Availability of a storage system
Embodiments of the present disclosure provide a method for a storage system, a storage system and a computer program product. The method comprises determining a first drive in a drive array is temporarily unavailable. The method further comprises setting the first drive in a frozen state. The method further comprises: in response to receiving a write request for the first drive during the frozen state, pending the write request or recording the write request in a second drive in the drive array. The method further comprises: in response to receiving a read request for the first drive during the frozen state, reconstructing data to which the read request is directed through data stored in a third drive in the drive array.
1. A method for a storage system including a drive array, the method comprising:
determining that a first drive in the drive array is temporarily unavailable;
setting the first drive in a frozen state;
in response to receiving a write request for the first drive during the frozen state, putting the write request in a buffer area;
in response to receiving a read request for the first drive during the frozen state, reconstructing data to which the read request is directed through data stored in a third drive in the drive array;
in response to a number of write requests in the buffer area exceeding a threshold number, recording data to be written by the write requests in the buffer area into a file stored in a second drive; and
updating a synchronization indication associated with the first drive whether a block on the first drive is to be synchronized in response to the first drive becoming available.
2. The method according to claim 1 , wherein determining that the first drive is temporarily unavailable comprises:
determining that the first drive is temporarily unavailable by detecting a predetermined event including at least one of the followings:
the first drive starting an online firmware update process,
the first drive being performing a garbage collection process,
input/output latency of the first drive exceeding a threshold,
an error occurring on the first drive,
the first drive being removed,
all paths to the first drive being missing, and
a network traffic burst.
3. The method according to claim 1 , wherein reconstructing the data to which the read request is directed includes:
in response to receiving the read request during the frozen state, reading data stored in the third drive; and
reconstructing the data to which the read request is directed with the read data.
4. The method according to claim 1 , further comprising:
in response to the first drive becoming available,
setting the first drive in a synchronized state; and
synchronizing data recorded in the file to the first drive.
5. The method according to claim 4 , further comprising:
in response to receiving a second write request for the first drive during the synchronization, determining whether target data in the file corresponding to an address to which the second write request is directed has been synchronized to the first drive;
in response to determining that the target data has not been synchronized to the first drive,
discarding the target data;
setting the synchronization indication that a block corresponding to the address to which the second write request is directed needn't be synchronized; and
writing the target data into the first drive.
6. The method according to claim 1 , further comprising:
in response to timeout of the frozen state, reconstructing data stored in the first drive.
7. A storage system, comprising:
a drive array; and
a controller configured to:
determine that a first drive in the drive array is temporarily unavailable; and
set the first drive in a frozen state;
in response to receiving a write request for the first drive during the frozen state, put the write request in a buffer area;
in response to receiving a read request for the first drive during the frozen state, reconstruct data to which the read request is directed through data stored in a third drive in the drive array;
in response to a number of write requests in the buffer area exceeding a threshold number, record data to be written by write requests in the buffer area in a file stored in a second drive; and
update a synchronization indication associated with the first drive whether a block on the first drive is to be synchronized in response to the first drive becoming available.
8. The storage system according to claim 7 , wherein the controller is configured to determine that the first drive is temporarily unavailable by detecting a predetermined event including at least one of the followings:
the first drive starting an online firmware update process,
the first drive being performing a garbage collection process,
input/output latency of the first drive exceeding a threshold,
an error occurring on the first drive,
the first drive being removed,
all paths to the first drive being missing, and
a network traffic burst.
9. The storage system according to claim 7 , wherein the controller, when reconstructing the data to which the read request is directed, is configured to:
in response to receiving the read request during the frozen state,
read data stored in the third drive; and
reconstruct the data to which the read request is directed with the read data.
10. The storage system according to claim 7 , wherein the controller is further configured to:
in response to the first drive becoming available,
set the first drive in a synchronized state; and
synchronize data recorded in the file to the first drive.
11. The storage system according to claim 10 , wherein the controller is further configured to:
in response to receiving a second write request for the first drive during the synchronization, determine whether target data in the file corresponding to an address to which the second write request is directed has been synchronized to the first drive;
in response to determining that the target data has not been synchronized to the first drive,
discard the target data;
set the synchronization indication that a block corresponding to the address to which the second write request is directed needn't be synchronized; and
write the target data to the first drive.
12. The storage system according to claim 7 , wherein the controller is further configured to:
in response to timeout of the frozen state, reconstruct data stored in the first drive.
13. A computer program product for a storage system including a drive array, the computer program product comprising:
a non-transitory computer readable medium encoded with computer-executable code, the code configured for the execution of:
determining that a first drive in the drive array is temporarily unavailable;
setting the first drive in a frozen state;
in response to receiving a write request for the first drive during the frozen state, putting the write request in a buffer area;
in response to receiving a read request for the first drive during the frozen state, reconstructing data to which the read request is directed through data stored in a third drive in the drive array;
in response to a number of write requests in the buffer area exceeding a threshold number, recording data to be written by the write requests in the buffer area into a file stored in a second drive; and
updating a synchronization indication associated with the first drive whether a block on the first drive is to be synchronized in response to the first drive becoming available.
14. The computer program product of claim 13 , wherein determining that the first drive is temporarily unavailable comprises:
determining that the first drive is temporarily unavailable by detecting a predetermined event including at least one of the followings:
the first drive starting an online firmware update process,
the first drive being performing a garbage collection process,
input/output latency of the first drive exceeding a threshold,
an error occurring on the first drive,
the first drive being removed,
all paths to the first drive being missing, and
a network traffic burst.
15. The computer program product of claim 13 , wherein reconstructing the data to which the read request is directed includes:
in response to receiving the read request during the frozen state, reading data stored in the third drive; and
reconstructing the data to which the read request is directed with the read data.
16. The computer program product of claim 13 , wherein the code is further configured for the execution of:
in response to the first drive becoming available,
setting the first drive in a synchronized state; and
synchronizing data recorded in the file to the first drive.
17. The computer program product of claim 16 , wherein the code is further configured for the execution of:
in response to receiving a second write request for the first drive during the synchronization, determining whether target data in the file corresponding to an address to which the second write request is directed has been synchronized to the first drive;
in response to determining that the target data has not been synchronized to the first drive,
discarding the target data;
setting the synchronization indication that a block corresponding to the address to which the second write request is directed needn't be synchronized; and
writing the target data into the first drive.
18. The computer program product of claim 13 wherein the code is further configured for the execution of:
in response to timeout of the frozen state, reconstructing data stored in the first drive.