Method and system for managing data access in storage system
Embodiments of the present invention relate to a method and system for managing data access in a storage system. A method for managing data access in a storage system, the method comprising: obtaining state information about available resources in a storage control node in the storage system; determining, based on the state information, a credit score descriptive of processing capacity of the storage control node for data access; and publishing the credit score so as to notify a host of the processing capacity of the storage control node for the data access.
1. A method of managing data access in a storage system, comprising:
obtaining, by a storage control node in the storage system, state information about available resources in the storage system;
determining, by the storage control node based on the state information, a credit score descriptive of processing capacity of the storage control node for input/output (IO) access;
publishing, by the storage control node, the credit score so as to notify a host of the processing capacity of the storage control node for the IO access, a processing capacity demand associated with an IO request being determined by the host;
in response to the processing capacity demand being higher than the credit score, delaying receiving, at the storage control node, the IO request from the host; and
in response to the processing capacity demand being lower than or equal to the credit score, receiving, at the storage control node, the IO request from the host,
wherein the obtaining state information about available resources in the storage system comprises:
obtaining at least one of a performance of computing resources and a performance of cache resources in the storage control node; and
wherein the determining, based on the state information, a credit score descriptive of processing capacity of the storage control node for IO access comprises:
setting the credit score to be in direct proportion to the at least one of the performance of computing resources and the performance of cache resources.
2. The method according to claim 1 , further comprising:
in response to receiving, at the storage control node, the IO request from the host, scheduling the IO request for execution.
3. The method according to claim 1 , wherein the state information of available resources comprises a performance of cache resources, and the obtaining the performance of the cache resources in the storage control node comprises:
obtaining a recycling time for recycling occupied cache resources in the storage control node; and
setting the performance of the cache resources to be in inverse proportion to the recycling time.
4. The method according to claim 3 , wherein the obtaining a recycling time for recycling occupied cache resources in the storage control node comprises:
calculating the recycling time based on at least one of a potential residing time of a dirty data block in a cache in the storage system and a potential flushing time for flushing a dirty data block to a storage device in the storage system.
5. The method according to claim 4 , wherein the obtaining a recycling time for recycling occupied cache resources in the storage control node further comprises:
calculating the recycling time based on the number of dirty data blocks in the storage system.
6. The method according to claim 4 , wherein the obtaining a recycling time for recycling occupied cache resources in the storage control node further comprises:
calculating the recycling time based on the number of dirty data blocks associated with synchronization between the storage control node and another storage control node in the storage system.
7. The method according to claim 1 , wherein the state information about available resources comprises a performance of cache resources, and the obtaining the performance of the cache resources in the storage control node comprises:
calculating the performance of the cache resources based on a recycling plan for recycling occupied cache resources in the storage control node.
8. The method according to claim 7 , wherein the calculating the performance of the cache resources based on a recycling plan for recycling occupied cache resources in the storage control node comprises:
obtaining a length of at least one queue, indicative of dirty data blocks in the occupied cache which wait to be flushed to a storage device in the storage system; and
setting the performance of the cache resources to be in direct proportion to the length of at least one queue.
9. A system for managing data access in a storage system, the system comprising:
one or more processors;
a memory coupled to at least one processor of the one or more processors; and
computer program instructions stored in the memory which, when executed by the at least one processor, cause the system to execute a method of managing input/output (IO) access in a storage system, the method comprising:
obtaining state information about available resources in the storage system;
determining, based on the state information, a credit score descriptive of processing capacity of the storage control node for the IO access;
publishing the credit score so as to notify a host of the processing capacity of the storage control node for the IO access, a processing capacity demand associated with an IO request being determined by the host;
in response to the processing capacity demand being higher than the credit score, delaying receiving the IO request from the host; and
in response to the processing capacity demand being lower than or equal to the credit score, receiving the IO request from the host,
wherein the computer program instructions further cause the system to:
obtain at least one of a performance of computing resources and a performance of cache resources in the storage control node; and
set the credit score to be in direct proportion to the at least one of the performance of computing resources and the performance of cache resources.
10. The system according to claim 9 , wherein the computer program instructions further cause the system to:
in response to receiving the IO request from the host, schedule the IO request for execution.
11. The system according to claim 9 , wherein the computer program instructions further cause the system to:
obtain a recycling time for recycling occupied cache resources in the storage control node; and
set the performance of the cache resources to be in inverse proportion to the recycling time.
12. The system according to claim 11 , wherein the computer program instructions further cause the system to:
calculate the recycling time based on at least one of a potential residing time of a dirty data block in a cache in the storage system and a potential flushing time for flushing a dirty data block to a storage device in the storage system.
13. The system according to claim 12 , wherein the computer program instructions further cause the system to:
calculate the recycling time based on the number of dirty data blocks in the storage system.
14. The system according to claim 12 , wherein the computer program instructions further cause the system to:
calculate the recycling time based on the number of dirty data blocks associated with synchronization between the storage control node and another storage control node in the storage system.
15. The system according to claim 9 , wherein the computer program instructions further cause the system to:
calculate the performance of the cache resources based on a recycling plan for recycling occupied cache resources in the storage control node.
16. The system according to claim 15 , wherein the computer program instructions further cause the system to:
obtain a length of at least one queue, indicative of dirty data blocks in the occupied cache which wait to be flushed to a storage device in the storage system; and
set the performance of the cache resources to be in direct proportion to the length of at least one queue.
17. A method of managing data access in a storage system, comprising:
obtaining, by a storage control node in the storage system, state information about available resources in the storage system;
determining, by the storage control node based on the state information, a credit score descriptive of processing capacity of the storage control node for input/output (IO) access;
receiving, at the storage control node, an IO request from a host;
having received the IO request from the host, determining, by the storage control node, a processing capacity demand associated with the IO request;
in response to the processing capacity demand being higher than the credit score, delaying, by the storage processing node, execution of the IO request; and
in response to the processing capacity demand being lower than or equal to the credit score, executing, by the storage control node, the IO request,
wherein the obtaining state information about available resources in the storage system comprises:
obtaining at least one of a performance of computing resources and a performance of cache resources in the storage control node; and
wherein the determining, based on the state information, a credit score descriptive of processing capacity of the storage control node for IO access comprises:
setting the credit score to be in direct proportion to the at least one of the performance of computing resources and the performance of cache resources.