Dynamic cloud workload reallocation based on active security exploits in dynamic random access memory (DRAM)

A cloud infrastructure node configured to identify bit flips in computing instances of a cloud infrastructure service and migrate resources from identified computing instances, the cloud infrastructure node comprising:

• a processor;
• and
• a computer-readable medium including instructions that, when executed by the processor, cause the processor to:
• process, for each computing instance in the cloud infrastructure service, a set of memory rows to identify one or more bit flips in each of the computing instances;
• aggregate the identified bit flips for each computing instance by generating a bitmap comprising the identified bit flips for each computing instance;
• validate at least a subset of the one or more computing instances as comprising sustained bit flips by processing the bitmap for each computing instance, each of the one or more validated computing instances associated with a Rowhammer attack;
• and
• for each of the subset of one or more validated computing instances:
• migrate computing resources residing on each of the subset of one or more validated computing instances to one or more corresponding nodes in the cloud infrastructure service;
• and
• update a cloud scheduler to redirect processing requests from each of the subset of one or more validated computing instances to each of the one or more corresponding nodes.

A non-transitory computer-readable medium including stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a process, the process comprising:

• processing, for each computing instance in a cloud infrastructure service, a set of memory rows to identify one or more bit flips in each of the computing instances, each computing instance comprising a dynamic random-access memory (DRAM) cell;
• aggregating the identified bit flips for each computing instance;
• validating at least a subset of the one or more computing instances as comprising sustained bit flips based at least in part on the aggregated bit flips for each computing instance, each of the one or more validated computing instances associated with a Rowhammer attack;
• and
• for each of the subset of one or more validated computing instances:
• migrating computing resources residing on each of the subset of one or more validated computing instances to one or more corresponding nodes in the cloud infrastructure service;
• and
• updating a cloud scheduler to redirect processing requests from each of the subset of one or more validated computing instance to each of the one or more corresponding nodes.