All posts by Kiwistorageguy

Location, Location, Location

When you decided where to live you had to make some conscious decisions. You had to decide where your house was in relation to things that are important to you – schools, the office, transport hubs, freeways or motorways.

You had to decide based on your method of transport how close you needed to be to those things so that your experience was acceptable or great. If you worked in New York, it would not be practical to live in beautiful New Zealand as the commute just wouldn’t work unless you could work remotely. So location is important for things that are important to you.

Storage works in much the same way. A traditional HDD has many platters and the data is typically accessed on the drive from the inside of the platter to the outside of the platter. Physics is physics so information on the inside smaller section of the platter will be quicker to read/write than information on the larger outside.

Back in the old days,  DBAs would have to really think about placement of data. Either by specific spindle and RAID allocation or even getting down to block location on disks. Seek times on the inside of the platter were faster than the outside, so that is where high-performing tables and things like temp-DB needed to live.

Memory has really helped that issue, so has other forms of cache so long as the blocks that need to be cached can fit in the amount of allocated memory or cache, if not you hit a latency wall as you have to go off and seek from disk. This means your reads are essentially free, but writes still require some overhead and I/O tax.

SSD really does go a long way to resolving those issues. SSDs and other flash media are locality reference free! Essentially they are binary charges off and on that means that they are basically free for reads and writes which is why IO latencies are typically sub millisecond.

DBAs now no longer need to worry about where and how they place their data  or even if they used share storage. DBAs will always worry, but now they can worry about things further up the stack.

Imagine if you could live in beautiful New Zealand, work in New York and holiday in the Caribbean without the challenges and cost overheads of mechanical travel.  That is what locality free data access with SSDs and the right Storage OE can give you.

So many miss-truths

I have been in the vendor world now for many years and its great, I really enjoy my job and the companies that I have worked for.

What really gets me is some of the blatant lies and mis-truths that get reported especially when they come from so-called Analysts or the like. I recently read a Edison Article on HP Thin Deduplication and laughed out loud more than once at the claims in the incredulously biased article.

Lets start with “Post processing removes any direct performance impact”. It may remove it at the time of ingest, but it does not remove the impact it has on CPU and memory altogether. Normally Post Process deduplication is a scheduled event that till run when you schedule it – what happens if you run a busy workload during that process. It definitely impacts performance.

Flash helps enables deduplication to happen inline as long as you also have a decent amount of cache and an OE that can efficiently handle metadata. As capacities get bigger so does your metadata table needs.  NetApp was the first to bring deduplication to market and it was, and still is a post process. I have seen the impact fist hand on this going wrong when it hasn’t been managed correctly.

Next lets cover the cost of flash. Data reduction is an integral part of moving to flash,  and also an integral part of the TCO of flash so it should be mentioned. However whats key is that when you talk to customers about this that you validate your data. The company that  I work for, Pure Storage will give you an average data reduction of 3:1 for Database, 6:1 for VSI and 10:1 for VDI workloads. This information is gathered from our cloud assist portal gathering information for all our arrays in the wild and reporting on the non thin-provisioned capacity. The article discussed expressly mentions the deduplication ratios easily being 10:1 over and over again, whereas HP online states that their average data reduction is 4:1. Why is that important – well if you do base your cost per GB on data reduction then 10:1 will mean your cost per GB is a lot better than 4:1, but which information is the accurate of the two? The Pure information, like the NetApp ticker information is consistent messaging across the board. It is key that you look at this information when making your decision and that it is consistent and verifiable.

Take a look at the competitive differences where they rate everyone and claim HP is the best. All 4 vendors rated have very different data reduction methodologies, some like Pure include deduplication and compression but don’t count Thin Provisioning, HP counts Thin Provisioning and deduplication. XtremeIO and Solidfire are different again. How can they say that theirs is the best?

The report said HP Looked at telemetry data from 10s of thousands of systems??  The report states than an analysis was done between 16KiB and 4KiB block sizes and that there was little difference between the two with modest savings of 15%. That information was gained from telemetry data from their phone home system. I have seen similar data sent from NetApp, Hitachi and Pure and I would be very surprised if this was true. The data sent is extremely dense and takes masses of processing power just to manage fault calls let alone do deep statistical analysis. I would like to see some more information on this. I think IMHO that its just simply a very expensive exercise to change the block size. Look what happened with EMC XtremeIO recently going from XIOS 2.4 to 3.0 being a destructive upgrade going from 4KB to 8KB block sizes.


Thats enough of a rant for now, but I encourage you to do your homework before investing in any new technology. When you look at analyst reports, they are all paid for, but some are more paid for biased than others.

My advice, ask your vendor to prove it. Put a controller on the floor, run some real world work loads and not synthetic on your own data.



