Storage Quality of Service (QoS) In Windows Server 2012 R2

In Windows Server 2012 R2 Hyper-V we have the ability to set  quality-of-service (QoS) options for a virtual machine at the virtual disk level. There is no QoS (yet) for shared VHDX, so it’s a per individual VM, per virtual hard disk associated with that virtual machine setting for now.

What can we do?

  • Limit – Maximum IOPS
  • Reserve – Minimum IOPS threshold alerts
  • Measure – New Storage attributes in VM Metrics

image

Limit

Storage QoS allows you to specify maximum input/output operations per second (IOPS) value for a virtual hard disk associated with virtual machine. This puts a limit on what a virtual disk can use. This means that one or more VMs cannot steal away all IOPS from the others (perhaps even belonging to separate customers). So this is an automatic hard cap.

Reserve

We can also set a minimum IOPS value. This is often referred to as the reserve. This is not hard minimum. Here’s a worth of warning, unless you hopelessly overprovision your physical storage capabilities (ruling out disk, controller issues, HBA problems & other risks that impact deliverable IOPS) and dedicate it to a single Hyper-V host with a single VM (ruling out the unknown) you cannot ever guarantee IOPS. It’s best effort. It might fail but than events will alert you that things are going south. We will be notified when the IOPS to a specified virtual hard disk is below that reserve you specified?that is needed for its optimal performance.  We’ll talk more about this in another blog post.

Measure

The virtual machine metrics infrastructure have been extended with storage related attributes so we can monitor the performance (and so charge or show back).  To do this they use what they call “normalized IOPS” where every 8 K of data is counted as one I/O. This is how the values are measured and set. So it’s just for that purpose alone.

  • One 4K I/O = 1 Normalized I/O
  • One 8K I/O = 1 Normalized I/O
  • One 10K I/O = 2 Normalized I/Os
  • One 16K I/O = 2 Normalized I/Os
  • One 20K I/O = 3 Normalized I/Os

A Little Scenario

We take IO Meter and we put it inside 2 virtual machines. These virtual machine reside on a Hyper-V Cluster that is leveraging shared storage on a SAN. Let’s say you have a VM that requires 45000 IOPS at times and as long as it can get that when needed all is well.

All is well until one day a project that goes into production has not been designed/written with storage IOPS (real needs & effects) in mind. So while they have no issue the application behaves as a scrounging hog eating a humongous size of the IOPS the storage can deliver.

Now, you do some investigation (pays to be buddies with a good developer and own the entire infrastructure stack) and notice that they don’t need those IOPS as they:

  1. Can do more intelligent data retrieval slashing IOPS in half.
  2. They waste 75% of the time in several suboptimal algorithms for sorting & parsing data anyway.
  3. The number of users isn’t that high and the impact of reducing storage IOPS is non existent due to (2).

All valid excuses to take the IOPS away …You think let’s ask the PM to deal with this. They might, they might not, and if they do it might take time. But while that remains to be seen, you have a critical solution that serves many customers who’re losing real money because of that drop in IOPS has become an issue with the application. So what’s the easiest thing to do? Cap that IOPS hog! Here the video on how you deal with this on Vimeo: http://vimeo.com/82728497

image

Now let’s enable QoS as in the screenshot below. We give it a best effort 2000 IOPS minimum and a hard maximum of 3000 IOPS.

image

The moment you click “Apply” it kicks in! You can do this live, not service interruption/ system downtime is needed.

image

I actually have a hard cap of 50000 on the business critical app as well just to make sure the other VMs don’t get starved. Remember that minimum is a soft reserve. You get warned but it can’t give what potentially isn’t available. After all, as always, it’s technology, not magic.

In a next blog we’ll discuss QoS a bit more and what’s in play with storage IO management in Hyper-V, what the limitations are and as such we get an idea what Microsoft should pay attention to vNext.

Remarks

Well doing this for a 24 node Hyper-V cluster with 500 VMs could be a bit of challenge.

