Server StorageIO Data Infrastructure Insights and Analysis
|
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Drew Robb (@robbdrew) has a good piece (e.g. article) over at InfoStor titled Eight Ways to Avoid Cloud Storage Pricing Surprises that you can read here.
Drew start’s his piece out with this nice analogy or story:
| Let’s begin with a cautionary tale about pricing: a friend hired a moving company as they quoted a very attractive price for a complex move. They lured her in with a low-ball price then added more and more “extras” to the point where their price ended up higher than many of the other bids she passed up. And to make matters worse, they are already two weeks late with delivery of the furniture and are saying it might take another two weeks. |
Drew extends his example in his piece to compare how some cloud providers may start with pricing as low as some amount only for the customer to be surprised when they did not do their homework to learn about the various fees.
Note that most reputable cloud providers do not hide their fees even though there are myths that all cloud vendors have hidden fees, instead they list what those costs are on their sites. However that means the smart shopper or person procuring cloud services needs to go look for those fee’s and what they mean to avoid surprises. On the other hand if you can not find what extra fee’s would be along with what is or is not included in a cloud service price, to quote Jenny’s line in the movie Forest Gump, "…Run, Forest! Run!…".
In Drew’s piece he mentions five general areas to keep an eye on pertaining cloud storage costs including:
In Drew’s piece, he includes a comment from myself shown below.
Just as in the moving business, lowballing is alive and well in cloud pricing. Greg Schulz, an analyst with StorageIO Group, warned users to pay attention to services that have very low-cost per GByte/TByte yet have extra fees and charges for use, activity or place service caps. Compare those with other services that have higher base fees and attempt to price it based on your real storage and usage patterns. “Watch out for usage and activity fees with lower cost services where you may get charged for looking at or visiting your data, not to mention for when you actually need to use it,” said Schulz. “Also be aware of limits or caps on performance that may apply to a particular class of service.” |
As a follow-up to Drew’s good article, I put together the following thoughts that appeared earlier this year over at InfoStor titled Cloud storage: Is It All About Cost? that you can read here. In that article I start out with the basic question of:
So what is your take on cloud storage, and in what context? Is cloud storage all about removing cost, cost cutting, free storage? Or perhaps even getting something else in addition to free storage? |
I routinely talk with different people from various backgrounds, environments from around the world, and the one consistency I hear when it comes to cloud services including storage is that there is no consistency.
What I mean by this is that there are the cloud crowd cheerleaders who view or cheer for anything cloud related, some of them actually use the cloud vs. simply cheering.
Simple, how do you know if cloud is cheaper or more expensive if you do not know your own costs?
How do you know if cloud storage is available, reliable, durable if you do not have a handle on your environment?
Are you making apples to oranges comparisons or simple trading or leveraging hype and fud for or against?
| Similar to regular storage, how you choose to use and configure on-site traditional storage for high-availability, performance, security among other best practices should be applied to cloud solutions. After all, only you can prevent cloud (or on premise) data loss, granted it is a shared responsibility. Shared responsibility means your service provider or system vendor needs to deliver quality robust solution that you can then take responsibility for configure to use with resiliency. |
For some of you perhaps cloud might be about lowering, reducing or cutting storage costs, perhaps even getting some other service(s) in addition to free storage.
On the other hand, some of you might be
Yet another class of cloud storage (e.g. AWS EBS) are those intended or optimized to be accessed from within a cloud via cloud servers or compute instances (e.g. AWS EC2 among others) vs. those that are optimized for both inside the cloud as well as outside the cloud access (e.g. AWS S3 or Glacier with costs shown here). I am using AWS examples; however, you could use Microsoft Azure (pricing shown here), Google (including their new Nearline service with costs shown here), Rackspace, (calculator here or other cloud files pricing here), HP Cloud (costs shown here), IBM Softlayer (object storage costs here) and many others.
Not all types of cloud storage are the same, which is similar to traditional storage you may be using or have used in your environment in the past. For example, there is high-capacity low-cost storage, including magnetic tape for data protection, archiving of in-active data along with near-line hard disk drives (HDD). There are different types of HDDs, as well as fast solid-state devices (SSD) along with hybrid or SSHD storage used for different purposes. This is where some would say the topic of cloud storage is highly complex.
Data Protection Diaries
Cloud Conversations: AWS overview and primer)
Only you can prevent cloud data loss
Is Computer Data Storage Complex? It Depends
Eight Ways to Avoid Cloud Storage Pricing Surprises
Cloud and Object Storage Center
Cloud Storage: Is It All About Cost?
Cloud conversations: Gaining cloud confidence from insights into AWS outages (Part II)
Given outages, are you concerned with the security of the cloud?
Is the cost of cloud storage really cheaper than traditional storage?
Are more than five nines of availability really possible?
What should I look for in an enterprise file sync-and-share app?
How do primary storage clouds and cloud for backup differ?
What should I consider when using SSD cloud?
What’s most important to know about my cloud privacy policy?
Data Archiving: Life Beyond Compliance
My copies were corrupted: The 3-2-1 rule
Take a 4-3-2-1 approach to backing up data
In my opinion there are cheap clouds (products, services, solutions) and there are low-cost options as well as there are value and premium offerings. Avoid confusing value with cheap or low-cost as something might have a higher cost, however including more capabilities or fees included that if useful can be more value. Look beyond the up-front cost aspects of clouds also considering ongoing recurring fees for actually using a server or solution.
If you can find low-cost storage at or below a penny per GByte per month that could be a good value if it also includes many free access, retrieval GETS head and lists for management or reporting. On the other hand, if you find a service that is at or below a penny per GByte per month however charges for any access including retrieval, as well as network bandwidth fees along with reporting, that might not be as good of a value.
Look beyond the basic price and watch out for statements like "…as low as…" to understand what is required to get that "..as low as.." price. Also understand what the extra fee’s are which most of the reputable providers list these on their sites, granted you have to look for them. If you are already using cloud services, pay attention to your monthly invoices and track what you are paying for to avoid surprises.
