High availability distributed deduplicated storage system

1. A computer-implemented method of performing a storage operation in a distributed, deduplicated storage system, the method comprising:

during a period of availability of a first deduplication database computing device of a plurality of deduplication database computing devices and a second deduplication database computing device of the plurality of deduplication database computing devices,

the plurality of deduplication database computing devices storing signature blocks corresponding to a plurality of data blocks stored in one or more secondary storage devices of secondary storage, the plurality of data blocks corresponding to data blocks received from primary storage,

at least one signature block of the signature blocks comprising a signature of at least one data block of the plurality of data blocks, location information of the at least one data block in the one or more secondary storage devices, and a reference count value indicative of a quantity of one or more references in the secondary storage to the at least one data block,

the first deduplication database computing device configured to store a first subset of the signature blocks based at least in part on a data block distribution policy and designated as a failover deduplication database computing device for the second deduplication database computing device that is configured to store, based at least in part on the data block distribution policy, a second subset of the signature blocks that is different from and does not overlap with the first subset of the signature blocks;

receiving at a secondary storage computing device comprising a failover index and communicatively coupled to the plurality of deduplication database computing devices, a first set of one or more signatures corresponding to one or more data blocks stored in primary storage;

identifying, based at least in part on the data block distribution policy, the second deduplication database computing device as the deduplication database computing device assigned to store the first set of one or more signatures;

determining, based at least in part on a query of the failover index, that at least one signature of the first set of one or more signatures matches at least one signature of a second set of one or more signatures that was stored in the first deduplication database computing device during a previous period of unavailability of the second deduplication database computing device;

querying the first deduplication database computing device for the at least one signature of the first set of one or more signatures;

receiving from the first deduplication database computing device a location of a copy of a data block corresponding to the at least one signature of the first set of one or more signatures; and

storing in the secondary storage the location of the copy of the data block corresponding to the at least one signature of the first set of one or more signatures.

2. The method of claim 1 , wherein following the period of unavailability, the method further comprises:

determining that the second deduplication database computing device is available; and

in response to said determining that the second deduplication database computing device is available, copying the second set of one or more signatures from the first deduplication database computing device to the second deduplication database computing device.

3. The method of claim 1 , wherein following the period of unavailability, the method further comprises:

determining that the second deduplication database computing device is available; and

in response to determining that the second deduplication database computing device is available, retaining the first set of one or more signatures at the first deduplication database computing device.

4. The method of claim 1 , wherein each deduplication database computing device of the plurality of deduplication database computing devices is identified as a failover deduplication database computing device to at least another one of the plurality of deduplication database computing devices.

5. The method of claim 1 , further comprising identifying a third deduplication database computing device as the failover deduplication database computing device for the first deduplication database computing device and identifying the second deduplication database computing device as the failover deduplication database computing device for the third deduplication database computing device.

6. A distributed deduplicated storage system, comprising:

a plurality of deduplication database computing devices configured to store signature blocks corresponding to a plurality of data blocks stored in one or more secondary storage devices of secondary storage, the plurality of data blocks corresponding to data blocks received from primary storage, at least one signature block of the signature blocks comprising a signature of at least one data block of the plurality of data blocks, location information of the at least one data block in the one or more secondary storage devices, and a reference count value indicative of a quantity of one or more references in the secondary storage to the at least one data block,

wherein a first deduplication database computing device of the plurality of deduplication database computing devices is configured to store a first subset of the signature blocks based at least in part on a data block distribution policy and is identified as a failover deduplication database computing device for a second deduplication database computing device of the plurality of deduplication database computing devices that is configured to store, based at least in part on the data block distribution policy, a second subset of the signature blocks that is different from and does not overlap with the first subset of the signature blocks; and

a plurality of secondary storage computing devices communicatively coupled to the plurality of deduplication database computing devices, each of the plurality of secondary storage computing devices comprising one or more processors and storage, wherein following a period of unavailability of the second deduplication database computing device, at least one secondary storage computing device of the plurality of secondary storage computing devices further comprising a failover index is configured to:

