Server StorageIO Data Infrastructure Insights and Analysis
SAN, NAS, CAS, VTL, Clustered, Block, File, Modular, Grid and other forms of storage architecture options and access methods.
|
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
Updated 2/10/2018
RAID data protection remains relevant including erasure codes (EC), local reconstruction codes (LRC) among other technologies. If RAID were really not relevant anymore (e.g. actually dead), why do some people spend so much time trying to convince others that it is dead or to use a different RAID level or enhanced RAID or beyond raid with related advanced approaches?
When you hear RAID, what comes to mind?
A legacy monolithic storage system that supports narrow 4, 5 or 6 drive wide stripe sets or a modern system support dozens of drives in a RAID group with different options?
RAID means many things, likewise there are different implementations (hardware, software, systems, adapters, operating systems) with various functionality, some better than others.
For example, which of the items in the following figure come to mind, or perhaps are new to your RAID vocabulary?
There are Many Variations of RAID Storage some for the enterprise, some for SMB, SOHO or consumer. Some have better performance than others, some have poor performance for example causing extra writes that lead to the perception that all parity based RAID do extra writes (some actually do write gathering and optimization).
Some hardware and software implementations using WBC (write back cache) mirrored or battery backed-BBU along with being able to group writes together in memory (cache) to do full stripe writes. The result can be fewer back-end writes compared to other systems. Hence, not all RAID implementations in either hardware or software are the same. Likewise, just because a RAID definition shows a particular theoretical implementation approach does not mean all vendors have implemented it in that way. |
RAID is not a replacement for backup rather part of an overall approach to providing data availability and accessibility.
There are different RAID levels and implementations (hardware, software, controller, storage system, operating system, adapter among others) for various environments (enterprise, SME, SMB, SOHO, consumer) supporting primary, secondary, tertiary (backup/data protection, archiving).
General RAID comparisons
Thus one size or approach does fit all solutions, likewise RAID rules of thumbs or guides need context. Context means that a RAID rule or guide for consumer or SOHO or SMB might be different for enterprise and vise versa, not to mention on the type of storage system, number of drives, drive type and capacity among other factors.
General basic RAID comparisons
Thus the best RAID level is the one that meets your specific needs in your environment. What is best for one environment and application may be different from what is applicable to your needs.
Key points and RAID considerations include: · Not all RAID implementations are the same, some are very much alive and evolving while others are in need of a rest or rewrite. So it is not the technology or techniques that are often the problem, rather how it is implemented and then deployed. · It may not be RAID that is dead, rather the solution that uses it, hence if you think a particular storage system, appliance, product or software is old and dead along with its RAID implementation, then just say that product or vendors solution is dead. · RAID can be implemented in hardware controllers, adapters or storage systems and appliances as well as via software and those have different features, capabilities or constraints. · Long or slow drive rebuilds are a reality with larger disk drives and parity-based approaches; however, you have options on how to balance performance, availability, capacity, and economics. · RAID can be single, dual or multiple parity or mirroring-based. · Erasure and other coding schemes leverage parity schemes and guess what umbrella parity schemes fall under. · RAID may not be cool, sexy or a fun topic and technology to talk about, however many trendy tools, solutions and services actually use some form or variation of RAID as part of their basic building blocks. This is an example of using new and old things in new ways to help each other do more without increasing complexity. · Even if you are not a fan of RAID and think it is old and dead, at least take a few minutes to learn more about what it is that you do not like to update your dead FUD. |
There is some dead marketing that paints a broad picture that RAID is dead to prop up something new, which in some cases may be a derivative variation of parity RAID.
Data dispersal and durability
RAID continues to evolve with rapid rebuilds for some systems
Otoh, there are some specific products, technologies, implementations that may be end of life or actually dead. Likewise what might be dead, dying or simply not in vogue are specific RAID implementations or packaging. Certainly there is a lot of buzz around object storage, cloud storage, forward error correction (FEC) and erasure coding including messages of how they cut RAID. Catch is that some object storage solutions are overlayed on top of lower level file systems that do things such as RAID 6, granted they are out of sight, out of mind.
General RAID parity and erasure code/FEC comparisons
Then there are advanced parity protection schemes which include FEC and erasure codes that while they are not your traditional RAID levels, they have characteristic including chunking or sharding data, spreading it out over multiple devices with multiple parity (or derivatives of parity) protection.
Bottom line is that for some environments, different RAID levels may be more applicable and alive than for others.
