PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 19.11.2019 at 4:00 PM CET
Search International and National Patent Collections
Some content of this application is unavailable at the moment.
If this situation persists, please contact us atFeedback&Contact
1. (WO2017132599) SYSTEM AND METHOD FOR ALLOWING MULTIPLE GLOBAL IDENTIFIER (GID) SUBNET PREFIX VALUES CONCURRENTLY FOR INCOMING PACKET PROCESSING IN A HIGH PERFORMANCE COMPUTING ENVIRONMENT
Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

Claims:

What is claimed is:

1. A method for using multiple global identification subnet prefix values in a network environment in a high performance computing environment, the method comprising: providing, at a computer environment including a network fabric, a first subnet, the first subnet comprising a first network Host Channel Adapter (HCA) wherein the first network HCA comprises one or more ports operatively coupled with a non-transient memory device storing a first flag and a first end port Global Unique Identifier (GUID) table, the first end port GUID table including a plurality of alias identification entries, each of the plurality of alias identification entries having a capability to represent a different GUID address identifier to be associated with ports of the first network HCA;

receiving from the network fabric by the first network HCA a first packet comprising a header portion including a destination subnet prefix identifying a destination subnet of the network fabric;

allowing the first network HCA to receive the first packet from the first port of the first network HCA by:

selectively determining a logical state of the first flag;

selectively in accordance with a first logical state of the first flag:

ignoring the destination subnet prefix identifying the destination subnet of the network fabric;

inspecting a Global Routing Header (GRH) portion of the first packet to determine a destination Global Unique Identifier (Dest GUID);

comparing the Dest GUID with the plurality of GUID values stored in the first end port GUID table; and

accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID; and selectively in accordance with a second logical state of the first flag:

inspecting the destination subnet prefix portion of the first packet to determine a correspondence between the destination subnet prefix and one or more of: a default subnet prefix value, and/or an assigned subnet prefix value, and selectively accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID.

2. The method according to Claim 1 , wherein:

allowing the first network HCA to receive the first packet from the first port of the first network HCA comprises:

selectively in accordance with the second logical state of the first flag:

inspecting the Global Routing Header (GRH) portion of the first packet to determine a destination Global Unique Identifier (Dest GUID); comparing the Dest GUID with the plurality of GUID values stored in the first end port GUID table; and

accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID.

3. The method according to Claim 1 or 2, wherein receiving the first packet comprises:

receiving from the network fabric by the first network HCA a first packet comprising a header portion including a destination subnet prefix identifying a second subnet of the network fabric, the second subnet being different than the first subnet.

4. The method according to any preceding Claim, wherein:

selectively determining the logical state of the first flag comprises inspecting a value of an end port ignore switch register stored in the non-transient memory device.

5. The method according to any preceding Claim, further comprising:

receiving by the first network HCA the assigned subnet prefix value from a local Subnet

Manager (SM) of the first subnet; and

comparing the received assigned subnet prefix value with the destination subnet prefix of the first packet.

6. A system for using multiple global identification subnet prefix values in a network switch environment in a high performance computing environment, the system comprising:

a first subnet in an associated computer environment including a network fabric, the first subnet comprising:

a first network Host Channel Adapter (HCA) wherein the first network HCA comprises: a plurality of ports; and

a non-transient memory device operatively coupled with the plurality of ports and storing a first flag and a first end port Global Unique Identifier (GUID) table, the first end port GUID table including a plurality of alias identification entries, each of the plurality of alias identification entries having a capability to represent a different GUID address identifier to be associated with ports of the first network HCA;

logic stored in the non-transient memory device; and

a processor configured to execute the logic;

wherein a first packet is received from the network fabric by the first network HCA, the first packet comprising a header portion including a destination subnet prefix identifying a destination subnet of the network fabric;

wherein the first network HCA is allowed to receive the first packet from the first port of the first network HCA by:

selectively determining a logical state of the first flag;

selectively in accordance with a first logical state of the first flag:

ignoring the destination subnet prefix identifying the destination subnet of the network fabric;

inspecting a Global Routing Header (GRH) portion of the first packet to determine a destination Global Unique Identifier (Dest GUID);

comparing the Dest GUID with the plurality of GUID values stored in the first end port GUID table; and

accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID; and selectively in accordance with a second logical state of the first flag:

inspecting the destination subnet prefix portion of the first packet to determine a correspondence between the destination subnet prefix and one or more of: a default subnet prefix value, and/or an assigned subnet prefix value, and selectively accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID;

