The IOPS race is over

emc-f1-carInfrastructure has always been a tough place to compete in. Unlike applications, databases or middleware, infrastructure components are fairly easy to replace with another make and model, and thus the vendors try to show off their product as better than the one from the competition.

In case of storage subsystems, the important metrics has always been performance related and IOPS (I/O operations per second) in particular.

I remember a period when competitors of our high-end arrays (EMC Symmetrix, these days usually just called EMC VMAX) tried to artificially boost their benchmark numbers by limiting the data access pattern to only a few megabytes per front-end IO port. This caused their array to handle all I/O in the small memory buffer cache of each I/O port – and none of the I/O’s would really be handled by either central cache memory or backend disks. This way they could boost their IOPS numbers much higher than ours. Of course no real world application would ever only store a few megabytes of data so the numbers were pure bogus – but marketing wise it was an interesting move to say the least.

With the introduction of the first Sun based Exadata (the Exadata V2) late 2009, Oracle also jumped on the IOPS race and claimed a staggering one million IOPS. Awesome! So the gold standard was now 1 million IOPS, and the other players had to play along with the “mine’s bigger than yours” vendor contest.
Read more of this post

Baking a cake: trading CPU for IO?

Sometimes I hear people claim that by using faster storage, you can save on database licenses. True or false?

The idea is that many database servers are suffering from IO wait – which actually means that the processors are waiting for data to be transferred to or from storage – and in the meantime, no useful work can be done. Given the expensive licenses that are needed for running commercial database software, usually licensed per CPU core, this then leads to loss of efficiency.

Let’s see if we can visualise the problem here with a common world example – Baking a cake.

Read more of this post

Looking forward: 2016

We’re already over one week in 2016 and I realize I haven’t done much blogging lately.

One of the things that kept me busy is development on Outrun, and the joint Oracle / EMC Solution Center (OSC) on which I intend to write a bit more going forward.

Something I did about a year ago (without mentioning it too much) is upgrade my account to Professional. Not that I really need the extra add-ons, but I want my readers not to be disturbed by ads – OK, there’s ad blockers, but not everyone uses them, and on some platforms you simply can’t (iOS). Dirty Cash well spent (and no, I don’t get it reimbursed by my employer if you’d think that, my blog is mine, mine only and independent).

adblockwelcomeGiven that the number of page views on Dirty Cache passed a quarter million last year (thanks to all my readers), can you imagine the savings in bandwidth and productivity loss by not showing ads? ;-)

So what else can you expect from me this year?

Of course, more about running Oracle on EMC and why I think that’s a pretty good idea. As the competition with Oracle is heating up, I intend to write more on comparing the differences between the solutions of both companies, debunking some marketing and competitive claims, and more. I also hope to find time to maintain the wiki on the Outrun site, and in addition to Outrun documentation, it might be a good place to put Oracle / EMC related howto’s, best practices, FAQs and more.

You also might be wondering what’s going to happen around Oracle / EMC solutions during the Dell / EMC aquisition… Me too. But we can’t (and are not allowed to) comment on it until the merger is final. Until then, business as usual. When the time is ready I’ll comment on new Dell / EMC / Oracle stuff where possible.

Read more of this post

Silly Little Oracle Benchmark – RPM edition

slob-rpmA while ago Kevin Closson announced a new release of the well-known SLOB kit.

SLOB is a simple but powerful toolkit that drives lots and lots of IO on a real Oracle database (so for performance testing of database platforms, it’s much better than synthetic IO tests).

A previous version was bundled with Outrun but required the entire Outrun distribution to work properly. With the new 2.3 version I created an RPM package that can be installed separate on any Enterprise Linux 6.x (64 bit) server.

The wiki page (including instructions) can be found here: SLOB RPM Package wiki

Thanks to Kevin for granting permission to redistribute this awesome toolkit!

Read more of this post

Interview with Madora

A while ago I was interviewed by Kay Williams of Madora Consulting.

Madora Interview

As many customers are overwhelmed by licensing, audit and compliancy issues, I highly recommend my EMEA readers to reach out to Madora if you need independent assistance in that area.

In the interview we discussed a bit of my background, the challenges my customers are facing and how we help them, a bit on the future of Oracle and EMC as well as things like Cloud computing, how EMC sometimes competes with Oracle, my views on Oracle Engineered Systems, and where the two companies are fundamentally different. It has been out there for a while but I was enjoying vacation so I haven’t mentioned it before, but here it is :-)

Expected reading time about 10 minutes. Many thanks to Kay for the interview!

Enjoy: Madora – Interview with Bart Sjerps of EMC

This post first appeared on Dirty Cache by Bart Sjerps. Copyright © 2011 – 2015. All rights reserved. Not to be reproduced for commercial purposes without written permission.

Tales from the past – Disaster Recovery testing

A long time ago in a datacenter far, far away….

Turmoil has engulfed the IT landscape. Within the newly formed digital universe,
corporate empires are becoming more and more
dependent on their digital data and computer systems.
To avoid downtime when getting hit by an evil strike, the corporations are
starting to build disaster recovery capabilities in their operational architectures.