Via BizTech – How to Turn Storage Networks into Better Performers
|
If you are new to RAID, learn more about the past, present and future keeping mind context. Keeping context in mind means that there are different RAID levels and implementations for various environments. Not all RAID 0, 1, 1/0, 10, 2, 3, 4, 5, 6 or other variations (past, present and emerging) are the same for consumer vs. SOHO vs. SMB vs. SME vs. Enterprise, nor are the usage cases. Some need performance for reads, others for writes, some for high-capacity with low performance using hardware or software. RAID Rules of thumb are ok and useful, however keep them in context to what you are doing as well as using.
Take some time to learn, ask questions including what to use when, where, why and how as well as if an approach or recommendation are applicable to your needs. Check out the following links to read some extra perspectives about RAID and keep in mind, what might apply to enterprise may not be relevant for consumer or SMB and vise versa.
Some advise needed on SSD’s and Raid (Via Spiceworks)
RAID 5 URE Rebuild Means The Sky Is Falling (Via BenchmarkReview)
Double drive failures in a RAID-10 configuration (Via SearchStorage)
Industry Trends and Perspectives: RAID Rebuild Rates (Via StorageIOblog)
RAID, IOPS and IO observations (Via StorageIOBlog)
RAID Relevance Revisited (Via StorageIOBlog)
HDDs Are Still Spinning (Rust Never Sleeps) (Via InfoStor)
When and Where to Use NAND Flash SSD for Virtual Servers (Via TheVirtualizationPractice)
What’s the best way to learn about RAID storage? (Via Spiceworks)
Design considerations for the host local FVP architecture (Via Frank Denneman)
Some basic RAID fundamentals and definitions (Via SearchStorage)
Can RAID extend nand flash SSD life? (Via StorageIOBlog)
I/O Performance Issues and Impacts on Time-Sensitive Applications (Via CMG)
The original RAID white paper (PDF) that while over 20 years old, it provides a basis, foundation and some history by Katz, Gibson, Patterson et al
Storage Interview Series (Via Infortrend)
Different RAID methods (Via RAID Recovery Guide)
A good RAID tutorial (Via TheGeekStuff)
Basics of RAID explained (Via ZDNet)
RAID and IOPs (Via VMware Communities)
View additional NAS, NVMe, SSD, NVM, SCM, Data Infrastructure and HDD related topics via the following links.
Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.
What is my favorite or preferred RAID level?
That depends, for some things its RAID 1, for others RAID 10 yet for others RAID 4, 5, 6 or DP and yet other situations could be a fit for RAID 0 or erasure codes and FEC. Instead of being focused on just one or two RAID levels as the solution for different problems, I prefer to look at the environment (consumer, SOHO, small or large SMB, SME, enterprise), type of usage (primary or secondary or data protection), performance characteristics, reads, writes, type and number of drives among other factors. What might be a fit for one environment would not be a fit for others, thus my preferred RAID level along with where implemented is the one that meets the given situation. However also keep in mind is tying RAID into part of an overall data protection strategy, remember, RAID is not a replacement for backup.
Like other technologies that have been declared dead for years or decades, aka the Zombie technologies (e.g. dead yet still alive) RAID continues to be used while the technologies evolves. There are specific products, implementations or even RAID levels that have faded away, or are declining in some environments, yet alive in others. RAID and its variations are still alive, however how it is used or deployed in conjunction with other technologies also is evolving.
Ok, nuff said, for now.
Gs
Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.
Recently I put together a two-part series of some server storage I/O items to get a geek for a gift (read part I here and part II here) that also contain items that can be used for accessorizing servers such as the Lenovo ThinkServer TS140.
Image via Lenovo.com
Likewise I have done reviews of the Lenovo ThinkServer TS140 in the past which included me liking them and buying some (read the reviews here and here), along with a review of the larger TD340 here.
Do you need or want to do a Do It Yourself (DIY) build of a small server compute cluster, or a software defined storage cluster (e.g. scale-out), or perhaps a converged storage for VMware VSAN, Microsoft SOFS or something else?
Do you need a new server, second or third server, or expand a cluster, create a lab or similar and want the ability to tailor your system without shopping or a motherboard, enclosure, power supply and so forth?
Are you a virtualization or software defined person looking to create a small VMware Virtual SAN (VSAN) needing three or more servers to build a proof of concept or personal lab system?
Then the TS140 could be a fit for you.
Image via StorageIOlabs, click to see review
Recently I have seen a lot of site traffic on my site with people viewing my reviews of the Lenovo TS140 of which I have a few. In addition have got questions from people via comments section as well as elsewhere about the TS140 and while shopping at Amazon.com for some other things, noticed that there were some good value deals on different TS140 models.
I tend to buy the TS140 models that are bare bones having power supply, enclosure, CD/DVD, USB ports, power supply and fan, processor and minimal amount of DRAM memory. For processors mine have the Intel E3-1225 v3 which are quad-core and that have various virtualization assist features (e.g. good for VMware and other hypervisors).
