We are pleased to announce the official release of the 20th major version of StorPool Storage – the primary storage platform for large-scale cloud infrastructure running diverse, mission-critical workloads. This is a major milestone in the evolution of StorPool, with the addition of several new capabilities that future-proof the leading storage software and increase its potential applications.
StorPool Storage v20 offers important new capabilities for usability, optimization and storage versatility – NVMe/TCP Support, StorPool on AWS integration, NFS File Storage, upgraded business continuity features, sophisticated management and monitoring upgrades, integration improvements for OpenNebula and CloudStack and extended hardware and software compatibility of the StorPool platform.
StorPool Storage is designed for workloads that demand extreme reliability and low latency. It enables deploying high-performance, linearly-scalable primary storage systems on commodity hardware to serve large-scale clouds’ data storage and data management needs. With StorPool, businesses streamline their IT operations by connecting a single storage system to all their cloud platforms while benefiting from our utterly hands-off approach to storage infrastructure. The StorPool team designs, deploys, tunes, monitors, and maintains each storage system so that end-users experience fast and reliable services while our customers’ tech teams dedicate their time to the projects that aim to grow their business.
StorPool Storage v20 offers important new capabilities:
StorPool Storage now supports NVMe/TCP (NVMe over Fabrics, TCP transport) – the next-generation block storage protocol that leverages TCP/IP, the most common set of communication protocols extensively used in datacenters with standard Ethernet networking and controllers.
With NVMe/TCP, customers get high-performance, low-latency access to standalone NVMe SSD-based StorPool storage systems, using the standard NVMe/TCP initiators available in VMware vSphere, Linux-based hypervisors, container nodes, and bare-metal hosts.
The StorPool NVMe/TCP implementation is software-only and does not require specialized hardware to deliver the high throughput and fast response times required by modern workloads. NVMe/TCP targets are highly available – in the event of a node failure, StorPool fails over the targets on the failed storage node to a running node in the cluster.
StorPool on Amazon AWS
Using StorPool on AWS achieves extremely low latency and high IOPS, delivered to single-instance workloads such as large transactional databases, monolithic SaaS applications, and heavily loaded e-commerce websites. StorPool Storage can now be deployed on sets of three or more i3en.metal instances in AWS. The solution delivers blazing-fast 1.3M+ balanced random read/write IOPS to EC2 r5n and other compatible compute instances (m5n, c6i, r6i, etc.). StorPool frees customers from per-instance storage limitations and can deliver this level of performance to any compatible instance type with sufficient network bandwidth. It achieves these numbers while utilizing less than a fifth of client CPU resources for storage operations, leaving more than 80% for the user application(s) and database(s).
StorPool customers using AWS get the same white-glove service provided to on-premises customers, so they have peace of mind that their application’s foundation is running optimally in the cloud. StorPool’s team designs, deploys, tunes, monitors, and maintains each StorPool storage system on AWS. The complete StorPool Storage solution enables anyone to easily and economically deploy heavy enterprise applications to AWS, which was previously not achievable at the cost/performance ratio offered by StorPool.
NFS File Storage on StorPool
Last but definitely not least, StorPool is introducing support for running highly-available NFS Servers inside StorPool storage clusters for specific use cases. NFS services delivered with StorPool are suitable for throughput-intensive file workloads shared among internal and external end-users (video rendering, video editing, heavily-loaded web applications). They can also address moderate-load use cases (configuration files, scripts, images, email hosting) and support cloud platform operations (secondary storage for Apache CloudStack, NFS storage for OpenStack Glance). NFS file storage on StorPool is not suitable for IOPS-intensive file workloads like virtual disks for virtual machines.
Deploying NFS Servers on StorPool storage nodes leverages the ability of StorPool Storage to run hyper-converged with other workloads and the low resource consumption of StorPool software components. Running in virtual machines backed by StorPool volumes and managed by the StorPool operations team, NFS Servers can have multiple file shares. The cumulative provisioned storage of all shares exposed from each NFS Server can be up to 50 TB. StorPool ensures the high availability of each NFS service with the proven resilience of the StorPool block storage layer – NFS service data is distributed across all nodes in the cluster, and StorPool maintains data and service integrity in case of hardware failures.
