Server StorageIO Data Infrastructure Insights and Analysis
|
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
Scaling means different things to various people depending on the context or what it is referring to.
For example, scaling can me having or doing more of something, or less as well as referring to how more, or less of something is implemented.
Scaling occurs in a couple of different dimensions and ways:
Often I hear people talk about scaling only in the context of space capacity. However there are aspects including performance, availability as well as scaling-up or scaling-out. Scaling from application workloads perspectives include four main group themes which are performance, availability, capacity and economics (as well as energy).
The latter of the above items should be thought of more in terms of a by-product, result or goal for implementing scaling. Scaling should not result in a compromise of some other attribute such as increasing performance and loss of capacity or increased complexity. Scaling with stability also means that as you scale in some direction, or across some attribute (e.g. PACE), there should not be a corresponding increase in complexity of management, or loss of performance and availability. To use a popular buzz-term scaling with stability means performance, availability, capacity, economics should scale linear with their capabilities or perhaps cost less.
Some examples of scaling in different directions include:
Of course you can combine the above in various combinations such as the example of scaling up and out, as well as apply different names and nomenclature to see your needs or preferences. The following are a closer look at the above with some simple examples.
Example of scaling up (vertically)
Example of scaling-down (e.g. for smaller scenarios)
Example of scaling-out (horizontally)
Example of scaling-out and up(horizontally and vertical)
There are many aspects to scaling, as well as side-effects or impacts as a result of scaling.
Scaling can refer to different workload attributes as well as how to support those applications.
Regardless of what you view scaling as meaning, keep in mind the context of where and when it is used and that others might have another scale view of scale.
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
Earlier this year I did a review of the Lenovo ThinkServer TS140 in the StorageIO Labs (see the review here), in fact I ended up buying a TS140 after the review, and a few months back picked up another one. This StorageIOlab review looks at the Lenovo ThinkServer TD340 Tower Server which besides having a larger model number than the TS140, it also has a lot more capabilities (server compute, memory, I/O slots and internal hot-swap storage bays. Pricing varies depending on specific configuration options, however at the time of this post Lenovo was advertising a starting price of $1,509 USD for a specific configuration here. You will need to select different options to decide your specific cost.
The TD340 is one of the servers that Lenovo has had prior to its acquisition of IBM x86 server business that you can read about here. Note that the Lenovo acquisition of the IBM xSeries business group has begun as of early October 2014 and is expected to be completed across different countries in early 2015. Read more about the IBM xSeries business unit here, here and here.
Lets start with the overall experience which was very easy other than deciding what make and model to try. This includes going from first answering some questions to get the process moving, agreeing to keep the equipment safe, secure, insured as well as not damaging anything. Part of the process also involved answering some configuration related questions and shortly there after a large box from Lenovo arrived.
TD340 with Keyboard and Mouse (Monitor and keyboard not included)
One of the reasons I have a photo of the TD340 on a desk is that I initially put it in an office environment similar to what I did with the TS140 as Lenovo claimed it would be quiet enough to do so. I was not surprised and indeed the TD340 is quiet enough to be used where you would normally find a workstation or mini-tower. By being so quiet the TD340 is a good fit for environments that need a server that has to go into an office environment as opposed to a server or networking room.
Lenovo ThinkServer Setup
Lenovo TD340 as tested in BIOS setup, note the dual Intel Xeon E5-2420 v2 processors
TD340 "Selfie" with 4 x 8GB DDR3 DIMM (32GB) and PCIe slots (empty)
TD340 internal drive hot-swap bays
The TD340 that I tested was a Machine type 7087 model 002RUX which included 4 x 16GB DIMMs and both processor sockets occupied.
You can view the Lenovo TD340 data sheet with more speeds and feeds here, however the following is a summary.
After initial check out in an office type environment, I moved the TD340 into the lab area where it joined other servers to be used for various things.
Some of those activities included using the Windows Server 2012 Essentials along with associated admin activities as well as installing VMware ESXi 5.5.
TD340 with Keyboard and Mouse (Monitor and keyboard not included)
Unbelievably quiet which may not seem like a big deal, however if you are looking to deploy a server or system into a small office workspace, this becomes an important considerations. Otoh, if you are a power user and want a robust server that can be installed into a home media entertainment system, well, this might be a nice to have consideration ;). Speaking of IO slots, naturally I’m interested in Server Storage I/O so having multiple slots is a must have, along with the processor that is multi-core (pretty much standard these days) along with VT and EP for supporting VMware (these were disabled in the BIOS however that was an easy fix).
The only thing I did not like was that I ran into a compatibility issue trying to use a LSI 9300 series 12Gb SAS HBA which Lenovo is aware of, and perhaps has even addressed by now. What I ran into is that the adapters work however I was not able to get the full performance out of the adapters as compared to on other systems including my slower Lenovo TS140s.
Overall I give Lenovo and the TD340 an "B+" which would have been an "A" had I not gotten myself into a BIOS situation or been able to run the 12Gbps SAS PCIe Gen 3 cards at full speed. Likewise the Lenovo service and support also helped to improve on the experience. Otoh, if you are simply going to use the TD340 in a normal out of the box mode without customizing to add your own adapters or install your own operating system or Hypervisors (beyond those that are supplied as part of the install setup tool kit), you may have an "A" or "A+" experience with the TD340.