What I saw on Amazon the other day (also elsewhere) were some Intel i3-4130 dual core based systems (these do not have all the virtualization features, just the basics) in a bare configuration (e.g. no Hard Disk Drive (HDD), 4GB DRAM, processor, mother board, power supply and fan, LAN port and USB with a price of around $220 USD (your price may vary depending on timing, venue, prime or other membership and other factors). Not bad for a system that you can tailor to your needs. However what also caught my eye were the TS140 models that have the Intel E3-1225 v3 (e.g. quad core, 3.2Ghz) processor matching the others I have with a price of around $330 USD including shipping (your price will vary depending on venue and other factors).
Some caveats of this solution approach include:
Create a single or multi-server based system for
Like some other servers in this class, you need to pay attention to what it is that you are ordering, check out the various reviews, comments and questions as well as verify the make, model along with configuration. For example what is included and what is not included, warranty, return policy among other things. In the case of some of the TS140 models, they do not have a HDD, OS, keyboard, monitor, mouse along with different types of processors and memory. Not all the processors are the same, pay attention, visit the Intel Ark site to look up a specific processor configuration to see if it fits your needs as well as visit the hardware compatibility list (HCL) for the software that you are planning to use. Note that these should be best practices regardless of make, model, type or vendor for server, storage, I/O networking hardware and software.
This list assumes that you have obtained a model without a HDD, keyboard, video, mouse or operating system (OS) installed
You can easily add some GbE (or faster ports) including use the PCIe x1 slot, or use one of the other slots for a quad port GbE (or faster), not to mention get some InfiniBand single or dual port cards such as the Mellanox Connectx II or Connect III that support QDR and can run in IBA or 10GbE modes. If you only have two or three servers in a cluster, grid, ring configuration you can run point to point topologies using InfiniBand (and some other network interfaces) without using a switch, however you decide if you need or want switched or non-switched (I have a switch). Note that with VMware (and perhaps other hypervisors or OS) you may need to update the drives for the Realtek GbE LAN on Motherboard port (see links below).
For extra storage space capacity (and performance) you can easily add PCIe G2 or G3 HBAs (SAS, SATA, FC, FCoE, CNA, UTA, IBA for SRP, etc) or RAID cards among others. Depending on your choice of cards, you can then attach to more internal storage, external storage or some combination with different adapters, cables, interposers and connectivity options. For example I have used TS140s with PCIe Gen 3 12Gbs SAS HBAs attached to 12Gbs SAS SSDs (and HDDs) with the ability to drive performance to see what those devices are capable of doing.
As an example of how a TS140 can be configured, using one of the base E3-1224 v3 models with 4GB RAM, no HDD (e.g around $330 USD, your price will vary), add a 4TB Seagate HDD (or two or three) for around $140 USD each (your price will vary), add a 480GB SATA SSD for around $340 USD (your price will vary) with those attached to the internal SATA ports. To bump up network performance, how about a Mellanox Connectx II dual port QDR IBA/10GbE card for around $140 USD (your price will vary), plus around $65 USD for QSFP cable (you your price will vary), and some extra memory (use what you have or shop around) and you have a platform ready to go for around or under $1,000 USD. Add some more internal or external disks, bump up the memory, put in some extra network adapters and your price will go up a bit, however think about what you can have for a robust not so little system. For you VMware vgeeks, think about the proof of concept VSAN that you can put together, granted you will have to do some DIY items.
Image via Lenovo.com
Like many servers in its category (price, capabilities, abilities, packaging) you can do a lot of different things with them, as well as hardware define with accessories, or use your own software. Depending on how you end how hardware defining the TS140 with extra memory, HDDs, SSDs, adapters or other accessories and software your cost will vary. However you can also put together a pretty robust system without breaking your budget while meeting different needs.
Is this for everybody? Nope
Is this for more than a lab, experimental, hobbyist, gamer? Sure, with some caveats Is this apples to apples comparison vs. some other solutions including VSANs? Nope, not even close, maybe apples to oranges.
Do I like the TS140? Yup, starting with a review I did about a year ago, I liked it so much I bought one, then another, then some more.
Are these the only servers I have, use or like? Nope, I also have systems from HP and Dell as well as test drive and review others
Why do I like the TS140? It’s a value for some things which means that while affordable (not to be confused with cheap) it has features, salability and ability to be both hardware defined for what I want or need to use them as, along with software define them to be different things. Key for me is the PCIe Gen 3 support with multiple slots (and types of slots), reasonable amount of memory, internal housing for 3.5" and 2.5" drives that can attach to on-board SATA ports, media device (CD/DVD) if needed, or remove to use for more HDDs and SSDs. In other words, it’s a platform that instead of shopping for the motherboard, an enclosure, power supply, processor and related things I get the basics, then configure, and reconfigure as needed.
