Server StorageIO Data Infrastructure Insights and Analysis
|
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Recently I was invited by VMware vCloud Air to do a free hands-on test drive of their actual production environment. Some of you may already being using VMware vSphere, vRealize and other software defined data center (SDDC) aka Virtual Server Infrastructure (VSI) or Virtual Desktop Infrastructure (VDI) tools among others. Likewise some of you may already be using one of the many cloud compute or Infrastructure as a Service (IaaS) such as Amazon Web Services (AWS) Elastic Cloud Compute (EC2), Centurylink, Google Cloud, IBM Softlayer, Microsoft Azure, Rackspace or Virtustream (being bought by EMC) among many others.
VMware vCloud Air provides a platform similar to those just mentioned among others for your applications and their underlying resource needs (compute, memory, storage, networking) to be fulfilled. In addition, it should not be a surprise that VMware vCloud Air shares many common themes, philosophies and user experiences with the traditional on-premises based VMware solutions you may be familiar with.
You can give VMware vCloud Air a trial for free while the offer lasts by clicking here (service details here). Basically if you click on the link and register a new account for using VMware vCloud Air they will give you up to $500 USD in service credits to use in the real production environment while the offer lasts which iirc is through end of June 2015.
Click on above image to view video part I
Click on above image to view video part II
What this means is that you can go and setup some servers with as many CPUs or cores, memory, Hard Disk Drive (HDD) or flash Solid State Devices (SSD) storage, external IP networks using various operating systems (Centos, Ubuntu, Windows 2008, 20012, 20012 R2) for free, or until you use up the service credits.
Speaking of which, let me give you a bit of a tip or hint, even though you can get free time, if you provision a fast server with lots of fast SSD storage and leave it sit idle over night or over a weekend, you will chew up your free credits rather fast. So the tip which should be common sense is if you are going to do some proof of concepts and then leave things alone for a while, power the virtual cloud servers off to stretch your credits further. On the other hand, if you have something that you want to run on a fast server with fast storage over a weekend or longer, give that a try, just pay attention to your resource usage and possible charges should you exhaust your service credits.
For my test drive, I created a new account by using the above link to get the service credits. Note that you can use your regular VMware account with vCloud Air, however you wont get the free service credits. So while it is a few minutes of extra work, the benefit was worth it vs. simply using my existing VMware account and racking up more cloud services charges on my credit card. As part of this Server StorageIOlab test drive, I created two companion videos part I here and part II here that you can view to follow along and get a better idea of how vCloud works.
Phase one, create the virtual data center, database server, client servers and first setup
My goal was to set up a simple Virtual Data Center (VDC) that would consist of five Windows 2012 R2 servers, one would be a MySQL database server with the other four being client application servers. You can download MySQL from here at Oracle as well as via other sources. For applications to simplify things I used Hammerdb as well as Benchmark Factory that is part of the Quest Toad tool set for database admins. You can download a free trial copy of Benchmark Factory here, and HammerDB here. Another tool that I used for monitoring the servers is Spotlight on Windows (SoW) which is also free here. Speaking of tools, here is a link to various server and storage I/O performance as well as monitoring tools.
Links to tools that I used for this test-drive included:
Phase one steps and activity summary
Recap of what was done in phase one, watch the associated video here.
After the initial setup (e.g. part I video here), the next step was to add some more virtual machines and take a closer look at the environment. Note that most of the work in setting up this environment was Windows, MySQL, Hammerdb, Benchmark Factory, Spotlight on Windows along with other common tools so their installation is not a focus in these videos or this post, perhaps a future post will dig into those in more depth.
What was done during phase II (view the video here)
There is much more to VMware vCloud Air and on their main site there are many useful links including overviews, how-too tutorials, product and service offering details and much more here. Besides paying attention to your resource usage and avoid being surprised by service charges, two other tips I can pass along that are also mentioned in the videos (here and here) is to pay attention what region you setup your virtual data centers in, second is have your network thought out ahead of time to streamline setting up the NAT and firewall as well as gateway configurations.
