24AM -0700, Alex Mandel wrote:

On 03/12/2015 08:47 AM, Martin Spott wrote:
> On Thu, Mar 12, 2015 at 08:33:42AM -0700, Alex Mandel wrote:

> So I may re-activate the missing backups ?

Sure, any chance we can reduce the frequency of the adhoc backup to
every other day or twice a week?

Done, twice a week,

  Martin.
--
Unix _IS_ user friendly - it's just selective about who its friends are !
--------------------------------------------------------------------------

On Thu, Mar 12, 2015 at 4:33 PM, Alex Mandel <tech@wildintellect.com> wrote:

On 03/12/2015 01:01 AM, Markus Neteler wrote:

On Feb 13, 2015 6:58 PM, "Alex Mandel" <tech_dev@wildintellect.com> wrote:

PS: I'm negotiating with OSUOSL on a plan to install a new machine and
retire osgeo4. Will post when I have all the details. New machine will
be better configured for our performance needs.

Got the new machine ordered?

Thanks
Markus

We have rack space approved. I need to finalize the quote for SAC to
vote on.

Sorry to bother: do you have any news?

Today (European daytime) a page visit took up to 120 seconds to load.
I am considering to move the GRASS Web site elsewhere ...

--
Markus Neteler
http://courses.neteler.org
http://gis.cri.fmach.it/neteler/
http://grass.osgeo.org/

On 04/07/2015 11:33 AM, Markus Neteler wrote:

On Thu, Mar 12, 2015 at 4:33 PM, Alex Mandel <tech@wildintellect.com> wrote:

On 03/12/2015 01:01 AM, Markus Neteler wrote:

On Feb 13, 2015 6:58 PM, "Alex Mandel" <tech_dev@wildintellect.com> wrote:

PS: I'm negotiating with OSUOSL on a plan to install a new machine and
retire osgeo4. Will post when I have all the details. New machine will
be better configured for our performance needs.

Got the new machine ordered?

Thanks
Markus

We have rack space approved. I need to finalize the quote for SAC to
vote on.

Sorry to bother: do you have any news?

Today (European daytime) a page visit took up to 120 seconds to load.
I am considering to move the GRASS Web site elsewhere ...

--
Markus Neteler

Apologies, lost track of trying to get the order together after
performance improved with the hard drive replacement. 120 seconds? I've
never gotten anywhere near that. What time of day? do you have tests
from multiple locations? I just tested and was getting under 1 second
clicking on random pages (with my slowish home internet).

So the dilemna on the order, the quotes I have right now are around
$6000 but we only have $5000 earmarked in the budget from the Board. We
could shuffle some of the funds allocated in other line items, but I
don't want to make this decision unilaterally.

Or we could get less robust hardware or much smaller disks. The other
big question, 8 identical drives? or 6 identical and 2 smaller, the 2
smaller dedicated to the host OS (mirrored) the rest in RAID 5 x2 or
RAID 50?

Here's the last quote I did
http://www.siliconmechanics.com/quotes/284594?confirmation=995449031

Feedback please...

Thanks,
Alex

On Tue, Apr 7, 2015 at 8:43 PM, Alex Mandel <tech_dev@wildintellect.com> wrote:

Apologies, lost track of trying to get the order together after
performance improved with the hard drive replacement. 120 seconds? I've
never gotten anywhere near that.

Me frequently but I am 9 hours ahead of your time zone.

What time of day?

E.g. 9am UTC this morning.

do you have tests from multiple locations? I just tested and was getting under 1 second
clicking on random pages (with my slowish home internet).

ok try to ssh into the machine now.

Just to run "w" took me 18 seconds.

top shows up to 74.8%wa

Thanks for pushing through the new server.

Markus

Looks like performance was better for about 2 weeks after the drive
replacement and then dropped again. Wonder if it's another disk dying.

Yes replacement is the solution.

Thanks,
Alex

On 04/07/2015 12:50 PM, Markus Neteler wrote:

On Tue, Apr 7, 2015 at 8:43 PM, Alex Mandel <tech_dev@wildintellect.com> wrote:

Apologies, lost track of trying to get the order together after
performance improved with the hard drive replacement. 120 seconds? I've
never gotten anywhere near that.

Me frequently but I am 9 hours ahead of your time zone.

What time of day?

E.g. 9am UTC this morning.

do you have tests from multiple locations? I just tested and was getting under 1 second
clicking on random pages (with my slowish home internet).

ok try to ssh into the machine now.

Just to run "w" took me 18 seconds.

top shows up to 74.8%wa

Thanks for pushing through the new server.

Markus