Dynamic distribution of RSS engines to virtual machines based on flow data

One or more non-transitory computer-readable storage media storing one or more computer instructions which, when executed by one or more processors, cause the one or more processors to perform:

• receiving, from flow cache, one or more first absolute counts of data packets that belong to at least one data flow and that were processed within a first-time interval;
• computing, based on the one or more first absolute counts, one or more flow load indicator values;
• storing the one or more flow load indicator values in a lookup table;
• generating a sorted table by sorting entries of the lookup table based on the one or more flow load indicator values;
• determining a first count that represents a count of one or more filters that can be applied on one or more RSS engines;
• determining a second count that represents a count of data flows that are included in the sorted table and that have corresponding flow load indicator values that exceed a threshold value;
• determining whether the second count exceeds the first count;
• in response to determining that the second count exceeds the first count:
• selecting, from the sorted table, the first count of one or more first data flows that have high flow load indicator values;
• determining the first count of one or more filters that correspond to the one or more first data flows;
• assigning the first count of the one or more filters to at least one RSS engine from the one or more RSS engines;
• and
• assigning one or more remaining filters, which correspond to one or more remaining data flows in the sorted table, to one or more non-RSS queues.

A system configured to dynamically provision multiple receive side scaling (RSS) engines, the system comprising:

• one or more processors;
• one or more memory units;
• and
• one or more non-transitory computer-readable storage media storing one or more computer instructions which, when executed by the one or more processors, cause the one or more processors to perform:
• receiving, from flow cache, one or more first absolute counts of data packets that belong to at least one data flow and that were processed within a first-time interval;
• computing, based on the one or more first absolute counts, one or more flow load indicator values;
• storing the one or more flow load indicator values in a lookup table;
• generating a sorted table by sorting entries of the lookup table based on the one or more flow load indicator values;
• determining a first count that represents a count of one or more filters that can be applied on one or more RSS engines;
• determining a second count that represents a count of data flows that are included in the sorted table and that have corresponding flow load indicator values that exceed a threshold value;
• determining whether the second count exceeds the first count;
• in response to determining that the second count exceeds the first count:
• selecting, from the sorted table, the first count of one or more first data flows that have high flow load indicator values;
• determining the first count of one or more filters that correspond to the one or more first data flows;
• assigning the first count of the one or more filters to at least one RSS engine from the one or more RSS engines;
• and
• assigning one or more remaining filters, which correspond to one or more remaining data flows in the sorted table, to one or more non-RSS queues.