Learn more about data protection and related topics, themes, trends, tools and technologies via the following links:
Overall I like the VMware vCloud Air service which if you are VMware centric focused will be a familiar cloud option including integration with vCloud Director and other tools you may already have in your environment. Even if you are not familiar with VMware vSphere and associated vRealize tools, the vCloud service is intuitive enough that you can be productive fairly quickly. On one hand vCloud Air does not have the extensive menu of service offerings to choose from such as with AWS, Google, Azure or others, however that also means a simpler menu of options to choose from and simplify things.
I had wanted to spend some time actually using vCloud and the offer to use some free service credits in the production environment made it worth making the time to actually setup some workloads and do some testing. Even if you are not a VMware focused environment, I would recommend giving VMware vCloud Air a test drive to see what it can do for you, as opposed to what you can do for it…
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
It’s springtime in Kentucky and recently I had the opportunity to have a conversation with Kendrick Coleman to talk about S3motion, Buckets, Containers, Objects, AWS S3, Cloud and Object Storage, node.js, EMCcode and open source among other related topics which are available in a podcast here, or video here and available at StorageIO.tv.
In this Server StorageIO industry trends perspective podcast episode, @EMCcode (Part of EMC) developer advocate Kendrick Coleman (@KendrickColeman) joins me for a conversation. Our conversation spans spring-time in Kentucky (where Kendrick lives) which means Bourbon and horse racing as well as his blog (www.kendrickcoleman.com).
Btw, in the podcast I refer to Captain Obvious and Kendrick’s beard, for those not familiar with who or what @Captainobvious is that is made reference to, click here to learn more.
@Kendrickcoleman & @Captainobvious
Of course we also talk some tech including what is EMCcode, EMC Federation, Cloud Foundry, clouds, object storage, buckets, containers, objects, node.js, Docker, Openstack, AWS S3, micro services, and the S3motion tool that Kendrick developed.
Kendrick explains the motivation behind S3motion along with trends in and around objects (including GET, PUT vs. traditional Read, Write) as well as programming among related topic themes and how context matters.
I have used S3motion for moving buckets, containers and objects around including between AWS S3, Google Cloud Storage (GCS) and Microsoft Azure as well as to/from local. S3motion is a good tool to have in your server storage I/O tool box for working with cloud and object storage along with others such as Cloudberry, S3fs, Cyberduck, S3 browser among many others.
You can get S3motion free from git hub here.
Here are some links to learn more about AWS S3, Cloud and Object Storage along with related topics
Context matters when it comes to many things particular about objects as they can mean different things. Tools such as S3motion make it easy for moving your buckets or containers along with objects from one cloud storage system, solution or service to another. Also check out EMCcode to see what they are doing on different fronts from supporting new and greenfield development with Cloud Foundry and PaaS to Openstack to bridging current environments to the next generation of platforms. Also check out Kendricks blog site as he has a lot of good technical content as well as some other fun stuff to learn about. Look forward to having Kendrick on as a guest again soon to continue our conversations. In the meantime, check out S3motion to see how it can fit into your server storage I/O tool box.
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
|
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 series of posts and links to resources on server storage I/O performance and benchmarking (view more and follow-up posts here).
The best I/O is the I/O that you do not have to do, the second best is the one with the least impact as well as low overhead.
Drew Robb (@robbdrew) has a Data Storage Benchmarking Guide article over at Enterprise Storage Forum that provides a good framework and summary quick guide to server storage I/O benchmarking.
Via Drew: Data storage benchmarking can be quite esoteric in that vast complexity awaits anyone attempting to get to the heart of a particular benchmark. Case in point: The Storage Networking Industry Association (SNIA) has developed the Emerald benchmark to measure power consumption. This invaluable benchmark has a vast amount of supporting literature. That so much could be written about one benchmark test tells you just how technical a subject this is. And in SNIA’s defense, it is creating a Quick Reference Guide for Emerald (coming soon). But rather than getting into the nitty-gritty nuances of the tests, the purpose of this article is to provide a high-level overview of a few basic storage benchmarks, what value they might have and where you can find out more. Read more here including some of my comments, tips and recommendations. |
Drew’s provides a good summary and overview in his article which is a great opener for this first post in a series on server storage I/O benchmarking and related resources.
You can think of this series (along with Drew’s article) as server storage I/O benchmarking fundamentals (e.g. 101) for smarties (e.g. non-dummies ;) ).
