Method and distributed storage system for aggregating statistics

1. A distributed storage system coupled to one or more clients, comprising:

a plurality of storage nodes including multiple resources,

each of multiple storage nodes among the plurality of storage nodes being configured to execute an aggregation task which has been assigned to the storage node among aggregation tasks,

each of the aggregation tasks being a task for aggregating statistics relating to a resource among the multiple resources which corresponds to the task, to the storage node to which the task has been assigned, wherein

at least one of the plurality of storage nodes is configured to assign the aggregation tasks to the multiple storage nodes,

the at least one of the plurality of storage nodes is configured to assign, for a resource, the aggregation task, based on information denoting the number of aggregation source nodes of the resource.

2. The distributed storage system according to claim 1 , wherein

the at least one of the plurality of storage nodes is configured to assign the aggregation tasks based on information denoting relation of connection among the resources, the clients and the plurality of storage nodes.

3. The distributed storage system according to claim 2 , wherein

the at least one of the plurality of storage nodes is configured to assign, when an resource has been added in one or more of the plurality of storage nodes, an aggregation task for aggregating statistics relating to the added resource, based on a current configuration as for the added resource or a resource whose attributes is similar to attributes of the added resource.

4. The distributed storage system according to claim 2 , wherein

an aggregation task for aggregating statistics relating to a resource is assigned to a storage node which is accessed from a client so that the client access the resource and/or which includes at least a part of the resource.

5. The distributed storage system according to claim 1 , wherein

each of the plurality of the storage nodes includes multiple aggregation sources,

each of the multiple aggregation sources is configured to store statistics of resources,

for each of one or more of the plurality of storage nodes, resources of statistics are different among the multiple aggregation sources in the storage node,

for each of the multiple aggregation sources, an aggregation source node for a resource is a storage node includes the aggregation source being configured to store statistics of the resource,

for the resource, the at least one of the plurality of storage nodes is configured to select one of the multiple aggregation sources, based on the number of aggregation source nodes for each of the multiple aggregation sources, and

the at least one of the plurality of storage nodes is configured to assign the aggregation task based on the information denoting the number of aggregation source nodes for the selected aggregation source.

6. The distributed storage system according to claim 5 , wherein

each of the plurality of the storage nodes is configured to receive an access to a resource from at least one of the clients via front-end of the storage node,

each of the plurality of the storage nodes is configured to access to a resource in one or more other storage nodes of the plurality of storage nodes via back-end of the storage node,

the multiple aggregation source in each of the plurality of the storage nodes includes a first source for the front-end and a second source for the back-end.

7. The distributed storage system according to claim 2 , wherein

the at least one of the plurality of storage nodes is configured to assign, based on information denoting a storage node which receives, from an administrator, a statistic read request which is a request to read the values of statistics of a specific resource, the aggregation task for aggregating statistics relating to the specific resource, to the storage node which receives the statistic request.

8. The distributed storage system according to claim 1 , wherein

the at least one of the plurality of storage nodes is configured to dynamically change an arrangement of aggregation tasks in at least a part of the plurality of storage nodes, based on information denoting operational status of the plurality of storage nodes.

9. The distributed storage system according to claim 8 , wherein

the at least one of the plurality of storage nodes is configured to change the arrangement of aggregation tasks if the information denotes load imbalance of the plurality of storage nodes increases reaching a first threshold.

10. The distributed storage system according to claim 8 , wherein

the at least one of the plurality of storage nodes is configured to stop changing the arrangement of aggregation tasks if the information denotes load imbalance of the plurality of storage nodes decreases reaching a second threshold.

11. The distributed storage system according to claim 8 , wherein

the part of the plurality of storage nodes is storage nodes having higher priorities than priorities of the other part of the plurality of storage nodes.

12. A method for aggregating statistics in a distributed storage system comprising a plurality of storage nodes including multiple resources,

executing, by each of multiple storage nodes among the plurality of storage nodes, an aggregation task which has been assigned to the storage node among aggregation tasks,

each of the aggregation tasks being a task for aggregating statistics relating to a resource among the multiple resources which corresponds to the task, to the storage node to which the task has been assigned, wherein

at least one of the plurality of storage nodes is configured to assign the aggregation tasks to the multiple storage nodes,

the at least one of the plurality of storage nodes is configured to assign, for a resource, the aggregation task, based on information denoting the number of aggregation source nodes of the resource.