7. The system according to Claim 6, wherein:

the first network HCA is allowed to receive the first packet from the first port of the first network HCA by:

selectively in accordance with the second logical state of the first flag:

inspecting the Global Routing Header (GRH) portion of the first packet to determine a destination Global Unique Identifier (Dest GUID); comparing the Dest GUID with the plurality of GUID values stored in the first end port GUID table; and

accepting the first packet based on one entry in the first end port

GUID table having a GUID value matching the Dest GUID.

8. The system according to Claim 6 or 7, wherein:

the first network HCA receives from the network fabric a first packet comprising a header portion including a destination subnet prefix identifying a second subnet of the network fabric, the second subnet being different than the first subnet.

9. The system according to any of Claims 6 to 8, wherein:

the logic is executed by the processor to selectively determine the logical state of the first flag by inspecting a value of an end port ignore switch register stored in the non-transient memory device.

10. The system according to any of Claims 6 to 9, wherein:

the first network HCA receives the assigned subnet prefix value from a local Subnet Manager (SM) of the first subnet; and

the received assigned subnet prefix value is compared with the destination subnet prefix of the first packet.

11. A non-transitory machine readable medium having instructions stored thereon that when executed by an associated computer comprising a network fabric and a first subnet cause the associated computer to perform steps comprising:

providing, at a computer environment including a network fabric, a first subnet, the first subnet comprising a first network Host Channel Adapter (HCA) wherein the first network HCA comprises one or more ports operatively coupled with a non-transient memory device storing a first flag and a first end port Global Unique Identifier (GUID) table, the first end port GUID table including a plurality of alias identification entries, each of the plurality of alias identification entries having a capability to represent a different GUID address identifier to be associated with ports of the first network HCA;

receiving from the network fabric by the first network HCA a first packet comprising a header portion including a destination subnet prefix identifying a destination subnet of the network fabric;

allowing the first network HCA to receive the first packet from the first port of the first network HCA by:

selectively determining a logical state of the first flag;

selectively in accordance with a first logical state of the first flag:

ignoring the destination subnet prefix identifying the destination subnet of the network fabric;

inspecting a Global Routing Header (GRH) portion of the first packet to determine a destination Global Unique Identifier (Dest GUID);

comparing the Dest GUID with the plurality of GUID values stored in the first end port GUID table; and

accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID; and selectively in accordance with a second logical state of the first flag:

inspecting the destination subnet prefix portion of the first packet to determine a correspondence between the destination subnet prefix and one or more of: a default subnet prefix value, and/or an assigned subnet prefix value, and selectively accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID.

12. The non-transitory machine readable medium according to Claim 1 1 , wherein: allowing the first network HCA to receive the first packet from the first port of the first network HCA comprises:

selectively in accordance with the second logical state of the first flag:

inspecting the Global Routing Header (GRH) portion of the first packet to determine a destination Global Unique Identifier (Dest GUID); comparing the Dest GUID with the plurality of GUID values stored in the first end port GUID table; and

accepting the first packet based on one entry in the first end port GUID table having a GUID value matching the Dest GUID.

13. The non-transitory machine readable medium according to Claim 1 1 or 12, wherein the receiving the first packet comprises:

receiving from the network fabric by the first network HCA a first packet comprising a header portion including a destination subnet prefix identifying a second subnet of the network fabric, the second subnet being different than the first subnet.

14. The non-transitory machine readable medium according to any of Claims 11 to 13, wherein:

selectively determining the logical state of the first flag comprises inspecting a value of an end port ignore switch register stored in the non-transient memory device.

15. The non-transitory machine readable medium according to any of Claims 11 to 14, further comprising:

receiving by the first network HCA the assigned subnet prefix value from a local Subnet Manager (SM) of the first subnet; and

comparing the received assigned subnet prefix value with the destination subnet prefix of the first packet.

16. A computer program comprising program instructions in machine-readable format that when executed by a computer system cause the computer system to perform the method of any of Claims 1 to 5.

17. A computer program product comprising the computer program of Claim 16 stored in a non-transitory machine readable data storage medium.