Bounded latency and command non service methods and apparatus
The present disclosure generally presents a method and apparatus to provide a bounded latency, where a device would report “non-service” of a command at the defined system level timeout or earlier if the device was unable to successfully return the data to the host.
1. A method, comprising:
receiving one or more commands at a flash translation layer;
timestamping each command received at the flash translation layer, a timestamp of the respective command indicating a time when a latency threshold of the respective command will be exceeded;
adding each command received at the flash translation layer to a queue;
determining, for a next command to be performed in the queue, whether the respective command has timed out before being transferred from the queue for being performed based on the timestamp of the respective command; and
sending, for a command that has been determined to be timed out, a message to a host that the respective command has timed out.
2. The method according to claim 1 , wherein receiving the one or more commands at the flash translation layer includes receiving multiple commands at the flash translation layer.
3. The method according to claim 1 , wherein the flash translation layer is disposed in a memory device, and the memory device performs the receiving the one or more commands, the timestamping each command, the adding the command to the queue, the determining whether a command has timed out, and the sending the message to the host.
4. The method according to claim 1 , further comprising:
removing from the queue each command that has been determined to be timed out.
5. The method according to claim 1 , wherein the one or more commands are received at a solid state drive.
6. The method according to claim 1 , wherein the one or more commands are received at a hybrid drive.
7. The method according to claim 1 , wherein the one or more commands are received at a hard disk drive.
8. A method, comprising:
receiving one or more commands at a flash translation layer, wherein each command is required to be performed at a specified die;
timestamping each command received at the flash translation layer, a timestamp of the respective command indicating a time when a latency threshold of the respective command will be exceeded;
adding each command received at the flash translation layer to a queue;
determining, for a next command to be performed in the queue, whether the respective command has timed out before being transferred to the specified die based on the timestamp of the respective command;
sending, for a command that has been determined to be timed out, a message to a host that the respective command has timed out;
determining, for a next command to be performed in the queue that has not timed out, whether the respective command is expected to time out based on a latency for completion and the timestamp of the respective command, the latency for completion being based on a number of commands to be processed (i) before the respective command and (ii) by the specified die that is to perform the respective command; and
notifying, for a next command that is determined to be expected to time out, the host that the respective command is expected to time out.
9. The method according to claim 8 , wherein receiving the one or more commands at the flash translation layer includes receiving multiple commands at the flash translation layer.
10. The method according to claim 8 , further comprising:
removing from the queue each command that has been determined to be timed out.
11. The method according to claim 8 , further comprising:
determining, for each command in the queue, whether the respective command has timed out before being transferred to the specified die based on the timestamp of the respective command; and
determining, for each command in the queue that has not timed out, whether the respective command is expected to time out based on the respective latency for completion and the timestamp of the respective command.
12. The method according to claim 8 , wherein the one or more commands are received at a solid state drive.
13. The method according to claim 8 , wherein the one or more commands are received at a hybrid drive.
14. The method according to claim 8 , wherein the one or more commands are received at a hard disk drive.
15. A method, comprising:
receiving one or more commands at a flash translation layer, wherein each command is required to be performed at a specified die;
timestamping each command received at the flash translation layer, a timestamp of the respective command indicating a time when a latency threshold of the respective command will be exceeded;
adding each command received at the flash translation layer to a queue;
determining, for a next command to be performed in the queue that has not timed out, whether the respective command is expected to time out based on a latency for completion and the timestamp of the respective command, the latency for completion being based on a number of commands to be processed (i) before the respective command and (ii) by the specified die that is to perform the respective command; and
notifying, for a next command that is determined to be expected to time out, a host that the respective command is expected to time out.
16. The method according to claim 15 , wherein receiving the one or more commands at the flash translation layer includes receiving multiple commands at the flash translation layer, wherein the multiple commands are to be performed by a memory arrangement.
17. The method according to claim 15 , further comprising:
removing from the queue each command that has been determined to be timed out.
18. The method according to claim 15 , wherein the one or more commands are received at a solid state drive.
19. The method according to claim 15 , wherein the one or more commands are received at a hybrid drive.
20. The method according to claim 15 , wherein the one or more commands are received at a hard disk drive.