From my InfoStor piece: For cloud storage, instead of simply focusing on lowest cost of storage per capacity, look for value, along with ability to configure or use with as much resiliency as you need. Value will mean different things depending on your needs and cloud storage servers, yet the solution should be cost-effective with availability including durability, secure and applicable performance. |
Shopping for cloud servers and storage is similar to acquiring regular servers and storage in that you need to understand what you are acquiring along with up-front and recurring fee’s to understand the total cost of ownership and cost of operations not to mention making apples to apples vs. apples to oranges comparisons.
Btw, instead of simply using lower cost cloud services to cut cost, why not also use those capabilities to create or park another copy of your important data somewhere else just to be safe…
What say you about cloud costs?
Ok, nuff said, for now…
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
It’s that time of the year again for award season:
Eric has run for several years now an annual top VMware, Virtualization, Storage and related blogs voting now taking place until March 16th 2015 (click on the image below). You will find a nice mix of new school, old school and a few current or future school theme blogs represented with some being more VMware specific. However there are also many blogs at the vpad site that have a cloud, virtual, server, storage, networking, software defined, development and other related themes.
Click on the above image to cast your vote for favorite:
My StorageIOblog.com has been on the vLaunchPad site for several years now as well as having syndicated content that also appears via some of the other venues listed there.
In addition to my StorageIOblog and podcast, you will also find many of my fellow VMware vExperts among others at the vLaunchpad site so check them out as well.
This is a people’s choice process (yes it is a popularity process of sorts as well) however also a way of rewarding or thanking those who take time to create and share content with you and others. If you take time to read various blogs, listen to podcasts as well as consume other content, please take a few moments and cast your vote here (thank you in advance) which I hope includes StorageIOblog.com as part of the top ten, as well as being nominated in the Storage, Podcast and Independent blogger categories.
Ok, nuff said, for now…
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
VMware has announced version 6 (V6) of its software defined data center (SDDC) server virtualization hypervisor called vSphere aka ESXi. In addition to a new version of its software defined server hypervisor along with companion software defined management and convergence tools.
As a refresh for those whose world does not revolve around VMware, vSphere and software defined data centers (believe it or not there are some who exist ;), ESXi is the hypervisor that virtualizes underlying physical machines (PM’s) known as hosts.
The path to software defined data center convergence
Guest operating systems (or other hypervisors using nesting) run as virtual machines (VM’s) on top of the vSphere hypervisor host (e.g. ESXi software). Various VMware management tools (or third-party) are used for managing the virtualized data center from initial configuration, configuration, conversion from physical to virtual (P2V) or virtual to virtual (V2V) along with data protection, performance, capacity planning across servers, storage and networks.
VMware vSphere is flexible and can adapt to different sized environments from small office home office (SOHO) or small SMB, to large SMB, SME, enterprise or cloud service provider. There are a free version of ESXi along with paid versions that include support and added management tool features. Besides the ESXi vSphere hypervisor, other commonly deployed modules include the vCenter administration along with Infrastructure Controller services platform among others. In addition, there are optional solution bundles to add support for virtual networking, cloud (public and private), data protection (backup/restore, replication, HA, BC, DR), big data among other capabilities.
VMware has streamlined the installation, configuration and deployment of vSphere along with associated tools which for smaller environments makes things simply easier. For the larger environments, having to do less means being able to do more in the same amount of time which results in cost savings. In addition to easier to use, deploy and configure, VMware has extended the scaling capabilities of vSphere in terms of scaling-out (larger clusters), scaling-up (more and larger servers), as well as scaling-down (smaller environments and ease of use).
The quick synopsis of VMware vVOL’s overview:
How data storage access and managed via VMware today (read more here)
vVOL’s are not LUN’s like regular block (e.g. DAS or SAN) storage that use SAS, iSCSI, FC, FCoE, IBA/SRP, nor are they NAS volumes like NFS mount points. Likewise vVOL’s are not accessed using any of the various object storage access methods mentioned above (e.g. AWS S3, Rest, CDMI, etc) instead they are an application specific implementation. For some of you this approach of an applications specific or unique storage access method may be new, perhaps revolutionary, otoh, some of you might be having a DejaVu moment right about now.
vVOL is not a LUN in the context of what you may know and like (or hate, even if you have never worked with them), likewise it is not a NAS volume like you know (or have heard of), neither are they objects in the context of what you might have seen or heard such as S3 among others.
Keep in mind that what makes up a VMware virtual machine are the VMK, VMDK and some other files (shown in the figure below), and if enough information is known about where those blocks of data are or can be found, they can be worked upon. Also keep in mind that at least near-term, block is the lowest common denominator that all file systems and object repositories get built-up.
How VMware data storage accessed and managed with vVOLs (read more here)
Here is the thing, while vVOL’s will be accessible via a block interface such as iSCSI, FC or FCoE or for that matter, over Ethernet based IP using NFS. Think of these storage interfaces and access mechanisms as the general transport for how vSphere ESXi will communicate with the storage system (e.g. their data path) under vCenter management.
What is happening inside the storage system that will be presented back to ESXi will be different than a normal SCSI LUN contents and only understood by VMware hypervisor. ESXi will still tell the storage system what it wants to do including moving blocks of data. The storage system however will have more insight and awareness into the context of what those blocks of data mean. This is how the storage systems will be able to more closely integrate snapshots, replication, cloning and other functions by having awareness into which data to move, as opposed to moving or working with an entire LUN where a VMDK may live.
Keep in mind that the storage system will still function as it normally would, just think of vVOL as another or new personality and access mechanism used for VMware to communicate and manage storage. Watch for vVOL storage provider support from the who’s who of existing and startup storage system providers including Cisco, Dell, EMC, Fujitsu, HDS, HP, IBM, NetApp, Nimble and many others. Read more about Storage I/O fundamentals here and vVOLs here and here.
Depending on your experiences, you might use revolutionary to describe some of the VMware vSphere V6 features and functionalities. Otoh, if you have some Dejavu moments looking pragmatically at what VMware is delivering with V6 of vSphere executing on their vision, evolutionary might be more applicable. I will leave it up to you do decide if you are having a Dejavu moment and what that might pertain to, or if this is all new and revolutionary, or something more along the lines of technolutionary.
VMware continues to execute delivering on the Virtual Data Center aka Software Defined Data Center paradigm by increasing functionality, as well as enhancing existing capabilities with performance along with resiliency improvements. These abilities enable the aggregation of compute, storage, networking, management and policies for enabling a global virtual data center while supporting existing along with new emerging applications.
