Yellow Bricks

by Duncan Epping

virtual san

Re: VMware VSAN VS the simplicity of hyperconvergence

· ·

I was reading this awesome article by “the other” Scott Lowe. (That is how he calls himself on twitter.) I really enjoyed the article and think it is a pretty fair write-up. Although I’m not sure I really agree with some of the statements or conclusions drawn. Again, do not get me wrong… I really like the article and effort Scott has put in, and I hope everyone takes the time to read it!

A couple of things I want to comment on:

VMware VSAN VS the simplicity of hyperconvergence

I guess I should start with the title… Just like for companies like SimpliVity (Hey guys congrats on winning the well deserved award for best converged solution) and Nutanix their software is the enabler or their hyper-converged solution. Virtual SAN could be that, if you buy a certain type of hardware of course that is.

Hyper-converged infrastructure takes an appliance-based approach to convergence using, in general, commodity x86-based hardware and internal storage rather than traditional storage array architectures. Hyper-converged appliances are purpose-built hardware devices.

Keyword in this sentence if you ask me is “purpose-built”. In most cases there is nothing purpose-built about the hardware. (Except for SimpliVity as they use a purpose built component for deduplication.) In May of 2011 I wrote about these HPC Servers that SuperMicro was selling and how they could be a nice platform for virtualization, I even ask in my article which company would be the first to start using these in a different way. Funny, as I didn’t know back then that Nutanix was planning on leveraging these which was something I found out in August of 2011. The servers used by most of the Hyper-converged players today those HPC servers and are very much generic hardware devices. The magic is not the hardware being used, the magic is the software if you ask me and I am guessing vendors like Nutanix will agree on me that.

Due to its VMware-centric nature and that fact that VSAN doesn’t present typical storage constructs, such as LUNs and volumes, some describe it as a VMDK storage server.

Not sure I agree with this statement. What I personally actually like about VSAN is that it does present a “typical storage construct” namely a (Virtual SAN) data store. From a UI point of view it just looks like a regular datastore. When you deploy a virtual machine the only difference is that you will be picking a VM Storage Policy on top of that, other than that it is just business as usual. For users, nothing new or confusing about it!

As is the case in some hybrid storage systems, VSAN can accelerate the I/O operations destined for the hard disk tier, providing many of the benefits of flash storage without all of the costs. This kind of configuration is particularly well-suited for VDI scenarios with a high degree of duplication among virtual machines where the caching layer can provide maximum benefit. Further, in organizations that run many virtual machines with the same operating system, this breakdown can achieve similar performance goals. However, in organizations in which there isn’t much benefit from cached data — highly heterogeneous, very mixed workloads — the overall benefit would be much less.

VSAN can accelerate ANY type of I/O if you ask me. It has a write buffer and a read cache. Depending on the size of your working set (active data), the size of the cache and the type of policy used you should always benefit regardless of the type of workload used. From a writing perspective as mentioned it will always go to the buffer, but from a read perspective your working set should be in cache. Of course there are always types of workloads where this will not apply but for the majority it should.

VSAN is very much a “build your own” approach to the storage layer and will, theoretically, work with any hardware on VMware Hardware Compatibility list. However, not every hardware combination is tested and validated. This will be one of the primary drawbacks to VSAN…

This is not entirely true. VMware is working on a program called Virtual SAN ready nodes. These Virtual SAN ready nodes will be pre-configured, certified and tested configurations which are optimized for things like performance / capacity etc. I haven’t seen the final list yet, but I can imagine certain vendors like for instance Dell and HP will want to list specific types of servers with an X number of Disks and a specific SSD types to ensure optimal user experience. So although VSAN is indeed a “bring your own hardware” solution, but I think that is the great thing about VSAN… you have the flexibility to use the hardware you want to use. No need to change your operational procedures because you are introducing a new type of hardware, just use what you are familiar with.

PS: I want to point out there are some technical inaccuracies in Scott’s post. I’ve pointed these out and am guessing they will be corrected soon.

VSAN VDI Benchmarking and Beta refresh!

· ·

I was reading this blog post on VSAN VDI Benchmarking today on Vroom, the VMware Performance blog. You see a lot of people doing synthetic tests (max iops with sequential reads) on all sorts of storage devices, but lately more and more vendors are doing these more “real world performance tests”. While reading this article about VDI benchmarking, and I suggest you check out all parts (part 1, part 2, part 3), there was one thing that stood out to me and that was the comparison between VSAN and an All Flash Array.