Note that even if you are not a server, storage or I/O expert, you can still be considered a smarty vs. a dummy if you found the need or interest to read as well as learn more about benchmarking, metrics that matter, tools, technology and related topics.
There are different reasons for benchmarking, such as, you might be asked or want to know how many IOPs per disk, Solid State Device (SSD), device or storage system such as for a 15K RPM (revolutions per minute) 146GB SAS Hard Disk Drive (HDD). Sure you can go to a manufactures website and look at the speeds and feeds (technical performance numbers) however are those metrics applicable to your environments applications or workload?
You might get higher IOPs with smaller IO size on sequential reads vs. random writes which will also depend on what the HDD is attached to. For example are you going to attach the HDD to a storage system or appliance with RAID and caching? Are you going to attach the HDD to a PCIe RAID card or will it be part of a server or storage system. Or are you simply going to put the HDD into a server or workstation and use as a drive without any RAID or performance acceleration.
What this all means is understanding what it is that you want to benchmark test to learn what the system, solution, service or specific device can do under different workload conditions.
Some benchmark and related topics include
Example of a step test results with various workers and workload
The following are related links to read more about server (cloud, virtual and physical) storage I/O benchmarking tools, technologies and techniques.
Drew Robb’s benchmarking quick reference guide
Server storage I/O benchmarking tools, technologies and techniques resource page
Server and Storage I/O Benchmarking 101 for Smarties.
Microsoft Diskspd download and Microsoft Diskspd overview (via Technet)
I/O, I/O how well do you know about good or bad server and storage I/Os?
Server and Storage I/O Benchmark Tools: Microsoft Diskspd (Part I and Part II)
We have just scratched the surface when it comes to benchmarking cloud, virtual and physical server storage I/O and networking hardware, software along with associated tools, techniques and technologies. However hopefully this and the links for more reading mentioned above give a basis for connecting the dots of what you already know or enable learning more about workloads, synthetic generation and real-world workloads, benchmarks and associated topics. Needless to say there are many more things that we will cover in future posts (e.g. keep an eye on and bookmark the server storage I/O benchmark tools and resources page 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 part-one of a two-part post pertaining Microsoft Diskspd.that is also part of a broader series focused on server storage I/O benchmarking, performance, capacity planning, tools and related technologies. You can view part-two of this post here, along with companion links here.
Many people use Iometer for creating synthetic (artificial) workloads to support benchmarking for testing, validation and other activities. While Iometer with its GUI is relatively easy to use and available across many operating system (OS) environments, the tool also has its limits. One of the bigger limits for Iometer is that it has become dated with little to no new development for a long time, while other tools including some new ones continue to evolve in functionality, along with extensibility. Some of these tools have optional GUI for easy of use or configuration, while others simple have extensive scripting and command parameter capabilities. Many tools are supported across different OS including physical, virtual and cloud, while others such as Microsoft Diskspd are OS specific.
Instead of focusing on Iometer and other tools as well as benchmarking techniques (we cover those elsewhere), lets focus on Microsoft Diskspd.
Microsoft Diskspd is a synthetic workload generation (e.g. benchmark) tool that runs on various Windows systems as an alternative to Iometer, vdbench, iozone, iorate, fio, sqlio among other tools. Diskspd is a command line tool which means it can easily be scripted to do reads and writes of various I/O size including random as well as sequential activity. Server and storage I/O can be buffered file system as well non-buffered across different types of storage and interfaces. Various performance and CPU usage information is provided to gauge the impact on a system when doing a given number of IOP’s, amount of bandwidth along with response time latency.
Microsoft Diskspd creates synthetic benchmark workload activity with ability to define various options to simulate different application characteristics. This includes specifying read and writes, random, sequential, IO size along with number of threads to simulate concurrent activity. Diskspd can be used for testing or validating server and storage I/O systems along with associated software, tools and components. In addition to being able to specify different workloads, Diskspd can also be told which processors to use (e.g. CPU affinity), buffering or non-buffered IO among other things.
Physical and virtual storage including hard disk drive (HDD), solid state devices (SSD), solid state hybrid drives (SSHD) in various systems or solutions. Storage can be physical as well as partitions or file systems. As with any workload tool when doing writes, exercise caution to prevent accidental deletion or destruction of your data.
