The wide availability of low cost and highly reliable sequencing instrumentation has contributed to huge advancements in genomic research and decreased time to discovery. These discoveries can lead to advances in medicine to treat diseases and better understand at an individual level the risk of disease – that treatments designed for the individual can eliminate or reduce the onset of the disease. Output from the sequencing machines is transferred to primary storage; the files are generally large and therefore the NAS is often optimized for high sequential throughput. HPC clusters are used to execute complex models against the data retrieved from sequencing machines. The output from one model often feeds another and the resulting data growth stemming from the ingest data taken from sequencing instrumentals can be staggering. Researchers downstream retrieve files, some small and some large, and perform their analysis. In this process, many researchers could be accessing the same data. When work is completed it can be moved to Tier 2 storage, where access is less frequent and the demand for performance is less demanding. The ANX 1500 provides distinct advantages to life sciences environments:
- Accelerating workflows and reducing time to discovery. The ANX 1500 can accelerate the serving of cached data, sitting alongside the primary storage. Administrators can select which directories to cache on the ANX 1500 and configure only clients having need for this data, reducing latency when accessing data. As the NAS in these environments is optimized for large sequential throughput, not high IOPS/low latency, users should note a noticeable difference in response times, most notably for smaller files which make up a larger percentage of file access in downstream analysis.
- Improving research times. The ANX 1500 can assist in these environments in caching NFS metadata. The ANX 1500 can handle over 2 million metadata operations per second. This can speed up research on the client side by reducing the latency associated with checks, ensuring that locally stored data on the client caches haven’t changed before executing local changes to data.
- Accelerating Tier 2 or near line storage. This is relevant when certain files become hot again and require access by many users. Rather than migrate the data from Tier 2 to Tier 1 storage, using the ANX 1500 to absorb these peaks could be far more cost effective, while offering solid performance in both throughput and latency.
- Extending the life of your current NAS. The ANX 1500 transparently slides into an existing NAS environment and is very simple to install, manage and operate. It requires significantly less power, space, cooling and capital than attempting to solve performance problems by continuously adding more NAS – and can have a large positive impact on CAPEX and OPEX budgets. By relieving the NAS of the burden of responding to NFS requests its life is extended, with added headroom to support more useable storage capacity, adequately protect this capacity, and provide better performance.