Another reason I like the TS140 is that I get to have the server basically my way, in that I do not have to order it with a smallest number of HDDs, or that it comes with an OS, more memory than needed or other things that I may or may not be able to use. Granted I need to supply the extra memory, HDDs, SSDs, PCIe adapters and network ports along with software, however for me that’s not too much of an issue.
What don’t I like about the TS140? You can read more about my thoughts on the TS140 in my review here, or its bigger sibling the TD340 here, however I would like to see more memory slots for scaling up. Granted for what these cost, it’s just as easy to scale-out and after all, that’s what a lot of software defined storage prefers these days (e.g. scale-out).
The TS140 is a good platform for many things, granted not for everything, that’s why like storage, networking and other technologies there are different server options for various needs. Exercise caution when doing apples to oranges comparison on price alone, compare what you are getting in terms of processor type (and its functionality), expandable memory, PCIe speed, type and number of slots, LAN connectivity and other features to meet your needs or requirements. Also keep in mind that some systems might be more expensive that include a keyboard, HDD with an OS installed that if you can use those components, then they have value and should be factored into your cost, benefit, return on investment.
And yes, I just added a few more TS140s that join other recent additions to the server storageIO lab resources…
Anybody want to guess what I will be playing with among other things during the up coming holiday season?
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
A year or so ago I did a piece tape summit resources. Despite being declared dead for decades, and will probably stay being declared dead for years to come, magnetic tape is in fact still alive being used by some organizations, granted its role is changing while the technology still evolves.
Here is the memo I received today from the PR folks of the Tape Storage Council (e.g. tape vendors marketing consortium) and for simplicity (mine), I’m posting it here for you to read in its entirety vs. possibly in pieces elsewhere. Note that this is basically a tape status and collection of marketing and press release talking points, however you can get an idea of the current messaging, who is using tape and technology updates.
True to the nature of magnetic tape as a data storage medium, this is not a low latency small post, rather a large high-capacity bulk post or perhaps all you need to know about tape for now, or until next year. Otoh, if you are a tape fan, you can certainly take the memo from the tape folks, as well as visit their site for more info.
From the tape storage council industry trade group:
Today the Tape Storage Council issued its annual memo to highlight the current trends, usages and technology innovations occurring within the tape storage industry. The Tape Storage Council includes representatives of BDT, Crossroads Systems, FUJIFILM, HP, IBM, Imation, Iron Mountain, Oracle, Overland Storage, Qualstar, Quantum, REB Storage Systems, Recall, Spectra Logic, Tandberg Data and XpresspaX. Data Growth and Technology Innovations Fuel Tape’s Future Abstract The Growth in Tape Enterprise tape has reached an unprecedented 10 TB native capacity with data rates reaching 360 MB/sec. Enterprise tape libraries can scale beyond one exabyte. Enterprise tape manufacturers IBM and Oracle StorageTek have signaled future cartridge capacities far beyond 10 TBs with no limitations in sight. Open systems users can now store more than 300 Blu-ray quality movies with the LTO-6 2.5 TB cartridge. In the future, an LTO-10 cartridge will hold over 14,400 Blu-ray movies. Nearly 250 million LTO tape cartridges have been shipped since the format’s inception. This equals over 100,000 PB of data protected and retained using LTO Technology. The innovative active archive solution combining tape with low-cost NAS storage and LTFS is gaining momentum for open systems users. Recent Announcements and Milestones
Significant Technology Innovations Fuel Tape’s Future
Reliability. Tape reliability levels have surpassed HDDs. Reliability levels for tape exceeds that of the most reliable disk drives by one to three orders of magnitude. The BER (Bit Error Rate – bits read per hard error) for enterprise tape is rated at 1×1019 and 1×1017 for LTO tape. This compares to 1×1016 for the most reliable enterprise Fibre Channel disk drive. Capacity and Data Rate. LTO-6 cartridges provide 2.5 TB capacity and more than double the compressed capacity of the preceding LTO-5 drive with a 14% data rate performance boost to 160 MB/sec. Enterprise tape has reached 8.5 TB native capacity and 252 MB/sec on the Oracle StorageTek T10000D and 10 TB native capacity and 360 MB/sec on the IBM TS1150. Tape cartridge capacities are expected to grow at unprecedented rates for the foreseeable future. Media Life. Manufacturers specifications indicate that enterprise and LTO tape media has a life span of 30 years or more while the average tape drive will be deployed 7 to 10 years before replacement. By comparison, the average disk drive is operational 3 to 5 years before replacement. LTFS Changes Rules for Tape Access. Compared to previous proprietary solutions, LTFS is an open tape format that stores files in application-independent, self-describing fashion, enabling