Optimized autonomous defragmentation of storage devices
The present disclosure generally relates to determining host device read patterns and then matching autonomous defragmentation to the read pattern to reduce latency impact and avoid unnecessary write amplification (WA). Host devices tend to read data in similar sized chunks. Additionally, host devices tend to read certain data sequentially. Based upon the typical chunk size and data read, the data can be defragmented in sizes to match the typical host device read chunks, and the data defragmented can then be read sequentially within a same plane even if the defragmented data is on different dies. The data is defragmented without relying upon a host command to be presented. Background operation time is used to move updated data such that a future sequential read is supported.
1. A data storage device, comprising:
a memory device; and
a controller coupled to the memory device, wherein the controller is configured to:
store sequentially read logical block address (LBA) coordinates in the memory device;
mark one or more segments of the sequentially read LBA coordinates as candidates for defragmentation;
select one or more candidates from relocation to one or more defragmentation blocks in the memory device;
write the selected one or more candidates to the one or more defragmentation blocks;
mark the one or more segments as urgent for defragmentation and process a read request; and
begin background operations (BKOPS) after processing the read request, wherein the defragmenting begins during BKOPS.
2. The data storage device of claim 1 , wherein the marked one or more segments are stored in non-volatile memory.
3. The data storage device of claim 1 , wherein the marked one or more segments are LBA overwrites.
4. The data storage device of claim 1 , wherein the writing comprises writing multiple candidates and wherein the multiple candidates are written to different memory dies of the memory device.
5. The data storage device of claim 4 , wherein the multiple candidates are written to a same plane on the different memory dies.
6. The data storage device of claim 1 , wherein the controller is configured to detect read trends of a host device.
7. The data storage device of claim 6 , wherein the one or more defragmentation blocks are selected based upon the detected read trends.
8. The data storage device of claim 1 , wherein the one or more segments are sized to reflect a size of data chunks read by a host device.
9. The data storage device of claim 1 , wherein the writing occurs to a same die and plane from which the one or more segments are marked.
10. A data storage device, comprising:
a memory device; and
a controller coupled to the memory device, wherein the controller is configured to:
monitor a host device's read length pattern;
record the host device's read length pattern;
utilize the recorded host device's read length pattern to set defragmentation granularity;
defragment data stored in the memory device;
mark one or more segments as urgent for defragmentation and process a read request; and
begin background operations (BKOPS) after processing a read request, wherein the defragmenting begins during BKOPS.
11. The data storage device of claim 10 , wherein the recording comprises maintaining a histogram of each data segment read.
12. The data storage device of claim 11 , wherein the histogram indicates a number of reads of each length.
13. The data storage device of claim 10 , wherein the controller is configured to detect a logical block address (LBA) overwrite has occurred prior to defragmenting the data.
14. The data storage device of claim 10 , wherein the host device's read length pattern indicates a number of word lines to be relocated during the defragmenting.
15. A data storage device, comprising:
memory means; and
a controller coupled to the memory means, wherein the controller is configured to:
detect a pattern of host device read requests;
log host device access rate to data;
defragment the data based upon the detected pattern;
mark one or more segments as urgent for defragmentation and process a read request; and
begin background operations (BKOPS) after processing a read request, wherein the defragmenting begins during BKOPS.
16. The data storage device of claim 15 , wherein detecting a pattern comprises determining whether the host device provides read requests within a threshold timeframe.
17. The data storage device of claim 15 , wherein a timing of the defragmentation is based upon the detected pattern.
18. The data storage device of claim 15 , wherein the controller is configured to detect a rewrite request of the host device.
19. The data storage device of claim 15 , wherein the defragmenting comprises rewriting segments of the data to other locations of the memory means, wherein the segments are sized based upon the detected host device read requests.
20. The data storage device of claim 15 , wherein the defragmenting comprises rewriting data that has been overwritten, wherein the data that has been overwritten is a part of a larger data segment, wherein only the data that has been overwritten is rewritten to a new location in the memory means, and wherein other data of the larger data segment remains in place in the memory means.