If you were not part of the beta to gain early hands-on experience with VMware vSphere V6 and associated technologies, download a copy to check it out as part of making your upgrade or migration plans.
Check out the various VMware resources including communities links here
VMware vSphere Hypervisor getting started and general vSphere information (including download)
VMware vSphere data sheet, compatibility guide along with speeds and feeds (size and other limits)
VMware Blogs and VMware vExpert page
Various fellow VMware vExpert blogs including among many others vsphere-land, scott lowe, virtuallyghetto and yellow-bricks among many others found at the vpad here.
StorageIO Out and About Update – VMworld 2014 (with Video)
VMware vVOL’s and storage I/O fundamentals (Storage I/O overview and vVOL, details Part I and Part II)
How many IOPs can a HDD or SSD do in a VMware environment (Part I and Part II)
VMware VSAN overview and primer, DIY converged software defined storage on a budget
Overall VMware vSphere V6 has a great set of features that support both ease of management for small environments as well as the scaling needs of larger organizations.
Ok, nuff said, for now…
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
|
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is the first of a two-part (part II here) series of my experiences (and impressions) using an Intel NUC ( a 4th generation model) for various things about cloud, virtual, physical and software defined server storage I/O networking.
The NUC has been around new for a few years and continues to evolve and recently I bought my first one (e.g. a 4th generation model) to join some other servers that I have. My reason for getting a NUC is to use it as a simple low-power platform to run different software on including bare-metal OS, hypervisors, cloud, virtual and software defined server storage and networking applications on that might otherwise be on an old laptop or mini-tower.
Intel® NUC with Intel® Core™ i5 Processor and 2.5-Inch Drive Support (NUC5i5RYH) via Intel.com
For those not familiar, NUC is a series of products from Intel called Next Unit Computing that offer an alternative to traditional mini-desktop or even laptop and notebooks. There are several different NUC models available including the newer 5th generation models (click here to see various models and generations). The NUCs are simple, small units of computing with an Intel processor and room for your choice of memory, persistent storage (e.g. Hard Disk Drive (HDD) or flash Solid State Device (SSD), networking, video, audio and other peripheral device attachment.
software (not supplied) is defined by what you choose to use such as a Windows or *nix operating system, VMware ESXi, Microsoft Hyper-V, KVM or Xen hypervisor, or some other applications. The base NUC package includes front and rear-side ports for attaching various devices. In terms of functionality, think of a laptop without a keyboard or video screen, or in terms of a small head-less (e.g. no monitor) mini-tower desktop workstation PC.
If you need to be the first with anything new, then jump direct to the recently released 5th generation models.
On the other hand, if you are looking for a bargain, there are some good deals on 4th generation or older. likewise depending on your processor speed and features needed along with available budget, those criteria and others will direct you to a specific NUC model.
I went with a 4th generation NUC realizing that the newer models were just around the corner as I figured could always get another (e.g. create a NUC cluster) newer model when needed. In addition I also wanted a model that had enough performance to last a few years of use and the flexibility to be reconfigured as needed. My choice was a model D54250WYK priced around $352 USD via Amazon (prices may vary by different venues).
My first NUC is a model D54250WYK (e.g. BOXD54250WYKH1 ) that you can view the specific speeds and feeds here at the Intel site along with ordering info here at Amazon (or your other preferred venue).
View and compare other NUC models at the Intel NUC site here.
The following images show the front-side two USB 3.0 ports along with head-phone (or speaker) and microphone jacks. Looking at the rear-side of the NUC there are a couple of air vents, power connector port (external power supply), mini-display and HDMI video port, GbE LAN, and two USB 3.0 ports.
Left is front view of my NUC model 54250 and Right is back or rear view of NUC
| NUC Model | BOXD54250WYKH1 (speeds/feeds vary by specific model) |
| Form factor | 1.95" tall |
| Processor | Intel Core i5-4250U with active heat sink fan |
| Memory | Two SO-DIMM DDR3L (e.g. laptop) memory, up to 16GB (e.g. 2x8GB) |
| Display | One mini DisplayPort with audio One mini HDMI port with audio |
| Audio | Intel HD Audio, 8 channel (7.1) digital audio via HDMI and DisplayPort, also headphone jack |
| LAN | Intel Gigabit Ethernet (GbE) (I218) |
| Peripheral and storage | Two USB 3.0 (e.g. blue) front side Two USB 3.0 rear side Two USB 2.0 (internal) One SATA port (internal 2.5 inch drive bay) Consumer infrared sensor (front panel) |
| Expansion | One full-length mini PCI Express slot with mSATA support One half-length mini PCI Express slot |
| Included in the box | Laptop style 19V 65W power adapter (brick) and cord, VESA mounting bracket (e.g. for mounting on rear of video monitor), integration (installation) guide, wireless antennae (integrated into chassis), Intel Core i5 logo |
| Warranty | 3-year limited |
There are various Intel Core i3 and i5 processors available depending on specific NUC model, such as my 54250WYK has a two core (1.3Ghz each) 4th generation i5-4250U (click here to see Intel speeds and feeds) which includes Intel Visual BIOS, Turbo Boost, Rapid Start and virtualization support among other features.
Note that features vary by processor type, along with other software, firmware or BIOS updates. While the 1.3Ghz two core (e.g. max 2.6Ghz) is not as robust as faster quad (or more) cores running at 3.0Ghz (or faster), for most applications including as a first virtual lab or storage sand box among other uses, it will be fast enough or comparable to a lower-mid range laptop capabilities.
In general I like the NUC so much that I bought one (model 54250) and would consider adding another in the future for somethings, however also see the need to continue using my other compute servers for different workloads.
This wraps up part I of this two-part series and what this means is that I like the idea of a Intel NUC I bought one. Continue reading in part-two here where I cover the options that I added to my NUC, initial configuration, deployment, use and additional impressions.
Ok, nuff said for now, check out part-two here.
Cheers
Gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 StorageIO and UnlimitedIO LLC All Rights Reserved
This is the second of a two-part series about my first and second impressions of the Intel NUC (Next Unit Computing). In the first post (here) I give an overview and my first impressions while in this post lets look at options added to my NUC model 54250, first deployment use and more impressions.
