Dynamic overprovisioning of storage device
The over-provisioning (OP) of a physical storage device (PSD) may be increased, and the useful life of the PSD increased, by converting uncompressed data stored on the PSD to compressed data. It may be determined that increasing the useful life of the PSD, and the data reduction resulting from the compression, outweigh the benefit of faster I/O response times if the data remains uncompressed. A first portion of the PSD may be initially reserved for compression. A second portion of the PSD may store compressed data. It may be determined whether it is desirable to increase the OP of the PSD to thereby reduce the effective write rate on the PSD. If compression is determined to be desirable, the dynamic portion may be compressed, thereby reducing the amount of storage space consumed by the data, and freeing up storage space that can be used by the PSD for OP.
1. A method comprising:
determining, at a first point in time, a current write rate for a physical storage device including a first portion designated for dynamically compressed data and a second portion designated for compressed data, wherein data in the first portion is initially uncompressed;
determining to increase over-provisioning for the physical storage device based at least in part on the current write rate over a current lifetime of the physical storage device up to the first point in time; and
responsive to said determining to increase the over-provisioning, compressing data in the first portion designated for dynamically compressed data, wherein said compressing data in the first portion responsive to said determining to increase over-provisioning based at least in part on the current write rate results in one or more unused sub-portions of the first portion and use of the one or more unused sub-portions for over-provisioning.
2. The method of claim 1 , wherein said determining to increase the over-provisioning includes:
determining an adjusted write rate that would enable the physical storage device to endure until a predefined endurance date; and
determining whether to increase the over-provisioning based at least in part on the adjusted write rate and an estimated decrease in write rate to the physical storage device if the first portion were compressed.
3. The method of claim 2 , further comprising:
for each of a plurality of over-provisioning increases on the physical storage device, determining a write amplification reduction resulting from said each over-provisioning increase,
wherein said determining whether to increase the over-provisioning includes:
estimating an over-provisioning increase if the first portion is increased; and
determining the estimated decrease in write rate based on the estimated over-provisioning increase.
4. The method of claim 1 , wherein the first portion corresponds to a plurality of tracks of one or more LSUs (logical storage units), wherein, for each of the plurality of tracks of one of the LSUs, a data structure for said one LSU includes an entry specifying that said each track is included in the first data portion designated for dynamically compressed data.
5. The method of claim 4 , wherein, for each of the plurality of tracks, a corresponding entry in the data structure specifies a location and length of the said each track within the first portion, and wherein the method further comprises:
for each of the plurality of tracks, updating the corresponding entry in the data structure for said each LSU of said each track in response to the compression of the data portion to reflect a reduced length of said each track.
6. The method of claim 1 , further comprising:
determining an endurance increase factor,
wherein said determining whether to increase the over-provisioning for the physical storage device is based at least in part on the endurance increase factor.
7. The method of claim 1 , wherein the current write rate is a first current write rate determined at the first point in time, and wherein the method further comprises, after said compressing data in the first portion:
determining a second current write rate for the physical storage device at a second point in time after the first point in time;
determining whether to decrease over-provisioning for the physical storage device based on the second current write rate;
if it is determined to decrease the over-provisioning, decompressing data in the first portion; and
as a result of said decompressing, allocating one or more sub-portions being used for over-provisioning to the first portion.
8. A system comprising:
a physical storage device including a first portion designated for dynamically compressed data and a second portion designated for compressed data, wherein data in the first portion is initially uncompressed;
executable logic that implements a method including:
determining, at a first point in time, a current write rate for the physical storage device;
determining to increase over-provisioning for the physical storage device based at least in part on the current write rate over a current lifetime of the physical storage device up to the first point in time; and
responsive to said determining to increase the over-provisioning, compressing data in the first portion designated for dynamically compressed data, wherein said compressing data in the first portion responsive to said determining to increase over-provisioning based at least in part on the current write rate results in one or more unused sub-portions of the first portion and use of the one or more unused sub-portions for over-provisioning.
9. The system of claim 8 , wherein said determining to increase the over-provisioning includes:
determining an adjusted write rate that would enable the physical storage device to endure until a predefined endurance date; and
determining whether to increase the over-provisioning based at least in part on the adjusted write rate and an estimated decrease in write rate to the physical storage device if the first portion were compressed.
