SMTX OS

Core Software of SmartX HCI

SMTX OS is the core software of the SmartX hyper-converged infrastructure. It has built-in components such as distributed block storage ZBS and native hypervisor ELF, as well as advanced features such as Intra-City MetroX (Active-Active), Asynchronous Replication, Network and Security etc.

Use Native Hypervisor ELF
Use Third-Party Hypervisors
ZBS(Distributed Block Storage)
ELF(Built-in Native Hypervisor)
ESXi(Build with VMware Hypervisor)

Storage

Distributed Block Storage ZBS

The distributed block storage component ZBS is independently developed by SmartX. Its high reliability and high performance capabilities ready for production have been tested with the long-term deployment and operations in the production environments such as finance industry. ZBS can be delivered in a hyper-converged form together with SmartX's native hypervisor ELF, VMware vSphere, etc.

Distributed Block Storage Architecture

Overview

Distributed Architecture

Eliminate the bottleneck of traditional controller architecture, fully make use of the performance of new storage media, and improve system concurrency and elastic expansion capabilities.

Storage Resource Pooling

Integrate system storage resources, realize unified planning / expansion and use-on-demand, improve resource utilization, and reduce operation & maintenance costs.

Software Defined

Fully decoupled from server hardware, not only provides users with more flexible hardware choices, quick integration of the latest hardware technologies to improve the overall system capabilities, but also quickly adapts to new CPU architectures such as ARM to meet users' needs.

Rich Enterprise-Level High Availability Features

Hard-Disk-Level Data Block Checksum

Deal with silent data corruption through data checksum.

Deal with silent data corruption through data checksum.

Node-Level Data Protection and Automatic Data Recovery

Data protection is performed between nodes through a multi-replica mechanism; when a component or a node fails, the available space is automatically used, and concurrent data recovery starts among multiple nodes, ensuring that the data redundancy satisfies the expectations at all times.

Rack-Level Protection

Through rack topology configuration, the replicas are automatically placed on different racks to prevent the cluster from being inaccessible caused by power outage or failure of a single rack further improving the storage reliability.

Snapshot Protection

By generating a snapshot for the storage, the data can be quickly restored to the state at the time when the snapshot was taken, ensuring data security.

Outstanding Performance

Fully Distributed Architecture

The distributed architecture eliminates controller bottlenecks, and the concurrent performance increases linearly with the number of nodes.

Automatic Tiering of Hot and Cold Data

Cold data automatically sinks to HDD, and hot data remains in the cache layer, fully making use of the advantages of SSD hardware and further improving performance.

All-Flash Support

Supports all-flash storage environments to fully meet enterprises' needs for high-performance scenarios.

Proprietary File System Based on Bare Metal Devices

A file system is directly built on bare devices, more suitable for accessing high-performance block storage, avoiding the overhead of the existing Linux file system.

Expand on Demand

Powerful Expansion Capability

Starting with 3 nodes, the capacity can be easily expanded online in a single storage pool, improving the performance significantly.

Flexible Expansion Method

The capacity can be expanded based on components or nodes, as well as by integrating hardware of different brands.

Intelligent Data Migration

The data distribution can be dynamically balanced within the cluster, and the distribution balance can be quickly restored after capacity expansion.

Compute

Native Hypervisor ELF

ELF is a free built-in native hypervisor of SMTX OS. It combines with distributed block storage ZBS, to form a complete hyper-converged virtualization solution. It supports most common virtualization scenarios, with performance greatly optimized in the underlying storage. ELF comes with virtualization network and security, and data protection.

Virtualization Features

Virtual Machine Management

A simple and convenient virtual machine life cycle management. One-click creation, batch operation, and safe confirmation of resource deletion make the management efficient and safe.

Virtual Machine High Availability

Enable the "high availability" function for the key-business virtual machines. When the host fails or the network is isolated, the business will be automatically restored immediately.

Virtual Machine Template

Create virtual machines in batch through templates to reduce repetitive work, deploy applications rapidly, and reduce space usage.

Intelligent Placement and Placement Group

Place virtual machines automatically according to host resources and availability zones. Also set custom placement policies based on placement groups to meet requirements such as license restrictions or application high availability.

Combination with Storage

I/O Localization

Intelligently optimize I/O based on the read and write features of the virtual machines to achieve software-defined performance improvement.

Storage Policies at Virtual Volume Level

Set the provisioning policies and the number of replicas with the granularity of virtual volumes to have a fine management.

End-to-End Performance Optimization

Based on SMTX OS native hypervisor and distributed storage components, the business can obtain an end-to-end, full-stack performance optimization. Combined with the industry-leading Optane Persistent Memory and 100Gb network acceleration technology, the demanding requirements for performance and latency from core productions can be met.

Watch how our CTO explains this solution:

Video Player is loading.
Current Time 0:00
/
Duration 0:00
Loaded: 0%
Progress: 0%
Stream Type LIVE
 
1x

Network and Security
New Release

New Release

Network Micro-Segmentation

VMs are easily grouped by application labels. Granular security policies for VM are applied to granular network segments. Inter/inner segments traffic are granted with least privilege access.

On-Demand Isolation or Diagnostics

Completely isolate infected virtual machines in time, blocking malicious attacks from spreading inside the data center; furthermore, set virtual machines into "diagnostic isolation" mode for debugging.

Sticky Policies

Security policies are always associated with virtual machines along the whole lifecycle, even with the migration, IP/MAC changing, label re-association or HA failover of the VM.

Data Protection

Intra-City MetroX

Real-time data synchronization between two availability zones in a form of cluster stretching. When the primary availability zone fails, the service recovery capability with RPO=0 and minute-level RTO is provided.

Asynchronous Replication

Reduce network dependence among different sites, replicate data among multiple clusters, and restore the business at a remote site with one click, to meet the data protection requirements with RPO ≥ 15 minutes.

Flexible and Open

Converged Deployment

Based on VMware Virtualization

SmartX's distributed block storage ZBS can be deployed on the same node as VMware hypervisor to implement a hyper-converged solution.

When using this architecture, SMTX OS runs in a virtual machine (which is called SCVM) on ESXi.
The compute virtualization services are provided by VMware ESXi.
By passing through the RAID card (HBA/JBOD mode) to SCVM, all the hard disks on the servers will be taken over by SCVM, providing distributed block storage services.

Deployment Architecture

Overview

Mature Ecosystem, Combined Advantages

While using the familiar VMware virtualization and all its ecosystem (such as disaster recovery, anti-virus, etc.), you can obtain all the advantages of SmartX's hyper-convergence and distributed storage.

High Reliability

In addition to the high reliability of distributed storage ZBS, SMTX OS additionally provides SCVM high availability to ensure that, when SCVM fails, the virtual machines on the node can still access storage services.

Virtualization and Storage Decoupling

While being compatible with the rich versions of ESXi, SmartX's distributed storage modules can be upgraded individually at any time to obtain the latest version.

View SMTX OS Compatible ESXi Versions

MetroX Disaster Recovery

The MetroX disaster recovery solution can be implemented by combining the high availability of vSphere virtual machines and the MetroX features of distributed storage ZBS.

View the Architectural Diagram

Other Scenarios

How to Migrate the original VMware system which is based on traditional storage?

Use SMTX Migration Tool to easily migrate VMware vSphere virtual machines to a cluster which runs SmartX's native hypervisor ELF.