Virtual machine load balancing

A non-transitory computer-readable medium storing instructions, which when executed by a processing device, cause the processing device to perform a method comprising:

• receiving a first packet addressed to a first virtual link layer address;
• determining whether the first virtual link layer address for the first packet is a private virtual link layer address for a first virtual machine of a first plurality of virtual machines on a first host computer or is shared by each of the first plurality of virtual machines on the first host computer;
• in response to determining that the first virtual link layer address is the private virtual link layer address for the first virtual machine, mapping the flow of packets to the first virtual machine using the private virtual link layer address;
• in response to determining that the first virtual link layer address is shared by the first plurality of virtual machines,
• mapping a flow of packets including the first packet to the first virtual machine within the first plurality of virtual machines, wherein the flow of packets is mapped using a load balancing algorithm, and
• forwarding the first packet to the first virtual machine;
• and
• receiving a second packet from the first virtual machine in response to the first packet, wherein the second packet includes the first virtual link layer address as a source address for the first virtual machine.

A first host computer comprising:

• a processing device;
• and
• a memory coupled to the processing device, the memory storing instructions which, when executed by the processing device, cause virtualization software of the first host computer to:
• receive a first packet addressed to a first virtual link layer address;
• determine whether the first virtual link layer address for the first packet is a private virtual link layer address for a first virtual machine of a first plurality of virtual machines on a first host computer or is shared by each of the first plurality of virtual machines on the first host computer;
• in response to determining that the first virtual link layer address is the private virtual link layer address for the first virtual machine, map the flow of packets to the first virtual machine using the private virtual link layer address;
• in response to determining that the first virtual link layer address is shared by the first plurality of virtual machines,
• map a flow of packets including the first packet to the first virtual machine within the first plurality of virtual machines, wherein the flow of packets is mapped using a load balancing algorithm, and
• forward the first packet to the first virtual machine;
• and
• receive a second packet from the first virtual machine in response to the first packet, wherein the second packet includes the first virtual link layer address as a source address for the first virtual machine.