VMware's PSA is awash in abbreviations and options

I am often questioned during my Storage for Virtual Environments seminar presentations about VMware’s Pluggable Storage Architecture (PSA). This system is fairly straightforward and concept: VMware provides native multipathing support for a variety of storage arrays, and allows third parties to substitute their own plug-ins at various points in the stack. But the profusion of acronyms and third-party options makes it difficult for end-users to figure out what is going on. In an effort to help, I present here another entry in my “VMware storage features in plain English” series.

Note: I am more of a storage guy than a virtualization expert. I consider myself one of those end-users who have had trouble figuring out what’s going on with PSA specifically, in VMware storage features in general. I welcome comments and suggestions for corrections or improvements to this and all of my articles. Thanks for your help!

Introducing Pluggable Storage Architecture (PSA)

Pluggable storage architecture was one of the major enhancements introduced in vSphere 4. Functionally similar to Microsoft’s MPIO stack for Windows, PSA includes native multipathing support and allows vendors to plug in their own advanced features.

I find the VMware diagram confusing. Is mine more or less accurate and readable?

The ESX kernel (VMkernel) walks down through three layers when communicating with storage:

1. In the top layer, VMware native NMP or third-party MPP software decides which SATP to use, or whether to use the native interface. MASK_PATH also operates at this layer.
2. The SATP layer includes native generic path selection (active/active, active/passive), standard ALUA, as well as allowing third-party plugins (SATP) to override its behavior. The SATP monitors these paths, reports changes, and initiates fail-over on the array as needed.
3. At the PSP layer, software decides which physical channel to use for I/O requests.

There are three types of PSA plugins for vSphere 4:

1. Storage Array Type Plug-In (SATP)
2. Path Selection Plug-in (PSP)
3. A complete third-party multipathing software stack (MPP)

As is the case with VAAI, VMware includes a number of third-party plug-ins in the ESXi install. Users can simply activate many of these according to their needs, though some require additional fees and licensing.

Storage Array Type Plug-in (SATP) List

Storage Array Type Plug-Ins (SATPs) to the VMware Pluggable Storage Architecture multipathing solution for the specific characteristics of the storage array. This is very important, since each storage array design differs substantially in detail and support, especially when it comes to load-balancing and failover between controllers, ports, and paths. So it is critical for VMware to have developed a standard interface to communicate with arrays.

SATPs allow load balancing across multiple paths, intelligent path selection, and over troubled conditions such as “chatter”, when passed rapidly fail back and forth between controllers.

The SATP has critical tasks to perform in the PSA stack:

1. Decide which method of communication to use with the storage (PSA or native)
2. Monitor the health of the physical I/O channels or paths
3. Report any changes in the state of the paths up the stack
4. Perform actions required to fail over storage between controllers on the array

VMware vSphere includes a variety of generic plugins for storage arrays. I’ve identified the following:

• VMW_SATP_LOCAL – Local SATP for direct-attached devices
• VMW_SATP_DEFAULT_AA – Generic for active/active arrays
• VMW_SATP_DEFAULT_AP – Generic for active/passive arrays
• VMW_SATP_ALUA – Asymmetric Logical Unit Access-compliant arrays

Although I have sometimes seen other SATP plug-ins mentioned, the following plug-ins are all that are listed in the VMware ESX Hardware Compatibility List.

• VMW_SATP_LSI – LSI/NetApp arrays from Dell, HDS, IBM, Oracle, SGI
• VMW_SATP_SVC – IBM SVC-based systems (SVC, V7000, Actifio)
• VMW_SATP_CX – EMC/Dell CLARiiON  and Celerra (also VMW_SATP_ALUA_CX)
• VMW_SATP_SYMM – EMC Symmetrix DMX-3/DMX-4/VMAX, Invista
• VMW_SATP_INV – EMC Invista and VPLEX
• VMW_SATP_EQL – Dell EqualLogic systems

EMC PowerPath and HDS HDLM also support a variety of storage arrays, but I would classify these as full MPP replacements for PSA, rather than SATP plug-ins.

You can see which SATP plug-ins are available using the following esxcli command:

esxcli nmp satp list

Path selection plug-in (PSP) List

In contrast to the diversity of VAAI and SATP plug-ins, the universe of path selection plug-ins is fairly small. Most storage arrays are supported with either Most Recently Used (MRU) or Fixed path selection approaches. Many also support Round Robin (RR) path selection. The only vendor with a specific PSP that is not also part of a full MPP (like EMC PowerPath or HDS HDLM) is Dell, which offers a special routed path selection plug-in for the EqualLogic iSCSI arrays.

• VMW_PSP_MRU – Most-Recently Used (MRU) – Supports hundreds of storage arrays
• VMW_PSP_FIXED – Fixed – Supports hundreds of storage arrays
• VMW_PSP_RR – Round-Robin – Supports dozens of storage arrays
• DELL_PSP_EQL_ROUTED – Dell EqualLogic iSCSI arrays

As mentioned, EMC PowerPath also offers path selection as a plug-in in addition to the full MPP stack. Many other vendors offer unique path selection plug-ins, over 100 in total, but these are not specifically called out in the VMware HCL apart from their existence. I would love to learn more about them, however.