the simple interchange of content across multiple platforms and workflows. LTFS is also being deployed in several innovative “Tape as NAS” active archive solutions that combine the cost benefits of tape with the ease of use and fast access times of NAS. The SNIA LTFS Technical Working Group has been formed to broaden cross–industry collaboration and continued technical development of the LTFS specification. TCOStudies. Tape’s widening cost advantage compared to other storage mediums makes it the most cost-effective technology for long-term data retention. The favorable economics (TCO, low energy consumption, reduced raised floor) and massive scalability have made tape the preferred medium for managing vast volumes of data. Several tape TCO studies are publicly available and the results consistently confirm a significant TCO advantage for tape compared to disk solutions. According to the Brad Johns Consulting Group, a TCO study for an LTFS-based ‘Tape as NAS’ solution totaled $1.1M compared with $7.0M for a disk-based unified storage solution. This equates to a savings of over $5.9M over a 10-year period, which is more than 84 percent less than the equivalent amount for a storage system built on a 4 TB hard disk drive unified storage system. From a slightly different perspective, this is a TCO savings of over $2,900/TB of data. Source: Johns, B. “A New Approach to Lowering the Cost of Storing File Archive Information,”. Another comprehensive TCO study by ESG (Enterprise Strategies Group) comparing an LTO-5 tape library system with a low-cost SATA disk system for backup using de-duplication (best case for disk) shows that disk deduplication has a 2-4x higher TCO than the tape system for backup over a 5 year period. The study revealed that disk has a TCO of 15x higher than tape for long-term data archiving. Select Case Studies Highlight Tape and Active Archive Solutions Dream Works Animation a global Computer Graphic (CG) animation studio has implemented a reliable, cost-effective and scalable active archive solution to safeguard a 2 PB portfolio of finished movies and graphics, supporting a long-term asset preservation strategy. The studio’s comprehensive, tiered and converged active archive architecture, which spans software, disk and tape, saves the company time, money and reduces risk. LA Kings of the NHL rely extensively on digital video assets for marketing activities with team partners and for its broadcast affiliation with Fox Sports. Today, the Kings save about 200 GB of video per game for an 82 game regular season and are on pace to generate about 32-35 TB of new data per season. The King’s chose to implement Fujifilm’s Dternity NAS active archive appliance, an open LTFS based architecture. The Kings wanted an open source archiving solution which could outlast its original hardware while maintaining data integrity. Today with Dternity and LTFS, the Kings don’t have to decide what data to keep because they are able to cost-effectively save everything they might need in the future. McDonald’s primary challenge was to create a digital video workflow that streamlines the management and distribution of their global video assets for their video production and post-production environment. McDonald’s implemented the Spectra T200 tape library with LTO-6 providing 250 TB of McDonald’s video production storage. Nightly, incremental backup jobs store their media assets into separate disk and LTO- 6 storage pools for easy backup, tracking and fast retrieval. This system design allows McDonald’s to effectively separate and manage their assets through the use of customized automation and data service policies. NCSA employs an Active Archive solution providing 100 percent of the nearline storage for the NCSA Blue Waters supercomputer, which is one of the world’s largest active file repositories stored on high capacity, highly reliable enterprise tape media. Using an active archive system along with enterprise tape and RAIT (Redundant Arrays of Inexpensive Tape) eliminates the need to duplicate tape data, which has led to dramatic cost savings. Queensland Brain Institute (QBI) is a leading center for neuroscience research. QBI’s research focuses on the cellular and molecular mechanisms that regulate brain function to help develop new treatments for neurological and mental disorders. QBI’s storage system has to scale extensively to store, protect, and access tens of terabytes of data daily to support cutting-edge research. QBI choose an Oracle solution consisting of Oracle’s StorageTek SL3000 modular tape libraries with StorageTek T10000 enterprise tape drives. The Oracle solution improved QBI’s ability to grow, attract world-leading scientists and meet stringent funding conditions. Looking Ahead to 2015 and Beyond Visit the Tape Storage Council at tapestorage.org |
Like it not tape is still alive being used along with the technology evolving with new enhancements as outlined above.
Good to see the tape folks doing some marketing to get their story told and heard for those who are still interested.
Does that mean I still use tape?
Nope, I stopped using tape for local backups and archives well over a decade ago using disk to disk and disk to cloud.
Does that mean I believe that tape is dead?
Nope, I still believe that for some organizations and some usage scenarios it makes good sense, however like with most data storage related technologies, it’s not a one size or type of technology fits everything scenario value proposition.