Would I recommend the TD340 to others? Yes for those who need this type and class of server for Windows, *nix, Hyper-V or VMware environments.
Would I buy a TD340 for myself? Maybe if that is the size and type of system I need, however I have my eye on something bigger. On the other hand for those who need a good value server for a SMB or ROBO environment with room to grow, the TD340 should be on your shopping list to compare with other solutions.
Disclosure: Thanks to the folks at Lenovo for sending and making the TD340 available for review and a hands on test experience including covering the cost of shipping both ways (the unit should now be back in your possession). Thus this is not a sponsored post as Lenovo is not paying for this (they did loan the server and covered two-way shipping), nor am I paying them, however I have bought some of their servers in the past for the StorageIOLab environment that are companions to some Dell and HP servers that I have also purchased.
Ok, nuff said
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
In case you have not heard, the joint initiative (JV) founded in the fall of 2009 between Intel VMware Cisco and EMC called VCE had a change of ownership today.
Well, kind of…
For those not familiar or who need a recap, VCE was created to create converged server, storage I/O networking hardware and software solutions combing technologies from its investors resulting in solutions called vBlocks.
The major investors were Cisco who provides the converged servers and I/O networking along with associated management tools as well as EMC who provides the storage systems along with their associated management tools. Minority investors include VMware (who is majority owned by EMC) who provides the server virtualization aka software defined data center management tools and Intel whose’s processor chip technologies are used in the vBlocks. What has changed from Zen (e.g. yesterday or in the past) and now is that Cisco has sold the majority (they are retaining about 10%) of its investment ownership in VCE to EMC. Learn more about VCE, their solutions and valueware in this post here (VCE revisited, now and Zen).
EMC pulling VCE in-house which should prop up its own internal sales figures by perhaps a few billion USDs within a year or so (if not sooner) is not as appealing to activists investors who want results now such as selling off parts of the company (e.g. EMC, VMware or other assets) or the entire company.
However EMC has been under pressure from activist shareholder Elliot Management to divest or sell-off portions of this business such as VMware so that the investors (including the activist) can make more money. For example there have been the recent stories about EMC looking to sell or merge with the likes of HP (who is now buying back shares and splitting up its own business) among others which certainly must make the activist investors happy.
However to the activist investors who want to see things sold to make money they are not happy with EMC off buying or investing it appears.
Via Bloomberg “The last thing on investors’ minds is the future of VCE,” Daniel Ives, an analyst with FBR Capital Markets, wrote in a note today. “EMC has a fire in its house right now and the company appears focused on painting its bedroom (e.g. VCE), while the Street wants a resolution on the strategic ownership situation sooner rather than later.” Read more at Bloomberg |
Note that EMC has organized itself into a federation that consists of EMC Information Infrastructure (EMCII) or what you might know a traditional EMC based storage and related software solutions, VMware, Pivotal and RSA. Also note that each of those federated companies have their own CEO as well as have holdings or ownership of other companies. However all report to a common federated leadership aka EMC. Thus when you hear EMC that could mean depending on the context the federation mother ship which controls the individual companies, or it could also be used to refer to EMCII aka the traditional EMC. Click here to learn more about the EMC federation.
Looking beyond near-term or quick gains, EMC could be simply doing something others do to take ownership and control over certain things while reducing complexities associated with joint initiatives. For example with EMC and Cisco in a close partnership with VCE, both parties have been free to explore and take part in other joint initiatives such as Cisco with EMC competitors NetApp, HDS among others. Otoh EMC partners with Arista for networking, not to mention via VMware acquired virtual network or software defined network Nicira now called NSX.
EMC is also in a partnership with Lenovo for developing servers to be used by EMC for various platforms to support storage, data and information services while shifting the lower-end SMB storage offerings such as Iomega to the Lenovo channel.
Note that Lenovo is in the process of absorbing the IBM xSeries (e.g. x86 based) business unit that started closing earlier in October (will take several months to completely close in all countries around the world). For its part Cisco is also partnering with hyper-converged solution provider Simplivity while EMC has announced its statement of direction to bring to market its own hyper-converged platform by end of the year. For those not familiar, Hyper-converged solutions are simply the next evolution of converged or pre-bundled turnkey systems (some of you might have just had a Dejavu moment) that today tend to be targeted for SMBs and ROBOs however used for targeted applications such as VDI in larger environments.
IF EMC is about to release as it has made statement of direction statements of a hyper-converged solution by year-end to compete head-on with those from Nutanix, Simplivity and Tintri as well as perhaps to a lesser extent VMwares EVO:Rail, by having more control over VCE means reducing if not eliminating complexity around vBlocks which are Cisco based with EMC storage vs. what ever EMC brings to market for hyper-converged. In the past under the VCE initiatives storage was limited to EMC and servers along with networking from Cisco, hypervisors from VMware, however what happens in the future remains to be seen.
