Our recent Webcast: Flash – Plan for the Disruption was very well received and well attended. We thank everyone who was able to make the live event. For those of you who couldn’t make it, it’s now available on demand. Check it out here.
There wasn’t enough time to respond to all of the questions during the Webcast, so we have consolidated answers to all of them in this blog post from the presentation team. Feel free to comment and provide your input.
Q. Are you going to cache both read and writes in NetApp FlashCache?
A. Flash Cache is a level 2 Read cache and it is used to accelerate random read operations. NetApp offers an additional capability called Flash Pool which caches both random reads and random overwrites. Both technologies are part of the NetApp Virtual Storage Tier family within the Data ONTAP operating environment.
Q. Is eMLC flash available today?
A. Yes, a number of Flash vendors are shipping eMLC today.
Q. Also can you review the write cycle performance of SLC vs. MLC?
A. Write cycles for SLC are typically around 100,000. With eMLC, write cycles of 30,000 per bit can be achieved.
Q. Has specific analysis been conducted on what applications and relative data can be cached at the server versus at the storage controller (tolerance for latency, user patience, etc.)?
A. This varies but server caching will typically be used for applications with the most hot spots such as databases. If there is a particular requirement for ultra low latency such as in OLTP environments, server caching may be appropriate. Server caching can also yield significant benefit to increase VM density. Generally, server caching will be deployed to accelerate a specific application while storage controller caching will be used to accelerate storage which is shared across multiple applications.
Q. Does the data running over the network storage PDUs or Ethernet Layer2/IP traffic?
A. Ethernet Layer 2 in this demo, thought it could have been scaled to for L3 IP routed traffic.
Q. What is the difference between flash tier and flash cache?
A. A flash tier is persistent storage whereby datasets are pinned to flash technology for some period of time (or permanently). In Automated Storage Tiering, data may be migrated to and from the flash tier based on the temperature of the data. A flash cache, on the other hand is a caching technology in which the most frequently accessed data is copied to flash for data access but then evicted as the data cools down. Data is copied to the flash cache either on the basis of calculated data temperature or on a first-in first-out basis.
Q. Given the large advantages of flash on power (direct), cooling, and DC footprint, why do enterprise data centers not just completely switch out their HDDs? It seems like there is a good ROI even without considering performance. Is it the operational complexities that make this challenging?
A. For many applications, this is not cost justified given the significant price difference of the SSD and HDD devices. Since hot data typically amounts to less than 20% of total data, a small amount of flash can be deployed successfully. In the caching case, this can be around 1%.