On a related note for cloud and object storage, visit www.objectstoragecenter.com
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 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 first post of a two part series, read the second 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 question to ask yourself is not if flash Solid State Device (SSD) technologies are in your future, Instead the questions are when, where, using what, how to configure and related themes. SSD including traditional DRAM and NAND flash-based technologies are like real estate where location matters; however, there are different types of properties to meet various needs. This means leveraging different types of NAND flash SSD technologies in different locations in a complementary and cooperative aka hybrid way. For example nand flash SSD as part of an enterprise tiered storage strategy can be implemented server-side using PCIe cards, SAS and SATA drives as targets or as cache along with software, as well as leveraging SSD devices in storage systems or appliances.
Seagate 1200 Enterprise SAS 12Gbs SSD Image via Seagate.com
Another place where nand flash can be found and compliments SSD devices are so-called Solid State Hybrid Drives (SSHD) or Hybrid Hard Disk Drives (HHDD) including a new generation that accelerate writes as well as reads such as those Seagate refers to as with Enterprise TurboBoost. The Enterprise TurboBoost drives (view the companion StorageIO Lab review TurboBoost white paper here) were previously known as the Solid State Hybrid Drives (SSHD) or Hybrid Hard Disk Drives (HHDD). Read more about TurboBoost here and here.
Keep in mind that the best server or storage I/O is that one that you do not have to do, with the second best being the one with the least overhead resolved as close to the processor (compute) as possible or practical. The following figure shows that the best place to resolve server and storage I/O is as close to the compute processor as possible however only a finite amount of storage memory located there. This is where the server memory and storage I/O hierarchy comes into play which is also often thought of in the context of tiered storage balancing performance and availability with cost and architectural limits.
Also shown is locality of reference which refers to how close data is to where it is being used and includes cache effectiveness or buffering. Hence a small amount of cache of flash and DRAM in the right location can have a large benefit. Now if you can afford it, install as much DRAM along with flash storage as possible, however if you are like most organizations with finite budgets yet server and storage I/O challenges, then deploy a tiered flash storage strategy.
Server memory storage I/O hierarchy, locality of reference
Back to the Seagate 1200 12Gbs Enterprise SAS SSD which is covered in this StorageIO Industry Trends Perspective thought leadership white paper. The focus of the white paper is to look at how the Seagate 1200 Enterprise class SSD’s and 12Gbps SAS address current and next generation tiered storage for virtual, cloud, traditional Little and Big Data infrastructure environments.
This includes providing proof points running various workloads including Database TPC-B, TPC-E and Microsoft Exchange in the StorageIO Labs along with cache software comparing SSD, SSHD and different HDD’s including 12Gbs SAS 6TB near-line high-capacity drives.
The proof points in this white paper are from an applications focus perspective representing more of an end-to-end real-world situation. While they are not included in this white paper, StorageIO has run traditional storage building-block focus workloads, which can be found at StorageIOblog (Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?). These include tools such as Iometer, iorate, vdbench among others for various IO sizes, mixed, random, sequential, reads, writes along with “hot-band" across different number of threads (concurrent users). “Hot-Band” is part of the SNIA Emerald energy effectiveness metrics for looking at sustained storage performance using tools such as vdbench. Read more about other various server and storage I/O benchmarking tools and techniques here.
For the following series of proof-points (TPC-B, TPC-E and Exchange) a system under test (SUT) consisted of a physical server (described with the proof-points) configured with VMware ESXi along with guests virtual machines (VMs) configured to do the storage I/O workload. Other servers were used in the case of TPC workloads as application transactional requester to drive the SQL Server database and resulting server storage I/O workload. VMware was used in the proof-points to reflect a common industry trend of using virtual server infrastructures (VSI) supporting applications including database, email among others. For the proof-point scenarios, the SUT along with storage system device under test were dedicated to that scenario (e.g. no other workload running) unless otherwise noted.
Server Storage I/O configuration for proof-points
For this proof-point, Microsoft Jet Stress Exchange performance workloads were placed (e.g. Exchange Database – EDB file) on each of the different devices under test with various metrics shown including activity rates and response time for reads as well as writes. For the Exchange testing, the EDB was placed on the device being tested while its log files were placed on a separate Seagate 400GB Enterprise 12Gbps SAS SSD.