Tough to say as EMC can not afford to have its sales force lose focus on its traditional core products while ramping up other business, however, the EMC direct and partner teams want and need to keep up account control which means gaining market share and footprint in those accounts. This also means EMC needs to find ways to take cost out of the sales and marketing process where possible to streamline which perhaps brining VCE will help do.
Will this perhaps give the EMC direct and partner sales teams a new carrot or incentive to promote converged and hyper-converged at the cost of other competitors or incumbents? Perhaps, lets see what happens in the coming weeks.
In a nut shell, IMHO EMC is doing a couple of things here one of which is cleaning up some ownership in JVs to give it self more control, as well as options for doing other business transactions (mergers and acquisitions (M&A), sales or divestiture’s, new joint initiatives, etc). Then there is streamline its business from decision-making to quickly respond to new opportunities as well as routes to markets and other activities (e.g. removing complexity and cost vs. simply cutting cost).
Does this signal the prelude to something else? Perhaps, we know that EMC has made a statement of direction about hyper-converged which with VCE now more under EMC control, perhaps we will see more options from under the VCE umbrella both for lower-end and entry SMB as well as SME and large enterprise organizations.
They are going to make noise as long as they can continue to make more money or get what they want. Publicly I would be shocked if the activist investors were not making statements that EMC should be selling assets not buying or investing.
On the other hand, any smart investor, financial or other analyst should see though the fog of what this relatively simple transaction means in terms of EMC getting further control of its future.
Of course the question will stay does EMC remain in control of its current federation of EMC, VMware, Pivotal, RSA along each of their respective holdings, does EMC doe a block buster merger, divestiture or acquisition?
Some things to keep an eye on:
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
Recently Seagate made an announcement that they have shipped over 10 million Hybrid Hard Disk Drives (HHDD) also known as Solid State Hybrid Drives (SSHD) over that past few years. Disclosure Seagate has been a StorageIO client.
I know where some of those desktop class HHDD’s including Momentus XTs ended up as I bought some of the 500GB and 750GB models via Amazon and have them in various systems. Likewise I have installed in VMware servers the newer generation of enterprise class SSHD’s which Seagate now refers to as Turbo models as companions to my older HHDD’s
The HHDD’s continue to evolve from initially accelerating reads to now being capable of speeding up write operations across different families (desktop/mobile, workstation and enterprise). What makes a HHDD or SSHD is that as their name implies, they are a hybrid combing a traditional spinning magnetic Hard Disk Drive (HDD) along with flash SSD storage. The flash persistent memory is in addition to the DRAM or non-persistent memory typically found on HDDs used as a cache buffer. These HHDDs or SSHDs are self-contained in that the flash are built-in to the actual drive as part of its internal electronics circuit board (controller). This means that the drives should be transparent to the operating systems or hypervisors on servers or storage controllers without need for special adapters, controller cards or drivers. In addition, there is no extra software needed to automated tiering or movement between the flash on the HHDD or SSHD and its internal HDD, its all self-contained managed by the drives firmware (e.g. software).
Jim Handy over at Objective Analysis has this interesting post discussing Hybrid Drives Not Catching On. The following is an excerpt from Jim’s post.
Why were our expectations higher? There were a few reasons: The hybrid drive can be viewed as an evolution of the DRAM cache already incorporated into nearly all HDDs today.
The net result is shipments of 10 million units since its 2010 introduction, for an average of 2.5 million per year, out of a total annual HDD shipments of around 500 million units, or one half of one percent. Continue reading more of Jim’s post here. |
In his post, Jim raises some good points including that HHDD’s and SSHD’s are still a fraction of the overall HDD’s shipped on an annual basis. However IMHO the annual growth rate has not been a flat average of 2.5 million, rather starting at a lower rate and then increasing year over year. For example Seagate issued a press release back in summer 2011 that they had shipped a million HHDD’s a year after their release. Also keep in mind that those HHDD’s were focused on desktop workstations and in particular, at Gamers among others.
The early HHDD’s such as the Momentus XTs that I was using starting in June 2010 only had read acceleration which was better than HDD’s, however did not help out on writes. Over the past couple of years there have been enhancements to the HHDD’s including the newer generation also known as SSHD’s or Turbo drives as Seagate now calls them. These newer drives include write acceleration as well as with models for mobile/laptop, workstation and enterprise class including higher-performance and high-capacity versions. Thus my estimates or analysis has the growth on an accelerating curve vs. linear growth rate (e.g. average of 2.5 million units per year).
| Units shipped per year | Running total units shipped | |
| 2010-2011 | 1.0 Million | 1.0 Million |
| 2011-2012 | 1.25 Million (est.) | 2.25 Million (est.) |
| 2012-2013 | 2.75 Million (est.) | 5.0 Million (est.) |
| 2013-2014 | 5.0 Million (est) | 10.0 Million |
StorageIO estimates on HHDD/SSHD units shipped based on Seagate announcements
However IMHO there is more to the story beyond numbers of HHDD/SSHD shipped or if they are accelerating in deployment or growing at an average rate. Some of those perspectives are in my comments over on Jim Handy’s site with an excerpt below.