Intel® NUC with Intel® Core™ i5 Processor and 2.5-Inch Drive Support (NUC5i5RYH) via Intel.com
Since the NUC is a basic brick with a processor mounted on its mother board, you will need to add memory, some type of persistent storage device (mSATA, SATA or USB based) and optionally a WiFi card.
One of the nice things about the NUC is that in many ways it is the equivalent functionality of a laptop or mini-tower without the extra overhead (cost, components, packaging) enabling you to customize as needed for your specific requirements. For example there is no keyboard, mouse, video screen, WiFi, Hard Disk Drive (HDD) or flash Solid State Device (SSD) included with an operating system pre-installed. There is no least memory required enabling you to decide how much to configure while using compatible laptop style memory. Video and monitors attach via HDMI or mini-port including VGA devices via an adapter cable. Keyboard and mouse if needed are handled via USB ports.
Here is what I added to my NUC model 5420.
| 1 | Crucial 16GB Kit (2 x 8GB) DDR3 1600 (PC3-12800) SODIMM 204-Pin Notebook Memory |
| 1 | Intel Network 7260 WiFi Wireless-AC 7260 H/T Dual Band 2×2 AC+Bluetooth HMC. Here is link to Intel site for various drivers. |
| 1 | 500GB Samsung Electronics 840 EVO mSATA 0.85-Inch Solid State Drive |
| 1 | SATA HDD, SSD or HHDD/SSHD (I used one of my existing drives) |
Note that you will also need to supply some type of Keyboard Video Mouse (KVM), in my case I used a HDMI to VGA adapter cable to attach the NUC via HDMI (for video) and USB (keyboard and mouse) to my Startech KVM switch.
Following images show on the left Intel WiFi card installed and on the right, a Samsung 840 EVO mSATA 500GB flash SSD installed above the WiFi card. Also notice on the far right of the images the two DDR3 "notebook" class DRAM DIMM slots.
Left: Intel WiFi card installed and Right Samsung EVO mSATA SSD card (sits above WiFi card)
Note that the NUC (as do many laptops) accepts 9mm or smaller thin 7mm height HDDs and SSDs in its SATA drive bay. I mention this because some of the higher-capacity 2TB 2.5" SFF drives are taller than 9m as shown in the above image and do not fit in the NUC internal SATA drive bay. While many devices and systems support 2.5" drive slots for HDD, SSD or HHDD/SSHDs, pay attention to the height and avoid surprises when something does not fit like it was assumed to.
Low-profile and tall-profile 2.5" SFF HDDs
Additional drives and devices can be attached using external USB 3.0 ports including HDDs, SSDs or even USB to GbE adapters if needed. You will need to supply your own operating system, hypervisor, storage, networking or other software, such as Windows, *nix, VMware ESXi, Hyper-V, KVM, Xen, OpenStack or any of the various ZFS based (among others) storage appliances.
Initial setup and physical configuration of the NUC is pretty quick with the only tool needed being a Philips screw driver.
Intel NUC 5420 and components ready for installation
With all the components including the NUC itself laid out for a quick inventory including recording serial numbers (see image above), the next step is to open up the NUC by removing four Philip screws from the bottom. Once the screws are removed and bottom plate removed, the SATA drive bay opens up to reach the slots of memory, mSATA SSD and WiFi card (see images below). Once the memory, mSATA and WiFi cards are installed, the SATA drive bay coverage those components and it is time to install a 2.5" standard height HDD or SSD. For my first deployment I installed temporarily installed on of my older HHDDs a 750GB Seagate Momentus XT that will be replaced by something newer soon.
View of NUC with bottom cover removed, Left empty SATA drive bay, Right HDD installed
After the components are installed, it is time to replace the bottom cover plate of the NUC securing in place with the four screws previously removed. Next up is attaching any external devices via USB and other ports including KVM and LAN network connection. Once the hardware is ready, its time to power up the NUC and checkout the Visual BIOS (or UEFI) as shown below.
NUC VisualBIOS screen shot examples
At this point unless you have already installed an operating system, hypervisor or other software on a HDD, SSD or USB device, it is time to install your prefered software.
First up was Windows 7 as I already had an image built on the HHDD that required some drivers to be added. specifically, a visit to the Intel resources site (See NUC resources and links section later in this post) was made to get a LAN GbE, WiFi and USB drivers. Once those were installed the on-board GbE LAN port worked good as did the WiFi. Another driver that needed to be download was for a USB-GbE adapter to add another LAN connection. Also a couple of reboots were required for other Windows drivers and configuration changes to take place to correct some transient problems including KVM hangs which eventually cleared themselves up.
Following Windows 7, next up was a clean install of Windows 2012 R2 which also required some drivers and configuration changes. One of the challenges is that Windows 2012 R2 is not officially supported on the NUC with its GbE LAN and WiFi cards. However after doing some searches and reading a few posts including this and this, a solution was found and Windows 2012 R2 and its networking are working good.
Next up was a quick install of Ubuntu 14.04 which went pretty smooth, as well as using Clonezilla to do some drive maintenance, move images and partitions among other things.
My first attempt at installing a standard VMware ESXi 5.5U2 image ran into problems due to the GbE LAN port not being seen. The solution is to use a different build, or custom ISO that includes the applicable GbE LAN driver (e.g. net-e1000e-2.3.2.x86_64.vib) and some useful information at Florian Grehl site (@virten) and over at Andreas Peetz site (@VFrontDe) including SATA controller driver for xahci. Once the GbE driver was added (same driver that addresses other Intel NIC I217/I218 based systems) along with updating the SATA driver, VMware worked fine.
Needless to say there are many other things I plan on doing with the NUC both as a standalone bare-metal system as well as a virtual platform as I get more time and projects allow.
In addition to the NUC models available via Intel and its partners and accessorizing as needed, there are also special customized and ruggedized NUC versions similar to what you would expect to find with laptop, notebooks, and other PC based systems.
Left MSI ProBox rear-view Right MSI ProBox front view
If you are looking to do more than what Intel and its partners offer, then there are some other options such as to increase the number of external ports among other capabilities. One option which I recently added to my collection of systems is an DIY (Do It Yourself) MSI ProBox (VESA mountable) such as this one here.
