Using a raw mirror to initialize a storage system
A method of initializing a data storage system (DSS) is provided. The method includes (a) in response to the DSS booting, reading data from a first plurality of disks marked as part of a raw mirror which mirrors configuration data of the DSS between the first plurality of disks; (b) comparing sequence numbers from the read data read and selecting data from a disk of the first plurality having a latest sequence number; (c) obtaining configuration data of the DSS from the selected data; (d) using the configuration data to construct a topology of the DSS which includes information describing a relationship between a second plurality of disks of the DSS, RAID groups of the DSS, and logical disks presented to users, the second plurality of disks being larger than and including the first plurality of disks; and (e) initializing the RAID groups and the logical disks described by the topology based on the information of the topology.
1. A method of initializing a data storage system (DSS), the method comprising:
in response to the DSS booting, reading data from a first plurality of disks of the DSS which are marked as part of a raw mirror, the raw mirror mirroring configuration data of the DSS between the first plurality of disks, wherein reading the data from the first plurality of disks includes:
reading a plurality of blocks from each of the first plurality of disks and
calculating checksums for each block read and comparing to a checksum stored for that block;
comparing sequence numbers from the data read from each of the first plurality of disks and selecting data from a disk of the first plurality of disks having a latest sequence number, including:
comparing sequence numbers read from corresponding blocks of the first plurality of disks, including excluding blocks whose calculated checksums do not match their stored checksums and
selecting, on a block-by-block basis, a block having the latest sequence number;
obtaining configuration data of the DSS from the selected data;
using the configuration data to construct a topology of the DSS, the topology including information describing a relationship between a second plurality of disks of the DSS, RedundantArray of Independent Disks (RAID) groups of the DSS, and logical disks presented by the DSS to users, the second plurality of disks being larger than and including the first plurality of disks; and
initializing the RAID groups and the logical disks described by the topology based on the information of the topology.
2. The method of claim 1 wherein the method further comprises:
marking the blocks whose calculated checksums do not match their stored checksums as having errors; and
operating a background service to rebuild the blocks marked as having errors.
3. The method of claim 1 wherein reading the data from the first plurality of disks further includes checking each block fora magic number that identifies that block as being part of the raw mirror.
4. A computer program product comprising a non-transitory computer-readable medium storing instructions, which, when performed by processing circuitry of a data storage system (DSS), cause the DSS to initialize by:
in response to the DSS booting, reading data from a first plurality of disks of the DSS which are marked as part of a raw mirror, the raw mirror mirroring configuration data of the DSS between the first plurality of disks, wherein reading the data from the first plurality of disks includes:
reading a plurality of blocks from each of the first plurality of disks and
calculating checksums for each block read and comparing to a checksum stored for that block;
comparing sequence numbers from the data read from each of the first plurality of disks and selecting data from a disk of the first plurality of disks having a latest sequence number, including:
comparing sequence numbers read from corresponding blocks of the first plurality of disks including excluding blocks whose calculated checksums do not match their stored checksums and
selecting, on a block-by-block basis, a block having the latest sequence number;
obtaining configuration data of the DSS from the selected data;
using the configuration data to construct a topology of the DSS, the topology including information describing a relationship between a second plurality of disks of the DSS, RedundantArray of Independent Disks (RAID) groups of the DSS, and logical disks presented by the DSS to users, the second plurality of disks being larger than and including the first plurality of disks; and
initializing the RAID groups and the logical disks described by the topology based on the information of the topology.
5. The computer program product of claim 4 wherein the instructions, when performed by the processing circuitry, further cause the DSS to:
mark the blocks whose calculated checksums do not match their stored checksums as having errors; and
operate a background service to rebuild the blocks marked as having errors.
6. The computer program product of claim 4 wherein reading the data from the first plurality of disks further includes checking each block fora magic number that identifies that block as being part of the raw mirror.