Managing remote replication in storage systems
A method is used in managing remote replication in storage systems. The method monitors network traffic characteristics of a network. The network enables communication between a first storage system and a second storage system. The method predicts a change in at least one of an application demand of an application of a set of applications executing on the first storage server and a network state of the network, where the set of applications have been identified for performing a replication to the second storage system. Based on the prediction, the method dynamically manages replication of the set of applications in accordance with a performance target associated with each application.
1. A method of managing remote replication in storage systems, the method comprising:
monitoring network traffic characteristics of a network, wherein the network enables communication between a first storage system and a second storage system;
predicting a change in at least one of an application demand of an application of a set of applications executing on the first storage server and a network state of the network, wherein the set of applications have been identified for performing a replication to the second storage system; and
based on the prediction, dynamically managing replication of the set of applications in accordance with a performance target associated with each application by journaling write requests to delay performing replication of at least one of the set of applications to avoid impacting the performance target of at least one other application of the set of applications.
2. The method of claim 1 , wherein predicting the change in the network state comprises determining a predicted future state of the network indicating bandwidth availability for the network.
3. The method of claim 1 , wherein the prediction of the change in at least one of the application demand and the network state comprises predicting a probability that at least one of the application demand and network state will change.
4. The method of claim 3 , wherein predicting the probability comprises:
applying a statistical model to at least one of the application demand and network state.
5. The method of claim 4 further comprising:
updating the statistical model with the predicted change in at least one of the application demand and the network state.
6. The method of claim 1 , wherein the first storage system indicates a primary storage system and the second storage system indicates a remote storage system, wherein data of the primary storage system is remotely replicated to the remote storage system.
7. The method of claim 1 , wherein the network traffic characteristics of the network includes bandwidth of the network available to the set of applications.
8. The method of claim 1 , wherein the set of applications include a subset of applications that are critical to a user of the first and second storage systems and a subset of applications that are less critical to the user of the first and second storage systems.
9. The method of claim 1 , wherein dynamically managing replication of the set of applications in accordance with the performance target comprises:
adjusting execution of at least one application of the set of application executing on the first storage system, based on the prediction of the change in at least one of the application demand and the network state.
10. The method of claim 9 , wherein adjusting the execution of the at least one application of the set of applications comprises:
dynamically changing a latency of the at least one application.
11. A system for use in managing remote replication in storage systems, the system comprising a processor configured to:
monitor network traffic characteristics of a network, wherein the network enables communication between a first storage system and a second storage system;
predict a change in at least one of an application demand of an application of a set of applications executing on the first storage server and a network state of the network, wherein the set of applications have been identified for performing a replication to the second storage system; and
based on the prediction, dynamically manage replication of the set of applications in accordance with a performance target associated with each application by journaling write requests to delay performing replication of at least one of the set of applications to avoid impacting the performance target of at least one other application of the set of applications.
12. The system of claim 11 , wherein the processor configured to predict the change in the network state is further configured to:
determine a predicted future state of the network indicating bandwidth availability for the network.
13. The system of claim 11 , wherein the processor configured to predict the change in at least one of the application demand and the network state is further configured to predict a probability that at least one of the application demand and network state will change.
14. The system of claim 13 , wherein the processor configured to predict the probability is further configured to:
apply a statistical model to at least one of the application demand and network state.
15. The system of claim 14 further configured to:
update the statistical model with the predicted change in at least one of the application demand and the network state.
16. The system of claim 11 , wherein the first storage system indicates a primary storage system and the second storage system indicates a remote storage system, wherein data of the primary storage system is remotely replicated to the remote storage system.
17. The system of claim 11 , wherein the set of applications include a subset of applications that are critical to a user of the first and second storage systems and a subset of applications that are less critical to the user of the first and second storage systems.
18. The system of claim 11 , wherein the processor configured to dynamically manage replication of the set of applications in accordance with the performance target is further configured to:
adjust execution of at least one application of the set of application executing on the first storage system, based on the prediction of the change in at least one of the application demand and the network state.
19. The system of claim 18 wherein the processor configured to adjust the execution of the at least one application of the set of applications is further configured to:
dynamically change a latency of the at least one application.
20. A computer program product for managing remote replication in storage systems, the computer program product comprising:
a non-transitory computer readable storage medium having computer executable program code embodied therewith, the program code executable by a computer processor to:
monitor network traffic characteristics of a network, wherein the network enables communication between a first storage system and a second storage system;
predict a change in at least one of an application demand of an application of a set of applications executing on the first storage server and a network state of the network, wherein the set of applications have been identified for performing a replication to the second storage system; and
based on the prediction, dynamically manage replication of the set of applications in accordance with a performance target associated with each application by journaling write requests to delay performing replication of at least one of the set of applications to avoid impacting the performance target of at least one other application of the set of applications.