Join me for aTechNet Live Meeting: Hyper-V Storage Efficiencies & Optimizations in Windows Server 2012 R2

So you have been  playing with or down right seriously testing Windows Server 2012 and perhaps even Windows Server 2012 R2. That’s great. Many of you might have it running in production or are working on that. That’s even better.

Windows Server 2012 has brought us unseen capabilities & performance enhancements that make it a future proof fundament for many versions to come and it is ready for the ever accelerating pace of hardware improvements. R2 has fine tuned some points and added improvements that are stepping stones to better today and even greater in vNext. I’d like to invite you to a free TechNet Live Meeting on Hyper-V Storage Efficiencies & Optimizations in Windows Server 2012 R2 and look at some of these capabilities with me.

image

As a virtualization guy two subjects are very dear to me and that is networking & storage, and this event is about a subset of the storage improvements. You might have heard about ODX and UNMAP but you have not had the change to play with it. You have read about the tremendous scalability of the IOPS in a VM and about large sector support for the next generation of hard disks drives. Well some of these we’ll demonstrate (ODX, UNMAP, Dynamically expanding VHDX performance) if the demo gods are with us. Others we’ll discuss so you’ll know where this comes into play and how you’ll benefit from them even without realizing you do. So without further delay register for the free TechNet Live Event here.

Using RAMDisk To Test Windows Server 2012 Network Performance

I’m testing & playing different Windows Server 2012 & Hyper-V networking scenarios with 10Gbps, Multichannel, RDAM, Converged networking etc. Partially this is to find out what works best for us in regards to speed, reliability, complexity, supportability and cost.

Basically you have for basic resources in IT around which the eternal struggle for the prefect balance finds place. These are:

  • CPU
  • Memory
  • Networking
  • Storage

We need both the correct balance in capabilities, capacities and speed for these in well designed system. For many years now, but especially the last 2 years it very save to say that, while the sky is the limit, it’s become ever easier and cheaper to get what we need when it comes to CPU, Memory. These have become very powerful, fast and affordable relative to the entire cost of a solution.

Networking in the 10Gbps era is also showing it’s potential in quantity (bandwidth), speed (latency) and cost (well it’s getting there) without reducing the CPU or memory to trash thanks to a bunch of modern off load technologies. And basically in this case it’s these qualities we want to put to the test.

The most trouble some resource has been storage and it has been for quite a while. While SSD do wonders for many applications the balance between speed, capacity & cost isn’t that sweet as for our other resources.

In some environments were I’m active they have a need for both capacity and IOPS and as such they are in luck as next to caching a lot of spindles still equate to more IOPS. For testing the boundaries of one resource one needs to make sure non of the others hit theirs. That’s not easy as for performance testing can’t always have a truck load of spindles on a modern high speed SAN available.

RAMDisk to ease the IOPS bottleneck

To see how well the 10Gbps cards with and without Teaming, Multichannel, RDMA are behaving and what these configuration are capable of I wanted to take as much of the disk IOPS bottle neck out of the equation as possible. Apart from buying a Violin system capable of doing +1 million IOPS, which isn’t going to happen for some lab work, you can perhaps get the best possible IOPS by combining some local SSD and RAMDisk. RAMDisk is spare memory used as a virtual disk. It’s very fast and cost effective per IOPS. But capacity wise it’s not the worlds best, let alone most cost effective solution.

image

I’m using free RAMDisk software provided by StarWind. I chose this as they allow for large sized RAMDisks. I’m using the ones of 54GB right now to speed test copying fixed sized VHDX files. It install flawlessly on Windows Server 2012 and it hasn’t caused me any issues. Throw in some SSDs on the servers for where you need persistence and you’re in business for some very nice lab work.

clip_image001

You also need to be aware it doesn’t persist data when you reboot the system or lose power. This is not an issue if all we are doing is speed testing as we don’t care. Otherwise you’ll need to find a workaround and realize those ‘”flush the data to persistent storage” isn’t full proof or super fast, the SSDs do help here.

You have to register but the good news is that they don’t spam you to death at all, which I find cool. As said the tool is free, works with Windows Server 2012 and allows for larger RAMDisks where other free ones are often way to limited in size.

