Efficient communications amongst computing nodes for operating autonomous vehicles

Patent metadata

Field	Value
Publication number	US-11044318-B2
Application number	US-201916252572-A
Country	US
Kind code	B2
Filing date	Jan 19, 2019
Priority date	Jul 21, 2016
Publication date	Jun 22, 2021
Grant date	Jun 22, 2021

Abstract

A first request is received from a first processing node to produce data blocks of a first data stream representing a first communication topic. The first processing node is one of the processing nodes handling a specific function. Each of the processing nodes is executed within a specific node container having a specific operating environment. A global memory segment is allocated from a global memory to store the data blocks of the first data stream. A first local memory segment is mapped to the global memory segment. The first local memory segment is allocated from a first local memory of a first node container containing the first processing node. The first processing node directly accesses the data blocks of the first data stream stored in the global memory segment by accessing the mapped first local memory segment within the first node container.

First claim

What is claimed is:

1. A computer-implemented method for managing data streams of a plurality of processing nodes, the method comprising:
receiving a first request from a first processing node to produce data blocks of a first data stream representing a first communication topic to be subscribed by another processing node, wherein the first processing node is one of a plurality of processing nodes, and wherein each of the processing nodes is executed within a specific node container having a specific operating environment;
in response to the first request, allocating a global memory segment from a global memory to store the data blocks of the first data stream;
mapping a first local memory segment to the global memory segment, the first local memory segment being allocated from a first local memory of a first node container containing the first processing node, wherein the first processing node accesses at least a portion of the data blocks of the first data stream stored in the global memory segment by accessing the mapped first local memory segment within the first node container;
receiving a second request from a second processing node to subscribe the first communication topic; and
in response to the second request, mapping a second local memory segment to a first global memory segment, the second local memory segment being allocated from a second local memory of a second node container containing the second processing node, wherein the second processing node accesses at least a portion of the data blocks of the first data stream stored in the global memory segment by accessing the mapped second local memory segment within the second node container.

2. The method of claim 1 , wherein the first data stream is one of a plurality of data streams associated with a plurality of communication topics, and wherein each of the data streams is associated with one of a plurality of global memory segments allocated from the global memory for storing corresponding data blocks, respectively.

3. The method of claim 1 , wherein the first node container comprises a first virtual machine and the first local memory is associated with the first virtual machine, and wherein the second node container comprises a second virtual machine and the second local memory is associated with the second virtual machine.

4. The method of claim 1 , wherein the second processing node is one of a plurality of processing nodes subscribing the first communication topic, and wherein each of the subscribing processing nodes maps a local memory segment from its respective local memory to the first global memory segment for accessing the data blocks of the first data stream.

5. The method of claim 1 , further comprising:
monitoring access of the data blocks stored in the first global memory segment by the first processing node and the second processing node; and
releasing the first global memory segment back to a free global memory pool of the global memory if the access is inactive for a predetermined period of time.

6. The method of claim 5 , wherein monitoring access of the data blocks stored in the first global memory segment comprises:
determining whether all data blocks of the first data stream have been read by the second processing node; and
determining whether there is any new data block produced by the first processing node, wherein the first global memory segment is released if all data blocks of the first data stream have been read and no new data block has been produced for the predetermined period of time.

7. The method of claim 6 , further comprising, prior to releasing the global memory segment:
unmapping the first local memory segment of the first local memory from the global memory segment; and
unmapping the second local memory segment of the second local memory from the global memory segment.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of managing data streams of a plurality of processing nodes, the operations including
receiving a first request from a first processing node to produce data blocks of a first data stream representing a first communication topic to be subscribed by another processing node, wherein the first processing node is one of a plurality of processing nodes, and wherein each of the processing nodes is executed within a specific node container having a specific operating environment;
in response to the first request, allocating a global memory segment from a global memory to store the data blocks of the first data stream;
mapping a first local memory segment to the global memory segment, the first local memory segment being allocated from a first local memory of a first node container containing the first processing node, wherein the first processing node accesses at least a portion of the data blocks of the first data stream stored in the global memory segment by accessing the mapped first local memory segment within the first node container;
receiving a second request from a second processing node to subscribe the first communication topic; and
in response to the second request, mapping a second local memory segment to a first global memory segment, the second local memory segment being allocated from a second local memory of a second node container containing the second processing node, wherein the second processing node accesses at least a portion of the data blocks of the first data stream stored in the global memory segment by accessing the mapped second local memory segment within the second node container.

9. The machine-readable medium of claim 8 , wherein the first data stream is one of a plurality of data streams associated with a plurality of communication topics, and wherein each of the data streams is associated with one of a plurality of global memory segments allocated from the global memory for storing corresponding data blocks, respectively.

10. The machine-readable medium of claim 8 , wherein the first node container comprises a first virtual machine and the first local memory is associated with the first virtual machine, and wherein the second node container comprises a second virtual machine and the second local memory is associated with the second virtual machine.

11. The machine-readable medium of claim 8 , wherein the second processing node is one of a plurality of processing nodes subscribing the first communication topic, and wherein each of the subscribing processing nodes maps a local memory segment from its respective local memory to the first global memory segment for accessing the data blocks of the first data stream.

12. The machine-readable medium of claim 8 , wherein the operations further comprise:
monitoring access of the data blocks stored in the first global memory segment by the first processing node and the second processing node; and
releasing the first global memory segment back to a free global memory pool of the global memory if the access is inactive for a predetermined period of time.

13. The machine-readable medium of claim 12 , wherein monitoring access of the data blocks stored in the first global memory segment comprises:
determining whether all data blocks of the first data stream have been read by the second processing node; and
determining whether there is any new data block produced by the first processing node, wherein the first global memory segment is released if all data blocks of the first data stream have been read and no new data block has been produced for the predetermined period of time.

14. The machine-readable medium of claim 13 , wherein the ope

Assignees

• Baidu Usa Llc
• Baidu Com Times Tech Beijing Co Ltd

Inventors

• Wang Quan
• Xia Liming
• Feng Jingchao
• Qu Ning
• Peng James

Classifications

• H04L67/12 Primary

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title

• B60W30/14

  {Adaptive} cruise control · CPC title

• G06F12/1036

  for multiple virtual address spaces, e.g. segmentation (G06F12/1045 takes precedence) · CPC title

• H04L67/02

  based on web technology, e.g. hypertext transfer protocol [HTTP] · CPC title

• G06F12/06 Primary

  Addressing a physical block of locations, e.g. base addressing, module addressing, memory dedication (G06F12/08 takes precedence) · CPC title