Hyannis Port Research, Inc.

Allen Bast

Anthony D Amicangioli

B Joshua Rosen

Christophe Juhasz

A distributed computing system, such as may be used to implement an electronic trading system, supports a notion of fairness in latency. The system does not favor any particular client. Thus, being connected to a particular access point into the system (such as via a gateway) does not give any particular device an unfair advantage or disadvantage over another. That end is accomplished by precisely controlling latency, that is, the time between when request messages arrive at the system and a time at which corresponding response messages are permitted to leave. The precisely controlled, deterministic latency can be fixed over time, or it can vary according to some predetermined pattern, or vary randomly within a pre-determined range of values.

Highly deterministic latency in a distributed system

A distributed system includes a plurality of compute nodes configured to process messages. The compute nodes each process messages corresponding an assigned value of a common parameter of the messages. The values are assigned to the compute nodes such that two or more compute nodes are available to process each message. The values can be assigned to the compute nodes in a grouping configuration or a striping configuration. The compute nodes also circulate one or more tokens among nodes, and perform a self-maintenance operation during a given state of possession of the token. During a self-maintenance operation, the values assigned to the compute node can be reassigned to other compute nodes to ensure processing of corresponding messages.

Distributed system with fault tolerance and self-maintenance

Systems and methods for clock synchronization are disclosed in which a primary node generates special physical layer clock sync symbols from the output of a reference clock and inserts the clock sync symbols within a symbol stream to one or more secondary nodes. Upon receiving a symbol stream, a secondary node can extract the clock sync symbols from the stream to synchronize its local clock with the reference clock of the primary node. In particular, the clock sync symbols can be inserted into the symbol stream at any arbitrary symbol location, e.g., even between consecutive symbols of a symbol encoded data frame. The clock sync symbols can also replace some control symbols in the symbol stream, such as idle or comma symbols. Accordingly, the clock sync symbols can be inserted into a symbol stream at fixed intervals, irregular intervals, or at any arbitrary time for high resolution clock synchronization.

Systems and methods for clock synchronization using special physical layer clock sync symbols

A distributed system for processing messages includes one or more gateways, sequencers, and compute nodes. The gateway sends a message to the sequencer and the compute node for processing. The sequencer associates the message with an identifier indicating a relative sequence of the message among a plurality of messages. The compute node processes the message to generate a preliminary result, and determines, based on the identifier, whether the compute node processed the message in sequence or out of sequence relative to another message of a plurality of messages. If the compute node determines that the message was received out of sequence, the compute node may process a sequence of messages including the message and at least one preceding message in an appropriate sequence.

Sequencer bypass with transactional preprocessing in distributed system

An electronic trading system and corresponding method are based on a point-to-point mesh architecture. The electronic trading system comprises a gateway, core compute node, and sequencer. The core compute node performs an electronic trading matching function. The gateway transmits a message to the core compute node via a first direct connection. The gateway transmits the message via a second direct connection to the sequencer which, in turn, transmits a sequence-marked message to the core compute node via a third direct connection. The core compute node determines relative ordering of the message among other messages in the electronic trading system based on the sequence-marked message to complete the electronic trading matching function, deterministically. The gateway, core compute node, sequencer, and respective direct connections form at least a portion of the point-to-point mesh architecture and enable the electronic trading system to perform high-speed, deterministic, electronic trading of financial instruments while exhibiting low latency, fairness, and fault tolerance, among other features.

Electronic trading system and method based on point-to-point mesh architecture

A distributed computing system, such as may be used to implement an electronic trading system, controls inbound message flow rates. Limiting a per-client or per-connection inbound message rate also helps ensure fair provisioning of computing resources, so that a single client's excessive use of resources cannot overwhelm the system to such an extent that it prevents other clients from interacting with the distributed system. It is also desirable to have system-wide control of the overall inbound message rate across all client connections. Such system-wide control ensures that the distributed system as a whole can maintain the required levels of service, including offering a predictable level of access for all clients.

Growing community of inventors

Sharon, MA, United States of America

Allen Bast