It has allowed me to do some really nice testing. Perhaps you want to check this out as well. WARNING: The below picture is a lab setup … I’m not a magician and it’s not the kind of IOPS I have all over the datacenters with 4 Cheapo SATA disks I touched my special magic pixie dust.

image

With #WinServ 2012 storage costs/performance/capacity are the only thing limiting you  http://twitter.yfrog.com/mnuo9fp #SMB3.0 #Multichannel

Some quick tests with a 52GB NTFS RAMDisk formatted with a 64K NTFS Allocation unit size.

image image

I also tested with another free tool from SoftPerfect ® RAM Disk FREE. It performs well but I don’t get to see the RAMDisk in the Windows Disk Management GUI, at least not on Windows Server 2012. I have not tested with W2K8R2.

NTFS Allocation unit size 4K NTFS Allocation unit size 64K
image image

Hyper-V Guest Storage Performance: Above & Beyond 1 Million IOPS

Making a million IOPS possible in a Windows Server 2012 Hyper-V VM

A lot of you will have seen the demos of a Hyper-V guest with VHDX disks running on Windows Server 2012 doing a million apps, if you haven’t yet, take a look here. While some quickly dismissed this as “irrelevant boasting” without real life relevance, I respectfully disagree. This is smart future proofing by Microsoft and provides a hypervisor ready for the future hardware capabilities and capable to handle the most demanding workloads today & in the years to come. Sure such a demo is under lab/ideal conditions and does not reflect the majority of real life environments but it’s nice to see what a hypervisor is capable of if and when you might need it. Remember there was a day that 4GB was a lot of RAM and 2TB sounded gigantic. Also remember that some people have larger needs than others.  Until Windows Server 2008 R2 you had some limitations in storage IO performance that would not allow for a million IOPS. These had to be addressed or all the efforts with regards to capabilities and performance in regard to storage, CPU, networking and memory would just hit those particular bottlenecks. So it is addressing real needs and indeed also smart future proofing.

Capabilities of virtual machine storage IO throughput in Windows 2008 R2

The capabilities listed below dictate the IO capabilities in virtual machines running on Windows Server 2008 R2 Hyper-V:

  1. Limited to one IO channel per virtual SCSI Controller
  2. 256 queue depth/SCSI for all devices attached to that SCSI adapter.
  3. There was one fixed vCPU (0) dedicated to handling IO.

image

The picture above illustrates these limits. You see two virtual SCSI Controllers each having 2 VHD virtual disks attached. Each disk shares the one channel the controller it is attached to has.

These limits could become a bottle neck but that was never was too big of a problem with a maximum of 4 vCPUs in Windows 2008 R2 Hyper-V. If needed for performance we might have attached VHDs to different virtual SCSI controllers for the best possible performance in Windows Server 2008 R2 Hyper-V .

With 64 vCPUs and ever more demanding workloads these limitations would become a (serious) issue so this needed to be addressed. If not, despite all other efforts in regards to the 4 big resources (memory, storage and network) in Windows 2012, this would remain the limiting factor of IOPS inside a virtual machine on Windows 2012.

Windows Server 2012 improvements to virtual machine storage IO scaling

image

The picture above illustrates the improvements in Windows Server 2012 Hyper-V IO Scaling:

  1. There is now 1 channel per 16 vCPUs, per virtual SCSI device, per controller. So that means you have 4 channels, per VHDX attached to a virtual SCSI Controller when you have 64 vCPUs in the virtual machine. Compared to before, this is a significant improvement and a much needed one with the 64 vCPUs capability there is now.
  2. IO interrupt handling is now distributed amongst all vCPUs and this process is NUMA aware. This is a huge improvement!
  3. There is now a 256 queue depth/device attached to a specific SCSI adapter. That’s another big improvement.

That people, is how you get a virtual machine to handle a million IOPS. Nice! The questions or doubts whether Hyper-V can deliver the capacity, throughput & performance have been wiped of the table, yes also for virtual storage IOPS. You can now go straight to how it will address your business needs. From my experience it does so brilliantly and very cost effectively. Life might not be perfect but it is very good Smile