In talking with IT professionals (e.g. what the vendors/industry calls users/customers) they are generally not aware that these devices exist, or if they are aware of them, they are only aware of what was available in the past (e.g. the consumer class read optimized versions). I do talk with some who are aware of the newer generation devices however their comments are usually tied to lack of system integrator (SI) or vendor/OEM support, or sole source. Also there was a focus on promoting the HHDD’s to “gamers” or other power users as opposed to broader marketing efforts. Also most of these IT people are not aware of the newer generation of SSHD or what Seagate is now calling “Turbo” drives. When talking with VAR’s, there is a similar reaction which is discussion about lack of support for HHDD’s or SSHD’s from the SI/vendor OEMs, or single source supply concerns. Also a common reaction is lack of awareness around current generation of SSHD’s (e.g. those that do write optimization, as well as enterprise class versions). When talking with vendors/OEMs, there is a general lack of awareness of the newer enterprise class SSHD’s/HHDD’s that do write acceleration, sometimes there is concern of how this would disrupt their “hybrid” SSD + HDD or tiering marketing stories/strategies, as well as comments about single source suppliers. Have also heard comments to the effect of concerns about how long or committed are the drive manufactures going to be focused on SSHD/HHDD, or is this just a gap filler for now. Not surprisingly when I talk with industry pundits, influencers, amplifiers (e.g. analyst, media, consultants, blogalysts) there is a reflection of all the above which is lack of awareness of what is available (not to mention lack of experience) vs. repeating what has been heard or read about in the past. IMHO while there are some technology hurdles, the biggest issue and challenge is that of some basic marketing and business development to generate awareness with the industry (e.g. pundits), vendors/OEMs, VAR’s, and IT customers, that is of course assuming SSHD/HHDD are here to stay and not just a passing fad… |
What about the performance of today’s HHDD’s and SSHD’s, particular those that can accelerate writes as well as reads?
Enterprise Turbo SSHD read and write performance (Exchange Email)
What about the performance of today’s HHDD’s and SSHD’s, particular those that can accelerate writes as well as reads?
Enterprise Turbo SSHD read and write performance (TPC-B database)
Enterprise Turbo SSHD read and write performance (TPC-E database)
Additional details and information about HHDD/SSHD or as Seagate now refers to them Turbo drives can be found in two StorageIO Industry Trends Perspective White Papers (located here and another here).
Refer to the following links to learn more about HHDD and SSHD devices.
StorageIO Momentus Hybrid Hard Disk Drive (HHDD) Moments
Enterprise SSHD and Flash SSD
Part of an Enterprise Tiered Storage Strategy
Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?
2011 Summer momentus hybrid hard disk drive (HHDD) moment
More Storage IO momentus HHDD and SSD moments part I
More Storage IO momentus HHDD and SSD moments part II
New Seagate Momentus XT Hybrid drive (SSD and HDD)
Another StorageIO Hybrid Momentus Moment
SSD past, present and future with Jim Handy
Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?
I continue to be bullish on hybrid storage solutions from cloud, to storage systems as well as hybrid-storage devices. However like many technology just because something makes sense or is interesting does not mean its a near-term or long-term winner. My main concern with SSHD and HHDD is if the manufactures such as Seagate and WD are serious about making them a standard feature in all drives, or simply as a near-term stop-gap solution.
What’s your take or experience with using HHDD and/or SSHDs?
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
In this Industry Trends Perspectives video pod cast episode (On YouTube) I had a chance to visit with Nathan LeClaire of docker.com at the recent VMworld 2014 in San Francisco for a quick overview of docker and containers are about, what you need to know and where to find more information. Check out this StorageIO Industry Trends Perspective episode "Docker for Smarties" aka not for dummies via YouTube by clicking here or on the image below.
For those not familiar with docker.
Docker overview
Three things to know about docker
Checkout the Docker for non-dummies 
video here.
What’s your take, is docker in your future or are you already using 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
The CompTIA folks are looking for some comments and feedback from those who are involved with data storage in various ways as part of planning for their upcoming enhancements to the Storage+ certification testing.
As a point of disclosure, I am member of the CompTIA Storage+ certification advisory committee (CAC), however I don’t get paid or receive any other type of renumeration for contributing my time to give them feedback and guidance other than a thank, Atta boy for giving back and playing it forward to help others in the IT community similar to what my predecessors did.
I have been asked to pass this along to others (e.g. you or who ever forwards it on to you).
Please take a few moments and feel free to share with others this link here to the survey for CompTIA Storage+.
What they are looking for is to validate the exam blueprint generated from a recent Job Task Analysis (JTA) process.
In other words, does the certification exam show real-world relevance to what you and your associates may be doing involved with data storage.
This is opposed to being aligned with those whose’s job it is to create test questions and may not understand what it is you the IT pro involved with storage does or does not do.
If you have ever taken a certification exam test and scratched your head or wondered out why some questions that seem to lack real-world relevance were included, vs. ones of practical on-the-job experience were missing, here’s your chance to give feedback.