Diskspd provides output in text as well as XML formats. See an example of Diskspd output further down in this post.
You can download your free copy of Diskspd from the Microsoft site here.
The download and installation are quick and easy, just remember to select the proper version for your Windows system and type of processor.
Another tip is to remember to set path environment variables point to where you put the Diskspd image.
Also stating what should be obvious, don’t forget that if you are going to be doing any benchmark or workload generation activity on a system where the potential for a data to be over-written or deleted, make sure you have a good backup and tested restore before you begin, if something goes wrong.
If you are not familiar with server storage I/O performance benchmarking or using various workload generation tools (e.g. benchmark tools), Drew Robb (@robbdrew) has a Data Storage Benchmarking Guide article over at Enterprise Storage Forum that provides a good framework and summary quick guide to server storage I/O benchmarking.
Via Drew: Data storage benchmarking can be quite esoteric in that vast complexity awaits anyone attempting to get to the heart of a particular benchmark. Case in point: The Storage Networking Industry Association (SNIA) has developed the Emerald benchmark to measure power consumption. This invaluable benchmark has a vast amount of supporting literature. That so much could be written about one benchmark test tells you just how technical a subject this is. And in SNIA’s defense, it is creating a Quick Reference Guide for Emerald (coming soon). But rather than getting into the nitty-gritty nuances of the tests, the purpose of this article is to provide a high-level overview of a few basic storage benchmarks, what value they might have and where you can find out more. Read more here including some of my comments, tips and recommendations. |
In addition to Drew’s benchmarking quick reference guide, along with the server storage I/O benchmarking tools, technologies and techniques resource page (Server and Storage I/O Benchmarking 101 for Smarties.
Tip: When you run Microsoft Diskspd it will create a file or data set on the device or volume being tested that it will do its I/O to, make sure that you have enough disk space for what will be tested (e.g. if you are going to test 1TB you need to have more than 1TB of disk space free for use). Another tip is to speed up the initializing (e.g. when Diskspd creates the file that I/Os will be done to) run as administrator.
Tip: In case you forgot, a couple of other useful Microsoft tools (besides Perfmon) for working with and displaying server storage I/O devices including disks (HDD and SSDs) are the commands "wmic diskdrive list [brief]" and "diskpart". With diskpart exercise caution as it can get you in trouble just as fast as it can get you out of trouble.
You can view the Diskspd commands after installing the tool and from a Windows command prompt type:
C:\Users\Username> Diskspd
The above command will display Diskspd help and information about the commands as follows.
Usage: diskspd [options] target1 [ target2 [ target3 …] ]
version 2.0.12 (2014/09/17)Available targets:
file_path
#: Available options:
| -? | display usage information | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| -a#[,#[…]] | advanced CPU affinity – affinitize threads to CPUs provided after -a in a round-robin manner within current KGroup (CPU count starts with 0); the same CPU can be listed more than once and the number of CPUs can be different than the number of files or threads (cannot be used with -n) | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| -ag | group affinity – affinitize threads in a round-robin manner across KGroups | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
-b| block size in bytes/KB/MB/GB [default=64K] | -B | base file offset in bytes/KB/MB/GB/blocks [default=0] (offset from the beginning of the file) | -c | create files of the given size. Size can be stated in bytes/KB/MB/GB/blocks | -C | cool down time – duration of the test after measurements finished [default=0s]. | -D | Print IOPS standard deviations. The deviations are calculated for samples of duration | -d | duration (in seconds) to run test [default=10s] | -f | file size – this parameter can be used to use only the part of the file/disk/partition for example to test only the first sectors of disk | -fr | open file with the FILE_FLAG_RANDOM_ACCESS hint | -fs | open file with the FILE_FLAG_SEQUENTIAL_SCAN hint | -F | total number of threads (cannot be used with -t) | -g | throughput per thread is