October 11, 2012 at 14:33Fluid Data: A “Small” Victory in Big Data Storage - Part 2
In the previous part, we started introducing the new Fluid Data technology, designed to improve the lives of those who deal with really big data. Some, but not all, advantages of this solution were also analyzed using the Dell Compellent storage system as an example. Well, without delay, we suggest continuing your acquaintance.
Admins are divided into two types: those that do not yet backups, and those that already do. You can probably wrap the Earth a couple of times with the beard of this joke, but it still won’t lose its relevance. Today, the continuity of the business process for a company is sometimes very critical, which means that a good storage system should offer a solution to possible problems. What "troubles" can iron expect? At least a power outage, the human factor (user errors), viruses, etc. However, the traditional approaches to protecting and recovering data have accumulated quite a lot of “atavisms” over time: they began to require too much disk space, while not showing any indicators of reliability and speed of work. For example, the generation of snapshots quite effectively protects data (of course, provided that the time between two consecutive shots is quite small). However, one often has to use a full mirror copy and clones of the entire volume. But there is also RAID, which does not facilitate the task at all. Add to this the inefficient allocation of capacities, which we talked about in the previous article, and you will get a stalemate: you can take pictures, but a large number of them simply have nowhere to store. And here you either have to increase the time between two consecutive recovery points, or be able to roll back for a short period of time. Obviously, both are not a cake. which we talked about in a previous article, and you get a stalemate: you can take pictures, but a large number of them simply have nowhere to store. And here you either have to increase the time between two consecutive recovery points, or be able to roll back for a short period of time. Obviously, both are not a cake. which we talked about in a previous article, and you get a stalemate: you can take pictures, but a large number of them simply have nowhere to store. And here you either have to increase the time between two consecutive recovery points, or be able to roll back for a short period of time. Obviously, both are not a cake.
Therefore, the solution used in Dell Compellent systems, called Data Instant Replay, is quite natural and logical. Its principle is somewhat reminiscent of the behavior of most online games - only information about changes in the game world is flown to the server, and not video / sound / chat / mat ... As applied to data backups, this means refusing full mirror copies and subsequent volume clones to the side records only data changes since the last snapshot. Such an approach will inevitably lead to a saving in disk space, and in combination with Dynamic Capacity it will do doubledamage profit.
Well, having received such a profitable tool and minimizing the time between two shots, you need to take care of the automation of the process. Do not poke the button yourself every 15 seconds? It smells like Foxconn, so to speak. Менее Nevertheless, this trivial task is solved by setting up a no less trivial built-in scheduler that allows you to automatically start the “replication” process.
It remains only to give some example from life (the picture does not count), proving the "usefulness" of the technology. Imagine that the task is to test new applications or services that the company possibly plans to introduce in the future. What is the guarantee that during the test everything will go "without a hitch, without a hitch"? With Data Instant Replay, this can be done without any risk of data loss or corruption.
And now I would like to consider the situation typical for companies that have several large representative offices that are geographically remote from each other, but which need to have access to the same information. At the same time, the information itself should be relevant for everyone and be updated promptly in case of any changes. There are several solutions. For example, you can run everything "in the clouds." But what if you need to organize data backup to a remote site?
Now this approach, let’s say, is not very popular due to its cost and complexity in the organization. For example, sometimes identical equipment is required at once at both sites. And yet, additional expenses will be brought by the organization of a high-speed communication channel to synchronize this "good".
But who said that these problems cannot be solved at an affordable price? Dell certainly did not say. And they developed the technology of "thin" replication (orig. Thin Replication) called Remote Instant Replay. Its ideology is similar to the method of creating backups described above: after the initial synchronization of sites in the future, only changes in data run through communication channels.
The benefits are obvious:
• reduced equipment costs;
• reducing costs and bandwidth requirements for communication channels;
• increase the speed of information recovery.
Also, the relative omnivorousness of the technology should be written down as an advantage, that is, on backup sites you can use low-cost SAS and SATA disks without losing your channel bandwidth. Fiber Channel-to-iSCSI Converter integrated into Dell Compellent systems can even further increase efficiency, allowing you to get by with your native IP network without protocol conversion.