You can see which SATP plug-ins are available using the following esxcli command:

esxcli nmp psp list

Tell Me More About PSA!

As mentioned above, I am by no means an expert in VMware Pluggable Storage Architecture. Rather, I am interested in learning more and passing on this knowledge to others. I welcome your comments and feedback, and especially your corrections to the information presented here. I will try to keep this page updated as new versions of vSphere are introduced and as I learn more about this technology. Thank you for your help and understanding!

Further Reading:

• What’s New in VMware vSphere 4: Storage
• Next-Generation ESX Storage: A Pluggable Core Storage Architecture
• Storage Changes in the VMware vSphere 4 Family
• Pluggable Storage Architecture, exploring the next version of ESX/vCenter
• Vmware vSphere 4.1 PSA (Pluggable Storage Architecture) Understanding
• Explain the Pluggable Storage Architecture (PSA) Layout

© sfoskett for Stephen Foskett, Pack Rat, 2011. | VMware PSP and SATP in Plain English
This post was categorized as Enterprise storage, Everything, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

What is Multipath? And Why?

The good old days: One device, one path

In the beginning, computers connected to peripherals and other computers through a single bus or channel and life was easy. Although one might mistake the names of the dominant printer connection (parallel) for some kind of multipath system when compared to the modem connection (serial), this was not the case. Only the bits traveled in parallel – the logical connection was a simple single path.

Early-90's servers might confuse admins with two SCSI connections to a single device

Then things got complicated. The SCSI protocol allowed for multiple devices in a chain, and even for two different “initiators” (computers or controllers) to interact with these “targets”. Some folks even dual-attached devices to a single computer with multiple controllers.

Why would one device and one computer need more than one connection? It boils down to two factors:

1. Performance – I/O channels have typically been slower than the computer could handle, so multiple channels might be used to increase the amount of data that can flow in and out.
2. Reliability – If one connection failed, the other might still be usable, reducing the risk of an outage.

Late-90's enterprise systems might have four or more paths to a single storage array

Pretty soon, enterprise computer architecture had gotten incredibly complex. I remember connecting a massive HP V-class server to an EMC Symmetrix with eight separate Fibre Channel cables. Each disk “LUN” showed up twice, and we had hundreds of them. We managed all of these virtual storage paths using HP’s PVLinks dynamic multipathing software. We used Veritas DMP and EMC PowerPath to do pretty much the same thing on Solaris and other UNIX systems.

Active/Passive to Active/Active

The earliest path management software provided two incredibly important functions: It figured out which of the SCSI targets it saw were actually different names for the same one, and it allowed the operating system to choose one and fail over to the other in case of an interruption. These were Active/Passive links – no matter how many paths were presented (and Fibre Channel switches sometimes presented eight or more), only one was active at any one time.

Modern systems have abstracted and virtual I/O channels, making path management much more important

But the EMC Symmetrix and similar high-end storage systems changed all this. Symmetrix storage was fully virtualized – the presentation of LUNs to servers was entirely disconnected from the actual disks and RAID sets in the array. This meant the Symmetrix could handle I/O requests across different paths and controllers for the same LUN. EMC and the rest responded with Active/Active path management software, allowing I/O to travel in parallel for the first time.

How is Dual Active Different?

Not everything called Active/Active is created equal. In fact, many supposed Active/Active setups really shouldn’t be called that since they don’t use both paths for all data. Instead, I like to call these Dual Active – both paths are active but with different data.

Consider the differences between the following two solutions:

A true active/active setup uses all paths for all data all the time

A "dual active" setup uses both paths, but each target is directed to one or the other

See the difference? Although the paths are active in both cases, they are not the same. Both approaches have merit, and neither is inherently superior, but they should have different names applied. Even active/passive has its place, since simplicity is often a virtue.

Dual Active Outside Storage

These same concepts apply outside the field of storage and I/O. Many server clustering systems use the same terminology, right down to the misapplication of “active/active” when “dual active” is more appropriate. It’s easy to miss the significance of this difference, but it can make more of an impact in clustering since CPU workloads are harder to balance.

Let me know what you think. If there is interest, I might dive into path management strategies like round robin!

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Multipath: Active/Passive, Dual Active, and Active/Active
This post was categorized as Computer History, Enterprise storage, Everything, Gestalt IT, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

Most important: Please register to be a marrow donor, especially if you might be a match for Nick Glasgow of EMC!

Misc

• The week of May 16 will forever be known as the week Twitter lost control of their eponymous service. There were some great posts, many of which went beyond whining and offered context on why Twitter is so important, but the one that sticks in my head most was a simple statement: “Goodbye People I Never Knew“
• But it wasn’t all bad news related to Twitter. Witness this awesome idea: A Modest Proposal For More Microstructure: Twitter /Locations
• My friend Donavon was featured in Baltimore Business Journal talking about his nifty home servers, and pictured with his humidor!
• A simple pearl of MBA wisdom: Ignore sunk costs
• And if you’re using LinkedIn, here are Five Dos and Don’ts
• The best new product of May? Easily it’s Lego’s new Frank Lloyd Wright models!
• Wilco’s new album was leaked, but rather than freak out they put up a free streaming version. It’s Grrrrrrreat!