throttled to given bytes per millisecond note that this can not be specified when using completion routines | -h | disable both software and hardware caching | -i | number of IOs (burst size) before thinking. must be specified with -j | -j | time to think in ms before issuing a burst of IOs (burst size). must be specified with -i | -I | Set IO priority to | -l | Use large pages for IO buffers | -L | measure latency statistics | -n | disable affinity (cannot be used with -a) | -o | number of overlapped I/O requests per file per thread (1=synchronous I/O, unless more than 1 thread is specified with -F) [default=2] | -p | start async (overlapped) I/O operations with the same offset (makes sense only with -o2 or grater) | -P | enable printing a progress dot after each | -r | random I/O aligned to | -R | output format. Default is text. | -s | stride size (offset between starting positions of subsequent I/O operations) | -S | disable OS caching | -t | number of threads per file (cannot be used with -F) | -T | stride between I/O operations performed on the same file by different threads [default=0] (starting offset = base file offset + (thread number * | -v | verbose mode | -w | percentage of write requests (-w and -w0 are equivalent). absence of this switch indicates 100% reads IMPORTANT: Your data will be destroyed without a warning | -W | warm up time – duration of the test before measurements start [default=5s]. | -x | use completion routines instead of I/O Completion Ports | -X | use an XML file for configuring the workload. Cannot be used with other parameters. | -z | set random seed [default=0 if parameter not provided, GetTickCount() if value not provided] | |
| | Write buffers command options. By default, the write buffers are filled with a repeating pattern (0, 1, 2, …, 255, 0, 1, …) | ||
| -Z | zero buffers used for write tests | ||
-Z| use a global | -Z | use a global | |
| Synchronization command options | |||||||||
| -ys | signals event| -yf | signals event | -yr | waits on event | -yp | allows to stop the run when event | -ye | sets event | |
| Event Tracing command options | |
| -ep | use paged memory for NT Kernel Logger (by default it uses non-paged memory) |
| -eq | use perf timer |
| -es | use system timer (default) |
| -ec | use cycle count |
| -ePROCESS | process start & end |
| -eTHREAD | thread start & end |
| -eIMAGE_LOAD | image load |
| -eDISK_IO | physical disk IO |
| -eMEMORY_PAGE_FAULTS | all page faults |
| -eMEMORY_HARD_FAULTS | hard faults only |
| -eNETWORK | TCP/IP, UDP/IP send & receive |
| -eREGISTRY | registry calls |
|
The following are related links to read more about servver (cloud, virtual and physical) storage I/O benchmarking tools, technologies and techniques.
resource page
Server and Storage I/O Benchmarking 101 for Smarties.
Microsoft Diskspd download and Microsoft Diskspd overview (via Technet)
I/O, I/O how well do you know about good or bad server and storage I/Os?
Server and Storage I/O Benchmark Tools: Microsoft Diskspd (Part I and Part II)
This wraps up part-one of this two-part post taking a look at Microsoft Diskspd benchmark and workload generation tool. In part-two (here) of this post series we take a closer look including a test drive using Microsoft Diskspd.
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
This is part-two of a two-part post pertaining Microsoft Diskspd.that is also part of a broader series focused on server storage I/O benchmarking, performance, capacity planning, tools and related technologies. You can view part-one of this post here, along with companion links here.
Talking about tools and technologies is one thing, installing as well as trying them is the next step for gaining experience so how about some quick hands-on time with Microsoft Diskspd (download your copy here).
The following commands all specify an I/O size of 8Kbytes doing I/O to a 45GByte file called diskspd.dat located on the F: drive. Note that a 45GByte file is on the small size for general performance testing, however it was used for simplicity in this example. Ideally a larger target storage area (file, partition, device) would be used, otoh, if your application uses a small storage device or volume, then tune accordingly.
In this test, the F: drive is an iSCSI RAID protected volume, however you could use other storage interfaces supported by Windows including other block DAS or SAN (e.g. SATA, SAS, USB, iSCSI, FC, FCoE, etc) as well as NAS. Also common to the following commands is using 16 threads and 32 outstanding I/Os to simulate concurrent activity of many users, or application processing threads.
