NoSQL Case Solution
PERFORMANCE ISSUES OF NoSQL DATABASES
As more and more deployments move to the cloud and with an increase in the size of data sets (Big Data), Non-Relational Databases or NoSQL are being increasingly adopted. NoSQL databases are particularly prone to be affected by a performance cliff, which happens when the working set of the application exceeds the system RAM. Due to the inherent way in which NoSQL databases work applications IO performance issues crop up. Solid State Devices are gaining popularity too, given the low latency high throughput option they present. All cloud providers now have SSD as part of their offerings, as direct attached devices and also as network attached devices. Larger direct attached SSDs are only available with larger and more expensive instance types. The problem with instance store disks is that they can lose data on a hard reset or if the base machine were to restart. Since the data cannot survive past hard resets and restarts, the data on these devices needs to be backed up at all times on a more reliable device type.
DEEP INSIGHT INTO IO BEHAVIOR THROUGH ANALYTICS
PerfAccel provides deep analytics into IO behavior, through:
- Tracking I/O, read hits and read misses
- Tracking latency and throughput measurement at application level
- Identifying hot files
Such an IO tracking helps administrators understand the dynamics of active data better and use this intelligence to better data placement and improve performance of NoSQL database deployments.
USING CACHE INTELLIGENTLY
Using the data intelligence, administrators can configure their caching policies and rules to ensure that the right working set resides in the cache. This would include:
- Caching only hot areas of the file or frequently accessed files
- Controlling which data to cache and which to not
- Sticky flagging for performance critical data
- Pre-fetching files for large jobs
RESOLVE THE INSTANCE STORE SSD BOTTLENECK
Using the insight from data analytics, PerfAccel can use the instance store devices more efficiently, by using the faster device available as a cache and through the optimal placement of frequently used hot data. The application directly benefits since all the reads coming from this device are much faster, increasing performance and reducing latency. In addition, since these read operations are offloaded by the cache, the back-end storage device which holds the entire data set is more responsive as it has to serve fewer IOPS. Thus, PerfAccel cache not only improves read performance, it also implicitly improves the write performance of the application.
SINGLE WINDOW MANAGEMENT
A single GUI pane combined analytics and insight through performance dashboards, as well as a simple command line, for managing across large grid deployments with a centralized data repository for analytics. PerfAccel’s flexible interface lets users configure their own policies of persistent cache, pre-fetching, predictive cache, real-time cache size configuration and auto-caching hundreds of NFS mount points.
DATAGRES provides software that helps companies visualize, control and accelerate their application performance using deep storage intelligence. DATAGRES’ flagship product PerfAccel is a very powerful analytics driven software solution that operates at a file level and can show the exact I/O pattern of an application data access especially in a scale-out grid environment. As a result, it can provide an effective way of controlling I/Os and also accelerate for higher throughput and lower latencies using high-performance SSD devices.
The company is headquartered in Palo Alto, California and is venture-backed by Nexus Venture Partners
For more information, visit www.datagres.com.