Management of power state transitions of a memory sub-system
A transitory idle state is established for a memory sub-system that can be transitioned from an active state to one or more idle states including the transitory idle state and a deep idle state. A power consumption metric and transition time for each idle state is identified. A transitional energy metric is determined for each idle state based on the corresponding power consumption metric transition time. An energy target time is determined for the transitory idle state. Based on the energy target time, an idle state optimization time is determined for the transitory idle state. The memory sub-system is maintained in the transitory idle state for a duration of the idle state optimization time.
1. A method comprising:
establishing, by a processing device, a transitory idle state for a memory sub-system, wherein the memory sub-system comprises an active state and a set of idles states comprising the transitory idle state and a deep idle state;
identifying a power consumption metric for each idle state of the set of idle states of the memory sub-system;
identifying a transition time corresponding to transition to and from each idle state of the set of idle states;
determining a transitional energy metric based on the power consumption metric and the transition time for each idle state of the set of idle states;
determining an energy target time based on the transitional energy metric and the power consumption metric corresponding to the transitory idle state;
determining an idle state optimization time for the transitory idle state based on the energy target time; and
controlling the memory sub-system to maintain operation in the transitory idle state for a duration of the idle state optimization time.
2. The method of claim 1 , further comprising:
receiving, from a host system, a command to transition the memory component from an active state to a deep idle state; and
in response to the command, transitioning the memory component from the active state to the transitory idle state.
3. The method of claim 1 , further comprising:
identifying an expiration of the idle state optimization time; and
transitioning the memory sub-system from the transitory idle state to the deep idle state in response to the expiration of the idle state optimization time.
4. The method of claim 1 , further comprising generating a set of idle state duration data corresponding to a plurality of instances of entry of the memory sub-system into one or more idle states of the memory sub-system.
5. The method of claim 4 , further comprising:
generating a first idle time metric based on the set of idle state duration data; and
generating a second idle time metric based on the set of idle state duration data.
6. The method of claim 5 , further comprising:
determining the energy target time is less than a threshold idle time metric; and
establishing the energy target time as the idle state optimization time.
7. The method of claim 5 , further comprising:
determining the energy target time is greater than or equal to a threshold idle time metric; and
establishing a combination of the first idle time metric and the second idle time metric as the idle state optimization time.
8. A system comprising:
a memory component; and
a processing device, operatively coupled with the memory component, to:
establish a transitory idle state for a memory sub-system comprising an active state and a deep idle state, wherein a first transitional energy associated with the transitory idle state is less than a second transitional energy associated with the deep idle state;
determine an idle state optimization time for the transitory idle state;
receive, from a host system, a first command associated with transitioning the memory sub-system from the active state to the deep idle state;
transition the memory sub-system to the transitory idle state in response to receiving the first command; and
maintain the memory sub-system in the transitory idle state for a duration of the idle state optimization time.
9. The system of claim 8 , the processing device is further to:
receive a second command from the host system during the idle state optimization time; and
transition the memory sub-system from the transitory idle state to the active state in response to receiving the second command during the idle state optimization time.
10. The system of claim 8 , the processing device is further to:
identify an expiration of the duration of the idle state optimization time; and
transition the memory sub-system from the transitory idle state to the deep idle state in response to identifying the expiration of the duration of the idle state optimization time.
11. The system of claim 8 , wherein a first exit latency associated with the transitory idle state is less than a second exit latency associated with the deep idle state.
12. The system of claim 8 , wherein a first entry latency associated with the transitory idle state is less than a second entry latency associated with the deep idle state.
13. The system of claim 8 , wherein context data is written to non-volatile memory in response to entry of the memory sub-system into the deep idle state.
14. A non-transitory computer readable medium comprising instructions, which when executed by a processing device, cause the processing device to perform operations comprising:
establishing a transitory idle state associated with a memory sub-system;
identifying a power consumption metric for each idle state of a set of idle states of the memory sub-system, wherein the set of idle states comprises a shallow idle state, the transitory idle state and a deep idle state;
identifying a transition time corresponding to transition to and from each idle state of the set of idle states;
determining a transitional energy metric based on the power consumption metric and the transition time for each idle state of the set of idle states;
determining an energy target time based on the transitional energy metric and the power consumption metric corresponding to the transitory idle state;
determining an idle state optimization time for the transitory idle state based on the energy target time; and
controlling the memory sub-system to maintain operation in the transitory idle state for a duration of the idle state optimization time.
15. The non-transitory computer readable medium of claim 14 , the operations further comprise:
generating a set of idle state duration data corresponding to a plurality of instances of entry of the memory sub-system into one or more idle states of the memory sub-system;
generating a first idle time metric based on the set of idle state duration data; and
generating a second idle time metric based on the set of idle state duration data.
16. The non-transitory computer readable medium of claim 15 , the operations further comprise:
determining the energy target time is less than a threshold idle time metric; and
establishing the energy target time as the idle state optimization time.
17. The non-transitory computer readable medium of claim 15 ,
determining the energy target time is greater than or equal to a threshold idle time metric; and
establishing a combination of the first idle time metric and the second idle time metric as the idle state optimization time.
18. The non-transitory computer readable medium of claim 14 , wherein a first exit latency associated with the transitory idle state is less than a second exit latency associated with the deep idle state.
19. The non-transitory computer readable medium of claim 14 , wherein a first transitional energy associated with the transitory idle state is less than a second transitional energy associated with the deep idle state.