US 11,915,053 B2
Interruption predictions for cloud compute instances
Idan Schwartz, Tel Aviv (IL); Ohad Muchnik, Tel Aviv (IL); Jonathan Cohen, Tel Aviv (IL); Kevin McGrath, Vienna, VA (US); and Amiram Shachar, Las Vegas, NV (US)
Assigned to NETAPP, INC., San Jose, CA (US)
Filed by NetApp, Inc., Sunnyvale, CA (US)
Filed on Mar. 19, 2021, as Appl. No. 17/206,871.
Claims priority of provisional application 63/105,947, filed on Oct. 27, 2020.
Prior Publication US 2022/0129322 A1, Apr. 28, 2022
Int. Cl. G06F 9/50 (2006.01); G06F 9/48 (2006.01)
CPC G06F 9/5038 (2013.01) [G06F 9/4887 (2013.01); G06F 9/505 (2013.01); G06F 9/5072 (2013.01); G06F 2209/503 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
applying, by a computing system, a prediction classifier on spare cloud resource data associated with a spare cloud resource on which a container is scheduled for execution;
outputting, by the computing system from the applying of the prediction classifier, a risk score indicating a likelihood of an interruption occurring for the spare cloud resource within a future time period, wherein the risk score comprises a live interruption risk score component corresponding to a first risk of the container on the spare cloud resource being interrupted and a denied scheduling risk score component corresponding to a second risk of the container being denied to launch on the spare cloud resource; and
rebalancing, by the computing system, the container from the spare cloud resource to another cloud resource based on the risk score.