10. The system of claim 9 , wherein the method further includes:
for each of a plurality of over-provisioning increases on the first physical storage device, determining a write amplification reduction resulting from said each over-provisioning increase,
wherein said determining whether to increase the over-provisioning includes:
estimating an over-provisioning increase if the first portion is increased; and
determining the estimated decrease in write rate based on the estimated over-provisioning increase.
11. The system of claim 8 , wherein the first portion corresponds to a plurality of tracks of one or more LSUs (logical storage units), wherein, for each of the plurality of tracks of one of the LSUs, a data structure for said one LSU includes an entry specifying that said each track is included in the first data portion designated for dynamically compressed data.
12. The system of claim 11 , wherein, for each of the plurality of tracks, a corresponding entry in the data structure specifies a location and length of said each track within the first portion, and wherein the method further comprises:
for each of the plurality of tracks, updating the corresponding entry in the data structure for said each LSU of said each track in response to the compression of the data portion to reflect a reduced length of said each track.
13. The system of claim 8 , wherein the method further includes:
determining an endurance increase factor,
wherein said determining whether to increase the over-provisioning for the physical storage device is based at least in part on the endurance increase factor.
14. The system of claim 8 , wherein the current write rate is the first current write rate determined at a first point in time, and wherein the method further includes, after said compressing data in the first portion:
determining a second current write rate for the physical storage device at a second point in time after the first point in time;
determining whether to decrease over-provisioning for the physical storage device based on the second current write rate;
if it is determined to decrease the over-provisioning, decompressing data in the first portion; and
as a result of said decompressing, allocating one or more sub-portions being used for over-provisioning to the first portion.
15. For a physical storage device including a first portion designated for dynamically compressed data and a second portion designated for compressed data, wherein data in the first portion is initially uncompressed, non-transitory computer-readable media having software stored thereon that, when executed, performs a method comprising:
determining, at a first point in time, a current write rate for the physical storage device;
determining to increase over-provisioning for the physical storage device based at least in part on the current write rate over a current lifetime of the physical storage device up to the first point in time; and
responsive to said determining to increase the over-provisioning, compressing data in the first portion designated for dynamically compressed data, wherein said compressing data in the first portion responsive to said determining to increase over-provisioning based at least in part on the current write rate results in one or more unused sub-portions of the first portion and use of the one or more unused sub-portions for over-provisioning.
16. The non-transitory computer-readable media of claim 15 , wherein said determining to increase the over-provisioning includes:
determining an adjusted write rate that would enable the physical storage device to endure until a predefined endurance date; and
determining whether to increase the over-provisioning based at least in part on the adjusted write rate and an estimated decrease in write rate to the physical storage device if the first portion were compressed.
17. The non-transitory computer-readable media of claim 16 , wherein the method further comprises:
for each of a plurality of over-provisioning increases on the first physical storage device, determining a write amplification reduction resulting from said each over-provisioning increase,
wherein said determining whether to increase the over-provisioning includes:
estimating an over-provisioning increase if the first portion is increased; and
determining the estimated decrease in write rate based on the estimated over-provisioning increase.
18. The non-transitory computer-readable media of claim 15 , wherein the first portion corresponds to a plurality of tracks of one or more LSUs, wherein, for each of the plurality of tracks of one of the LSUs, a data structure for said one LSU includes an entry specifying that track said each track is included in the first data portion designated for dynamically compressed data.
19. The non-transitory computer-readable media of claim 15 , wherein the method further comprises:
determining an endurance increase factor,
wherein said determining whether to increase the over-provisioning for the physical storage device is based at least in part on the endurance increase factor.
20. The non-transitory computer-readable media of claim 15 , wherein the current write rate is a first current write rate determined at the first point in time, and wherein the method further comprises, after compressing data in the first portion:
determining a second current write rate for the physical storage device at a second point in time after the first point in time;
determining whether to decrease over-provisioning for the physical storage device based on the second current write rate;
if it is determined to decrease the over-provisioning, decompressing data in the first portion; and
as a result of said decompressing, allocating one or more sub-portions being used for over-provisioning to the first portion.