System and method for segmenting volumes across a multi-node storage system
A method, computer program product, and computing system for dividing a volume into a plurality of segments. The plurality of segments may be assigned to a plurality of nodes of a multi-node storage system. One or more input/output (IO) request paths for accessing the plurality of segments may be defined based upon, at least in part, assigning the plurality of segments to the plurality of nodes.
1. A computer-implemented method, executed on a computing device, comprising:
dividing a volume into a plurality of segments;
assigning the plurality of segments to a plurality of nodes of a multi-node storage system, thus defining one or more assigned nodes and one or more unassigned nodes for each segment of the plurality of segments; and
defining one or more input/output (IO) request paths for accessing the plurality of segments based upon, at least in part, assigning the plurality of segments to the plurality of nodes and a type of data of an IO request, wherein the type of data of the IO request includes one or more of an IO request referencing meta data of a particular segment and an IO request referencing user data of a particular segment, wherein defining the one or more IO request paths for accessing the plurality of segments includes defining one or more primary IO request paths for accessing each segment from the assigned node and defining one or more non-primary IO request paths for accessing each segment from at least one unassigned node of the plurality of nodes, wherein the one or more primary IO request paths include one or more IO request paths from a host initiating the IO request to the assigned node, wherein the one or more non-primary IO request paths include one or more IO request paths from the host initiating the IO request to the unassigned node and from the unassigned node to the assigned node.
2. The computer-implemented method of claim 1 , further comprising one or more of:
storing, at a node, metadata associated with one or more segments assigned to that node; and
caching, at the node, user data associated with the one or more segments assigned to that node.
3. The computer-implemented method of claim 1 , further comprising:
receiving the IO request referencing at least one segment of the plurality of segments;
determining a node to which the at least one segment is assigned; and
sending the IO request to the node to which the at least one segment is assigned via the primary IO request path to the node to which the at least one segment is assigned.
4. The computer-implemented method of claim 3 , wherein the IO request references a first segment assigned to a first node and a second segment assigned to a second node.
5. The computer-implemented method of claim 4 , further comprising:
dividing the IO request into a first portion referencing the first segment assigned to the first node and a second portion referencing the second segment assigned to the second node;
sending the first portion of the IO request to the first node via the primary IO request path defined for the first portion of the IO request; and
sending the second portion of the IO request to the second node via the primary IO request path defined for the second portion of the IO request.
6. The computer-implemented method of claim 2 , storing, at a node, the metadata associated with the one or more segments assigned to the node includes:
storing, on each node, a copy of the metadata associated with the one or more segments assigned to each other node;
generating a shared lock for each page of the metadata associated with the one or more segments; and
providing, to the node to which the one or more segments are assigned, ownership of the shared lock for each page of the metadata associated with the one or more segments assigned to the node.
7. The computer-implemented method of claim 1 , further comprising:
identifying a node failure within the multi-node storage system, thus defining at least one failed node; and
reassigning one or more segments assigned to the at least one failed node to one or more surviving nodes.
8. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
dividing a volume into a plurality of segments;
assigning the plurality of segments to a plurality of nodes of a multi-node storage system, thus defining one or more assigned nodes and one or more unassigned nodes for each segment of the plurality of segments; and
defining one or more input/output (IO) request paths for accessing the plurality of segments based upon, at least in part, assigning the plurality of segments to the plurality of nodes and a type of data of an IO request, wherein the type of data of the IO request includes one or more of an IO request referencing meta data of a particular segment and an IO request referencing user data of a particular segment, wherein defining the one or more IO request paths for accessing the plurality of segments includes defining one or more primary IO request paths for accessing each segment from the assigned node and defining one or more non-primary IO request paths for accessing each segment from at least one unassigned node of the plurality of nodes, wherein the one or more primary IO request paths include one or more IO request paths from a host initiating the IO request to the assigned node, wherein the one or more non-primary IO request paths include one or more IO request paths from the host initiating the IO request to the unassigned node and from the unassigned node to the assigned node.