Test configuration: Seagate 400GB 12000 2.5” SSD (ST400FM0073) 12Gbps SAS, 600GB 2.5” Enterprise 15K with TurboBoost™ (ST600MX) 6 Gbps SAS, 600GB 2.5” Enterprise Enhanced 15K V4 (15K RPM) HDD (ST600MP) with 6 Gbps SAS, Seagate Enterprise Capacity Nearline (ST6000NM0014) 6TB 3.5” 7.2K RPM HDD 12 Gbps SAS and 3TB 7.2K SATA HDD. Email server hosted as guest on VMware vSphere/ESXi V5.5, Microsoft SBS2011 Service Pack 1 64 bit. Guest VM (VMware vSphere 5.5) was on a SSD based dat, had a physical machine (host), with 14 GB DRAM, quad CPU (4 x 3.192GHz) Intel E3-1225 v300, with LSI 9300 series 12Gbps SAS adapters in a PCIe Gen 3 slot with Jet Stress 2010. All devices being tested were Raw Device Mapped (RDM) where EDB resided. VM on a SSD based separate data store than devices being tested. Log file IOPs were handled via a separate SSD device also persistent (no delayed writes). EDB was 300GB and workload ran for 8 hours.
Microsoft Exchange proof-points comparing various storage devices
SSD’s are a good fit for both transaction database activity with reads and write as well as query-based decision support systems (DSS), data warehouse and big data analytics. The following are proof points of SSD capabilities for database activity. In addition to supporting database table files and objects, along with transaction journal logs, other uses include for meta-data, import/export or other high-IO and write intensive scenarios. Two database workload profiles were tested including batch update (write-intensive) and transactional. Activity involved running Transaction Performance Council (TPC) workloads TPC-B (batch update) and TPC-E (transaction/OLTP simulate financial trading system) against Microsoft SQL Server 2012 databases. Each test simulation had the SQL Server database (MDF) on a different device with transaction log file (LDF) on a separate SSD. TPC-B for a single device results shown below.
TPC-B (write intensive) results below show how TPS work being done (blue) increases from left to right (more is better) for various numbers of simulated users. Also shown on the same line for each amount of TPS work being done is the average latency in seconds (right to left) where lower is better. Results are shown from top to bottom for each group of users (100, 50, 20 and 1) for the different drives being tested (top to bottom). Note how the SSD device does more work at a lower response time vs. traditional HDD’s
Test configuration: Seagate 400GB 12000 2.5” SSD (ST400FM0073) 12Gbps SAS, 600GB 2.5” Enterprise 15K with TurboBoost™ (ST600MX) 6 Gbps SAS, 600GB 2.5” Enterprise Enhanced 15K V4 (15K RPM) HDD (ST600MP) with 6 Gbps SAS, Seagate Enterprise Capacity Nearline (ST6000NM0014) 6TB 3.5” 7.2K RPM HDD 12 Gbps SAS and 3TB Seagate 7.2K SATA HDD Workload generator and virtual clients Windows 7 Ultimate 64 bit. Microsoft SQL Server 2012 database was on Windows 7 guest. Guest VM (VMware vSphere 5.5) had a dedicated 14 GB DRAM, quad CPU (4 x 3.192GHz) Intel E3-1225 v300, with LSI 9300 series 12Gbps SAS adapters in a PCIe Gen 3 slot along with TPC-B (www.tpc.org) workloads.
VM with guest OS along with SQL tempdb and masterdb resided on separate SSD based data store from devices being tested (e.g., where MDF (main database tables) and LDF (log file) resided). All devices being tested were Raw Device Mapped (RDM) independent persistent with database log file on a separate SSD device also persistent (no delayed writes) using VMware PVSCSI driver. MDF and LDF file sizes were 142GB and 26GB with scale factor of 10000, with each step running for one hour (10-minute preamble). Note that these proof-points DO NOT use VMware or any other third-party cache software or I/O acceleration tool technologies as those are covered later in a separate proof-point.
TPC-B SQL Server database proof-points comparing various storage devices
The following shows results from TPC-E test (OLTP/transactional workload) simulating a financial trading system. TPC-E is an industry standard workload that performs a mix of reads and writes database queries. Proof-points were performed with various numbers of users from 10, 20, 50 and 100 to determine (TPS) Transaction per Second (aka I/O rate) and response time in seconds. The TPC-E transactional results are shown for each device being tested across different user workloads. The results show how TPC-E TPS work (blue) increases from left to right (more is better) for larger numbers of users along with corresponding latency (green) that goes from right to left (less is better). The Seagate Enterprise 1200 SSD is shown on the top in the figure below with a red box around its results. Note how the SSD as a lower latency while doing more work compared to the other traditional HDD’s
Test configuration: Seagate 400GB 12000 2.5” SSD (ST400FM0073) 12Gbps SAS, 600GB 2.5” Enterprise 15K with TurboBoost™ (ST600MX) 6 Gbps SAS, 600GB 2.5” Enterprise Enhanced 15K V4 (15K RPM) HDD (ST600MP) with 6 Gbps SAS, Seagate Enterprise Capacity Nearline (ST6000NM0014) 6TB 3.5” 7.2K RPM HDD 12 Gbps SAS and 3TB Seagate 7.2K SATA HDD Workload generator and virtual clients Windows 7 Ultimate 64 bit. Microsoft SQL Server 2012 database was on Windows 7 guest. Guest VM (VMware vSphere 5.5) had a dedicated 14 GB DRAM, quad CPU (4 x 3.192GHz) Intel E3-1225 v300, with LSI 9300 series 12Gbps SAS adapters in a PCIe Gen 3 slot along with TPC-B (www.tpc.org) workloads.