Internal view MSI ProBox (no memory, processor or disks)
With the MSI ProBox, they are essentially a motherboard with an empty single cpu socket (e.g. LGA 1150 up to 65W) for supporting various processors, two empty DDR3 DIMM slots, 2 empty 2.5" SATA ports among other capabilities. Enclosures such as the MSI ProBox give you flexibility creating something more robust beyond a basic NUC yet smaller than a traditional server depending on your specific needs.
Looking for other small form factor modular and ruggedized server options as an alternative to a NUC, than check out those from Xi3, Advantech, Cadian Networks, and Logic Supply among many others.
Overall I like the NUC and see many uses for it from consumer, home including entertainment and media systems, video security surveillance as well as a small server or workstation device. In addition, I can see a NUC being used for smaller environments as desktop workstations or as a lower-power, lower performance system including as a small virtualization host for SOHO, small SMB and ROBO environments. Another usage is for home virtual lab as well as gaming among other scenarios including simple software defined storage proof of concepts. For example, how about creating a small cluster of NUCs to run VMware VSAN, or Datacore, EMC ScaleIO, Starwind, Microsoft SOFS or Hyper-V as well as any of the many ZFS based NAS storage software applications.
Small, low-power, self-contained with flexibility to choose my memory, WiFi, storage (HDD or SSD) without the extra cost of those items or software being included.
Would be nice to have another GbE LAN port however I addressed that by adding a USB 3.0 to GbE cable, likewise would be nice if the 2.5" SATA drive bay supported tall height form-factor devices such as the 2TB devices. The work around for adding larger capacity and physically larger storage devices is to use the USB 3.0 ports. The biggest warning is if you are going to venture outside of the official supported operating system and application software realm be ready to load some drivers, possibly patch and hack some install scripts and then plug and pray it all works. So far I have not run into any major show stoppers that were not addressed with some time spent searching (google will be your friend), then loading the drivers or making configuration changes.
Various Intel products support search page
Intel NUC support and download links
Intel NUC model 54250 page, product brief page (and PDF version), and support with download links
Intel NUC home theater solutions guide (PDF)
Intel HCL for NUC page and Intel Core i5-4250U processor speeds and feeds
VMware on NUC tips
VMware ESXi driver for LAN net-e1000e-2.3.2.x86_64
VMware ESXi SATA xahci driver
Server storage I/O Intel NUC nick knack notes – First impressions
Server Storage I/O Cables Connectors Chargers & other Geek Gifts (Part I and Part II)
Software defined storage on a budget with Lenovo TS140
Intel NUC provides a good option for many situations that might otherwise need a larger mini-tower desktop workstations or similar systems both for home, consumer and small office needs. NUC can also be used for specialized pre-configured application specific situations that need low-power, basic system functionality and expansion options in a small physical footprint. In addition NUC can also be a good option for adding to an existing physical and virtual LAB or as a basis for starting a new one.
So far I have found many uses for NUC which free up other systems to do other tasks while enabling some older devices to finally be retired. On the other hand like most any technology, while the NUC is flexible, its low power and performance are not enough to support other applications. However the NUC gives me flexibility to leverage the applicable unit of compute (e.g. server, workstation, etc.) that is applicable to a given task or put another way, use the right technology tool for the task at hand.
For now I only need a single NUC to be a companion to my other HP, Dell and Lenovo servers as well as MSI ProBox, however maybe there will be a small NUC cluster, grid or ring configured down the road.
What say you, do you have a NUC if so, how is it being used and tips, tricks or hints to share with others?
Ok, nuff said for now.
Cheers
Gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 StorageIO and UnlimitedIO LLC All Rights Reserved
|
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is part one of a two-part series about Amazon Web Services (AWS) re:Invent 2014 and other recent cloud updates, read part two here.
A few weeks ago I attended Amazon Web Service (AWS) re:Invent 2014 in Las Vegas for a few days. For those of you who have not yet attended this event, I recommend adding it to your agenda. If you have interest in compute servers, networking, storage, development tools or management of cloud (public, private, hybrid), virtualization and related topic themes, you should check out AWS re:invent.
AWS made several announcements at re:invent including many around development tools, compute and data storage services. One of those to keep an eye on is cloud based Aurora relational database service that complement existing RDS tools. Aurora is positioned as an alternative to traditional SQL based transactional databases commonly found in enterprise environments (e.g. SQL Server among others).
Using the AWS Management Portal for vCenter adds a plug-in within your VMware vCenter to manage your AWS infrastructure. The vCenter for AWS plug-in includes support for AWS EC2 and Virtual Machine (VM) import to migrate your VMware VMs to AWS EC2, create VPC (Virtual Private Clouds) along with subnet’s. There is no cost for the plug-in, you simply pay for the underlying AWS resources consumed (e.g. EC2, EBS, S3). Learn more about AWS Management Portal for vCenter here, and download the OVA plug-in for vCenter here.
AWS Andy Jassy (Image via AWS)
November 12, 2014 (Day 1) Keynote (highlight video, full keynote). This is the session where AWS SVP Andy Jassy made several announcements including Aurora relational database that complements existing RDS (Relational Data Services). In addition to Andy, the key-note sessions also included various special guests ranging from AWS customers, partners and internal people in support of the various initiatives and announcements.
Amazon.com CTO Werner Vogels (Image via AWS)
November 13, 2014 (Day 2) Keynote (highlight video, full keynote). In this session, Amazon.com CTO Werner Vogels appears making announcements about the new Container and Lambda services.
Announcements and enhancements made by AWS during re:Invent include:
Hardware security module (HSM) based key managed service for creating and control of encryption keys to protect security of digital assets and their keys. Integration with AWS EBS and others services including S3 and Redshift along with CloudTrail logs for regulatory, compliance and management. Learn more about AWS KMS here
For those who are not familiar, AWS has a suite of database related services including SQL and no SQL based, simple to transactional to Petabyte (PB) scale data warehouses for big data and analytics. AWS offers the Relational Database Service (RDS) which is a suite of different database types, instances and services. RDS instance and types include SimpleDB, MySQL, Postgress, Oracle, SQL Server and the new AWS Aurora offering (read more below). Other little data database and big data repository related offerings include DynamoDB (a non-SQL database), ElasticCache (in memory cache repository) and Redshift (large-scale data warehouse and big data repository).