While the congress of the Republic endlessly debates whether
the high cost of decent recovery methods is justified,
the Supreme CIO Chancellor has secretly dispatched a Jedi Apprentice,
one of the guardians of reliability and availability,
to validate existing recovery plans…

Another story from my days as UNIX engineer in the late nineties. I obfuscated all company or people names to protect their reputation or disclose sensitive information, but former colleagues might recognize parts of the stories or maybe everything. Also, some of it is a long time ago and I cannot be sure all I say is factually correct. The human memory is notoriously unreliable.

oobsignIn those days, our company was still relying on tape backup as the only Disaster Recovery (DR) strategy. The main datacenter had a bunch of large tape silos, where, on a daily basis, trays of tapes were unloaded, packed and labeled in a small but strong suitcase, and sent to an off-site location (Pickup Truck Access Method) so the invaluable data could be salvaged in case our entire datacenter would go up in flames.

Read more of this post

Introducing Outrun for Oracle


outrun-logo-transparentIf you want to get your hands dirty with Oracle database, the first thing you have to do is build a system that actually runs Oracle database. Unless you have done that several times before, chances are that this will take considerable time spent on trial-and-error, several reinstalls, fixing install problems and dependencies and so on. The time it takes for someone who is reasonably experienced on Linux, but has no prior Oracle knowledge, would probably range from a full working day (8 hours, best case) to many days. I also have witnessed people actually giving up.

Even for experienced users, doing the whole process manually over and over again is very time consuming, and deploying five or more systems by hand is a guarantee that each one of them is slightly different – and thus a candidate for subtle problems that happen on one but not the others. Virtualization and consolidation is all about consistency and making many components as if they were only one.

There are literally dozens of web pages (such as blog posts) that contain detailed instructions on how to set up Oracle on a certain platform. Some examples:

The Gruff DBA – Oracle 12cR1 2-node RAC on CentOS 6.4 on VMware Workstation 9 – Introduction
Pythian – How to Install Oracle 12c RAC: A Step-by-Step Guide
Martin Bach – Installing Oracle RAC on Oracle Linux 7-part 1

Even if you follow the guidelines in such articles, you are likely to run into problems due to running a different OS, different Oracle version, network problems, and so on. Not to mention that in many cases the “best practices” provided by various vendors are often not honoured because they tend to be overlooked due to information overload…

Some people have hinted to use automated deployment tools such as Ansible (i.e. Frits Hoogland – Using Ansible for executing Oracle DBA tasks) but there are (as far as I know) no complete out-of-the-box solutions.

EMC has published several white papers and reference architectures with instructions on how to set up Oracle to run best on EMC. Still, some of the papers are not a step-by-step manual so you have to extract configuration details manually from various (sometimes conflicting) sources and convert them in configuration file entries, commands, etc.

So I decided a while ago to go for a different approach, and build a virtual appliance that does all of these things for you while still offering (limited) flexibility in different platform and versions, and preferences for configuration.

Read more of this post

Tales from the past – Overheated Datacenter

A long time ago in a datacenter far, far away….

It is a period of digital revolution.

Rebel Dot Com companies, striking from hidden basements and secret lofts,
have won their first fights against long-standing evil corporate empires.

During the battles, rebel geeks have managed to invent secret technology to
replace corporations old ultimate weapons,
such as snail mail and public telephone networks currently powering the entire planet.

Contracted by the Empire’s sinister CIOs, the UNIX Engineer and author of this blog
races against the clock across the UNIX root directories,
to prepare new IT infrastructure for the upcoming battle –
while at the same time, trying to keep the old weapons of mass applications available and running
as best as he can to safeguard the customers freedom in the digital galaxy.

In the late nineties, before I switched to the light side of the Force and joined EMC, I was UNIX engineer and working as a contractor for financial institutions. This is a first in a number of stories from that period and later. I obfuscated all company or people names to protect their reputation or disclose sensitive information, but former colleagues might recognize parts of the stories or maybe everything. Also, some of it is a long time ago and I cannot be sure all I say is factually correct. The human memory is notoriously unreliable.

It was a friday late afternoon.

Everyone in my department already left for the weekend, but I was working on critical infrastructure project that was on a tight deadline, otherwise I guess I would have left already, too.

At some point I needed to re-install a UNIX server, which in those days was done by physically booting them from an install CD – so I needed to go to the datacenter room and get physical console access to get that going. I walked to the datacenter floor, which hosted several large UNIX systems, a mainframe, a number of EMC Symmetrix storage systems, network gear, lots of Intel servers mostly running Windows NT and maybe a few Novell.

There were large tape libraries for backup, lots of server racks, fire extinguishers and whatever you typically find in a large datacenter floor like that. I used my keycard to open the door to the datacenter and stepped in… The first thing I thought was, wow, it’s warm in here…

Read more of this post

Comparing database replication features

It’s still a hot topic in my customer conversations: Should we use Oracle Data Guard or something else for providing disaster recovery?
I’ve written an explanation a while ago. Recently I also created a powerpoint slide comparing various features – in an attempt to be as unbiased as possible (I think I partly succeeded ;)

I’ve put the comparison in a static page on my blog and will update it any time I get new insights or think I can improve it otherwise.

View the comparison here: Comparing DR features

This post first appeared on Dirty Cache by Bart Sjerps. Copyright © 2011 – 2015. All rights reserved. Not to be reproduced for commercial purposes without written permission.

The Oracle Parking Garage

Oracle parking garage

(Thanks to House of Brick Technologies)