Pack the cluster in a box!
Recently, the materials were all about the network and the network, it is necessary to dilute the trend.
Two servers and a JBOD disk shelf - the minimum set that allows you to build a fault-tolerant solution. At a minimum, this is 4U rack space, additional power cables, and server connections to storage. All this adds complexity to the initial installation and configuration of the system.
To simplify the solution, reduce energy consumption, reduce the cost and the required space in the rack, a new class of systems was developed - a cluster in a box. A single chassis includes two servers, fault-tolerant power, cooling, and a single disk space.
')
With this approach, the solution does not require special conditions in the server, special knowledge in the field of fault tolerance and clustering, since all connections are already laid. All you need to do during installation is to connect the system to the power supply and local network.
Examples of this solution are our products ETegro Hyperion RS420 G4 and Hyperion RS430 G4.
The Hyperion RS420 G4 model is made in 2U format for two servers with a single storage:
On the front side there are 12 hot-swap disks in universal disk baskets, allowing you to install SAS disks of size 3.5 "and 2.5". The servers are turned on independently, the button with the System ID LED is also displayed.
Each node supports two Intel Xeon E5-2600 v2 processors (up to 130 W, allows using any models of the series), 512 GB of RAM (16 slots), two 10G Base-T Ethernet ports, two internal slots for SATA drives for OS installation It has a dedicated service processor and a dedicated Ethernet port for remote control.
For communication between nodes, there is an internal Gigabit Ethernet channel through the internal backplane. This implementation allows you to organize cluster synchronization ("heartbeat") without the use of external interfaces.
The system has free PCI-E slots for installing additional expansion cards, such as additional network cards or PCI-E flash accelerators, one slot is always occupied by a SAS controller.
The cluster disk space is scaled both by the external SAS port on each node, and by installing an additional SAS controller to connect new cascades of disk shelves.
Compared to a cluster of 2 separate servers and an external disk shelf, power savings are up to 40%, space is 50%, cost reduction is up to 20% with a 12-disk configuration.
Hyperion RS430 G4 Server Update
A review of the Hyperion RS430 G4 server was once published. Two dual-processor servers with 10G SFP + in one box, 35 disks each - product specific and popular strictly in certain circles.
I would like to expand the popularity, so we thought and came up with a natural change (in addition to production improvements), which we will now discuss.
The most obvious thing is the replacement of plastic handles for extracting backplates with metal levers, which significantly simplified support life and eliminated the need to keep a supply of plastic.
Handles for removal from the rack were replaced with fold-out levers, which also slightly corrected the karma.
But these are cosmetic changes, the most important change inside.
What can be altered in a system where all components support hot swapping, and disks are divided between servers equally 35-35?
We have written a lot about the concept of Shared DAS and the pleasures of avoiding traditional storage to direct disk management and logical change will stop dividing the disks between servers and make them all accessible to each server as 70-70.
The benefit of the structure allows you to do this "little blood" - all communications are carried out through printed circuit boards, and it is enough to change only one component so that access to each expander was brought from each server.
In connection with the use of four expanders, you need at least 16 SAS ports per server — either two sets of SAS HBAs, or two sets of LSI Syncro .
Now the server is suitable not only for storing everything and everyone, but also for building fault-tolerant solutions for:
In our line of laboratory Shared DAS solutions arrived :)
Two servers and a JBOD disk shelf - the minimum set that allows you to build a fault-tolerant solution. At a minimum, this is 4U rack space, additional power cables, and server connections to storage. All this adds complexity to the initial installation and configuration of the system.
To simplify the solution, reduce energy consumption, reduce the cost and the required space in the rack, a new class of systems was developed - a cluster in a box. A single chassis includes two servers, fault-tolerant power, cooling, and a single disk space.
')
With this approach, the solution does not require special conditions in the server, special knowledge in the field of fault tolerance and clustering, since all connections are already laid. All you need to do during installation is to connect the system to the power supply and local network.
Examples of this solution are our products ETegro Hyperion RS420 G4 and Hyperion RS430 G4.
The Hyperion RS420 G4 model is made in 2U format for two servers with a single storage:
On the front side there are 12 hot-swap disks in universal disk baskets, allowing you to install SAS disks of size 3.5 "and 2.5". The servers are turned on independently, the button with the System ID LED is also displayed.
Each node supports two Intel Xeon E5-2600 v2 processors (up to 130 W, allows using any models of the series), 512 GB of RAM (16 slots), two 10G Base-T Ethernet ports, two internal slots for SATA drives for OS installation It has a dedicated service processor and a dedicated Ethernet port for remote control.
For communication between nodes, there is an internal Gigabit Ethernet channel through the internal backplane. This implementation allows you to organize cluster synchronization ("heartbeat") without the use of external interfaces.
The system has free PCI-E slots for installing additional expansion cards, such as additional network cards or PCI-E flash accelerators, one slot is always occupied by a SAS controller.
The cluster disk space is scaled both by the external SAS port on each node, and by installing an additional SAS controller to connect new cascades of disk shelves.
Compared to a cluster of 2 separate servers and an external disk shelf, power savings are up to 40%, space is 50%, cost reduction is up to 20% with a 12-disk configuration.
Hyperion RS430 G4 Server Update
A review of the Hyperion RS430 G4 server was once published. Two dual-processor servers with 10G SFP + in one box, 35 disks each - product specific and popular strictly in certain circles.
I would like to expand the popularity, so we thought and came up with a natural change (in addition to production improvements), which we will now discuss.
The most obvious thing is the replacement of plastic handles for extracting backplates with metal levers, which significantly simplified support life and eliminated the need to keep a supply of plastic.
Handles for removal from the rack were replaced with fold-out levers, which also slightly corrected the karma.
But these are cosmetic changes, the most important change inside.
What can be altered in a system where all components support hot swapping, and disks are divided between servers equally 35-35?
We have written a lot about the concept of Shared DAS and the pleasures of avoiding traditional storage to direct disk management and logical change will stop dividing the disks between servers and make them all accessible to each server as 70-70.
The benefit of the structure allows you to do this "little blood" - all communications are carried out through printed circuit boards, and it is enough to change only one component so that access to each expander was brought from each server.
In connection with the use of four expanders, you need at least 16 SAS ports per server — either two sets of SAS HBAs, or two sets of LSI Syncro .
Now the server is suitable not only for storing everything and everyone, but also for building fault-tolerant solutions for:
In our line of laboratory Shared DAS solutions arrived :)
Source: https://habr.com/ru/post/250345/
All Articles