Posts by Boyan

Scale-out storage: Proprietary? Commodity? Or both?

Some points from practice:

1) if you need high performance -> block; if you need huge capacity -> object; For example we're yet to see a database that needs 250k IOPS and is 1PB.

2) commodity vs. specialized HW - no matter how much spell is put on specialized HW by vendors delivering it most cases its simply not true that their solution can out-perform a good SDS implementation on standard hardware And no, good SDS does not need a FS underneath. Not the case with Ceph, but there are enough examples.

3) open-source or not - in most cases it's price discussion, however there is nothing is free in life. A open-source project comes DIY - you spend (tens, sometimes hundreds of) thousands in time and salaries. Proprietary comes "out of the box", so there is a trade off between time and money.

Also open-source solutions usually rely on a number of other solutions to provide vital functionality, which adds layers of complexity, inefficiency and risk. For example - unnamed (mentioned in the article) opesource system needs $10k a piece storage nodes and proprietary alternative needs $2k/piece storage nodes. That's 5x difference on money spent for HW. Again - you always pay in one way or another and at current stage (for good or bad) opensource alternatives simply loose on price/performance and price/functionality to proprietary alternatives.

All-flash array bake-off: Load DynamiX finds six AFAs go into four

There are some things very wrong with this paper:

1) for $5.9M you get an AFA that only does 144k IOPS and massive 16.12GB/s throughput. This is a very strange config and throughput is totally out-of-balance with IOPS. Nothing is mentioned for the network that can push this huge traffic. What is it, is it included in the price, is it not, etc.;

2) The price is a total rip-off. Even the Kick-Start package from our company (disclaimer, I work there, obviously) makes north of 200K IOPS and starts at about $20k:

https://storpool.com/get-started-build-high-performance-cloud

4) The paper doesn't say anything about capacity of the systems. And storage systems are priced per GB/TB usually, so we're comparing apples to...nothing;

4) The calculation of the column "K IOPS / Dollars" is not correct. The correct one is: 144K IOPS / $5,900,000 = 0.000024. Even if what they really meant was "IOPS / K Dollars" then the number is 24.4, but it's insanely high. Again from the Kick-start package above the "IOPS/ K Dollars" is 10,000 (!).

Cheers,

B

Gartner sees enterprise SSD-HDD revenue crossover in 2017

It's interesting to see volumes, not revenue.

As Doug S also mentions - the more expensive 10K/15K RPM SAS drives are already biting the dust. Then at current $/GB prices enterprise SSDs are 10x more expensive than high-performance SATA HDDs. We already see even in hybrid SSD systems cost (i.e. vendor revenue) of SSDs is 3x > of cost HDD, let alone all-flash.

The Register guide to software-defined infrastructure

The SDS piece is rather one-sided.

While some vendors try to lock you in, in the end it is a standard storage interface exposed somewhere so you can use to migrate from one system to another. In minutes (or days depending on how much data you have :) And eliminating "vendor lock-in" is illusory - you still have to use a solution from a vendor. However being locked on the storage software is less of a lock in than being locked-in on software AND the hardware.

And if the proposition of the storage software vendor is to manage other companies' arrays - this is storage virtualization, not SDS.

VC cash, growing market propels SimpliVity into hyperconverged orbit

Interesting times ahead

It is interesting to see if Nutanix or Simplivity are going to be "taken out of the market". It is unlikely that some of the big players (maybe except for VMware) will be able catch-up organically, leaving them the alternative to acquire another player. Anyhow as Server SAN, converged and hyper-converged solutions are the future, we'll soon see some market consolidation.

Does your company really need all that storage?

Do you really need a SAN

It is true that very few companies need PB of storage or more and it is usually object, rarely block. Most companies really need several TBs or several tens of TB, rarely even hundreds of TBs. While having shared storage is a must, you do not need to think of storage as a separate layer (think SAN) anymore - you can run fast, reliable, scalable shared storage on the compute nodes. With standard components all-way - from servers and drives to standard Ethernet. This will help increase utilization, slash costs and make things simpler.