Database synchronization using resizable invertible bloom filters with database snapshots
A centralized database management system performs data synchronization with lower bandwidth consumption and higher efficiency using a resizable invertible bloom filter. The system may include a resizable invertible bloom filter module that constructs and maintains invertible bloom filters that are resizable based on a number of differences between different snapshots. The resizable invertible bloom filter module may maintain a list of possible sizes for a resizable invertible bloom filter. The resizable invertible bloom filter module may determine and maintain a list of applicable partition sizes, each partition size being a product of a divisor and a resizing factor. If the number of differences exceeds the number of expected differences and results in failure in decoding, the system may retry a larger size in a set of predetermined sizes. The system may continue to try larger sizes until a minimal size required for successful decoding is found.
1. A method comprising:
generating a first resizable invertible bloom filter of a source data table based on information of the source data table at a first point in time;
generating a second resizable invertible bloom filter for the source data table based on information of the source data table at a second point in time, wherein the first resizable invertible bloom filter and the second resizable invertible bloom filter have a same first size that is determined based on an estimated number of changes in the source data table between the first point in time and the second point in time;
determining an actual number of changes in the source data table between the first point in time and the second point in time;
responsive to the actual number of changes being greater than the estimated number of changes, expanding the first size of the first and second resizable invertible bloom filters to a second size by reassigning elements from the first and the second resizable invertible bloom filters, the expanding resulting in a first expanded resizable invertible bloom filter and a second expanded resizable invertible bloom filter;
identifying changes in the source data table that occurred between the first point in time and the second point in time based on the first expanded resizable invertible bloom filter and the second expanded resizable invertible bloom filter; and
sending instructions to a destination data table, the instructions comprising information to perform an operation that synchronizes the destination data table with the source data table based on the identified changes.
2. The method of claim 1 , wherein the first and second sizes are determined based on mathematical constraints.
3. The method of claim 1 , wherein the first and second sizes are determined based on a set of prime divisors and a set of resizing factors, and wherein each size is a product of a prime divisor of the set of prime divisors and a resizing factor of the set of resizing factors.
4. The method of claim 3 , wherein each resizing factor of the set of resizing factors is a prime number.
5. The method of claim 4 , wherein each prime divisor of the set of prime divisors is multiplied by each resizing factor of the set of resizing factors in descending order.
6. The method of claim 3 , wherein each prime divisor in the set of prime divisors has a same value, and wherein each prime divisor of the set of prime divisors is multiplied by each resizing factor of the set of resizing factors.
7. The method of claim 1 , wherein identifying the changes in the source data table further comprises:
generating a third resizable invertible bloom filter by subtracting the second resizable invertible bloom filter from the first resizable invertible bloom filter, the third resizable invertible bloom filter comprising information associated with a change in the source data table that occurred between the first point in time and the second point in time.
8. The method of claim 7 , further comprising identifying the changes by decoding the third invertible bloom filter.
9. A non-transitory computer-readable storage medium storing executable computer instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the instructions comprising instructions to:
generate a first resizable invertible bloom filter of a source data table based on information of the source data table at a first point in time;
generate a second resizable invertible bloom filter for the source data table based on information of the source data table at a second point in time, wherein the first resizable invertible bloom filter and the second resizable invertible bloom filter have a same first size that is determined based on an estimated number of changes in the source data table between the first point in time and the second point in time;
determine an actual number of changes in the source data table between the first point in time and the second point in time;
responsive to the actual number of changes being greater than the estimated number of changes, expand the first size of the first and second resizable invertible bloom filters to a second size by reassigning elements from the first and the second resizable invertible bloom filters based, the expanding resulting in a first expanded resizable invertible bloom filter and a second expanded resizable invertible bloom filter;
identify changes in the source data table that occurred between the first point in time and the second point in time based on the first expanded resizable invertible bloom filter and the second expanded resizable invertible bloom filter; and
send instructions to a destination data table, the instructions comprising information to perform an operation that synchronizes the destination data table with the source data table based on the identified changes.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the first and second sizes are determined based on mathematical constraints.
11. The non-transitory computer-readable storage medium of claim 9 , wherein the first and second sizes are determined based on a set of prime divisors and a set of resizing factors, and wherein each size is a product of a prime divisor of the set of prime divisors and a resizing factor of the set of resizing factors.
12. The non-transitory computer-readable storage medium of claim 11 , wherein each resizing factor of the set of resizing factors is a prime number.
13. The non-transitory computer-readable storage medium of claim 12 , wherein each prime divisor of the set of prime divisors is multiplied by each resizing factor of the set of resizing factors in descending order.
14. The non-transitory computer-readable storage medium of claim 11 , wherein each prime divisor in the set of prime divisors has a same value, and wherein each prime divisor of the set of prime divisors is multiplied by each resizing factor of the set of resizing factors.
15. The non-transitory computer-readable storage medium of claim 9 , wherein identifying the changes in the source data table further comprises:
generating a third resizable invertible bloom filter by subtracting the second resizable invertible bloom filter from the first resizable invertible bloom filter, the third resizable invertible bloom filter comprising information associated with a change in the source data table that occurred between the first point in time and the second point in time.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions comprising instructions to identify the changes by decoding the third invertible bloom filter.
17. A computing system comprising:
a processor; and
a non-transitory computer-readable storage medium storing instructions, the instructions when executed by the processor cause the processor to perform steps including:
generating a first resizable invertible bloom filter of a source data table based on information of the source data table at a first point in time;
generating a second resizable invertible bloom filter for the source data table based on information of the source data table at a second point in time, wherein the first resizable invertible bloom filter and the second resizable invertible bloom filter have a same first size that is determined based on an estimated number of changes in the source data table between the first point in time and the second point in time;
determining an actual number of changes in the source data table between the first point in time and the second point in time;
responsive to the actual number of changes being greater than the estimated number of changes, expanding the first size of the first and second resizable invertible bloom filters to a second size by reassigning elements from the first and the second resizable invertible bloom filters, the expanding resulting in a first expanded resizable invertible bloom filter and a second expanded resizable invertible bloom filter;
identifying changes in the source data table that occurred between the first point in time and the second point in time based on the first expanded resizable invertible bloom filter and the second expanded resizable invertible bloom filter; and
sending instructions to a destination data table, the instructions comprising information to perform an operation that synchronizes the destination data table with the source data table based on the identified changes.
18. The system of claim 17 , wherein the first and second sizes are determined based on a set of prime divisors and a set of resizing factors, and wherein each size is a product of a prime divisor of the set of prime divisors and a resizing factor of the set of resizing factors.
19. The system of claim 17 , wherein identifying the changes in the source data table further comprises:
generating a third resizable invertible bloom filter by subtracting the second resizable invertible bloom filter from the first resizable invertible bloom filter, the third resizable invertible bloom filter comprising information associated with a change in the source data table that occurred between the first point in time and the second point in time.
20. The system of claim 19 , wherein the steps further include identifying the changes by decoding the third invertible bloom filter.