Drobo 5D and Drobo Mini
Recently we conducted performance tests on the new Thunderbolt-powered Drobo 5D and Drobo Mini. Click here to see those results (think fast ... very fast!).
StorageReview.com Reviews Drobo B1200i
New auto tiering update and up to 6X throughput gains with SSDs and the B1200i's value proposition keeps getting better
Read the StorageReview.com Drobo B1200i Review.
ESG Lab Validation Report on Drobo B1200i
ESG Lab confirms that the Drobo B1200i can easily support the application demands
of today’s small and mid-sized business: e-mail, database, and file services
Recently ESG Lab performed remote hands-on evaluation and testing of the Drobo B1200i storage solution. Using industry standard tools and methodologies, ESG testing is designed to demonstrate the performance benefit achieved for real-world SMB workloads with an all-hard-drive configuration as well as with the introduction of SSDs for a hybrid solution to accelerate transactional performance.
ESG Lab tested the performance of a B1200i with a focus on two main areas: (1) the overall performance impact of Automated Data-Aware Tiering on accelerating I/O and throughput and (2) its ability to enable the solution to support real-world mixed workloads by simultaneously scaling applications. The Lab selected three applications common to small and medium-sized businesses: e-mail, database, and file server.
For a discussion of B1200i performance validated for SMB configurations, including greater than 2X acceleration with SSDs, view a recent webcast.
NOTE: IOPS (input/output operations per second) is a common performance measurement used to benchmark computer storage devices such as hard disk drives (HDD), solid state drives (SSD), and storage area networks (SAN). The typical IOPS for a single 7,200 rpm HDD is approximately 75-100.
Database and File Server
The chart shows the performance benefit of the SSD devices with Automated Data-aware Tiering on I/O-intensive workloads.
- HDD-only configurations deliver the I/O performance that a typical SMB would require in a small virtual server environment:
- 500-600 IOPS support a pair of clustered virtual hosts running file server and database workloads typical of organizations with 250 or fewer users.
- The addition of SSD and Automated Data-Aware Tiering improved I/O-intensive workload performance.
- Database operations improved by 2.3 times over an SAS-only configuration.
- File server operations improved by 2.4 times over an SAS-only configuration.
E-mail Response Times
The test was configured to emulate 500 users with 200 MB mailboxes performing typical Exchange operations at an I/O rate of 0.18 IOPS per mailbox. A response-time goal of 20 milliseconds or less for database reads was required to pass the test. These values are defined by Microsoft as a limit beyond which end-users will feel that their e-mail system is acting slowly. The chart shows the e-mail response time as applications are added.
- The SSD configuration enabled the B1200i to handle all three workloads.
- The SAS configuration was able to support two workloads simultaneously (file server and e-mail).
- Response time for e-mail was well below the Microsoft recommended limit (a good thing!).
- The SAS configuration with the e-mail-only workload can support 500 mailboxes.
- The SSD configuration with the e-mail-only workload can support up to 1,200 mailboxes.
- The database workload was able to support 43 concurrent users, which translates to DB of 4300 customers
- The file server workload was able to support up to 10,411 users.
Video on Demand
Finally, ESG Lab emulated large file video-on-demand. The chart shows the performance improvement gained by adding SSD drives to the configuration for this throughput-intensive workload.
- The addition of SSD and Automated Data-aware Tiering also improved system throughput.
- With SSD, video on demand large file reads improved by 5% over the SAS-only configuration.
- SSDs can benefit throughput, but have less of an impact on streaming performance, which is usually not bound by the IOPS of each hard drive like in transactional workloads.
About ESG Lab Testing
The goal of ESG Lab reports is to educate IT professionals about data center technology products for companies of all types and sizes. ESG Lab reports are not meant to replace the evaluation process that should be conducted before making purchasing decisions, but rather to provide insight into these emerging technologies. The objective is to go over some of the more valuable feature/functions of products, show how they can be used to solve real customer problems and identify any areas needing improvement. ESG Lab's expert third-party perspective is based on our own hands-on testing as well as on interviews with customers who use these products in production environments.
ESG Lab worked with Drobo technical team members to add an array to the existing test bed environment shown at right. The test environment includes both physical and virtual hosts and a pair of B1200i storage arrays. One array was used to support the performance testing, the second was used to explore features and functions. Both arrays are connected to the hosts via the test environment LAN using the iSCSI protocol. This ESG Lab report was sponsored by Drobo.
Steve Duplessie, founder of ESG, has further thoughts about Drobo. Although capacity, reliability, and performance used to be scarce commodities in IT storage, times have changed and now time is a scarce commodity. Drobo saves him time and he wishes that everything in his life technologically was as simple as Drobo! Click here to see him explain further.