The following quotes show the strength of VSAN if you ask me:

we see that VSAN can consolidate 677 heavy users (VDImark) for 7-node and 767 heavy users for 8-node cluster. When compared to the all flash array, we don’t see more than 5% difference in the user consolidation.

Believe me when I say that 5% is not a lot. If you are actively looking at various solutions, I would highly recommend to include the “overhead costs” to your criteria list as depending on the solution chosen this could make a substantial difference. I have seen other solutions requiring a lot more resources. But what about response time, cause that is where the typical All Flash Array shines… ultra low latency, how about VSAN?

Similar to the user consolidation, the response time of Group-A operations in VSAN is similar to what we saw with the all flash array.

Both very interesting results if you ask me. Especially the < 5% in user consolidation is what stood out to me the most! Once again, for more details on these tests read the VDI Benchmarking blog part 1, part 2, part 3!

Beta Refresh

For those who are testing VSAN, there is a BETA refresh available as of today. This release has a fix for the AHCI driver issue… and it increases the disk group limit from 6 to 7. From a disk group perspective this will  come in handy as many servers have 8, 16 or 24 disk slots allowing you to do 7HHDs + 1 SSD per group. Also some additional RVC commands have been added in the storage policy space, I am sure they will come in handy!

Nice side affect of the number of HDDs going up is increase in max capacity:

(8 hosts * (5 diskgroups * 7 HDDs)) * Size of HDD = Total capacity

With 2 TB disks this would result in:

(8 * (5 * 7)) * 2TB = 560TB

Now keep on testing with VSAN and don’t forget to report feedback through the community forums or your VMware rep.

Virtual SAN and maintenance windows…

· ·

After writing the article that “4 is the minimum number of hosts for VSAN” I received a lot of questions via email and on twitter etc about the cost associated with it and if this was a must. Let me start with saying that I wrote this article to get people thinking about Sizing their VSAN environment. When it comes to it, Virtual SAN and maintenance windows can be a difficult topic.

I guess there are a couple of things to consider here. Even in a regular storage environment you typically do upgrades in a rolling fashion meaning that if you have two controllers one will be upgraded while they other handles IO. In that case you are also at risk. The thing is though, as a virtualization administrator you have a bit more flexibility, and you expect certain features to work as expected like for instance vSphere HA. You need to ask yourself what is the level of risk I am willing to take, the level of risk I can take?

When it comes to placing a host in to Maintenance Mode, from a VSAN point of view you will need to ask yourself:

  • Do I want to move data from one host to another to maintain availability levels?
  • Do I just want to ensure data accessibility and take the risk of potential downtime during maintenance?

I guess there is something to say for either. When you move data from one node to another, to maintain availability levels, your “maintenance window” could be stretched extremely long. As you would potentially be copying TBs over the network from host to host it could take hours to complete. If your ESXi upgrade including a host reboot takes about 20 minutes, is it acceptable to wait for hours for the data to be migrated? Or do you take the risk, inform your users about the potential downtime, and as such do the maintenance with a higher risk but complete it in minutes rather than hours? After those 20 minutes VSAN would sync up again automatically, so no data loss etc.

It is impossible for me to give you advice on this one to be honest, I would highly recommend to also sit down with your storage team. Look at what their current procedures are today, what they have included in their SLA to the business (if there is one), and how they handle upgrades / periodic maintenance.

 

VSAN performance: many SAS low capacity VS some SATA high capacity?

· ·

Something that I have seen popping up multiple times now is the discussion around VSAN and spindles for performance. Someone mentioned on the community forums they were going to buy 20 x 600GB SAS drives for their VSAN environment for each of their 3 hosts. These were 10K SAS disks, which obviously outperform the 7200 RPM SATA drives. I figured I would do some math first:

  • Server with 20 x 600GB 10K SAS = $9,369.99 per host
  • Server with 3 x 4TB Nearline SAS = $4,026.91 per host

So that is about a 4300 dollar difference. Note that I did not spec out the full server, so it was a base model without any additional memory etc, just to illustrate the Perf vs Capacity point. Now as mentioned, of course the 20 spindles would deliver additional performance. Because after all you have additional spindles and better performing spindles. So lets do the math on that one taking some average numbers in to account:

  • 20 x 10K RPM SAS with 140 IOps each = 2800 IOps
  • 3 x 7200 RPM NL-SAS with 80 IOps each = 240 IOps

That is a whopping 2560 IOps difference in total. That does sound like an awe full lot doesn’t it? To  a certain extent it is a lot, but will it really matter in the end? Well the only correct answer here is: it depends.

