Shulou(Shulou.com)06/03 Report--

What is cloud origin?

"Cloud Native" is a term that is often used but not well defined. We believe that "cloud native applications" should have the following characteristics:

They are not separate, they are discrete, logically detachable parts, each packaged and deployed separately. Usually this is done in containers, just like a normal Linux package in some cases. All of its software stacks should not be forced to run on the same computer. They can be scheduled to run anywhere, on any server, or in any area. They should also be able to perceive each other in distributed deployment systems.

By adding parallel instances of specific computing logic, applications should be able to scale quickly as needed.

The services that the application depends on for coordinating communication or state preservation should be able to detect and modify programmatically and dynamically as needed, regardless of its physical infrastructure.

By clearly defining the meaning of cloud native, we can better define the division of responsibilities of the various cloud native technology components. Examples of these cloud native application components include scheduling software, network software, and storage software.

What makes Portworx different?

Portworx recently sponsored and participated in the famous DockerCon and ContainerCon conferences. The team agreed that this was one of the hottest technical meetings in recent years and a clear sign of the explosive growth of the container market.

The rapid growth of the container market has created many new suppliers, and many participants asked us, "how are you different from other container storage vendors?" To explain this, we need to start by describing Portworx itself.

What is Portworx?

Portworx has developed a new storage architecture-container-defined storage. It is built based on a highly distributed environment. The scheduling software deploys and manages it as a container and extends the storage into the Docker container as a local volume plug-in.

Portworx provides a modern way to deploy DevOps applications. We can have the scheduling tool deploy the storage infrastructure as a container. As a result, large-scale deployment of storage will become very simple and do not require complex manual operations.

Portworx focuses on heavy loads and its container-granularity operations on ordinary servers. The core of Portworx is built for modern servers and takes advantage of the latest advances in NVMe, SSD, and faster network technologies.

The Portworx architecture enables users to extend their services in a hybrid cloud environment without having to use a central metadata server in the data path. This is critical for workflows that adopt container definitions. In order to facilitate local integration with scheduling software such as Kubernetes, Mesos, Swarm, etc., we consider the container-centric DevOps workflow when designing Portworx deployment. The Portworx architecture also supports DevOps-centric internal storage services, as well as containerized applications.

What are the main differentiation features of Portworx?

In addition to the local storage of containers, the main advantages of Portworx container-defined storage include:

Container fine-grained volume management: stateful containerization applications such as databases require persistent data on distributed nodes. Portworx uses stateful Stateful Fabric to manage data volumes, or container-SLA-aware, to do this. Replicate volume data to ensure its state while meeting the performance and availability of containerized applications. More importantly, Portworx can manage its snapshots, clone replicas, and replication operations at each container level, allowing DevOps to manage microservices separately, rather than the binding groups used as traditional storage systems like LUNs. It is convenient to use Portworx to manage stateful container Stateful Containers, and the availability and management of data at each container level is simple and highly automated.

1. Host address access storage: host address access storage implements extended storage without any central metadata server. Each volume is mapped directly to the host (that is, no translation is required). Compared to current storage solutions, the Portworx approach has three advantages:

It eliminates the need to manage and maintain the central database, and simplifies storage management and configuration.

Add new nodes to make elastic expansion more convenient.

Support for storage cluster cloud native architecture (private or public cloud) across data centers and clouds.

Auto-tuning: Portworx automatically optimizes the optimal data placement and tiering algorithm based on the configuration parameters of each server. This eliminates the need to manually intervene, tune, or configure RAID parameters or drive groups. All drives will be used by Portworx as a large global pool, and the Portworx software will determine the optimal configuration of storage.

Lighthouse Cloud Monitoring Management: your data can be stored in your cloud or in a local environment, all of which can be managed through Portworx's Lighthouse Cloud Monitoring service and intuitive user interface.

Fast synchronization: fast synchronization provides a synchronization supporting environment for accelerating application performance in a multi-node environment. It allows databases to run at higher IOPS rates and supports higher-density deployments by reducing contention on local drives.

Global namespace: volumes can be shared among multiple applications running on different servers.

Cloud native extensions, including:

Automatic snapshots and backups to S3

Data feedback, virtual volumes in the cloud can access data from different clouds or data centers

CoS is paired with different EBS volume types

Restful APIs can be used to query namespace modifications-avoiding expensive namespace operations in metadata management, such as is, find, etc.

Portworx adopts a new container storage method.

As more and more containers are deployed in the enterprise, most storage vendors feel compelled to support containers, such as Docker's volume plug-ins. However, Array connected to Docker ignores the distributed nature of containers, as well as the precise architecture and ease of use that requires containers, schedulers, and storage as a seamless whole.

Some new distributed software projects for containers may avoid using the methods of traditional storage vendors, but we find that distributed software attempts to store data paths are flawed, which can lead to serious performance problems and scale limitations.

Portworx provides enterprise customers with the first true container-specific infrastructure. Therefore, it is a necessary part of deploying stateful container applications with strict, scalable, automated, distributed storage layers, and helps to improve the container ecosystem.

Portworx product introduction:

Https://v.qq.com/x/page/u3011mm1jhq.htmlPortworx product introduction

The case of Portworx- Yulai Automobile

The case of https://v.qq.com/x/page/z3011le3t63.htmlPortworx- Yulai Automobile

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.