I was having another stimulating conversation in silicon valley last night, and one of the ideas that made sense is for solid state memory servers to be part of the cloud computing option. It’s just a matter of time. Amazon has their current instance offerings with a division of performance and memory.

Standard Instances

Instances of this family are well suited for most applications.

Small Instance (default)*

1.7 GB memory
1 EC2 Compute Unit (1 virtual core with 1 EC2 Compute Unit)
160 GB instance storage (150 GB plus 10 GB root partition)
32-bit platform
I/O Performance: Moderate

Large Instance

7.5 GB memory
4 EC2 Compute Units (2 virtual cores with 2 EC2 Compute Units each)
850 GB instance storage (2×420 GB plus 10 GB root partition)
64-bit platform
I/O Performance: High

Extra Large Instance

15 GB memory
8 EC2 Compute Units (4 virtual cores with 2 EC2 Compute Units each)
1,690 GB instance storage (4×420 GB plus 10 GB root partition)
64-bit platform
I/O Performance: High

High-Memory Instances

Instances of this family offer large memory sizes for high throughput applications, including database and memory caching applications.

High-Memory Double Extra Large Instance

34.2 GB of memory
13 EC2 Compute Units (4 virtual cores with 3.25 EC2 Compute Units each)
850 GB of instance storage
64-bit platform
I/O Performance: High

High-Memory Quadruple Extra Large Instance

68.4 GB of memory
26 EC2 Compute Units (8 virtual cores with 3.25 EC2 Compute Units each)
1690 GB of instance storage
64-bit platform
I/O Performance: High

High-CPU Instances

Instances of this family have proportionally more CPU resources than memory (RAM) and are well suited for compute-intensive applications.

High-CPU Medium Instance

1.7 GB of memory
5 EC2 Compute Units (2 virtual cores with 2.5 EC2 Compute Units each)
350 GB of instance storage
32-bit platform
I/O Performance: Moderate

High-CPU Extra Large Instance

7 GB of memory
20 EC2 Compute Units (8 virtual cores with 2.5 EC2 Compute Units each)
1690 GB of instance storage
64-bit platform
I/O Performance: High

But as with Virident’s offering you can get higher performance with high memory addressing if you are MySql or memcached, resulting in a higher performance per watt which should translate into a higher performance per dollar.

GreenCloud Server for MySQL

The GreenCloud Server for MySQL delivers extreme performance improvement over industry standard servers using disk arrays or SSDs, including high-performance PCIe SSDs, on Web 2.0 workloads. Virident optimized versions of MyISAM and InnoDB storage engines directly access datasets stored in the storage class memory tier to eliminate I/O bottlenecks. GreenCloud servers sustain significantly higher query rates, dramatically lower the cost of scaling to larger datasets, and simplify the replication and sharding processes usually employed for scaling. The extreme performance additionally makes it possible to obtain new insights into data and deliver new services by running complex operations such as multi-table joins, which are beyond the reach of traditional servers.

50-70x performance versus Industry Standard Servers with hybrid disk/DRAM configuration on third party benchmarks.

5 -7x versus fastest PCIe-based SSD systems.

Binary compatible with existing InnoDB and MyISAM databases.

30-35x Improvement in QPS/Watt.

10-15x Improvement in QPS/$.

GreenCloud Server for Memcached

The Virident GreenCloud Server for Memcached delivers a new standard of high-performance and cache size scaling for the popular distributed caching application. These servers can deliver 250K object gets per second with low and predictable latencies and support caches with up to 3 billion objects, increasing performance by up to 4x and the available cache memory by up to 8x versus industry standard servers. These performance and scaling benefits permit larger key spaces to be supported by a single server and decrease cache miss rates thereby reducing load on backend database servers.

Industry–leading performance
▫ Up to 250K object gets per second w/ average size of 200-300 bytes
▫ Supports a larger object cache – up to 3 Billion objects

Higher cache hit rates due to larger caches – up to 8x versus industry standard servers
▫ Lower the backend database load up to 50%

50-70% decrease in TCO
▫ GreenCloud servers can replace 4 or more traditional servers in a sever consolidation project

I would expect AWS is evaluating this, and it will be here by the summer.