Another common parameter used in the following was -r for random, 7200 seconds (e.g. two hour) test duration time, display latency ( -L ) disable hardware and software cache ( -h), forcing cpu affinity (-a0,1,2,3). Since the test ran on a server with four cores I wanted to see if I could use those for helping to keep the threads and storage busy. What varies in the commands below is the percentage of reads vs. writes, as well as the results output file. Some of the workload below also had the -S option specified to disable OS I/O buffering (to view how buffering helps when enabled or disabled). Depending on the goal, or type of test, validation, or workload being run, I would choose to set some of these parameters differently.
diskspd -c45g -b8K -t16 -o32 -r -d7200 -h -w0 -L -a0,1,2,3 F:\diskspd.dat >> SIOWS2012R203_Eiscsi_145_noh_write000.txt
diskspd -c45g -b8K -t16 -o32 -r -d7200 -h -w50 -L -a0,1,2,3 F:\diskspd.dat >> SIOWS2012R203_Eiscsi_145_noh_write050.txt
diskspd -c45g -b8K -t16 -o32 -r -d7200 -h -w100 -L -a0,1,2,3 F:\diskspd.dat >> SIOWS2012R203_Eiscsi_145_noh_write100.txt
diskspd -c45g -b8K -t16 -o32 -r -d7200 -h -S -w0 -L -a0,1,2,3 F:\diskspd.dat >> SIOWS2012R203_Eiscsi_145_noSh_test_write000.txt
diskspd -c45g -b8K -t16 -o32 -r -d7200 -h -S -w50 -L -a0,1,2,3 F:\diskspd.dat >> SIOWS2012R203_Eiscsi_145_noSh_write050.txt
diskspd -c45g -b8K -t16 -o32 -r -d7200 -h -S -w100 -L -a0,1,2,3 F:\diskspd.dat >> SIOWS2012R203_Eiscsi_145_noSh_write100.txt
The following is the output from the above workload command.
Note that as with any benchmark, workload test or simulation your results will vary. In the above the server, storage and I/O system were not tuned as the focus was on working with the tool, determining its capabilities. Thus do not focus on the performance results per say, rather what you can do with Diskspd as a tool to try different things. Btw, fwiw, in the above example in addition to using an iSCSI target, the Windows 2012 R2 server was a guest on a VMware ESXi 5.5 system.
The following are related links to read more about server (cloud, virtual and physical) storage I/O benchmarking tools, technologies and techniques.
Drew Robb’s benchmarking quick reference guide
Server storage I/O benchmarking tools, technologies and techniques resource page
Server and Storage I/O Benchmarking 101 for Smarties.
Microsoft Diskspd download and Microsoft Diskspd overview (via Technet)
I/O, I/O how well do you know about good or bad server and storage I/Os?
Server and Storage I/O Benchmark Tools: Microsoft Diskspd (Part I and Part II)
Reporting including CPU usage (you can’t do server and storage I/O without CPU) along with IOP’s (activity), bandwidth (throughout or amount of data being moved), per thread and total results along with optional reporting. While a GUI would be nice particular for beginners, I’m used to setting up scripts for different workloads so having an extensive options for setting up different workloads is welcome. Being associated with a specific OS (e.g. Windows) the CPU affinity and buffer management controls will be handy for some projects.
Diskspd has the flexibility to use different storage interfaces and types of storage including files or partitions should be taken for granted, however with some tools don’t take things for granted. I like the flexibility to easily specify various IO sizes including large 1MByte, 10MByte, 20MByte, 100MByte and 500MByte to simulate application workloads that do large sequential (or random) activity. I tried some IO sizes (e.g. specified by -b parameter larger than 500MB however, I received various errors including "Could not allocate a buffer bytes for target" which means that Diskspd can do IO sizes smaller than that. While not able to do IO sizes larger than 500MB, this is actually impressive. Several other tools I have used or with have IO size limits down around 10MByte which makes it difficult for creating workloads that do large IOP’s (note this is the IOP size, not the number of IOP’s).
Oh, something else that should be obvious however will state it, Diskspd is free unlike some industry de-facto standard tools or workload generators that need a fee to get and use.
For some users a GUI or configuration wizard would make the tool easier to get started with, on the other hand (oth), I tend to use the command capabilities of tools. Would also be nice to specify ranges as part of a single command such as stepping through an IO size range (e.g. 4K, 8K, 16K, 1MB, 10MB) as well as read write percentages along with varying random sequential mixes. Granted this can easily be done by having a series of commands, however I have become spoiled by using other tools such as vdbench.
Overall I like Diskspd and have added it to my Server Storage I/O workload and benchmark tool-box
Keep in mind that the best benchmark or workload generation technology tool will be your own application(s) configured to run as close as possible to production activity levels.