Finally, let us dwell on one more urgent problem, which sooner or later befalls any successful business. We are talking about the inevitable increase in information volumes. For storage, this problem translates into a scalability requirement. The trouble is that solution providers are not fools either and want to make money. A simple analogy: a manufacturer has the ability to produce flash drives for 64 GB at an affordable price. But why should he do this if at the moment at the “peak of popularity” 8 GB? Yes, and then what to do with flash drives for 1, 2 and 4 GB? Obviously, it is necessary to introduce the consumer into a “better life” gradually - this is beneficial for both producers and sellers (it is not beneficial only for the consumer himself). Therefore, at first there will be solutions for 16, then for 32, and only then the coveted 64 GB.
How does this relate to storage? In the most direct way. In the "classic" case, manufacturers artificially limit the possibilities of their solutions, pre-designing them with an eye to rapid obsolescence.
At Dell, believe it or not, we decided to move away from this principle. Dell Compellent storage systems are designed for a long life cycle. The platform itself, as the “appetite” grows, can be scaled from two to a thousand terabytes of capacity. At the same time, variable combinations of both FC and iSCSI server interfaces and used disks (SSD, FC, SAS and SATA) are allowed. You can even install SAS drives of different capacities and speeds in the same disk shelf.
On the other hand, special attention is paid to protection against failures. Cluster-controlled controllers, each equipped with redundant fans and power supplies, together provide optimal system performance. However, each controller is independently connected to disk shelves and disks to eliminate a single point of failure. And virtualizing the controller ports and duplicating the I / O channel between servers and drives eliminates the need for additional software.
Do not put up with the "predatory" approaches of traditional storage systems, offering the customer obviously doomed to obsolescence and limited compatibility solutions. Dell Compellent provides dynamic virtualized storage that easily adapts to constant change.
The main features can be written:
• optimization of the data storage process, which allows you to effectively allocate disk space;
• built-in intelligent data management functions and the ability to automate them;
• improved technology for instant snapshots;
• initial system design for the long term without being tied to proprietary technologies and specific manufacturers.
What is there to add? If you want to do well, do it with Dell.
Sir, defend yourself! And back up!
Admins are divided into two types: those that do not yet backups, and those that already do. You can probably wrap the Earth a couple of times with the beard of this joke, but it still won’t lose its relevance. Today, the continuity of the business process for a company is sometimes very critical, which means that a good storage system should offer a solution to possible problems. What "troubles" can iron expect? At least a power outage, the human factor (user errors), viruses, etc. However, the traditional approaches to protecting and recovering data have accumulated quite a lot of “atavisms” over time: they began to require too much disk space, while not showing any indicators of reliability and speed of work. For example, the generation of snapshots quite effectively protects data (of course, provided that the time between two consecutive shots is quite small). However, one often has to use a full mirror copy and clones of the entire volume. But there is also RAID, which does not facilitate the task at all. Add to this the inefficient allocation of capacities, which we talked about in the previous article, and you will get a stalemate: you can take pictures, but a large number of them simply have nowhere to store. And here you either have to increase the time between two consecutive recovery points, or be able to roll back for a short period of time. Obviously, both are not a cake. which we talked about in a previous article, and you get a stalemate: you can take pictures, but a large number of them simply have nowhere to store. And here you either have to increase the time between two consecutive recovery points, or be able to roll back for a short period of time. Obviously, both are not a cake. which we talked about in a previous article, and you get a stalemate: you can take pictures, but a large number of them simply have nowhere to store. And here you either have to increase the time between two consecutive recovery points, or be able to roll back for a short period of time. Obviously, both are not a cake.
Therefore, the solution used in Dell Compellent systems, called Data Instant Replay, is quite natural and logical. Its principle is somewhat reminiscent of the behavior of most online games - only information about changes in the game world is flown to the server, and not video / sound / chat / mat ... As applied to data backups, this means refusing full mirror copies and subsequent volume clones to the side records only data changes since the last snapshot. Such an approach will inevitably lead to a saving in disk space, and in combination with Dynamic Capacity it will do double
Well, having received such a profitable tool and minimizing the time between two shots, you need to take care of the automation of the process. Do not poke the button yourself every 15 seconds? It smells like Foxconn, so to speak. Менее Nevertheless, this trivial task is solved by setting up a no less trivial built-in scheduler that allows you to automatically start the “replication” process.
