LINBIT (DRBD, LINSTOR), Storage Solutions
As the world’s leading provider of Software-Defined Storage, High Availability, and Disaster Recovery software, LINBIT (“DRBD, LINSTOR”) adds server clustering capabilities to any containerized, virtualized, or bare metal environment.
With native integration to Kubernetes, LINSTOR makes building, running, and controlling block storage simple. LINSTOR is open-source software designed to manage block storage devices for large Linux server clusters. Its enterprise subscription LINBIT SDS, which includes DRBD, LINSTOR & Expert Support, is used for providing persistent Linux block storage for Kubernetes, OpenStack, OpenNebula, and OpenShift environments.
The LINSTOR system consists of multiple server and client components.
- A LINSTOR controller manages the configuration of the LINSTOR cluster and all of its managed storage resources.
- The LINSTOR satellite component manages creation, modification and deletion of storage resources on each node that provides or uses storage resources managed by LINSTOR.
- All communication between LINSTOR components uses LINSTOR’s own network protocol, based on TCP/IP network connections.
- The storage system can be managed by directly using a command line utility to interact with the active LINSTOR controller. Alternatively, users may integrate the LINSTOR system into the storage architecture of other software systems, such as Kubernetes.
- Seamless integration to various cloud environments with many additional software including Ha Controller, STORK, Kubectl Plugin, Operator
LINBIT SDS Features
For the community, from the community.
Easily create, remove, modify volumes from CLI or API / Driver Support.
Multi – Tier Storage
Data can be stored on either HDD, SSD, NVME or PMEM. Live migration is possible between each other.
Possibility to have multiple clusters in different geographical locations.
Data deduplication is one such technology that enables better utilisation of both storage devices and network bandwidth.
Low CPU & Memory Utilization
LINBIT SDS is performing better while consuming lowest CPU & memory in the market.
Ultra Fast Performance
World IOPS record is broken with LINBIT SDS + DRBD.
Wide Platform Support
Openshift, Opennebula, Openstack, Kubernetes, Docker, Hyper-v, Vmware, Proxmox
Unmatched In-Kernel Data Replication
Up to 32 replicated persistent volumes provided by DRBD.
LINBIT SDS detects failures and automatically recovers from failed drives, network interfaces, failing switches, etc.
Each volume can be provisioned on local disks, or remote access can be achieved using DRBD-Diskless, ISCSI, NFS, NVME-OF etc.
High performance, scalability, availability, and reliability.
In order to provide integrity, LINBIT SDS supports 3 synchronization methods which is; Variable-rate, Fixed-rate, Checksum-based.
LINBIT VSAN appliance gives you the ability to do Hyper-converged infrastructure. With the support of Hyper-converged, you can increase flexibility, simplify deployments, lower the costs. In short, do more with less.
Separated Data Path
Since LINBIT SDS components are not on the data path, you can easily upgrade and manage the entire cluster with ease.
Built-in HA (Highly Available), scale-out iSCSI target, and NFS server is managed by LINBIT SDS.
The same volume may be attached to many servers/clients.
Multi Threaded Process
Ability to use multiple CPU cores in parallel in order to increase the performance per server.
Infiniband , RDMA and 10/40/56/100 Gbit Еthernet support.
Network, Redundancy and Load Balancing
Network redundancy can be archived by TCP/IP. With RDMA load balancing is possible.
LINBIT SDS Networking Protocol
(Diskless mode) developed for maximum throughput and lowest possible latency.
Online Volume Changes
Reconfiguration of the volume settings are possible without interruption.
Provide seamless integration, simple management, and high availability.
Available on all of the client nodes, simultaneously accessible (Read only) and fully consistent.
Snapshots and Clones
Instantaneous, copy on write (CoW), snapshots and clones.
Each pool may have a different set of drives. There may be a single pool or multiple pools per cluster. For best performance, SSD Pools can be created or HDD pools can be configured for big storage needs.
Spinning drives need ssd caching for some scenarios, therefore LINBIT SDS supports that. (dmcache or bcache)
Automate volume creation and management. Resource groups, resource definitions are possible.
Allows more storage visible to the users than is physically available on the system. Thin provisioning also allows snapshots and clones.
3 Types of replication
Synchronous, Asynchronous, semi-synchronous replication.
Trim/Discard are two names for the same feature: a request to a storage system, telling it that some data range is not being used anymore and can get recycled.
DRBD, Distributed Replicated Storage System
DRBD software is a distributed replicated storage system for the Linux platform. It is implemented as a kernel driver, several userspace management applications, and some shell scripts.
DRBD is traditionally used in high availability (HA) computer clusters, but beginning with version 9, it can also be used to create larger software defined storage pools with a focus on cloud integration.
DRBD Linux Kernel Driver
The kernel driver presents virtual block devices to the system. It is an important building block of the DRBD. It reads and writes data to optional local backing devices.
The DRBD kernel driver mirrors data writes to one (or multiple) peer(s). In synchronous mode it will signal completion of a write request after it receives completion events from the local backing storage device and from the peer(s).
