Fault tolerant design for clock-synchronization systems

    公开(公告)号:US11799577B2

    公开(公告)日:2023-10-24

    申请号:US17891215

    申请日:2022-08-19

    Applicant: Google LLC

    CPC classification number: H04J3/0641 H04J3/065 H04L7/0016 H04L12/44

    Abstract: A system is provided for synchronizing clocks. The system includes a plurality of devices in a network, each device having a local clock. The system is configured to synchronize the local clocks according to a primary spanning tree, where the primary spanning tree has a plurality of nodes connected through a plurality of primary links, each node of the plurality of nodes representing a respective device of the plurality of devices. The system is also configured to compute a backup spanning tree before a failure is detected in the primary spanning tree, wherein the backup spanning tree includes one or more backup links that are different from the primary links. As such, upon detection of a failure in the primary spanning tree, the system reconfigures the plurality of devices such that clock synchronization is performed according to the backup spanning tree.

    Fault Tolerant Design For Clock-Synchronization Systems

    公开(公告)号:US20220393783A1

    公开(公告)日:2022-12-08

    申请号:US17891215

    申请日:2022-08-19

    Applicant: Google LLC

    Abstract: A system is provided for synchronizing clocks. The system includes a plurality of devices in a network, each device having a local clock. The system is configured to synchronize the local clocks according to a primary spanning tree, where the primary spanning tree has a plurality of nodes connected through a plurality of primary links, each node of the plurality of nodes representing a respective device of the plurality of devices. The system is also configured to compute a backup spanning tree before a failure is detected in the primary spanning tree, wherein the backup spanning tree includes one or more backup links that are different from the primary links. As such, upon detection of a failure in the primary spanning tree, the system reconfigures the plurality of devices such that clock synchronization is performed according to the backup spanning tree.

    Switch proxy controller for switch virtualization

    公开(公告)号:US10798022B2

    公开(公告)日:2020-10-06

    申请号:US16253645

    申请日:2019-01-22

    Applicant: Google LLC

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for switch virtualization by a switch proxy controller. In an aspect, a method includes receiving, by a switch proxy controller, a first request from a first switch fabric, where the first request indicates a first identifier that identifies the first request from other requests from the first switch fabric, generating a second request that indicates a second identifier that identifies the second request from other requests sent from the switch proxy controller to a switch, providing the second request to the switch, receiving, by the switch proxy controller, a first reply that indicates the second identifier indicated in the second request, generating, based on the second identifier indicated in the first reply, a second reply that indicates the first identifier, and selecting the first switch fabric to receive the second reply based on the second identifier.

    Fault tolerant design for clock-synchronization systems

    公开(公告)号:US11463187B2

    公开(公告)日:2022-10-04

    申请号:US17091158

    申请日:2020-11-06

    Applicant: Google LLC

    Abstract: A system is provided for synchronizing clocks. The system includes a plurality of devices in a network, each device having a local clock. The system is configured to synchronize the local clocks according to a primary spanning tree, where the primary spanning tree has a plurality of nodes connected through a plurality of primary links, each node of the plurality of nodes representing a respective device of the plurality of devices. The system is also configured to compute a backup spanning tree before a failure is detected in the primary spanning tree, wherein the backup spanning tree includes one or more backup links that are different from the primary links. As such, upon detection of a failure in the primary spanning tree, the system reconfigures the plurality of devices such that clock synchronization is performed according to the backup spanning tree.

    Admission Control for Latency-Critical Remote Procedure Calls in Datacenters

    公开(公告)号:US20220239598A1

    公开(公告)日:2022-07-28

    申请号:US17579989

    申请日:2022-01-20

    Applicant: Google LLC

    Abstract: A distributed sender driven Admission Control System (ACS) is described herein, leveraging Weighted-Fair Quality of Service (QoS) queues, found in standard NICs and switches, to guarantee RPC level latency service level objectives (SLOs) by a judicious selection of QoS weights and traffic-mix across QoS queues. ACS installs cluster-wide RPC latency SLOs by mapping LS RPCs to higher weight QoS queues, and coping with overloads by adaptively apportioning LS RPCs amongst QoS queues based on measured completion times for each queue. When the network demand spikes unexpectedly to predetermined threshold percentage of provisioned capacity, ACS achieves a latency SLO that is significantly lower than the state-of-art congestion control at the 99.9th-p and admits significantly more RPCs meeting SLO target when RPC sizes are not aligned with priorities.

Patent Agency Ranking