Enterprise Computing

• vSphere finally hit, and lots of in-depth information appeared. I loved learning more about vSphere Memory/CPU Hotplug, a topic I knew nothing about! Also, see my Gestalt IT post answering Will the vSphere 4 Upgrade Require Another VMFS Update?
• The Doeswijk Data Model presents a wonderful way of thinking about storage capacity and growth.
• One of my favorite Windows 7/Server 2008 R2 features is the way that VHDs are handled: Learn more in Native VHD Support in Windows 7 and Less Virtual, More Machine – Windows 7 and the magic of Boot to VHD
• New to storage? Brent Ozar (aka The Man) wrote a series on SAN Multipathing. See Part 1: What are Paths? and Part 2: What Multipathing Does
• As everyone following my Twitter or Flickr feed knows, I was in Prague last week at the Sys-Con Cloud Expo. While there, I met up with a few others, including Guy Bunker, Sam Johnston, Roman Stanek, and others. See Time for a debrief!, Review of the Reviews, and the Photo Album

© sfoskett for Stephen Foskett, Pack Rat, 2009. | Back From The Pile: Interesting Links From Mid-May
This post was categorized as Enterprise storage, Personal, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

Hopefully, VMware's three pillars (vCloud, vClient, and VDC-OS) are a little more solid (not to mention closer) than the Three Pillars of Creation in the Eagle Nebula

VMware packed a lot into their 2008 VMworld conference, including an outline of their “three pillars” strategy, focused on vClient, vCloud, and something they are calling the Virtual Datacenter Operating System. While it is debatable if this last item really is an operating system, it’s certainly a major strategic change in messaging.

VDC-OS is divided into four “vServices” (Management, Cloud, Application, and Infrastructure), and one core Infrastructure vService is vStorage. Since my focus is enterprise storage, I thought I would take a moment to examine the current and future status of vStorage.

EMC’s Chad Sakac has taken up the challenge of communicating vStorage to the world, in a post to his blog, a pair of YouTube videos (multipathing, I/O dedupe), and (apparently) a session or two at VMworld. But I’m not sure it’s really entirely clear just what vStorage is and what this means to existing and future VMware storage developments. So let’s dive in and take a look.

vStorage = Storage vService for VMware Infrastructure

Let’s get one thing out of the way immediately: VDC-OS is not a new product – it’s a framework to organize VMware’s existing and future datacenter-targeted products like ESX. The company is sweeping away the current hodgepodge of server product elements and placing them all into a more-organized structure called VDC-OS.

As such, the whole thing is not fully baked at present – there are lots of missing elements, and these point to future products from VMware and others. I applaud the organization, and feel that this is the first really viable next-generation datacenter vision that I have seen. It accurately reflects the current reality of the corporate data center and includes a migration path to take it to a compelling new level.

VMware has a realistic approach to bringing current datacenter elements into the future

As we can see in VMware’s diagram (above), the Virtual Datacenter OS is made up of VMware Infrastructure, with application vServices resting on infrastructure vServices or the cloud. This last bit is the fundamental breakthrough that makes VDC-OS more than just slideware – if it works, applications (virtual appliances) can transparently move from local infrastructure to cloud infrastructure owned and operated by others. It’s transformative, and if they pull it off, this could usher in a new datacenter world.

vStorage is one of the core infrastructure services, along with vCompute and vNetwork. Although it’s not entirely clear at this point, vStorage presumably includes all existing VMware storage technologies as well as the new APIs for multipathing and I/O deduplication highlighted at the show. I envision a future in which vStorage is a set of APIs for everything from I/O to device management, and VMware even includes virtual storage appliances in this umbrella.

vStorage: What’s In It?

At the very least, vStorage includes the following:

• VMFS for shared storage
• Thin Provisioning support in VMware Infrastructure is apparently coming in 2009, but is also apparently incompatible with fault tolerance.
• Linked Clones is another desktop technology coming to VI 2009.
• The Site Recovery Manager API has also become part of vStorage, though this isn’t getting much press.
• VMware Consolidated Backup (VCB) will also apparently be a vStorage API.
• The existing snapshot API will also presumably included.
• The new API for Multipathing covers the old generic native multipathing (NMP) from ESX as well as EMC’s most excellent PowerPath. The latter is presumably an extra-cost option that enables lots of niftiness, as demonstrated by Chad in this video.
• Another new API claims to deduplicate I/O, reducing traffic for certain supported disk operations, as demonstrated in Chad’s second video.

What is in and what is out is still kind of up in the air. But you can see that vStorage includes most of our old favorites (VMFS, SRM, VCB), some desktop elements (thin volumes, linked clones), and some new surprises (PowerPath, I/O dedupe). There is enough meat here to separate this from traditional slideware: VDC-OS has legs!

© sfoskett for Stephen Foskett, Pack Rat, 2008. | What is VMware VDC-OS vStorage?
This post was categorized as Enterprise storage, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.