Optimized record lookups

A system comprising:

• one or more processors;
• a computer-readable storage medium storing a lookup index, the lookup index comprising:
• a plurality of index buckets associated with storage units on the computer-readable storage medium, wherein each index bucket comprises a respective set of the storage units;
• a plurality of data object records representing data objects on a storage device, the plurality of data object records being stored in the storage units, each storage unit storing a respective portion of the plurality of data object records, the respective portion corresponding to a particular index bucket associated with the storage unit;
• a plurality of index filters stored in the storage units, each storage unit storing a respective index filter from the plurality of index filters, the respective index filter comprising at least one lookup entry corresponding to each of the respective portion of the plurality of data object records in the storage unit;
• and
• computer-readable instructions which, when executed by the one or more processors, cause the system to:
• in response to one or more input-output requests associated with a data object, identify a corresponding index bucket from the plurality of index buckets for the data object;
• query the respective index filter in each of the respective set of storage units associated with the corresponding index bucket for a data object record associated with the data object;
• and
• determine whether any of the set of storage units associated with the corresponding index bucket contains the data object record.

A non-transitory computer-readable storage medium comprising:

• storage units storing data object records representing data objects in a storage;
• and
• a lookup index comprising a plurality of index buckets, each index bucket being associated with a set of the storage units and comprising a respective index filter for each respective one of the set of storage units, the set of storage units containing a respective portion of the data object records, wherein each respective index filter comprises at least one lookup entry for each data object record in the respective one of the set of storage units;
• computer-readable instructions stored thereon which, when executed by one or more processors, cause the one or more processors to:
• receive an input-output request associated with a data object;
• and
• in response to the input-output request, perform a lookup operation for the data object on the lookup index, the lookup operation comprising:
• identifying an index bucket in the lookup index for the data object;
• and
• based on each respective index filter associated with the index bucket identified in the lookup index for the data object, determining whether any of the set of storage units associated with the index bucket contains a data object record corresponding to the data object.

A non-transitory computer-readable storage medium comprising:

• computer-readable instructions stored thereon which, when executed by one or more processors, cause the one or more processors to:
• identify a plurality of dirty object records corresponding to an index bucket in a lookup index, the index bucket being associated with a set of storage units on a storage, the plurality of dirty object records being queued for copying to one or more of the set of storage units;
• for each respective storage unit from the set of storage units:
• determine a first respective number of the plurality of dirty object records that can be added to the respective storage unit, the first respective number being based on at least one of a number of available object record slots in the respective storage unit and a number of new object records in the plurality of dirty object records;
• and
• determine, from the plurality of dirty object records, a second respective number of object records associated with the respective storage unit;
• based on the first respective number of the plurality of dirty object records that can be added to the respective storage unit and the second respective number of object records associated with the respective storage unit, select a particular storage unit from the set of storage units for the plurality of dirty object records;
• identify which dirty object records from the plurality of dirty object records to copy to the particular storage unit based on the number of new object records in the plurality of dirty object records and the second respective number of object records associated with the particular storage unit;
• and
• update the particular storage unit based on the dirty object records identified.