“With each iteration of StorPool Storage, we build more ways for users to maximize the value and productivity of their data,” said Boyan Ivanov, CEO of StorPool Storage. “These upgrades offer substantial advantages to customers dealing with large data volumes and high-performance applications, even in complex hybrid and multi-cloud environments.”
StorPool storage systems are ideal for storing and managing data of demanding primary workloads such as databases, web servers, virtual desktops, real-time analytics solutions, and other mission-critical software. In addition to the new capabilities, in 2022 alone, StorPool has added or improved many features for data protection, availability, and integration with popular cloud infrastructure tools. These include:
- StorPool Bridge Performance Improvement – Optimized the encryption/decryption of data in flight; improved handling of snapshot replication during TRIM operations in primary storage systems
- StorPool VolumeCare
- Snapshot Replication between Clusters in Multi-cluster Setups – administrators can now configure VolumeCare to execute backups between StorPool sub-clusters. This feature is helpful for cases where sub-clusters in a multi-cluster deployment act both as primary storage systems that run live workloads and backup storage systems to each other.
- Added Remote Backup Policy – With this policy, all snapshots created by VolumeCare are directly replicated to a remote storage cluster without keeping snapshot data in the primary storage system, while all other benefits are maintained (only changed data is replicated, snapshots trees are maintained, etc.). The policy enables remote backup scenarios where customers do not need to keep local backups of user data in the primary storage cluster.
- Status Tracking for Protected Clusters – Ensures that in case the primary storage cluster is unreachable (e.g., due to network issues, power outage, severe hardware failure), snapshots stored in the backup storage cluster will not be deleted even if their retention period expires.
Management and Monitoring
- IOPS and Bandwidth Limits per GiB – This feature allows specifying per-template, per-volume, and per-snapshot IOPS and bandwidth limits relative to the size of the block device. With this feature, StorPool Storage considers each block device’s size and automatically sets the appropriate IOPS and bandwidth limits when it is created or when its size changes. For example, a 100 GiB volume with 1.5 IOPS/GiB and 123 KiB/s/GiB limits will have limits of 150 IOPS and 12 MiB/s. The main use case of the feature is to easily provide multiple storage tiers on an SSD-only storage cluster to address various customer needs while avoiding more complex hardware setups.
- Additional Metrics Collected to Improve Alerting – The storpool_stat service now collects comprehensive network topology details from “storpool_ping netInfo” to assist with cluster monitoring and troubleshooting. The “storpool_server” services now collect average latency for each storage drive in StorPool storage systems to assist in handling RAID controller issues or misbehaving drives. We also started collecting iSCSI configuration from “storpool_mgmt” service for more comprehensive iSCSI-related monitoring alerts.
OpenNebula Addon Improvements
- Added support for OpenNebula version 6.4
- Following the guidance on Support Life Cycle for OpenNebula Environments, removed code related to unsupported OpenNebula versions (all prior to OpenNebula version 5.12)
CloudStack Plug-in Improvements
- StorPool Plug-in Added Upstream to Apache CloudStack 4.17 – The StorPool Storage plug-in is now natively included with each CloudStack 4.17 installation. Thanks to the built-in automation of the plug-in, cloud builders can seamlessly manage their cloud from CloudStack’s familiar user interfaces, and all storage-related operations are transparently passed down to the underlying StorPool primary storage system.
- Confirmed compatibility with Kioxia CD6 NVMe SSDs. StorPool Storage supports standard datacenter-grade hardware on a per-component basis. For a full list of supported components, you can refer to the system requirements – https://storpool.com/latest/StorPool-System-Requirements-latest.pdf.
- Compatibility improvements for NICs using the bnxt_en driver (e.g., Broadcom NetXtreme-E BCM57414).
- Added support for 5.14/5.15+ Linux kernels on Ubuntu 20.04 and Ubuntu 22.04 LTS
- Discontinued support for CentOS 6 and Ubuntu 16.04
Before starting your new storage project, ensure you’ve made the right choice and guaranteed maximum performance and reliability for your data. Talk with a StorPool Storage expert!