receive a first set of one or more signatures corresponding to one or more data blocks stored in the primary storage,

identify, based at least in part on the data block distribution policy, the second deduplication database computing device as being assigned to store the first set of one or more signatures,

determine, based at least in part on a query of the failover index, that at least one signature of the first set of one or more signatures matches at least one signature of a second set of one or more signatures that was stored in the first deduplication database computing device during the period of unavailability of the second deduplication database computing device,

query the first deduplication database computing device for the at least one signature of the first set of one or more signatures,

receive from the first deduplication database computing device a location of a copy of a data block corresponding to the at least one signature of the first set of one or more signatures, and

store in the secondary storage the location of the copy of the data block corresponding to the at least one signature of the first set of one or more signatures.

7. The system of claim 6 , wherein following the period of unavailability, the at least one secondary storage computing device is further configured to:

determine that the second deduplication database computing device is available; and

copy the second set of one or more signatures from the first deduplication database computing device to the second deduplication database computing device.

8. The system of claim 6 , wherein following the period of unavailability, the at least one secondary storage computing device is further configured to:

determine that the second deduplication database computing device is available; and

retain the first set of one or more signatures at the first deduplication database computing device.

9. The system of claim 6 , wherein each deduplication database computing device of the plurality of deduplication database computing devices is identified as a failover deduplication database computing device to at least another one of the plurality of deduplication database computing devices.

10. The system of claim 6 , further comprising a third deduplication database computing device identified as the failover deduplication database computing device for the first deduplication database computing device, wherein the second deduplication database computing device is identified as the failover deduplication database computing device for the third deduplication database computing device.

11. A computer-implemented method of performing a storage operation in a distributed, deduplicated storage system, comprising:

designating a first deduplication database computing device of a plurality of deduplication database computing devices as a failover deduplication database computing device for a second deduplication database computing device of the plurality of the plurality of deduplication database computing devices,

the plurality of deduplication database computing devices storing signature blocks corresponding to a plurality of data blocks stored in one or more secondary storage devices of secondary storage, the plurality of data blocks corresponding to data blocks received from primary storage,

at least one signature block of the signature blocks comprising a signature of at least one data block of the plurality of data blocks, location information of the at least one data block in the one or more secondary storage devices, and a reference count value indicative of a quantity of one or more references in the secondary storage to the at least one data block,

the first deduplication database computing device configured to store a first subset of the signature blocks based at least in part on a data block distribution policy and the second deduplication database computing device configured to store a second subset of the signature blocks that is different from and does not overlap with the first subset of the signature blocks based at least in part on the data block distribution policy;

during a period of unavailability of the second deduplication database computing device and as part of a first secondary copy operation:

receiving at a secondary storage computing device comprising a failover index and communicatively coupled to the plurality of deduplication database computing devices, a first set of one or more signatures comprising one or more signatures which correspond to one or more data blocks stored in primary storage;

determining that the second deduplication database computing device is unavailable; and

storing the first set of one or more signatures in the first deduplication database computing device;

after the period of unavailability of the second deduplication database computing device:

determining that the second deduplication database computing device is available;

receiving at the secondary storage computing at least one signature of a second set of one or more signatures that matches at least one signature of the first set of one or more signatures that was stored in the first deduplication database computing device during the period of unavailability of the second deduplication database computing device;

querying, based at least in part on a search of the failover index, the first deduplication database computing device for the at least one signature of the second set of one or more signatures;

receiving from the first deduplication database computing device a location of a copy of a data block corresponding to the at least one signature of the second set of one or more signatures; and

storing in the secondary storage the location of the copy of the data block corresponding to the at least one signature of the second set of one or more signatures.

12. The method of claim 11 , wherein following the period of unavailability, the method further comprises copying one or more signature block entries corresponding to the first set of one or more signatures to the second deduplication database computing device.

13. The method of claim 11 , wherein following the period of unavailability, the method further comprises retaining one or more signature block entries corresponding to the first set of one or more signatures at the first deduplication database computing device.