It remains only to give some example from life (the picture does not count), proving the "usefulness" of the technology. Imagine that the task is to test new applications or services that the company possibly plans to introduce in the future. What is the guarantee that during the test everything will go "without a hitch, without a hitch"? With Data Instant Replay, this can be done without any risk of data loss or corruption.
Admins replicated, replicated, but not replicated
And now I would like to consider the situation typical for companies that have several large representative offices that are geographically remote from each other, but which need to have access to the same information. At the same time, the information itself should be relevant for everyone and be updated promptly in case of any changes. There are several solutions. For example, you can run everything "in the clouds." But what if you need to organize data backup to a remote site?
Now this approach, let’s say, is not very popular due to its cost and complexity in the organization. For example, sometimes identical equipment is required at once at both sites. And yet, additional expenses will be brought by the organization of a high-speed communication channel to synchronize this "good".
But who said that these problems cannot be solved at an affordable price? Dell certainly did not say. And they developed the technology of "thin" replication (orig. Thin Replication) called Remote Instant Replay. Its ideology is similar to the method of creating backups described above: after the initial synchronization of sites in the future, only changes in data run through communication channels.
The benefits are obvious:
• reduced equipment costs;
• reducing costs and bandwidth requirements for communication channels;
• increase the speed of information recovery.
Also, the relative omnivorousness of the technology should be written down as an advantage, that is, on backup sites you can use low-cost SAS and SATA disks without losing your channel bandwidth. Fiber Channel-to-iSCSI Converter integrated into Dell Compellent systems can even further increase efficiency, allowing you to get by with your native IP network without protocol conversion.
Happiness does not happen much
Finally, let us dwell on one more urgent problem, which sooner or later befalls any successful business. We are talking about the inevitable increase in information volumes. For storage, this problem translates into a scalability requirement. The trouble is that solution providers are not fools either and want to make money. A simple analogy: a manufacturer has the ability to produce flash drives for 64 GB at an affordable price. But why should he do this if at the moment at the “peak of popularity” 8 GB? Yes, and then what to do with flash drives for 1, 2 and 4 GB? Obviously, it is necessary to introduce the consumer into a “better life” gradually - this is beneficial for both producers and sellers (it is not beneficial only for the consumer himself). Therefore, at first there will be solutions for 16, then for 32, and only then the coveted 64 GB.
How does this relate to storage? In the most direct way. In the "classic" case, manufacturers artificially limit the possibilities of their solutions, pre-designing them with an eye to rapid obsolescence.
At Dell, believe it or not, we decided to move away from this principle. Dell Compellent storage systems are designed for a long life cycle. The platform itself, as the “appetite” grows, can be scaled from two to a thousand terabytes of capacity. At the same time, variable combinations of both FC and iSCSI server interfaces and used disks (SSD, FC, SAS and SATA) are allowed. You can even install SAS drives of different capacities and speeds in the same disk shelf.
On the other hand, special attention is paid to protection against failures. Cluster-controlled controllers, each equipped with redundant fans and power supplies, together provide optimal system performance. However, each controller is independently connected to disk shelves and disks to eliminate a single point of failure. And virtualizing the controller ports and duplicating the I / O channel between servers and drives eliminates the need for additional software.
Afterword
Do not put up with the "predatory" approaches of traditional storage systems, offering the customer obviously doomed to obsolescence and limited compatibility solutions. Dell Compellent provides dynamic virtualized storage that easily adapts to constant change.
The main features can be written:
• optimization of the data storage process, which allows you to effectively allocate disk space;
• built-in intelligent data management functions and the ability to automate them;
• improved technology for instant snapshots;
• initial system design for the long term without being tied to proprietary technologies and specific manufacturers.
What is there to add? If you want to do well, do it with Dell.