Blog

In-VMware Host Caching – Datrium’s Appliance Specific Host Cache Versus Virtunet’s Host Cache for Any Storage.

Both Datrium and us differentiate from the rest of the storage appliance vendors in that both of us cache data to cache media in the VMware host instead of the storage appliance, which is the traditional approach.

But the similarities between Datrium's and our ESXi host cache end there. The top three differences between Datrium DVX DiESL and our VirtuCache are:

  1. Our host side caching accelerates any storage appliance, Datrium’s works only for their own appliance;

  2. We cache writes and reads to in-VMware host cache media, Datrium caches only reads;

  3. We can cache to host RAM and SSD, Datrium can cache to SSD only.

So if you are a Datrium customer and if you are looking to apply the concept of host side caching that you have come to like from Datrium, to your other storage appliances, then you could do so with VirtuCache. We will accelerate the performance of any SAN based storage appliance no matter how old or slow, by caching all storage IO (reads and writes) to any in-host SSD (or host RAM).

We believe that caching data to in-VMware host high-speed media (Flash / RAM) is a better option than caching in the storage appliance because the cache media in our case is closer to the CPU that consumes ‘hot’ data, and hence the same high-speed media performs better in the VMware host than in the appliance. This principle applies equally to both reads and writes and hence we cache both reads and writes to in-host SSD (or RAM). Whereas Datrium decided to cache only reads to ESXi host SSD. The writes in the case of Datrium are cached to their appliance NVRAM, much like a traditional appliance. Datrium founder has these arguments to make in favor of caching writes to the appliance and NOT to in-VMware host cache media, which we patently disagree with. Our counterpoints to Datrium are on this link.

Also, if you use host RAM to cache with VirtuCache, VirtuCache powered infrastructure will be higher performing than any storage array or hyper-converged appliance (including Datrium) because no storage appliance or HCI hardware is capable of using large amounts of RAM in the storage IO path. And RAM is the highest performing storage media there is.

Improving the performance of Dell Compellent SAN for VMware VMs

VirtuCache is software that improves the performance of Dell Compellent appliances without requiring you to upgrade the appliance or the SAN network. The performance improvement you will get from your Compellent appliance will rival an upgrade to an all-flash array.

Compellent appliances were the workhorses of the enterprise storage market a few years ago. They were cost effective at high capacities. The only drawback was that they are slower since they are primarily hard drive based, and when connected to VMware they exhibit all the 'IO blender' symptoms resulting in high VM level storage latencies.

Reducing Write Latencies in CEPH Storage

CEPH is a popular open source storage software. However its write latencies are high. VirtuCache caches CEPH volumes to in-host SSDs and by doing so reduces VM level latencies considerably.

Improving VDI Performance at Fairbanks Sewer and Water

Fairbanks Sewer and Water (FSW) wanted to improve the performance of their server VMs (especially their server VMs running SCADA) and Horizon View virtual desktop VMs. Their virtual desktop VMs were exhibiting all the classic symptoms of storage related issues – cursor freezes, long boot times, long VM provisioning times, jittery audio/video.

Improving the performance of Equallogic SAN for VMware VMs

VirtuCache is software that improves the performance of Equallogic appliances without requiring you to upgrade the appliance or the SAN network. The performance improvement you will get from your Equallogic appliance will rival an upgrade to an all-flash array.

Equallogic appliances were the workhorses of the enterprise storage market a few years ago. They were cost effective at high capacities. The only drawback was that they are slower since they are primarily hard drive based, and when connected to VMware they exhibit all the 'IO blender' symptoms resulting in high VM level storage latencies.

CEPH Storage with Server Side Caching for Genomics

As it relates to storage, genome sequencing workflow has two requirements.

  1. Need for cheap ($/GB) Petabyte scale storage.

  2. Need for faster processing of Genome files under analysis , many of which are a few hundred GB in size.

Reducing Build Times for DevOps

ServiceNow's Itapp Dev/Ops team wanted to improve storage performance from their existing HP 3PAR storage appliance and iSCSI storage network without requiring a hardware refresh.

VirtuCache Deployment: Virtucache was installed on 3 ESXi hosts caching to 1.6TB PM1725 PCIE flash cards. In our tests the PM1725 SSD did 250MBps at 1ms VM level latencies.

VirtuCache was configured to cache both reads and writes for all VMs (Write-Back caching). Writes were replicated to another SSD on another host (caching policy of 'Write Back One Replica'). All caching and replication related operations in VirtuCache are automatic. Write replication is done to prevent data loss in case of host failure. If a host were to fail, then VirtuCache immediately syncs the SAN from backup copy of writes that are on another host.

Benefits: Using VirtuCache, ServiceNow was successfully able to reduce code compile times to a third of what they were experiencing before.

A Counter Intuitive Approach to Solve the High Capacity, Low Latency Requirements for Video Storage

By not using dedupe, compression, or RAID, using slow HDDs in centralized storage, and moving SSDs to compute hosts, we arrived at low price per capacity and performance for video storage.

Here are unique requirements of video storage, some are obvious and others not so much, that inspired us to put together a different architecture than the conventional storage OEM design.

Reducing latencies in vGPU assisted VDI

VirtuCache is installed in VMware vSphere kernel. It then automatically caches frequently and recently used data from any backend storage to any high speed media (RAM/SSD) in the VMware host. By bringing large amounts of 'hot' data closer to the VMware host GPU and CPU, VirtuCache improves the performance of all applications running within VMs including GPU assisted operations.

Reducing write latencies in a VMware stretched SAN cluster

There are only a few applications, financial trading software being one example, that require very low latencies, lower even than what’s possible with an all-flash array (AFA). VirtuCache caching to in-host RAM results in lower VM latencies than an AFA. This is because RAM latencies are an order of magnitude lower than NVME SSDs, and in the case of VirtuCache the cache media (RAM) is connected to the host CPU through a high speed memory bus, versus in the case of an AFA where the NVME SSDs are behind the network and storage controller.

High write latencies in a stretched SAN cluster

Tourbillon Capital Partner is a hedge fund. They run proprietary trading software within VMware VMs that requires under 5 millisecond latencies. Tourbillon has two VMware clusters with a few nodes in each cluster. Each ESXi cluster is connected to a Pure Storage SAN array. Both ESXi clusters are in different datacenters, but connected to each other over a 10gbps WAN link. A stretched SAN cluster across these two ESXi clusters is created using Datacore software. Simply speaking what the Datacore stretched cluster accomplishes is that all VM writes are synchronously written to both Pure Storage arrays - the array that’s in the same datacenter as the VM, and also to the remote Pure Storage array. In this way Tourbillon’s IT folks assure themselves of seconds-to-minutes RPO and RTO time in case of a datacenter outage.

The problem with this architecture was that sometimes VM write latencies exceeded the 10ms ceiling that was required by their trading application. This was because writes had to go over their WAN link between datacenters. Even though the WAN link was 10gbps, it would spike to > 5ms latencies from time to time. Typically, the standard deviation for latencies in a long distance WAN link is quite a bit more than in shorter LAN links of the same speed.

Caching VM writes to in-host RAM reduced write latencies considerably

Tourbillon deployed VirtuCache to fix this issue. VirtuCache was installed in every host, in both ESXi clusters. It was configured to cache reads and writes to in-host RAM, with the write cache replicated to another host in the same datacenter, which in turn resulted in sub-millisecond VM write latencies at all times. In this way, VirtuCache effectively papered over the underlying high WAN latencies, when large volume of writes were transmitted from VMs.

VirtuCache reducing write latencies in a stretched SAN cluster
Page 3 of 612345...Last »