Distribution of snaps for load balancing data node clusters
Snaps are distributed among data nodes for load balancing and overload avoidance. A snap is initially associated with a first VNAS server on a first data node that hosts the primary volume being snapped. A second data node is selected based on loading. The second data node may be in the same or a different cluster. A second VNAS server is instantiated on the second data node. The snap is then mounted on the second VNAS server. The second VNAS server may be configured as the target for all reads to the snap. If the second data node is in a different cluster than the snap may be copied or moved from a first SAN node to a second SAN node. Multiple copies of snaps may be distributed, and individual snaps and copies may be associated with different SLOs.
1. An apparatus comprising:
a first data node;
a second data node;
a first storage area network (SAN) node that maintains client data on a primary volume associated with a filesystem maintained by a first virtual network attached storage (VNAS) server hosted by the first data node; and
program code in non-transitory memory comprising:
snap creation instructions that prompt creation of a snap of the primary volume on a snap volume on the first SAN node;
instantiation instructions that prompt instantiation of a second VNAS server hosted by the first data node;
instructions that mount the snap volume on the first SAN node on the second VNAS server;
copying instructions that copy the filesystem from the first VNAS server to the second VNAS server;
selection instructions that select the second data node based on load balancing, including loading associated with reads to the snap volume mounted on the second VNAS server;
instructions that instantiate a third VNAS server hosted by the second data node;
instructions that mount the snap volume on the third VNAS server;
instructions that unmount the snap volume from the second VNAS server, thereby prompting servicing all reads to the snap volume mounted on the third VNAS server, whereby snapped client data remains on the snap volume on the first SAN node and loading of the first data node associated with reads to the snap is moved from the first data node to the second data node;
wherein the snap volume is stored on a primary storage group of the first SAN node and comprising instructions that create a copy of the snap volume on a backup storage group and implement a first SLO (service level obligation) for access to the snap volume on a primary storage group and implement a second SLO for access to the copy of the snap volume on the backup storage group, where the first SLO is different than the second SLO.
2. The apparatus of claim 1 wherein the selection instructions balance loading of data nodes including the first data node within a first cluster.
3. The apparatus of claim 1 wherein the selection instructions balance loading of data nodes including the first data node within a plurality of clusters comprising a first cluster and a second cluster.
4. The apparatus of claim 3 wherein the first data node is in the first cluster and the second data node is in the second cluster and comprising instructions that copy or move the snap volume to a second SAN node that is in communication with the second data node.
5. The apparatus of claim 1 comprising instructions that create a snap device on the third VNAS server.
6. The apparatus of claim 1 comprising instructions that copy the filesystem from the second VNAS server to the third VNAS server.
7. The apparatus of claim 1 comprising instructions that configure the third VNAS server as a target for all reads to the snap.
8. The apparatus of claim 1 wherein the snap volume is stored on a primary storage group of the first SAN node and comprising instructions that create a copy of the snap volume outside the primary storage group.
9. The apparatus of claim 8 wherein the instructions that create the copy of the snap volume outside the primary storage group create a copy of the snap volume on a backup storage group.
10. A method comprising:
in a storage network comprising a first data node and a second data node in communication with a first storage area network (SAN) node that maintains client data on a primary volume associated with a filesystem maintained by a first virtual network attached storage (VNAS) server hosted by the first data node:
creating a snap of the primary volume on a snap volume on the first SAN node;
instantiating a second VNAS server hosted by the first data node;
mounting the snap volume on the second VNAS server;
copying the filesystem from the first VNAS server to the second VNAS server;
selecting the second data node based on load balancing, including loading associated with reads to the snap volume mounted on the second VNAS server;
instantiating a third VNAS server hosted by the second data node;
mounting the snap volume of the first SAN node on the third VNAS server;
unmounting the snap volume from the second VNAS server and servicing all reads to the snap volume with the third VNAS server;
wherein the snap is stored on a primary storage group of the first SAN node and comprising creating a copy of the snap volume on a backup storage group and implementing a first SLO (service level obligation) for access to the snap volume on the primary storage group and implementing a second SLO for access to the copy of the snap volume on the backup storage group, where the first SLO is different than the second SLO.
11. The method of claim 10 wherein selecting the second data node based on load balancing comprises balancing loading of data nodes including the first data node within a first cluster.
12. The method of claim 10 wherein selecting the second data node based on load balancing comprises balancing loading of data nodes including the first data node within a plurality of clusters comprising a first cluster and a second cluster.
13. The method of claim 12 , wherein the first data node is in the first cluster and the second data node is in the second cluster, comprising copying or moving the snap volume to a second SAN node that is in communication with the second data node.
14. The method of claim 10 comprising creating a snap device on the third VNAS server.
15. The method of claim 10 comprising copying the filesystem from the second VNAS server to the third VNAS server.
16. The method of claim 10 comprising configuring the third VNAS server as a target for all reads to the snap volume.
17. The method of claim 10 wherein the snap is stored on a primary storage group of the first SAN node and comprising creating a copy of the snap volume outside the primary storage group.
18. The method of claim 17 wherein creating the copy of the snap volume outside the primary storage group comprises creating a copy of the snap volume on a backup storage group.