In addition to database services offered by AWS, you can also combine various AWS resources including EC2 compute, EBS and other storage offerings to create your own solution. For example there are various Amazon Machine Images (AMI’s) or pre-built operating systems and database tools available with EC2 as well as via the AWS Marketplace , such as MongoDB and Couchbase among others. For those not familiar with MongoDB, Couchbase, Cassandra, Riak along with other non SQL or alternative databases and key value repositories, check out Seven Databases in Seven Weeks in my book review of it here.
Seven Databases in Seven Weeks and NoSQL movement available from Amazon.com
Aurora is a new relational database offering part of the AWS RDS suite of services. Positioned as an alternative to commercial high-end database, Aurora is a cost-effective database engine compatible with MySQL. AWS is claiming 5x better performance than standard MySQL with Aurora while being resilient and durable. Learn more about Aurora which will be available in early 2015 and its current preview here.
AWS will be adding a new C4 instance as a next generation of EC2 compute instance based on Intel Xeon E5-2666 v3 (Haswell) processors. The Intel Xeon E5-2666 v3 processors run at a clock speed of 2.9 GHz providing the highest level of EC2 performance. AWS is targeting traditional High Performance Computing (HPC) along with other compute intensive workloads including analytics, gaming, and transcoding among others. Learn more AWS EC2 instances here, and view this Server and StorageIO EC2, EBS and associated AWS primer here.
Containers such as those via Docker have become popular to support developers rapidly build as well as deploy scalable applications. AWS has added a new feature called EC2 Container Service that supports Docker using simple API’s. In addition to supporting Docker, EC2 Container Service is a high performance scalable container management service for distributed applications deployed on a cluster of EC2 instances. Similar to other EC2 services, EC2 Container Service leverages security groups, EBS volumes and Identity Access Management (IAM) roles along with scheduling placement of containers to meet your needs. Note that AWS is not alone in adding container and docker support with Microsoft Azure also having recently made some announcements, learn more about Azure and Docker here. Learn more about EC2 container service here and more about Docker here.
Continue reading about re:Invent 2014 and other recent AWS enhancements here in part two of this two-part series.
Ok, nuff said (for now)
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is part two of a two-part series about Amazon Web Services (AWS) re:Invent 2014 and other recent cloud updates, read part one here.
Announcements and enhancements made by AWS during re:Invent include:
In addition to announcing new higher performance Elastic Cloud Compute (EC2) compute instances along with container service, another new service is AWS Lambda. Lambda is a service that automatically and quickly runs your applications code in response to events, activities, or other triggers. In addition to running your code, Lambda service is billed in 100 millisecond increments along with corresponding memory use vs. standard EC2 per hour billing. What this means is that instead of paying for an hour of time for your code to run, you can choose to use the Lambda service with more fine-grained consumption billing.
Lambda service can be used to have your code functions staged ready to execute. AWS Lambda can run your code in response to S3 bucket content (e.g. objects) changes, messages arriving via Kinesis streams or table updates in databases. Some examples include responding to event such as a web-site click, response to data upload (photo, image, audio, file or other object), index, stream or analyze data, receive output from a connected device (think Internet of Things IoT or Internet of Device IoD), trigger from an in-app event among others. The basic idea with Lambda is to be able to pay for only the amount of time needed to do a particular function without having to have an AWS EC2 instance dedicated to your application. Initially Lambda supports Node.js (JavaScript) based code that runs in its own isolated environment.
Various application code deployment models
Lambda service is a pay for what you consume, charges are based on the number of requests for your code function (e.g. application), amount of memory and execution time. There is a free tier for Lambda that includes 1 million requests and 400,000 GByte seconds of time per month. A GByte second is the amount of memory (e.g. DRAM vs. storage) consumed during a second. An example is your application is run 100,000 times and runs for 1 second consuming 128MB of memory = 128,000,000MB = 128,000GB seconds. View various pricing models here on the AWS Lambda site that show examples for different memory sizes, times a function runs and run time.
How much memory you select for your application code determines how it can run in the AWS free tier, which is available to both existing and new customers. Lambda fees are based on the total across all of your functions starting with the code when it runs. Note that you could have from one to thousands or more different functions running in Lambda service. As of this time, AWS is showing Lambda pricing as free for the first 1 million requests, and beyond that, $0.20 per 1 million request ($0.0000002 per request) per duration. Duration is from when you code runs until it ends or otherwise terminates rounded up to the nearest 100ms. The Lambda price also depends on the amount of memory you allocated for your code. Once past the 400,000 GByte second per month free tier the fee is $0.00001667 for every GB second used.
Why would you use AWS Lambda vs. provisioning an Container, EC2 instance or running your application code function on a traditional or virtual machine?
If you need control and can leverage an entire physical server with its operating system (O.S.), application and support tools for your piece of code (e.g. JavaScript), that could be an option. If you simply need to have an isolated image instance (O.S., applications and tools) for your code on a shared virtual on-premises environment then that can be an option. Likewise if you have the need to move your application to an isolated cloud machine (CM) that hosts an O.S. along with your application paying for those resources such as on an hourly basis, that could be your option. Simply need a lighter-weight container to drop your application into that’s where Docker and containers comes into play to off-load some of the traditional application dependencies overhead.
However, if all you want to do is to add some code logic to support processing activity for example when an object, file or image is uploaded to AWS S3 without having to standup an EC2 instance along with associated server, O.S. and complete application activity, that’s where AWS Lambda comes into play. Simply create your code (initially JavaScript) and specify how much memory it needs, define what events or activities will trigger or invoke the event, and you have a solution.
View AWS Lambda pricing along with free tier information here.
AWS is increasing the performance and size of General Purpose SSD and Provisioned IOP’s SSD volumes. This means that you can create volumes up to 16TB and 10,000 IOP’s for AWS EBS general-purpose SSD volumes. For EBS Provisioned IOP’s SSD volumes you can create up to 16TB for 20,000 IOP’s. General-purpose SSD volumes deliver a maximum throughput (bandwidth) of 160 MBps and Provisioned IOP SSD volumes have been specified by AWS at 320MBps when attached to EBS optimized instances. Learn more about EBS capabilities here. Verify your IO size and verify AWS sizing information to avoid surprises as all IO sizes are not considered to be the same. Learn more about Provisioned IOP’s, optimized instances, EBS and EC2 fundamentals in this StorageIO AWS primer here.
