Google Inc.

Jiazhen Zheng

Srinivas Vaduvatha

Weihuang Wang

Abhishek Agarwal

Prashant R Chandra

Weiwei Jiang

Hugh McEvoy Walsh

Gurushankar Rajamani

Xiaoming Wang

Ajay Venkatesan

Shivang Ghetia

Chandan Muddamsetty

Hugh Mcevoy Walsh

A hash table system, including a plurality of hash tables, associated with respective hash functions, for storing key-value pairs; an overflow memory for storing key-value pairs moved from the hash tables due to collision; and an arbiter for arbitrating among commands including update commands, match commands, and rehash commands, wherein for each system clock cycle, the arbiter selects as a selected command one of an update command, a match command, or a rehash command, and wherein the hash table system completes execution of each selected command within a bounded number of system clock cycles.

Efficient hash table lookup

Aspects of the disclosure are directed to a high performance connection scheduler for reliable transport protocols in data center networking. The connection scheduler can handle enqueue events, dequeue events, and update events. The connection scheduler can include a connection queue, scheduling queue, and quality of service arbiter to support scheduling a large number of connections at a high rate.

High performance connection scheduler

A packet cache system includes a cache memory allocator for receiving a memory address corresponding to a non-cache memory and allocated to a packet, and associating the memory address with a cache memory address; a hash table for storing the memory address and the cache memory address, with the memory address as a key and the cache memory address as a value; a cache memory for storing the packet at a location indicated by the cache memory address; and an eviction engine for determining one or more cached packets to remove from the cache memory and place in the non-cache memory when occupancy of the cache memory is high.

Packet cache system and method

Aspects of the disclosure are directed to a packet cache eviction engine for reliable transport protocols of a network. The packet cache eviction engine can manage on-chip cache occupancy by evicting lower priority packets to off-chip memory and ensuring that higher priority packets are kept on-chip to achieve higher performance and lower latency in processing packets in the network.

Hardware architecture of packet cache eviction engine

An application specific integrated circuit (ASIC) is provided for reliable transport of packets. The network interface card may include a reliable transport accelerator (RTA). The RTA may include a cache lookup database. The RTA may be configured to determine, from a received data packet, a connection identifier and query the cache lookup database for a cache entry corresponding to a connection context having the connection identifier. In response to the query, the RTA may receive a cache hit or a cache miss.

Off-chip memory backed reliable transport connection cache hardware architecture

A communication protocol system is provided for reliable transport of packets. A content addressable memory hardware architecture including an acknowledgment coalescing module in communication with a content addressable memory (CAM). The acknowledgment coalescing module coalesces multiple acknowledgement packets as a single acknowledgement packet to reduce the overall numbers of the packet transmission in the communication protocol system. In addition, the acknowledgment coalescing module may also provide a piggyback mechanism to carry acknowledge information in a regular data packet. Thus, the need to generate a new acknowledgement packet may be eliminated. Accordingly, the network congestion and latency may be reduced, and the communication and transmission efficiency are enhanced.

Acknowledgement coalescing module utilized in content addressable memory (CAM) based hardware architecture for data center networking

Aspects of the disclosure are directed to high performance connection cache eviction for reliable transport protocols in data center networking. Connection priorities for connection entries are determined to store the connection entries in a cache based on their connection priority. During cache eviction, the connection entries with a lowest connection priority are evicted from the cache. Cache eviction can be achieved with low latency at a high rate.

High performance cache eviction

A communication protocol system is provided for reliable transport of packets. A content addressable memory hardware architecture including a reorder engine and a retransmission engine may be utilized for the reliable transport of the packets. In this regard, a reorder engine includes a content addressable memory (CAM) and one or more processors in communication with the CAM. The one or more processors are configured to receive a first set of data packets when executed by the one or more processors. The one or more processors are configured to access the content addressable memory to process the first set of data packets. The one or more processors are configured to save data information of the first set of the data packets in the content addressable memory.

Growing community of inventors

Sunnyvale, CA, United States of America

Jiazhen Zheng