VM with guest OS along with SQL tempdb and masterdb resided on separate SSD based data store from devices being tested (e.g., where MDF (main database tables) and LDF (log file) resided). All devices being tested were Raw Device Mapped (RDM) independent persistent with database log file on a separate SSD device also persistent (no delayed writes) using VMware PVSCSI driver. MDF and LDF file sizes were 142GB and 26GB with scale factor of 10000, with each step running for one hour (10-minute preamble). Note that these proof-points DO NOT use VMware or any other third-party cache software or I/O acceleration tool technologies as those are covered later in a separate proof-point.
TPC-E (Financial trading) SQL Server database proof-points comparing various storage devices
Continue reading part-two of this two-part series here including the virtual server storage I/O blender effect and solution.
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
I often get asked, or, told that computer data storage is complex with so many options to choose from, apples to oranges comparison among other things.
On a recent trip to Europe while being interviewed by a Dutch journalist in Nijkerk Holland at a Brouwer Storage Consultancy event I was presenting at, the question came up again about storage complexity. Btw, you can read the article on data storage industry trends here (its in dutch).
I hesitated and thought for a moment and responded that in some ways it’s not as complex as some make it seem, although there is more to data storage than just cost per capacity. As I usually do when asked or told how complex data storage is my response is a mixed yes it (storage, data and information infrastructure) are complex, however lets put it in perspective which is storage any more complex than other things?
Our conversation then evolved with an example that I find shopping for an automobile complex unless I know exactly what I’m looking for. After all there are cars trucks SUV’s used new buy lease different manufacturers makes and models speeds cargo capacity management tools and interfaces not to mention metrics and fuel.
This is where I usually mention how IMHO buying a new car or vehicle is with all the different options, that is unless you know what you want, or know your selection criteria and options. Same with selecting a new laptop computer, tablet or smart phone, not to mention a long list of other things that to the outsiders can also seem complex, intimidating or overwhelming. However lets take a step back to look at storage then return to compare some other things that may be confusing to those who are not focused on them.
Similar to other technologies, there are different types of data storage to meet various needs from performance to space capacity as well as support various forms of scaling.
Server and storage I/O fundamentals
Various types of storage devices including HDD’s, SSHD/HHDD’s and SSD’s
Various types of storage devices
Storage options, block, file, object, ssd, hdd, primary, secondary, local and cloud
During my return trip to the US from the Dutch event, I had a layover at London Heathrow (LHR) and walking the concourse it occurred to me that while there are complexities involved with different technologies including storage, data and information infrastructures, there were other complexities.
Same thing with shoes so any differ options not to mention cell phones or laptops and tablets, PCIe, or how about tv’s?
I wan to go on a trip do I book based on lowest cost for air fare then hotel and car rental, or do I purchase a package? For the air fare is it the cheapest yet that takes all day to get from point a to b via plane changes at points c d and e not to mention paying extra fees vs paying a higher price for a direct flight with extra amenities?
Getting hungry so what to do for dinner, what type of cuisine or food?
How about a new handbag or perhaps shoes?
How about a new backpack, brief case or luggage?
What to drink for a beverage, so many options unless you know what you want.
Complexity of choosing what cell phone, PDA or other electronics
How about what to read including print vs. online accessible content?
Once I got home from my European trip I had some mechanical things to tend to including replacing some spark plugs.
How about automobile parts from tires, to windshield wiper blades to spark plugs?
Sure if you know the exact part number and assuming that part number has not changed, then you can start shopping for the part. However recently I had a part number based on a vehicle serial number (e.g. make, model, year, etc) only to receive the wrong part. Sure the part numbers were correct, however along the line somewhere the manufacture made a change and not all downstream vendors knew about the part change, granted I eventually received the correct part.
Ok, hopefully you got the point from the above examples among many others in that we live in world full of options and those options can bring complexity.
What type of network or server? How about operating system, browser, database, programming or development language as there are different needs and options?
Sure there are many storage options as not everything is the same.
Likewise while there can be simple answer with a trend of what to use before the question is understood (perhaps due to a preference) or explained, the best or applicable answer may be it depends. However saying it depends may seem complex to those who just want a simple answer.
So is storage more complex than other technologies, tools, products or services?
What say you?
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