I mean, if we were talking about a regular RAID based storage system it would be clear straight away… the 20 disks would win for sure. However we are talking VSAN here and VSAN heavily leans on SSD for performance. Meaning that each diskgroup is fronted by an SSD and that SSD is used for both Read Caching (70% of capacity) and write buffering (30%) of capacity. Illustrated in the diagram below.

The real question is what is your expected IO pattern? Will most IO come from read cache? Do you expect a high data change rate and as such could de-staging be problematic when backed by just 3 spindles? Then on top of that, how and when will data be de-staged? I mean, if data sits in write buffer for a while it could be the data changes 3 or 4 times before being destaged, preventing the need to hit the slow spindles. It all depends on your workload, your IO pattern, your particular use case. Looking at the difference in price, I guess it makes sense to ask yourself the question what $ 4300 could buy you?

Well for instance 3 x 400GB Intel S3700 capable of delivering 75k read IOps and 35k write IOps (~800 dollars per SSD). That is extra, as with the server with 20 disks you would also still need to buy SSD and as the rule of thumb is roughly 10% of your disk capacity you can see what either the savings are or the performance benefits could be. In other words, you can double up on the cache without any additional costs compared to the 20-disk server. I guess personally I would try to balance it a bit, I would go for higher capacity drives but probably not all the way up to 4TB. I guess it also depends on the server type you are buying, will they have 2.5″ drive slots or 3.5″? How many drive slots will you have and how many disks will you need to hit the capacity requirements? Are there any other requirements? As this particular user mentioned for instance he expected extremely high sustained IOs and potentially full backups daily, as you can imagine that could impact the number of spindles desired/required to meet performance expectations.

The question remains, what should you do? To be fair, I cannot answer that question for you… I just wanted to show that these are all things one should think about before buying hardware.

Just a nice little fact, today a VSAN host can have 5 Disk Groups with 7 disks, so 35 disks in total. With 32 hosts in a cluster that is 1120 disks… That is some nice capacity right with 4TB disks that are available today.

I also want to point out that a tool is being developed as we speak which will help you making certain decisions around hardware, cache sizing etc. Hopefully more news on that soon,

** Update, as of 26/11/2013 the VSAN Beta Refresh allows for 7 disks in a disk group… **

 

VSAN and Network IO Control / VDS part 2

· ·

About a week ago I wrote this article about VSAN and Network IO Control. I originally wrote a longer article that contained more options for configuring the network part but decided to leave a section out of it for simplicity sake. I figured as more questions would come I would publish the rest of the content I developed. I guess now is the time to do so.

In the configuration described below we will have two 10GbE uplinks teamed (often referred to as “etherchannel” or “link aggregation”). Due to the physical switch capabilities the configuration of the virtual layer will be extremely simple. We will take the following recommended minimum bandwidth requirements in to consideration for this scenario:

  • Management Network –> 1GbE
  • vMotion VMkernel –> 5GbE
  • Virtual Machine PG –> 2GbE
  • Virtual SAN VMkernel interface –> 10GbE

When the physical uplinks are teamed (Multi-Chassis Link Aggregation) the Distributed Switch load balancing mechanism is required to be configured as:

  1. IP-Hash
    or
  2. LACP

It is required to configure all portgroups and VMkernel interfaces on the same Distributed Switch using either LACP or IP-Hash depending on the type physical switch used. Please note all uplinks should be part of the same etherchannel / LAG. Do not try to create anything fancy here as a physically and virtually incorrectly configured team can and probably will lead to more down time!

  • Management Network VMkernel interface = LACP / IP-Hash
  • vMotion VMkernel interface = LACP / IP-Hash
  • Virtual Machine Portgroup = LACP / IP-Hash
  • Virtual SAN VMkernel interface = LACP / IP-Hash

As various traffic types will share the same uplinks we also want to make sure that no traffic type can push out other types of traffic during times of contention, for that we will use the Network IO Control shares mechanism.

We will work under the assumption that only have 1 physical port is available and all traffic types share the same physical port for this exercise. Taking a worst case scenario approach in to consideration will guarantee performance even in a failure scenario. By taking this approach we can ensure that Virtual SAN always has 50% of the bandwidth to its disposal while leaving the remaining traffic types with sufficient bandwidth to avoid a potential self-inflicted DoS. When both Uplinks are available this will equate to 10GbE, when only one uplink is available the bandwidth is also cut in half; 5GbE. It is recommended to configure shares for the traffic types as follows:

 

Traffic Type Shares Limit
Management Network  20 n/a
vMotion VMkernel Interface  50 n/a
Virtual Machine Portgroup  30 n/a
Virtual SAN VMkernel Interface  100 n/a

 

The following diagram depicts this configuration scenario.