Note that you will not be rewarded with an Amex or Amazon gift card, Starbucks or Dunkin Donuts certificates, free software download or some other incentive to play and win, however if you take the survey let me know and will be sure to tweet you an Atta boy or Atta girl! However they are giving away a free T-Shirt to every 10 survey takers.
Btw, if you really need something for free, send me a note (I’m not that difficult to find) as I have some free copies of Resilient Storage Networking (RSN): Designing Flexible Scalable Data Infrastructures (Elsevier) you simply pay shopping and handling. RSN can be used to help prepare you for various storage testing as well as other day-to-day activities.
CompTIA is looking for survey takers who have some hands-on experience or involved with data storage (e.g. can you spell SAN, NAS, Disk or SSD and work with them hands-on then you are a candidate ;).
Welcome to the CompTIA Storage+ Certification Job Task Analysis (JTA) Survey Here is what (and whom) CompTIA is looking for feedback from: As a small token of CompTIA appreciation for your participation, they will provide an official CompTIA T-shirt to every tenth (1 of every 10) person who completes this survey. Go here for official rules. Click here to complete the CompTIA Storage+ survey Contact CompTIA with any survey issues, research@comptia.org |
What say you, take a few minutes like I did and give some feedback, you will not be on the hook for anything, and if you do get spammed by the CompTIA folks, let me know and I in turn will spam them back for spamming you as well as me.
Ok, nuff said
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
| ||||||||||||||||||||||||||||||||
August 2014 Industry trend and perspectives
The following is a synopsis of some StorageIOblog posts, articles and comments in different venues on various industry trends, perspectives and related themes about clouds, virtualization, data and storage infrastructure topics among related themes. StorageIO comments and perspectives in the news
Virtual Desktop Infrastructures (VDI) remains a popular industry and IT customer topic, not to mention being one of the favorite themes of Solid State Device (SSD) vendors. SSD component and system solution vendors along with their supporters love VDI as the by-product of aggregation (e.g. consolidation) which applies to VDI is aggravation. Aggravation is the result of increased storage I/O performance (IOP’s, bandwidth, response time) from consolidating the various desktops. It should not be a surprise that some of the biggest fans encouraging organizations to adopt VDI are the SSD vendors. Read some of my comments and perspectives on VDI here at FedTech Magazine. Speaking of virtualizing the data center, software defined data centers (SDDC) along with software defined networking (SDN) and software defined storage (SDS) remain popular including some software defined marketing (SDM). Here are some of my comments and perspectives moving beyond the hype of SDDC.
Recently the Fibre Channel Industry Association (FCIA) who works with the T11 standards body of both legacy or classic Fibre Channel (FC) as well as newer FC over Ethernet (FCoE) made some announcements. These announcements including enhancements such as Fibre Channel Back Bone version 6 (FC-BB-6) among others. Both FC and FCoE are alive and doing well, granted one has been around longer (FC) and can be seen at its plateau while the other (FCoE) continues to evolve and grow in adoption. In some ways, FCoE is in a similar role today to where FC was in the late 90s and early 2000s ironically facing some common fud. You can read my comments here as part of a quote in support of the announcement , along with my more industry trend perspectives in this blog post here. Buyers guides are popular with both vendors, VAR’s as well as IT organizations (e.g. customers) following are some of my comments and industry trend perspectives appearing in Enterprise Storage Forum. Here are perspectives on buyers guides for Enterprise File Sync and Share (EFSS), Unified Data Storage and Object Storage. EMC has come under pressure as mentioned in earlier StorageIO update newsletters to increase its shareholder benefit including spin-off of VMware. Here are some of my comments and perspectives that appeared in CruxialCIO. Read more industry trends perspectives comments on the StorageIO news page. StorageIO video and audio pod casts
StorageIOblog posts and perspectives
Despite being declared dead, traditional or classic Fibre Channel (FC) along with FC over Ethernet (FCoE) continues to evolve with FC-BB-6, read more here. VMworld 2014 took place this past week and included announcements about EVO:Rack and Rail (more on this in a future edition). You can get started learning about EVO:Rack and RAIL at Duncan Epping (aka @DuncanYB) Yellow Bricks site. VMware Virtual SAN (VSAN) is at the heart of EVO which you can read an overview here in this earlier StorageIO update newsletter (March 2014).
Also watch for some extra content that I’m working on including some video podcasts articles and blog posts from my trip to VMworld 2014. However one of the themes in the background of VMworld 2014 is the current beta of VMware vSphere V6 along with Virtual Volumes aka VVOL’s. The following are a couple of my recent posts including primer overview of VVOL’s along with a poll you can cast your vote. Check out Are VMware VVOL’s in your virtual server and storage I/O future? and VMware VVOL’s and storage I/O fundamentals (Part 1) along with (Part 2). | ||||||||||||||||||||||||||||||||
StorageIO events and activities The StorageIO calendar continues to evolve including several new events being added for September and well into the fall with more in the works including upcoming Dutch European sessions the week of October 6th in Nijkerk Holland (learn more here). The following are some upcoming September events. These include live in-person seminars, conferences, keynote and speaking activities as well as on-line webinars, twitter chats, Google+ hangouts among others.