Well I learnt my lesson. I had my settings setup to allow anyone to comment which was a bad mistake as I got spammed.
So now if you want to comment on this blog, you will need to register.

What was interesting is that they were all hitting the same blog entry, the one about XtremeIOMG and not even the latest one.

Must be a Goggle BOT thing!

EMC Merger – Clarrion powered inkjets

Up and down the web we are seeing posts like this one at The Register talking about EMC and HP possibly merging to create some kind of super behemoth mega IT company – really!

67 year old Joe Tucci is set to retire, after 13 years as head of mega storage company EMC and all of a sudden they are talking to HP, that doesn’t make any sense to me.  Some punters are saying talks have been going on for 12 months, so before Tucci was going to retire last time. Is that why he held out?

HP are a full stack provider. The have compute, network and storage already. HP has invested millions in acquiring new technologies like LeftHand and 3Par to replace their dying EVA brand so why would they look at EMC? Thats right they don’t have a hypervisor.

Quite simply they want VMWare.

Lets face it HP don’t need another storage company. EMC could do with a compute and network company though – CISCO would make more sense or even building out with Lenovo and maybe Brocade – they are two partial stack vendors in need of completing the family.

Other talks are that Dell wants some of the company, they used to OEM EMC which they did well in before making the poor decision to invest in EqualLogic the fledgling iSCSI only array.

So how long do we have to wait before the magpies pick EMC apart after Tucci retires, or will he simply not retire again as was the case last time he we set to retire.

Gartner MQ for All Flash Arrays

Pure Storage named a leader in Gartner’s 2014 Magic Quadrant for Solid-State Arrays.

Did you know? Gartner has published a new report on the solid-state storage array market.

Download your complimentary copy of Gartner’s Magic Quadrant for Solid-State Arrays now – and learn more about the key players that are driving this new sector’s growth (it might surprise you). You’ll also discover why Gartner positioned Pure Storage a “leader” in the SSA category.


Download now »

© Pure Storage, Inc. 650 Castro Street, Suite #260 Mountain View, CA 94041

Storage Management – It should be easy

As a storage administrator your looking for a tool that can make your life as easy as possible right?

What do you want to know?

  • State of the controller
  • Capacity and how full it is
  • Latency
  • IOPS and Bandwidth

Those are “at a glance” features that are important to you.


From the Dashboard you want to be able to drill into your other data services in a single tool, not spanning multiple tools.

The Pure Storage management suite is simple, elegant and easy to use. It is based on an HTML5 interface so you no longer have to be concerned about versioning your JAVA and it runs directly off the array management IP network – how simple is that.

When you want to add a host or volume its as simple as going to the storage tab and clicking the + simple by hosts or volumes and you can create single or multiples of each.

host Volume

Protection groups for snapshots and replication is just as simple.  No need to add complicated text based management files.

If you want to perform a snapshot, select the volume and select snap – give it an optional prefix. If you want to recover that snapshot select the snapshot and gear icon to recover to the same location, delete, destroy, rename or even recover as a writable clone to an alternate host. Its that simple. On that note if you want to delete a snap go for it. You can always recover it if your within  24 hours before it gets purged and it isn’t linked in anyway to other snaps so you can delete one without impacting others. Awesome and simple.

By default the controller keeps 12 months of data, so you can within the same tool go back and analyse data from 12 months ago if your trouble shooting a problem.

Its simple, intuitive and easy to use.

XtremeIOMG – The first time I have seen a Tier1 Storage Vendor get SMASHED

As pointed out previously I have been in the storage game a while now. Like it or not bad things happen and like it or not they very rarely see the public eye.

This is the first time I have seen a Tier 1 Storage Vendor get SMASHED and you have to ask yourself why??

The back channel of this is that an EMC customer Andrew Dauncey blogged recently that he was surprised (and quite rightly so) that he had to do a disruptive/destructive upgrade from 2.x to 2.x of XIOS the XTremIO operating environment.

It is most definitely not normal behaviour to see such public blogs of this nature and it has gone viral.

Was it because The Register picked up on this article and published it, or was it simply the amount of people that follow Andrew.

I say we should be more open, if there is an issue get it out there. Lets not wait for a syndication to pick up on it. Storage affects so many things and it is not ok to mislead your customer base, especially for Tier 0 or Tier 1 enterprises but not for any reason.

See blog posts from Nigel Poultan, Vaughan Stewart and others linked to Andrews  site.


And so it begins

A long time ago in a galaxy not so far away I started doing storage so I felt its about time I started to talk about it as I am not shy on offering my opinion.

In the past 7 weeks I have moved to Pure Storage, a “startup” preparing to be the biggest thing in storage since my previous company NetApp.

I’m incredibly excited by the opportunity as Flash based storage is a $50Bn opportunity and Pure is poised to take the market by storm – hence the #OrangeArmy.