In addition to compute and storage resource enhancements, AWS has also announced several tools to support application development, configuration along with deployment (life-cycle management). These include tools that AWS uses themselves as part of building and maintaining the AWS platform services.
Management, reporting and monitoring capabilities including Data center infrastructure management (DCIM) for monitoring your AWS resources, configuration (including history), governance, change management and notifications. AWS Config enables similar capabilities to support DCIM, Change Management Database (CMDB), trouble shooting and diagnostics, auditing, resource and configuration analysis among other activities. Learn more about AWS Config here.
AWS announced a new service catalog that will be available in early 2015. This new service capability will enable administrators to create and manage catalogs of approved resources for users to use via their personalized portal. Learn more about AWS service catalog here.
To support code rapid deployment automation for EC2 instances, AWS has released CodeDeploy. CodeDeploy masks complexity associated with deployment when adding new features to your applications while reducing human error-prone operations. As part of the announcement, AWS mentioned that they are using CodeDeploy as part of their own applications development, maintenance, and change-management and deployment operations. While suited for at scale deployments across many instances, CodeDeploy works with as small as a single EC2 instance. Learn more about AWS CodeDeploy here.
For application code management, AWS will be making available in early 2015 a new service called CodeCommit. CodeCommit is a highly scalable secure source control service that host private Git repositories. Supporting standard functionalities of Git, including collaboration, you can store things from source code to binaries while working with your existing tools. Learn more about AWS CodeCommit here.
To support application delivery and release automation along with associated management tools, AWS is making available CodePipeline. CodePipeline is a tool (service) that supports build, checking workflow’s, code staging, testing and release to production including support for 3rd party tool integration. CodePipeline will be available in early 2015, learn more here.
Learn more about the above and other AWS services by actually truing hands on using their free tier (AWS Free Tier). View AWS re:Invent produced breakout session videos here, audio podcasts here, and session slides here (all sessions may not yet be uploaded by AWS re:Invent)
AWS continues to invest as well as re-invest into its environment both adding new feature functionality, as well as expanding the extensibility of those features. This means that AWS like other vendors or service providers adds new check-box features, however they also like some increase the depth extensibility of those capabilities. Besides adding new features and increasing the extensibility of existing capabilities, AWS is addressing both the data and information infrastructure including compute (server), storage and database, networking along with associated management tools while also adding extra developer tools. Developer tools include life-cycle management supporting code creation, testing, tracking, testing, change management among other management activities.
Another observation is that while AWS continues to promote the public cloud such as those services they offer as the present and future, they are also talking hybrid cloud. Granted you have to listen carefully as you may not simply hear hybrid cloud used like some toss it around, however listen for and look into AWS Virtual Private Cloud (VPC), along with what you can do using various technologies via the AWS marketplace. AWS is also speaking the language of enterprise and traditional IT from an applications and development to data and information infrastructure perspective while also walking the cloud talk. What this means is that AWS realizes that they need to help existing environments evolve and make the transition to the cloud which means speaking their language vs. converting them to cloud conversations to then be able to migrate them to the cloud. These steps should make AWS practical for many enterprise environments looking to make the transition to public and hybrid cloud at their pace, some faster than others. More on these and some related themes in future posts.
The AWS re:Invent event continues to grow year over year, I heard a figure of over 12,000 people however it was not clear if that included exhibiting vendors, AWS people, attendees, analyst, bloggers and media among others. However a simple validation is that the keynotes were in the larger rooms used by events such as EMCworld and VMworld when they hosted in Las Vegas as was the expo space vs. what I saw last year while at re:Invent. Unlike some large events such as VMworld where at best there is a waiting queue or line to get into sessions or hands on lab (HOL), while becoming more crowded, AWS re:Invent is still easy to get in and spend some time using the HOL which is of course powered by AWS meaning you can resume what you started while at re:Invent later. Overall a good event and nice series of enhancements by AWS, looking forward to next years AWS re:Invent.
Ok, nuff said (for now)
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
|
Ok, nuff said (for now)
Cheers
Gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Here is a quick video montage or mash-up if you prefer that Cory Peden (aka the Server and StorageIO Intern @Studentof_IT) put together using some video that recorded while at VMworld 2014 in San Francisco. In this YouTube video we take a quick tour around the expo hall to see who as well as what we run into while out and about.
Click on above image to view video
For those of you who were at VMworld 2014 the video (click above image) will give you a quick Dejavu memory of the sites and sounds while for those who were not there, see what you missed to plan for next year. Watch for appearances from Gina Minks (@Gminks) aka Gina Rosenthal (of BackupU)and Michael (not Dell) of Dell Data Protection, Luigi Danakos (@Nerdblurt) of HP Data Protection who lost his voice (tweet Luigi if you can help him find his voice). With Luigi we were able to get in a quick game of buzzword bingo before catching up with Marc Farley (@Gofarley) and John Howarth of Quaddra Software. Mark and John talk about their new solution from Quaddra which will enable searching and discovering data across different storage systems and technologies.
Other visits include a quick look at an EVO:Rail from Dell, along with Docker for Smarties overview with Nathan LeClaire (@upthecyberpunks) of Docker (click here to watch the extended interview with Nathan).
Check out the conversation with Max Kolomyeytsev of StarWind Software (@starwindsan) before we get interrupted by a sales person. During our walk about, we also bump into Mark Peters (@englishmdp) of ESG facing off video camera to video camera.
Watch for other things including rack cabinets that look like compute servers yet that have a large video screen so they can be software defined for different demo purposes.
Watch for more Server and StorageIO Industry Trend Perspective podcasts, videos as well as out and about updates soon, meanwhile check out others here.
Ok, nuff said (for now)
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is the second post of a two part series, read the first post here.
Earlier this year I had the opportunity to test drive some Seagate 1200 12Gbs Enterprise SAS SSD’s as a follow-up to some earlier activity trying their Enterprise TurboBoost Drives. Disclosure: Seagate has been a StorageIO client and was also the sponsor of this white paper and associated proof-points mentioned in this post.
The earlier proof-points focused on SSD as a target or storage device. In the following proof-points, the Seagate Enterprise 1200 SSD is used as a shared read cache (write-through). Using a write-through cache enables a given amount of SSD to give a performance benefit to other local and networked storage devices.