Note: Dates, times, venues and subject contents subject to change, refer to events page for current status Click here to view other upcoming along with earlier event activities. Watch for more 2014 events to be added soon to the StorageIO events calendar page. Topics include data protection modernization (backup/restore, HA, BC, DR, archive), data footprint reduction (archive, compression, dedupe), storage optimization, SSD, object storage, server and storage virtualization, software defined, big data, little data, cloud and object storage, performance and management trends among others. Vendors, VAR’s and event organizers, give us a call or send an email to discuss having us involved in your upcoming pod cast, web cast, virtual seminar, conference or other events. | ||||||||||||||||||||||||||||||||
Server and StorageIO Technology Tips and Tools In addition to the industry trends and perspectives comments in the news mentioned above, along with the StorageIO blog posts, the following are some of my recent articles and tips that have appeared in various industry venues.
Over at the new Storage Acceleration site I have a couple of pieces, the first is What, When, Why & How to Accelerate Storage and the other is Tips for Measuring Your Storage Acceleration. | ||||||||||||||||||||||||||||||||
StorageIO Update Newsletter ArchivesClick here to view earlier StorageIO Update newsletters (HTML and PDF versions) at www.storageio.com/newsletter. Subscribe to this newsletter (and pass it along) by clicking here (Via Secure Campaigner site). View archives of past StorageIO update news letters as well as download PDF versions at: www.storageio.com/newsletter | ||||||||||||||||||||||||||||||||
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) All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved | ||||||||||||||||||||||||||||||||
Note that this is a three part series with the first piece here (e.g. Are VMware VVOL’s in your virtual server and storage I/O future?), the second piece here (e.g.VMware VVOL’s and storage I/O fundamentals Part 1) and the third piece here (e.g. VMware VVOL’s and storage I/O fundamentals Part 2).
Picking up from where we left off in the first part of the VMware VVOL’s and storage I/O fundamentals, lets take a closer look at VVOL’s.
First however lets be clear that while VMware uses terms including object and object storage in the context of VVOL’s, its not the same as some other object storage solutions. Learn more about object storage here at www.objectstoragecenter.com
No, VVOL’s are accessed via the VMware software and associated API’s that are supported by various storage providers. VVOL’s are not LUN’s like regular block (e.g. DAS or SAN) storage that use SAS, iSCSI, FC, FCoE, IBA/SRP, nor are they NAS volumes like NFS mount points. Likewise VVOL’s are not accessed using any of the various object storage access methods mentioned above (e.g. AWS S3, Rest, CDMI, etc) instead they are an application specific implementation. For some of you this approach of an applications specific or unique storage access method may be new, perhaps revolutionary, otoh, some of you might be having a DejaVu moment right about now.
VVOL is not a LUN in the context of what you may know and like (or hate, even if you have never worked with them), likewise it is not a NAS volume like you know (or have heard of), neither are they objects in the context of what you might have seen or heard such as S3 among others.
Keep in mind that what makes up a VMware virtual machine are the VMK, VMDK and some other files (shown in the figure below), and if enough information is known about where those blocks of data are or can be found, they can be worked upon. Also keep in mind that at least near-term, block is the lowest common denominator that all file systems and object repositories get built-up.
VMware ESXi storage I/O, IOPS and data store basics
Here is the thing, while VVOL’s will be accessible via a block interface such as iSCSI, FC or FCoE or for that matter, over Ethernet based IP using NFS. Think of these storage interfaces and access mechanisms as the general transport for how vSphere ESXi will communicate with the storage system (e.g. their data path) under vCenter management.
What is happening inside the storage system that will be presented back to ESXi will be different than a normal SCSI LUN contents and only understood by VMware hypervisor. ESXi will still tell the storage system what it wants to do including moving blocks of data. The storage system however will have more insight and awareness into the context of what those blocks of data mean. This is how the storage systems will be able to more closely integrate snapshots, replication, cloning and other functions by having awareness into which data to move, as opposed to moving or working with an entire LUN where a VMDK may live. Keep in mind that the storage system will still function as it normally would, just think of VVOL as another or new personality and access mechanism used for VMware to communicate and manage storage.
VMware VVOL concepts (in general) with VMDK being pushed down into the storage system
Think in terms of the iSCSI (or FC or something else) for block or NFS for NAS as being the addressing mechanism to communicate between ESXi and the storage array, except instead of traditional SCSI LUN access and mapping, more work and insight is pushed down into the array. Also keep in mind that with a LUN, it is simply an address from what to use Logical Block Numbers or Logical Block Addresses. In the case of a storage array, it in turn manages placement of data on SSD or HDDs in turn using blocks aka LBA/LBN’s In other words, a host that does not speak VVOL would get an error if trying to use a LUN or target on a storage system that is a VVOL, that’s assuming it is not masked or hidden ;).
The Storage Provider aka SP is created by the, well, the provider of the storage system or appliance leveraging a VMware API (hint, sign up for the beta and there is an SDK). Simply put, the SP is a two-way communication mechanism leveraging VASA for reporting information, configuration and other insight up to VMware ESXi hypervisor, vCenter and other management tools. In addition the storage provider receives VASA configuration information from VMware about how to configure the storage system (e.g. storage containers). Keep in mind that the SP is the out of band management interface between the storage system supporting and presenting VVOL’s and VMware hypervisors.