However when that is not possible, the an alternative is to use tools that have the flexibility to be configured as close as possible to your application(s) workload characteristics. This means that the focus should not be as much on the tool, as opposed to how flexible is a tool to work for you, granted the tool needs to be robust.
Having said that, Microsoft Diskspd is a good and extensible tool for benchmarking, simulation, validation and comparisons, however it will only be as good as the parameters and configuration you set it up to use.
Check out Microsoft Diskspd and add it to your benchmark and server storage I/O tool-box like I have done.
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
Updated 1/23/2018
Server storage I/O benchmark performance resource tools, various articles and tips. These include tools for legacy, virtual, cloud and software defined environments.
The best server and storage I/O (input/output operation) is the one that you do not have to do, the second best is the one with the least impact.
This is where the idea of locality of reference (e.g. how close is the data to where your application is running) comes into play which is implemented via tiered memory, storage and caching shown in the figure above.
Server storage I/O performance applies to cloud, virtual, software defined and legacy environments
What this has to do with server storage I/O (and networking) performance benchmarking is keeping the idea of locality of reference, context and the application workload in perspective regardless of if cloud, virtual, software defined or legacy physical environments.
StorageIOblog: I/O, I/O how well do you know about good or bad server and storage I/Os?
StorageIOblog: Server and Storage I/O benchmarking 101 for smarties
StorageIOblog: Which Enterprise HDDs to use for a Content Server Platform (7 part series with using benchmark tools)
StorageIO.com: Enmotus FuzeDrive MicroTiering lab test using various tools
StorageIOblog: Some server storage I/O benchmark tools, workload scripts and examples (Part I) and (Part II)
StorageIOblog: Get in the NVMe SSD game (if you are not already)
Doridmen.com: Transcend SSD360S Review with tips on using ATTO and Crystal benchmark tools
ComputerWeekly: Storage performance metrics: How suppliers spin performance specifications
Via StorageIO Podcast: Kevin Closson discusses SLOB Server CPU I/O Database Performance benchmarks
Via @KevinClosson: SLOB Use Cases By Industry Vendors. Learn SLOB, Speak The Experts’ Language
Via BeyondTheBlocks (Reduxio): 8 Useful Tools for Storage I/O Benchmarking
Via CCSIObench: Cold-cache Sequential I/O Benchmark
Doridmen.com: Transcend SSD360S Review with tips on using ATTO and Crystal benchmark tools
CISJournal: Benchmarking the Performance of Microsoft Hyper-V server, VMware ESXi and Xen Hypervisors (PDF)
Microsoft TechNet:Windows Server 2016 Hyper-V large-scale VM performance for in-memory transaction processing
InfoStor: What’s The Best Storage Benchmark?
StorageIOblog: How to test your HDD, SSD or all flash array (AFA) storage fundamentals
Via ATTO: Atto V3.05 free storage test tool available
Via StorageIOblog: Big Files and Lots of Little File Processing and Benchmarking with Vdbench
Via StorageIO.com: Which Enterprise Hard Disk Drives (HDDs) to use with a Content Server Platform (White Paper)
Via VMware Blogs: A Free Storage Performance Testing Tool For Hyperconverged
Microsoft Technet: Test Storage Spaces Performance Using Synthetic Workloads in Windows Server
Microsoft Technet: Microsoft Windows Server Storage Spaces – Designing for Performance
BizTech: 4 Ways to Performance-Test Your New HDD or SSD
EnterpriseStorageForum: Data Storage Benchmarking Guide
StorageSearch.com: How fast can your SSD run backwards?
OpenStack: How to calculate IOPS for Cinder Storage ?
StorageAcceleration: Tips for Measuring Your Storage Acceleration
Spiceworks: Determining HDD SSD SSHD IOP Performance
Spiceworks: Calculating IOPS from Perfmon data
Spiceworks: profiling IOPs
Vdbench example via StorageIOblog.com
StorageIOblog: What does server storage I/O scaling mean to you?
StorageIOblog: What is the best kind of IO? The one you do not have to do
Testmyworkload.com: Collect and report various OS workloads
Whoishostingthis: Various SQL resources
StorageAcceleration: What, When, Why & How to Accelerate Storage
Filesystems.org: Various tools and links
StorageIOblog: Can we get a side of context with them IOPS and other storage metrics?