The illustration above shows the path the data takes within the DRBD kernel driver. Please note that the data path is very efficient. No user space components involved. Read requests can be carried out locally, not causing network traffic.
drbdsetup is the low level tool that interacts with the kernel driver. It manages the DRBD objects (resources, connections, devices, paths). It can modify all properties, and can dump the kernel driver’s active configuration. It displays status and status updates.
drbdmeta is used to prepare meta-data on block devices before they can be used for DRBD. You can use it to dump and inspect this meta-data as well. It is comparable to
drbdadm processes configuration declarative configuration files. Those files are identical on all nodes of an installation.
drbdadm extracts the necessary information for the host it is invoked on.
TCP/IP is the natural choice. It is the protocol of the Internet. Usually it is used on top of ethernet hardware (NICs and switches) in the data center. While it is the lingua franca of the network it has started to become outdated and is not the best choice to achieve the highest possible performance.
Compared to TCP/IP a young alternative is RDMA. It requires NICs that are RDMA capable. It can run over InfiniBand networks, which come with their own cables and switches. It can run over enhanced ethernet (DCB) or on top of TCP/IP via an iWARP NIC. It is all about enhancing performance while reducing load on the CPUs of your machines.
WinDRBD, Highly Available Replicated Disk Drives for Windows
WinDRBD is the port of Linbit’s DRBD kernel driver and userspace utilities to the Microsoft Windows family of operating systems (Windows Server, Windows 10). It is based on the original source code of DRBD, which makes it widely compatible with the Linux version of DRBD. Most features that come with Linux DRBD are also available on the WinDRBD port. In addition, WinDRBD can be used for booting a Windows client from a network resource.
Connecting a Windows WinDRBD resource with a Linux storage server enables you to benefit from features like LVM snapshots or zfs storage pools also on the Windows platforms.
Technically, the WinDRBD Windows driver consists of a thin Linux compatibility layer that emulates the Linux kernel APIs used by the DRBD driver for the Windows platform. Inside this layer, the original DRBD engine (with a few compiler-specific patches) is working.
To control the kernel driver the original DRBD user space utilities (drbdadm, drbdsetup and drbdmeta) are used. They are ported using the CygWin POSIX emulation library which is also included in the WinDRBD package (so there is no need to install CygWin alongside WinDRBD).
Since WinDRBD is both application agnostic and file system agnostic many different use cases are imaginable:
- Implement highly available Windows servers. For example highly available MSSQL database servers
- WinDRBD network boot: System volume (“C:”) over WinDRBD. To implement highly available centrally managed Windows clients WinDRBD here works as a replacement for iSCSI.
- Disaster recovery for Windows Clients. By using zfs / lvm snapshots on Linux peers, Windows storage can be rolled back in case of malware infection.
DRBD Proxy helps DRBD in real-time replication with long distance. DRBD Proxy buffers the writes into memory, reducing bandwidth, latency and distance issues, ensuring your WAN latency isn’t a bottleneck.
DRBD Proxy basically provides 2 advantages. Data compression and cache operations. The biggest problem for disaster recovery solutions is that the connection between the two locations is cut off or the quality is low. In order to overcome these problems, we launched our DRBD Proxy product, which can work fully integrated with DRBD.
DRBD Proxy creates a buffer area between the two locations, allowing your data to be transferred smoothly in case of disconnection.
It also supports all compression standards in the industry, allowing you to carry a lot of data with less bandwidth, thus reducing your costs.
Whether for regulatory compliance or peace of mind, an off-site replica of your data is designed to protect your important information during critical site outages, natural disasters, and other unfortunate circumstances. As a crucial part of your business continuity plan, LINBIT is dedicated to keeping your services applications up and running during even the most critical failures.
Common Use Cases
- Real time replica in Amazon AWS
- Connecting 2 or more company campuses
- Moving offices without downtime
- Off-site replicas for users in disaster prone areas
- Hosting providers who’s customers need a DR feature
Peace of mind
Unlike many proprietary vendors who make you purchase an expensive black box with licensed hardware and software and charge per machine Socket or per Gigabyte transferred, DRBD Proxy’s costs are per host/node. This makes Enterprise Level Disaster Recovery affordable for businesses of all sizes.
Near real-time replication
DRBD Proxy mitigates bandwidth, latency, and distance issues by buffering writes into memory ensuring that your WAN latency doesn’t become your disk throughput. Data is transferred as fast as your link can handle. Your organization can ensure Synchronous High Availability locally and Asynchronous Disaster Recovery replication off-site by using DRBD and DRBD Proxy together.
Cutting edge compression
To further mitigate bandwidth, latency, and distance constraints, DRBD Proxy includes native LZMA and LZ4 data compression options. For users looking to replicate an extensive amount of data using minimal CPU, LINBIT has partnered with AHA data compression hardware to minimize the CPU usage during data compression. For more information view our Technical Guide or contact us.
Not a backup
Our products are not backup solutions, they are real time replication solutions. We still recommend a sound snapshot technology is used along side our products. Real-time replication solutions like ours allow for minimal interruption during disasters.