I have had many opportunities to meet with prospective customers and system admins, and often times, the discussion centers around the performance and latency bottlenecks they experience using SATA SSDs. It is of no surprise since the SATA interface is limited to a data transfer speed of 6 gigabits1 per second (Gb/s). The SATA connection has been the same speed since 2009, with no planned performance improvements, so that’s as good as it gets!
Our value SAS SSDs offer a better alternative to overcome SATA SSD performance limitations. Value SAS SSDs from KIOXIA have a 12 Gb/s SAS interface that can enable a server to potentially double its data throughput. As SATA and SAS SSDs are connected to most server motherboards via a SAS HBA or RAID card, the slower SATA SSDs can be easily replaced with higher performance value SAS SSDs. Our lab set out to compare our KIOXIA RM7 Value SAS SSDs with SATA SSDs from a leading provider, and we decided to test the performance of both using transactional database and data analytical workloads.
Delivering Twice the Transactional Database Performance
We chose transactional database workloads as they are one of the most important applications run in data centers today and can be used in any industry that conducts transactions. These workloads rely heavily on the underlying storage to read or write rows of content very quickly. A Microsoft® SQL Server™ database was used to emulate real world transactional workloads, as well as HammerDB2 test software. We tested transactions per minute (TPM), read/write throughput and read/write latency.
The application level performance clearly reflected the raw performance numbers that were expected. The KIOXIA RM7 Value SAS SSDs were able to handle more than twice the database transactions (120% higher) when compared with SATA SSDs, as follows:
The value SAS drives also delivered 127% higher read throughput, 96% higher write throughput, along with a 5.8x improvement in read latency and a 4.8x improvement in write latency over the SATA SSDs. For servers experiencing slow or bottlenecked performance from storage, these types of workloads can benefit from the improvements in throughput and latency provided by value SAS SSDs. Check out the results compiled from our lab testing in the database transaction performance brief available here.
Significant Improvements in Data Analytical Performance
In addition, we tested data analysis workloads, which rely heavily on the underlying storage to deliver high throughput and low-latency response times to efficiently handle complex analytical queries.
The KIOXIA RM7 Value SAS SSDs were also able to deliver higher drive read throughput versus the SATA drives. For one virtual user that conducted the analytical queries in succession, database throughput was 92% higher. When seven virtual users conducted analytical queries in parallel, database throughput was over twice as fast at 108% (see results below).
Check out the results compiled from our lab testing in the data analytics performance brief available here.
With higher throughput and lower latency, value SAS SSDs can effectively process more transactions and large analytical datasets, facilitating advanced performance for key data center applications. The KIOXIA RM7 drives are roughly twice as performant when compared to legacy SATA drives, and in many use cases, those numbers can be higher due to latency improvements. Despite being higher performing SAS drives, they are competitively priced to be an easy replacement for SATA SSDs, enabling IT admins to maximize their server resources.
For additional viewing pleasure, see the 2-1/2 minute video that I moderate on this subject.
NOTES:
1 Definition of capacity - KIOXIA Corporation defines a megabyte (MB) as 1,000,000 bytes, a gigabyte (GB) as 1,000,000,000 bytes and a terabyte (TB) as 1,000,000,000,000 bytes. A computer operating system, however, reports storage capacity using powers of 2 for the definition of 1Gb = 230 bits = 1,073,741,824 bits, 1GB = 230 bytes = 1,073,741,824 bytes and 1TB = 240 bytes = 1,099,511,627,776 bytes and therefore shows less storage capacity. Available storage capacity (including examples of various media files) will vary based on file size, formatting, settings, software and operating system, and/or pre-installed software applications, or media content. Actual formatted capacity may vary.
2 HammerDB is benchmarking and load testing software that is used to test popular databases. It simulates the stored workloads of multiple virtual users against specific databases to identify transactional scenarios and derive meaningful information about the data environment, such as performance comparisons.
Registered trademarks or trademarks of Microsoft Corporation in the United States and/or other countries. All other company names, product names and service names may be trademarks of third-party companies.
DISCLAIMERS:
KIOXIA America, Inc. may make changes to specifications and product descriptions at any time. The information presented in this blog is for informational purposes only and may contain technical inaccuracies, omissions and typographical errors. Any performance tests and ratings are measured using systems that reflect the approximate performance of KIOXIA America, Inc. products as measured by those tests. In no event will KIOXIA America, Inc. be liable to any person for any direct, indirect, special or other consequential damages arising from the use of any information contained herein, even if KIOXIA America, Inc. are advised of the possibility of such damages.