Disk failure recovery for virtual disk with policies
View Patent ↗An administrator provisions a virtual disk in a remote storage platform and defines policies for that virtual disk. A virtual machine writes to and reads from the storage platform using any storage protocol. Virtual disk data within a failed storage pool is migrated to different storage pools while still respecting the policies of each virtual disk. Snapshot and revert commands are given for a virtual disk at a particular point in time and overhead is minimal. A virtual disk is cloned utilizing snapshot information and no data need be copied. Any number of Zookeeper clusters are executing in a coordinated fashion within the storage platform, thus increasing overall throughput. A timestamp is generated that guarantees a monotonically increasing counter, even upon a crash of a virtual machine. Any virtual disk has a “hybrid cloud aware” policy in which one replica of the virtual disk is stored in a public cloud.
1. A method of recovering from a disk failure within a storage platform of computer nodes, said method comprising:
detecting that a storage disk attached to one of said computer nodes has failed, said storage disk belonging to a failed storage pool of a plurality of storage disks;
identifying segments of data from a plurality of virtual disks that are stored within said failed storage pool, each of said virtual disks having policies that must be complied with;
for each of said segments, determining a candidate storage pool on a candidate computer node that complies with said policies of the virtual disk to which said each segment belongs;
retrieving from a metadata node of said storage platform, policies of one of said virtual disks;
comparing said retrieved policies of said one virtual disk with characteristics of one of said candidate storage pools and with characteristics of said candidate computer node; and
for each of said segments, copying a replica of said segment from a storage pool of said storage platform other than said failed storage pool onto said candidate storage pool, said candidate storage pool and the candidate computer node complying with the policies of the virtual disk to which said each segment belongs.
2. A method as recited in claim 1 further comprising:
disabling said failed storage pool to prevent data being written to or read from said disabled failed storage pool.
3. A method as recited in claim 1 wherein said policies of said virtual disks include a replication location policy and a residence policy.