I think it is safe to say that this past winter in the Boston area has been more like Spring. Unlike my three year old who is fond of using her shovel (the blue one pictured below) I and my back did not miss the snow. Nevertheless I was prepared with my arsenal to tackle snow on the car, drive way and the back yard. Here they are basking in the 70s in in a picture taken on March 10.
Cold Data is Accumulating much Faster than You Think
Cold data is something like a more normal snow fall in New England. We clear the car and drive way of the snow but can’t get rid of it completely. What is cold data? Data that is rarely accessed is referred to as cold data. Other names include static data or inactive data. While the chances of access of cold data are very slim, cold data however just sits around occupying valuable primary storage (which is rapidly becoming all flash!). For certain applications data starts to lose value quickly but still needs to be stored for a certain time frame. A simple example is archive mail boxes. Another example is the rapid accumulation of device data, say from IoT sensors. Let us also note that archival data that is beyond short term back up also presents the same challenge. Whatever the context may be, cold data is simply a consequence of rapid data growth.
Pain Points when Dealing with Cold Data
Now just like we shovel away snow storage administrators spend a lot of time and effort moving this cold to lower tier arrays or to tape. Time and effort aside, in the rare event that access is needed to this data, retrieval is once again a challenge with time consuming processes to load this data back onto the storage network. If you add the cost of your primary storage that is being used up by inactive data, the time and resources it takes to move the cold data out of the primary storage and the recovery costs you will quickly see the inefficiencies of the cold data management chewing up your resources.
Cloud Storage as the Alternative
The need of the hour is storage that is not only inexpensive but is online for easy access and does not involve manual processes to move the cold data (more like a snow blower). While cloud storage satisfies the first two requirements (inexpensive and online) the solution also needs to have the right automation tools to partition and haul the data.
EMC has long recognized this need and developed products to automatically push cold or archival data to thecloud both from primary storage as well as protection storage. For example with CloudArray you can create a seamless cloud tier that is directly connected to a high-performance storage array like VMAX. With the recent integration with VPLEX, CloudArray can do this for any array that is behind VPLEX! Yes also those 70+ EMC and third party models now have a pathway to cloud that is seamless and cost effective. Obviously we don’t have to wait for the snow to melt as long as we are clearing the driveways, hopefully now with a snow blower.