This is a storage pool created on the storage array or appliance (e.g. VMware vCenter works with array and storage provider (SP) to create) in place of using a normal LUN. With a SP and PE, the storage container becomes visible to ESXi hosts, VVOL’s can be created in the storage container until it runs out of space. Also note that the storage container takes on the storage profile assigned to it which are inherited by the VVOLs in it. This is in place of presenting LUN’s to ESXi that you can then create VMFS data stores (or use as raw) and then carve storage to VMs.
The PE provides visibility for the VMware hypervisor to see and access VMDK’s and other objects (e.g. .vmx, swap, etc) stored in VVOL’s. The protocol endpoint (PE) manages or directs I/O received from the VM enabling scaling across many virtual volumes leveraging multipathing of the PE (inherited by the VVOL’s.). Note that for storage I/O operations, the PE is simply a pass thru mechanism and does not store the VMDK or other contents. If using iSCSI, FC, FCoE or other SAN interface, then the PE works on a LUN basis (again not actually storing data), and if using NAS NFS, then with a mount point. Key point is that the PE gets out-of-the-way.
What are you VVOL plans, view results and cast your vote here
There certainly are many more details to VVOL’s. that you can get a preview of in the beta, a well as via various demos, webinars, VMworld sessions as more becomes public. However for now, hope you found this quick overview on VVOL’s. of use, since VVOL’s. at the time of this writing are not yet released, you will need to wait for more detailed info, or join the beta or poke around the web (for now). Also if you have not seen the first part overview to this piece, check it out here as I give some more links to get you started to learn more about VVOL’s.
Keep an eye on and learn more about VVOL’s. at VMworld 2014 as well as in various other venues.
IMHO VVOL’s. are or will be in your future, however the question will be is there going to be a back to the future moment for some of you with VVOL’s.?
What VVOL questions, comments and concerns are in your future and on your mind?
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
Note that this is a three part series with the first piece here (e.g. Are VMware VVOL’s in your virtual server and storage I/O future?), the second piece here (e.g.VMware VVOL’s and storage I/O fundamentals Part 1) and the third piece here (e.g. VMware VVOL’s and storage I/O fundamentals Part 2).
Some of you may already be participating in the VMware beta of VVOL involving one of the initial storage vendors also in the beta program.
Ok, now let’s go a bit deeper, however if you want some good music to listen to while reading this, check out @BruceRave GoDeepMusic.Net and shows here.
Instead of a VM host accessing its virtual disk (aka VMDK) which is stored in a VMFS formatted data store (part of ESXi hypervisor) built on top of a SCSI LUN (e.g. SAS, SATA, iSCSI, Fibre Channel aka FC, FCoE aka FC over Ethernet, IBA/SRP, etc) or an NFS file system presented by a storage system (or appliance), VVOL’s push more functionality and visibility down into the storage system. VVOL’s shift more intelligence and work from the hypervisor down into the storage system. Instead of a storage system simply presenting a SCSI LUN or NFS mount point and having limited (coarse) to no visibility into how the underlying storage bits, bytes as well as blocks are being used, storage systems gain more awareness.
Keep in mind that even files and objects still get ultimately mapped to pages and blocks aka sectors even on nand flash-based SSD’s. However also keep an eye on some new technology such as the Seagate Kinetic drive that instead of responding to SCSI block based commands, leverage object API’s and associated software on servers. Read more about these emerging trends here and here at objectstoragecenter.com. |
With a normal SCSI LUN the underlying storage system has no knowledge of how the upper level operating system, hypervisor, file system or application such as a database (doing raw IO) is allocating the pages or blocks of memory aka storage. It is up to the upper level storage and data management tools to map from objects and files to the corresponding extents, pages and logical block address (LBA) understood by the storage system. In the case of a NAS solution, there is a layer of abstractions placed over the underlying block storage handling file management and the associated file to LBA mapping activity.
Storage I/O and IOP basics and addressing: LBA’s and LBN’s
Getting back to VVOL, instead of simply presenting a LUN which is essentially a linear range of LBA’s (think of a big table or array) that the hypervisor then manages data placement and access, the storage system now gains insight into what LBA’s correspond to various entities such as a VMDK or VMX, log, clone, swap or other VMware objects. With this more insight, storage systems can now do native and more granular functions such as clone, replication, snapshot among others as opposed to simply working on a coarse LUN basis. The similar concepts extend over to NAS NFS based access. Granted, there are more to VVOL’s including ability to get the underlying storage system more closely integrated with the virtual machine, hypervisor and associated management including supported service manage and classes or categories of service across performance, availability, capacity, economics.
VVOL’s are building from earlier VMware initiatives including VAAI and VASA. With VAAI, VMware hypervisor’s can off-load common functions to storage systems that support features such as copy, clone, zero copy among others like how a computer can off-load graphics processing to a graphics card if present.