9. The computer program product of claim 8 , wherein the operations further comprise one or more of:
storing, at a node, metadata associated with one or more segments assigned to that node; and
caching, at the node, user data associated with the one or more segments assigned to that node.
10. The computer program product of claim 9 , wherein the operations further comprise:
receiving the IO request referencing at least one segment of the plurality of segments;
determining a node to which the at least one segment is assigned; and
sending the IO request to the node to which the at least one segment is assigned via the primary IO request path to the node to which the at least one segment is assigned.
11. The computer program product of claim 10 , wherein the IO request references a first segment assigned to a first node and a second segment assigned to a second node.
12. The computer program product of claim 11 , wherein the operations further comprise:
dividing the IO request into a first portion referencing the first segment assigned to the first node and a second portion referencing the second segment assigned to the second node;
sending the first portion of the IO request to the first node via the primary IO request path defined for the first portion of the IO request; and
sending the second portion of the IO request to the second node via the primary IO request path defined for the second portion of the IO request.
13. The computer program product of claim 9 , storing, at the node, the metadata associated with the one or more segments assigned to the node includes:
storing, on each node, a copy of the metadata associated with the one or more segments assigned to each other node;
generating a shared lock for each page of the metadata associated with the one or more segments; and
providing, to the node to which the one or more segments are assigned, ownership of the shared lock for each page of the metadata associated with the one or more segments assigned to the node.
14. The computer program product of claim 8 , wherein the operations further comprise:
identifying a node failure within the multi-node storage system, thus defining at least one failed node; and
reassigning one or more segments assigned to the at least one failed node to one or more surviving nodes.
15. A computing system comprising:
a memory; and
a processor configured to divide a volume into a plurality of segments, wherein the processor is further configured to assign the plurality of segments to a plurality of nodes of a multi-node storage system, thus defining one or more assigned nodes and one or more unassigned nodes for each segment of the plurality of segments, and wherein the processor is further configured to define one or more input/output (IO) request paths for accessing the plurality of segments based upon, at least in part, assigning the plurality of segments to the plurality of nodes and a type of data of an IO request, wherein the type of data of the IO request includes one or more of an IO request referencing meta data of a particular segment and an IO request referencing user data of a particular segment, wherein defining the one or more IO request paths for accessing the plurality of segments includes defining one or more primary IO request paths for accessing each segment from the assigned node and defining one or more non-primary IO request paths for accessing each segment from at least one unassigned node of the plurality of nodes, wherein the one or more primary IO request paths include one or more IO request paths from a host initiating the IO request to the assigned node, wherein the one or more non-primary IO request paths include one or more IO request paths from the host initiating the IO request to the unassigned node and from the unassigned node to the assigned node.
16. The computing system of claim 15 , wherein the processor is further configured to one or more of:
store, at a node, metadata associated with one or more segments assigned to that node; and
cache, at the node, user data associated with the one or more segments assigned to that node.
17. The computing system of claim 16 , wherein the processor is further configured to:
receive the IO request referencing at least one segment of the plurality of segments;
determine a node to which the at least one segment is assigned; and
sending the IO request to the node to which the at least one segment is assigned via the primary IO request path to the node to which the at least one segment is assigned.
18. The computing system of claim 17 , wherein the IO request references a first segment assigned to a first node and a second segment assigned to a second node.
19. The computing system of claim 18 , wherein the processor is further configured to:
divide the IO request into a first portion referencing the first segment assigned to the first node and a second portion referencing the second segment assigned to the second node;
sending the first portion of the IO request to the first node via the primary IO request path defined for the first portion of the IO request; and
sending the second portion of the IO request to the second node via the primary IO request path defined for the second portion of the IO request.
20. The computing system of claim 16 , storing, at a node, the primary copy of the metadata associated with the one or more segments assigned to the node includes:
store, on each node, a copy of the metadata associated with the one or more segments assigned to each other node;
generate a shared lock for each page of the metadata associated with the one or more segments; and
provide, to the node to which the one or more segments are assigned, ownership of the shared lock for each page of the metadata associated with the one or more segments assigned to the node.