Non-virtualized servers with dedicated storage and I/O paths.
Aggregation causes aggravation with I/O bottlenecks because of consolidation using server virtualization. The following figure shows non-virtualized servers with their own dedicated physical machine (PM) and I/O resources. When various servers are virtualized and hosted by a common host (physical machine), their various workloads compete for I/O and other resources. In addition to competing for I/O performance resources, these different servers also tend to have diverse workloads.
Virtual server storage I/O blender bottleneck (aggregation causes aggravation)
The figure above shows aggregation causing aggravation with the result being I/O bottlenecks as various applications performance needs converge and compete with each other. The aggregation and consolidation result is a blend of random, sequential, large, small, read and write characteristics. These different storage I/O characteristics are mixed up and need to be handled by the underlying I/O capabilities of the physical machine and hypervisor. As a result, a common deployment for SSD in addition to as a target device for storing data is as a cache to cut bottlenecks for traditional spinning HDD.
In the following figure a solution is shown introducing I/O caching with SSD to help mitigate or cut the effects of server consolation causing performance aggravations.
Addressing the VMware Server Storage I/O blender with cache
For these proof-points, the goal was to create an I/O bottleneck resulting from multiple VMs in a virtual server environment performing application work. In this proof-point, multiple competing VMs including a SQL Server 2012 database and an Exchange server shared the same underlying storage I/O infrastructure including HDD’s The 6TB (Enterprise Capacity) HDD was configured as a VMware dat and allocated as virtual disks to the VMs. Workloads were then run concurrently to create an I/O bottleneck for both cached and non-cached results.
Server storage I/O with virtualization roof-point configuration topology
The following figure shows two sets of proof points, cached (top) and non-cached (bottom) with three workloads. The workloads consisted of concurrent Exchange and SQL Server 2012 (TPC-B and TPC-E) running on separate virtual machine (VM) all on the same physical machine host (SUT) with database transactions being driven by two separate servers. In these proof-points, the applications data were placed onto the 6TB SAS HDD to create a bottleneck, and a portion of the SSD used as a cache. Note that the Virtunet cache software allows you to use a part of a SSD device for cache with the balance used as a regular storage target should you want to do so.
If you have paid attention to the earlier proof-points, you might notice that some of the results below are not as good as those seen in the Exchange, TPC-B and TPC-E results about. The reason is simply that the earlier proof-points were run without competing workloads, and database along with log or journal files were placed on separate drives for performance. In the following proof-point as part of creating a server storage I/O blender bottleneck the Exchange, TPC-B as well as TPC-E workloads were all running concurrently with all data on the 6TB drive (something you normally would not want to do).
Solving the VMware Server Storage I/O blender with cache
The cache and non-cached mixed workloads shown above prove how an SSD based read-cache can help to reduce I/O bottlenecks. This is an example of addressing the aggravation caused by aggregation of different competing workloads that are consolidated with server virtualization.
For the workloads shown above, all data (database tables and logs) were placed on VMware virtual disks created from a dat using a single 7.2K 6TB 12Gbps SAS HDD (e.g. Seagate Enterprise Capacity).
The guest VM system disks which included paging, applications and other data files were virtual disks using a separate dat mapped to a single 7.2K 1TB HDD. Each workload ran for eight hours with the TPC-B and TPC-E having 50 simulated users. For the TPC-B and TPC-E workloads, two separate servers were used to drive the transaction requests to the SQL Server 2012 database.
For the cached tests, a Seagate Enterprise 1200 400GB 12Gbps SAS SSD was used as the backing store for the cache software (Virtunet Systems Virtucache) that was installed and configured on the VMware host.
During the cached tests, the physical HDD for the data files (e.g. 6TB HDD) and system volumes (1TB HDD) were read cache enabled. All caching was disabled for the non-cached workloads.
Note that this was only a read cache, which has the side benefit of off-loading those activities enabling the HDD to focus on writes, or read-ahead. Also note that the combined TPC-E, TPC-B and Exchange databases, logs and associated files represented over 600GB of data, there was also the combined space and thus cache impact of the two system volumes and their data. This simple workload and configuration is representative of how SSD caching can complement high-capacity HDD’s
While the star and focus of these series of proof-points is the Seagate 1200 Enterprise 12Gbs SAS SSD, the caching software (virtunet) and Enterprise TurboBoost drives also play key supporting and favorable roles. However the 6TB 12Gbs SAS high-capacity drive caught my attention from a couple of different perspectives. Certainly the space capacity was interesting along with a 12Gbs SAS interface well suited for near-line, high-capacity and dense tiered storage environments. However for a high-capacity drive its performance is what really caught my attention both in the standard exchange, TPC-B and TPC-E workloads, as well as when combined with SSD and cache software.
This opens the door for a great combination of leveraging some amount of high-performance flash-based SSD (or TurboBoost drives) combined with cache software and high-capacity drives such as the 6TB device (Seagate now has larger versions available). Something else to mention is that the 6TB HDD in addition to being available in either 12Gbs SAS, 6Gbs SAS or 6Gbs SATA also has enhanced durability with a Read Bit Error Rate of 10 ^15 (e.g. 1 second read error per 10^15 average attempts) and an AFR (annual failure rate) of 0.63% (See more speeds and feeds here). Hence if you are concerned about using large capacity HDD’s and them failing, make sure you go with those that have a high Read Bit Error Rate and a low AFR which are more common with enterprise class vs. lower cost commodity or workstation drives. Note that these high-capacity enterprise HDD’s are also available with Self-Encrypting Drive (SED) options.
Read more in this StorageIO Industry Trends and Perspective (ITP) white paper compliments of Seagate 1200 12Gbs SAS SSD’s and visit the Seagate Enterprise 1200 12Gbs SAS SSD page here. Moving forward there is the notion that flash SSD will be everywhere. There is a difference between all data on flash SSD vs. having some amount of SSD involved in preserving, serving and protecting (storing) information.
Key themes to keep in mind include:
Flash and SSD are in your future, this comes back to the questions of how much flash SSD do you need, along with where to put it, how to use it and when.
Ok, nuff said (for now).
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
|
Ok, nuff said (for now)
Cheers
Gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
