Memory allocation buffer for reduction of heap fragmentation
View Patent ↗Systems and methods of a memory allocation buffer to reduce heap fragmentation. In one embodiment, the memory allocation buffer structures a memory arena dedicated to a target region that is one of a plurality of regions in a server in a database cluster such as an HBase cluster. The memory area has a chunk size (e.g., 2 MB) and an offset pointer. Data objects in write requests targeted to the region are received and inserted to the memory arena at a location specified by the offset pointer. When the memory arena is filled, a new one is allocated. When a MemStore of the target region is flushed, the entire memory arenas for the target region are freed up. This reduces heap fragmentation that is responsible for long and/or frequent garbage collection pauses.
1. A method for reducing delays due to memory fragmentation in a region server hosting a plurality of regions for a distributed database system, the region server maintaining a heap in the region server's memory, the method comprising:
implementing, at the region server, an in-memory store for each region, wherein the in-memory store for each region is to hold data to be written until the data reaches a predetermined size and to flush the data to a storage when the predetermined size is reached;
receiving a write request from a client, wherein the write request includes a target region and an data object for insertion into the target region; and
storing the data object in a memory arena dedicated to the target region at a location that is continued from a previous location such that, when an in-memory store for the target region flushes the data, space freed from the memory arena dedicated to the target region is contiguous,
wherein the memory arena dedicated to the target region is a space dedicated to the target region in the heap.
2. The method of claim 1 , wherein said storing the data object step is performed based on an availability of the memory arena dedicated to the target region.
3. The method of claim 1 , further comprising:
determining that the memory arena dedicated to the target region is unavailable; and
creating, in the heap, the memory arena dedicated to the target region by allocating one space of a select size in the heap.
4. The method of claim 3 , wherein the memory arena dedicated to the target region is determined unavailable when the memory arena dedicated to the target region does not exist in the heap.
5. The method of claim 3 , wherein the memory arena dedicated to the target region is determined unavailable when the memory arena dedicated to the target region does not have enough space for the data object.
6. The method of claim 1 , further comprising:
locating, in the heap, the memory arena dedicated to the target region; and
determining that the memory arena has enough space for the data object.
7. The method of claim 1 , further comprising:
locating, in the heap, the memory arena dedicated to the target region;
determining that the memory arena has not enough space for the data object; and
creating, in the heap, a new memory arena in the heap as the memory arena dedicated to the target region.
8. A server hosting a plurality of regions for a distributed database system, the server maintaining a heap in a memory of the server, the server's memory including instructions which, upon executed by a processor of the server, instruct the server to perform:
implementing, at the region server, an in-memory store for each region, wherein the in-memory store for each region is to hold data to be written until the data reaches a predetermined size and to flush the data to a storage when the predetermined size is reached;
receiving a write request from a client, wherein the write request includes a target region and an data object for insertion into the target region; and
storing the data object in a memory arena dedicated to the target region at a location that is continued from a previous location such that, when an in-memory store for the target region flushes the data, space freed from the memory arena dedicated to the target region is contiguous,
wherein the memory arena dedicated to the target region is a space dedicated to the target region in the heap.
9. The server of claim 8 , wherein said storing the data object step is performed based on an availability of the memory arena dedicated to the target region.
10. The server of claim 8 , further comprising:
determining that the memory arena dedicated to the target region is unavailable; and
creating, in the heap, the memory arena dedicated to the target region by allocating one space of a select size in the heap.
11. The server of claim 10 , wherein the memory arena dedicated to the target region is determined unavailable when the memory arena dedicated to the target region does not exist in the heap.
12. The server of claim 10 , wherein the memory arena dedicated to the target region is determined unavailable when the memory arena dedicated to the target region does not have enough space for the data object.
13. The server of claim 8 , further comprising:
locating, in the heap, the memory arena dedicated to the target region; and
determining that the memory arena has enough space for the data object.
14. The server of claim 8 , further comprising:
locating, in the heap, the memory arena dedicated to the target region;
determining that the memory arena has not enough space for the data object; and
creating, in the heap, a new memory arena in the heap as the memory arena dedicated to the target region.
15. A non-transitory machine-readable storage medium including executable instructions, which when executed by a processor, cause the processor to:
implement, at a server hosting a plurality of regions for a distributed database system and maintaining a heap in the server's memory, an in-memory store for each region, wherein the in-memory store for each region is to hold data to be written until the data reaches a predetermined size and to flush the data to a storage when the predetermined size is reached;
receive a write request from a client, wherein the write request includes a target region and an data object for insertion into the target region; and
store the data object in a memory arena dedicated to the target region at a location that is continued from a previous location such that, when an in-memory store for the target region flushes the data, space freed from the memory arena dedicated to the target region is contiguous,
wherein the memory arena dedicated to the target region is a space dedicated to the target region in the heap.
16. The medium of claim 15 , wherein said storing the data object step is performed based on an availability of the memory arena dedicated to the target region.
17. The medium of claim 15 , further comprising instructions that cause the processor to:
determine that the memory arena dedicated to the target region is unavailable; and
create, in the heap, the memory arena dedicated to the target region by allocating one space of a select size in the heap.
18. The medium of claim 17 , wherein the memory arena dedicated to the target region is determined unavailable when the memory arena dedicated to the target region does not exist in the heap or when the memory arena dedicated to the target region does not have enough space for the data object.
19. The medium of claim 15 , further comprising instructions that cause the processor to:
locate, in the heap, the memory arena dedicated to the target region; and
determine that the memory arena has enough space for the data object.
20. The medium of claim 15 , further comprising instructions that cause the processor to:
locate, in the heap, the memory arena dedicated to the target region;
determine that the memory arena has not enough space for the data object; and
create, in the heap, a new memory arena in the heap as the memory arena dedicated to the target region.