VASA however provides a means for visibility, insight and awareness between the hypervisor and its associated management (e.g. vCenter etc) as well as the storage system. This includes storage systems being able to communicate and publish to VMware its capabilities for storage space capacity, availability, performance and configuration among other things.
With VVOL’s VASA gets leveraged for unidirectional (e.g. two-way) communication where VMware hypervisor and management tools can tell the storage system of things, configuration, activities to do among others. Hence why VASA is important to have in your VMware CASA.
VVOL’s are a form of object storage access in that they differ from traditional block (LUN’s) and files (NAS volumes/mount points). However, keep in mind that not all object storage are the same as there are object storage access and architectures.
Object Storage basics, generalities and block file relationships
Avoid making the mistake of when you hear object storage that means ANSI T10 (the folks that manage the SCSI command specifications) Object Storage Device (OSD) or something else. There are many different types of underlying object storage architectures some with block and file as well as object access front ends. Likewise there are many different types of object access that sit on top of object architectures as well as traditional storage system.
An example of how some object storage gets accessed (not VMware specific)
Also keep in mind that there are many different types of object access mechanism including HTTP Rest based, S3 (e.g. a common industry defacto standard based on Amazon Simple Storage Service), SNIA CDMI, SOAP, Torrent, XAM, JSON, XML, DICOM, IL7 just to name a few, not to mention various programmatic bindings or application specific implementations and API’s. Read more about object storage architectures, access and related topics, themes and trends at www.objecstoragecenter.com
Lets take a break here and when you are ready, click here to read the third piece in this series VMware VVOL’s and storage I/O fundamentals Part 2.
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
Note that this is a three part series with the first piece here (e.g. Are VMware VVOL’s in your virtual server and storage I/O future?), the second piece here (e.g. VMware VVOL’s and storage I/O fundamentals Part 1) and the third piece here (e.g. VMware VVOL’s and storage I/O fundamentals Part 2).
With VMworld 2014 just around the corner, for some of you the question is not if Virtual Volumes (VVOL’s) are in your future, rather when, where, how and with what.
What this means is that for some hands on beta testing is already occurring or will be soon, while for others that might be around the corner or down the road.
Some of you may already be participating in the VMware beta of VVOL involving one of the first storage vendors also in the beta program.
On the other hand, some of you may not be in VMware centric environments and thus VVOL’s may not yet be in your vocabulary.
First, to be clear, as of the time this was written VMware VVOL’s are not released and only in beta as well as having been covered in earlier VMworld’s. Consequently what you are going to read here is based on what VVOL material has already been made public in various venues including earlier VMworld’s and VMware blogs among other places.
The quick synopsis of VMware VVOL’s overview:
As mentioned, as of this writing, VVOL’s are still a future item granted they exist in beta.
For those of you in VMware environments, now is the time to add VVOL to your vocabulary which might mean simply taking the time to read a piece like this, or digging deeper into the theories of operations, configuration, usage, hints and tips, tutorials along with vendor specific implementations.
Explore your options, and ask yourself, do you want VVOL or do you need it
What support does your current vendor(s) have for VVOL or what is their statement of direction (SOD) which you might have to get from them under NDA.
This means that there will be some first vendors with some of their products supporting VVOL’s with more vendors and products following (hence watch for many statements of direction announcements).
Speaking of vendors, watch for a growing list of vendors to announce their current or plans for supporting VVOL’s, not to mention watch some of them jump up and down like Donkey in Shrek saying "oh oh pick me pick me".
When you ask a vendor if they support VVOL’s, move beyond the simple yes or no, ask which of their specific products, it is a block (e.g. iSCSI) or NAS file (e.g. NFS) based and other caveats or configuration options.
Watch for more information about VVOL’s in the weeks and months to come both from VMware along with from their storage provider partners.
How will VVOL impact your organizations best practices, policies, workflow’s including who does what, along with associated responsibilities.
Check out the companion piece to this that takes a closer look at storage I/O and VMware VVOL fundamentals here and here.
Also check out this good VMware blog via Cormac Hogan (@CormacJHogan) that includes a video demo, granted its from 2012, however some of this stuff actually does take time and thus this is very timely. Speaking of VMware, Duncan Epping (aka @DuncanYB) at his Yellow-Bricks site has some good posts to check out as well with links to others including this here. Also check out the various VVOL related sessions at VMworld as well as the many existing, and soon to be many more blogs, articles and videos you can find via Google. And if you need a refresher, Why VASA is important to have in your VMware CASA.
Of course keep an eye here or whichever venue you happen to read this for future follow-up and companion posts, and if you have not done so, sign up for the beta here as there are lots of good material including SDKs, configuration guides and more.
What are you VVOL plans, view results and cast your vote here
Hope you found this quick overview on VVOL’s of use, since VVOL’s at the time of this writing are not yet released, you will need to wait for more detailed info, or join the beta or poke around the web (for now).
Keep an eye on and learn more about VVOL’s at VMworld 2014 as well as in various other venues.
IMHO VVOL’s are or will be in your future, however the question will be is there going to be a back to the future moment for some of you with VVOL’s?
Also what VVOL questions, comments and concerns are in your future and on your mind?
And remember to check out the second part to this series 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
