Search
Close this search box.

Throw away the Crystal Ball; HYDRAstor Scales Capacity and Performance Dynamically

Replication and deduplication are features that are fast becoming necessities when disk libraries are introduced into enterprise IT backup environments. But as I brought out in a previous blog entry, introducing multiple functions into disk libraries intended for enterprise caliber backup environments typically has some unpleasant trade-offs. A primary concern in enterprise IT shops is how large (or small) to initially configure the solution so companies neither overspend on oversized hardware nor purchase undersized hardware that cannot scale to meet their future requirements, so they need some way to forecast how their IT environment is going to look going forward.

Unfortunately most IT staff is not real good at reading crystal balls so the flexibility to independently scale individual components in enterprise disk-based backup solution is imperative. This is especially true since specific features within the disk library – deduplication, replication and storage capacity – each place different performance demands upon it, depending on how the environment grows.

It is because of these new demands that companies should consider disk libraries that are based on grid storage architectures like the NEC HYDRAstor that can independently scale capacity or performance to meet uncertain future demands. Specifically, here is how these requirements may stress a disk library and how the NEC HYDRAstor equips companies to dynamically respond to these needs.

  • Deduplication coupled with high backup throughput rates place a premium on CPU and memory. Deduplication algorithms need to analyze incoming blocks of data, index them, ascertain their uniqueness when compared to other blocks of data, and then store new unique blocks of data. During peak backup times in enterprise IT shops, these systems could experience throughput levels in the hundreds of MBs per second. However companies may not have a good sense of how fast backups will actually execute once they move from tape to disk. Also, the number of backup jobs may increase as backup jobs from business unit and departmental servers are directed to the new enterprise IT disk library. Using the NEC HYDRAstor, companies can scale performance (CPU and memory) by adding more Accelerator Nodes to their existing HYDRAstor at any time. Companies can add these new nodes to account for unexpected growth in backup jobs and deduplication overhead. New and old nodes then act as one integrated system.
  • Not all backup data deduplicate equally, so the need for more storage capacity may outweigh the need for more performance. How well corporate data deduplicates is always a best guess prior to implementing a deduplicating disk library. It could be as high as 500:1 (don’t count on it), as low as 2:1 or anywhere in between depending on application/data type, retention period and specific backup policites. While industry pundits generally put the deduplication ratios around 20:1, the only ratio that matters is the one your company actually achieves. It is when you are the anomaly that it matters. So if your data stores climb abnormally high because of low deduplication ratios or unexpected data growth, can the storage capacity of your disk library scale at all, scale independently of the performance component of it or scale linearly so performance is not impacted? Using the NEC HYDRAstor, companies have the option to add essentially unlimited amounts of storage capacity (known as Storage Nodes) independently of Accelerator Nodes.
  • Replication may have no impact or it could exacerbate an already problematic situation. How replication impacts the deduplicating disk library really depends on how and when a company uses replication. If data is replicated when no backups are occurring (during the day), the replication feature may have no impact at all on the disk library. However if companies try to replicate data at night or at the same time they are doing backups and deduplicating data, how much extra capacity do they need to add to the disk library now or in the future to support this feature? Using the NEC HYDRAstor, companies can address this question when and if it arises by dynamically adding Accelerator Nodes (ANs) that can even be specifically designated to just replicate data offsite. On individual ANs, administrators can also set up replication at the file system level so only critical file systems that require it are replicated.

Appropriately sizing disk libraries is a primary concern for enterprise companies, yet IT departments are often forced to rely upon crystal balls to forecast how their environments will grow. Selecting the NEC HYDRAstor as their disk-based target addresses this concern, because they can add what they need (performance or capacity) when they need it. In so doing, the NEC HYDRAstor removes the upfront gyrations and crystal ball gazing normally associated with trying to size disk libraries, while giving companies the freedom and flexibility to scale their disk library in whatever direction their environment dictates.

Share
Share

Click Here to Signup for the DCIG Newsletter!

Categories

DCIG Newsletter Signup

Thank you for your interest in DCIG research and analysis.

Please sign up for the free DCIG Newsletter to have new analysis delivered to your inbox each week.