Tag Archive for 'big-iron'

Dec14th2010

EQUINIX – Would you like fries with that?

Had a good tour of the EQUNIX facility in Sydney today. Been to a few around the world and yet again the structure, layout and operation procedures are identical to all. The McDonalds of IDC’s?

May15th2008

Nickel and Dimming Vendor Olympics?

In the middle of putting out a proposal for a very large client/tender at the moment. Well over a life time’s earnings in servers and an as yet un calculated retainer and service rate at this stage – electricity and bandwidth and human hours all cost money. I always try to get the best prices […]

Dec3rd2007

PostgreSQL Re-Index, Index Corruption

Ever had a situation like this: Select from database ID where name = RICHARD; Returns and ID of 55 for example. Then go and do a query like this: Select * from some_other_table where ID = 55; Returns, “Sorry does not exist, time to die…..” Well apparently indexes when corrupt – which is NOT SUPPOSED […]

Nov18th2007

Drive Roaming. DELL PERC4 Controllers

During a recent test run to see if a new PostgreSQL back end server would hasten things up in a main cluster – that has now become CPU bound and NOT IO…… the wizardry of that I will blog about later. In any case, the short of it is, that we were juggling PERC4 cards […]

Nov17th2007

DRAC4 Reset?

My hosting manager found out this cool info recently. DRAC cards are a pain when they do not work – which is not rare. They are very important and are only needed in rare circumstances. However if those circumstances arise – these cards MUST perform. I must say that the PE1800 and DRAC4 that we […]

Nov5th2007

The New Virtual Infrastructure

I have been using VMWARE/BOCHS and UML for around 7 years now. And boy have things moved quickly! Most recently VMWARE announced their new products. ESX 3.5 is basically the same as ESX3, the main new feature that all people could use is the central patch management system. The feature that is really putting this […]

Sep3rd2007

The Verdict Is In!

Excellent Results! CPU System load was DOWN. This is due to much better disk IO (reduced wait times) and as such, user processes get to breath and send stuff back to clients in a speedy fashion.