System and method for improving write performance for log structured storage systems
A method, computer program product, and computer system for identifying, by a computing device, a list of objects containing a plurality of physical layer blocks (PLBs). One or more next PLBs of the plurality of PLBs may be allocated from a selected free object of the list of objects. One or more additional free objects from the list of objects may be generated. Garbage collection may be performed between an inactive object of the plurality of objects and the selected free object.
1. A computer-implemented method comprising:
identifying, by a computing device, a list of objects containing a plurality of blocks;
allocating one or more next blocks of the plurality of blocks from a selected free object of the list of objects, wherein the selected free object is chosen and marked as active, wherein the selected free object receives all of the one or more next blocks while marked as active;
generating one or more additional free objects from the list of objects; and
performing garbage collection between an inactive object of the plurality of objects and the selected free object.
2. The computer-implemented method of claim 1 wherein an object containing the plurality of blocks is one of a super block and an Uber, wherein a super block includes a first number of blocks, wherein an Uber includes a second number of blocks.
3. The computer-implemented method of claim 1 wherein the selected free object is randomly chosen.
4. The computer-implemented method of claim 1 wherein performing garbage collection includes identifying a semi-populated object of the list of objects.
5. The computer-implemented method of claim 4 wherein performing garbage collection further includes performing garbage collection on each block in the semi-populated object.
6. The computer-implemented method of claim 5 wherein performing garbage collection further includes sequentially writing each of the blocks in the semi-populated object to the selected free object.
7. The computer-implemented method of claim 6 further comprising informing a drive where the semi-populated object is stored that the semi-populated object is free to be erased without requiring the drive to perform garbage collection.
8. A computer program product residing on a non-transitory computer readable storage medium having a plurality of instructions stored thereon which, when executed across one or more processors, causes at least a portion of the one or more processors to perform operations comprising:
identifying, by a computing device, a list of objects containing a plurality of blocks;
allocating one or more next blocks of the plurality of blocks from a selected free object of the list of objects, wherein the selected free object is chosen and marked as active, wherein the selected free object receives all of the one or more next blocks while marked as active;
generating one or more additional free objects from the list of objects; and
performing garbage collection between an inactive object of the plurality of objects and the selected free object.
9. The computer program product of claim 8 wherein an object containing the plurality of blocks is one of a super block and an Uber, wherein a super block includes a first number of blocks, wherein an Uber includes a second number of blocks.
10. The computer program product of claim 8 wherein the selected free object is randomly chosen.
11. The computer program product of claim 8 wherein performing garbage collection includes identifying a semi-populated object of the list of objects.
12. The computer program product of claim 11 wherein performing garbage collection further includes performing garbage collection on each block in the semi-populated object.
13. The computer program product of claim 12 wherein performing garbage collection further includes sequentially writing each of the blocks in the semi-populated object to the selected free object.
14. The computer program product of claim 13 wherein the operations further comprise informing a drive where the semi-populated object is stored that the semi-populated object is free to be erased without requiring the drive to perform garbage collection.
15. A computing system including one or more processors and one or more memories configured to perform operations comprising:
identifying, by a computing device, a list of objects containing a plurality of blocks;
allocating one or more next blocks of the plurality of blocks from a selected free object of the list of objects, wherein the selected free object is chosen and marked as active, wherein the selected free object receives all of the one or more next blocks while marked as active;
generating one or more additional free objects from the list of objects; and
performing garbage collection between an inactive object of the plurality of objects and the selected free object.
16. The computing system of claim 15 wherein an object containing the plurality of blocks is one of a super block and an Uber, wherein a super block includes a first number of blocks, wherein an Uber includes a second number of blocks.
17. The computing system of claim 15 wherein the selected free object is randomly chosen.
18. The computing system of claim 15 wherein performing garbage collection includes identifying a semi-populated object of the list of objects.
19. The computing system of claim 18 wherein performing garbage collection further includes performing garbage collection on each block in the semi-populated object.
20. The computing system of claim 19 wherein performing garbage collection further includes sequentially writing each of the blocks in the semi-populated object to the selected free object, and wherein the operations further comprise informing a drive where the semi-populated object is stored that the semi-populated object is free to be erased without requiring the drive to perform garbage collection.