BrightTalk Webinar: Data Center Monitoring – Metrics that Matter for Effective Management
StorageIOblog: Enterprise SSHD and Flash SSD Part of an Enterprise Tiered Storage Strategy
StorageIOblog: Has SSD put Hard Disk Drives (HDD’s) On Endangered Species List?
Microsoft TechNet: Measuring Disk Latency with Windows Performance Monitor (Perfmon)
Via Scalegrid.io: How to benchmark MongoDB with YCSB? (Perfmon)
Microsoft MSDN: List of Perfmon counters for sql server
Microsoft TechNet: Taking Your Server’s Pulse
StorageIOblog: Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?
CMG: I/O Performance Issues and Impacts on Time-Sensitive Applications
Virtualization Practice: IO IO it is off to Storage and IO metrics we go
InfoStor: Is HP Short Stroking for Performance and Capacity Gains?
StorageIOblog: Is Computer Data Storage Complex? It Depends
StorageIOblog: More storage and IO metrics that matter
StorageIOblog: Moving Beyond the Benchmark Brouhaha
Yellow-Bricks: VSAN VDI Benchmarking and Beta refresh!
YellowBricks: VSAN performance: many SAS low capacity VS some SATA high capacity?
YellowBricsk: VSAN VDI Benchmarking and Beta refresh!
StorageIOblog: Seagate 1200 12Gbs Enterprise SAS SSD StorgeIO lab review
StorageIOblog: Part II: Seagate 1200 12Gbs Enterprise SAS SSD StorgeIO lab review
StorageIOblog: Server Storage I/O Network Benchmark Winter Olympic Games
VMware VDImark aka View Planner (also here, here and here) as well as VMmark here
StorageIOblog: SPC and Storage Benchmarking Games
StorageIOblog: Speaking of speeding up business with SSD storage
StorageIOblog: SSD and Storage System Performance
Various Server Storage I/O tools in a hadoop environment
Michael-noll.com: Benchmarking and Stress Testing an Hadoop Cluster With TeraSort, TestDFSIO
Virtualization Practice: SSD options for Virtual (and Physical) Environments Part I: Spinning up to speed on SSD
StorageIOblog: Storage and IO metrics that matter
InfoStor: Storage Metrics and Measurements That Matter: Getting Started
SilvertonConsulting: Storage throughput vs. IO response time and why it matters
Splunk: The percentage of Read / Write utilization to get to 800 IOPS?
Various server storage I/O benchmarking tools
Spiceworks: What is the best IO IOPs testing tool out there
StorageIOblog: How many IOPS can a HDD, HHDD or SSD do?
StorageIOblog: Some Windows Server Storage I/O related commands
Openmaniak: Iperf overview and Iperf.fr: Iperf overview
StorageIOblog: Server and Storage I/O Benchmark Tools: Microsoft Diskspd (Part I and Part II)
Quest: SQL Server Perfmon Poster (PDF)
Server and Storage I/O Networking Performance Management (webinar)
Data Center Monitoring – Metrics that Matter for Effective Management (webinar)
Flash back to reality – Flash SSD Myths and Realities (Industry trends & benchmarking tips), (MSP CMG presentation)
DBAstackexchange: How can I determine how many IOPs I need for my AWS RDS database?
ITToolbox: Benchmarking the Performance of SANs
StorageIOblog: Dell Inspiron 660 i660, Virtual Server Diamond in the rough (Server review)
StorageIOblog: Part II: Lenovo TS140 Server and Storage I/O Review (Server review)
StorageIOblog: DIY converged server software defined storage on a budget using Lenovo TS140
StorageIOblog: Server storage I/O Intel NUC nick knack notes First impressions (Server review)
StorageIOblog & ITKE: Storage performance needs availability, availability needs performance
StorageIOblog: Why SSD based arrays and storage appliances can be a good idea (Part I)
StorageIOblog: Revisiting RAID storage remains relevant and resources
Interested in cloud and object storage visit our objectstoragecenter.com page, for flash SSD checkout storageio.com/ssd page, along with data protection, RAID, various industry links and more here.
Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.
Watch for additional links to be added above in addition to those that appear via comments.
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.
|
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
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
