Samsung Electronics Co., Ltd.

Cisco Technology, Inc.

Facebook, Inc.

Mrinmoy Ghosh

Mankamana Prasad Mishra

Satya Ranjan Mohanty

Ali Sajassi

Vijay Balakrishnan

Zhengyu Yang

Manu Awasthi

Dhananjaya Rao

Navneeth Kankani

Sameer Ranjit Gulrajani

In one embodiment, a method includes receiving, by a first router, data from a network component. The method also includes determining, by the first router, a first link bandwidth capacity between the first router and a host device and determining, by the first router, a first score for the first router based on the first link bandwidth capacity. The method also includes determining, by the first router, a second link bandwidth capacity between a second router and the host device and determining, by the first router, a second score for the second router based on the second link bandwidth capacity. The method further includes comparing, by the first router, at least the first score and the second score to determine a highest score and assigning, by the first router, an edge router associated with the highest score to communicate the data to the host device.

Systems and methods for determining network component scores using bandwidth capacity

A method is performed by a network controller. The method includes receiving information that defines a topology of a network having Ethernet Segments configured with virtual local area networks (VLANs) and including provider edges that are multi-homed to customer edges. The method further comprises, based on the topology, determining for the VLANs particular provider edges among the provider edges that are to operate as designated forwarders of traffic for the VLANs, such that the VLANs are load balanced across the particular provider edges. The method also includes programming the particular provider edges as the designated forwarders of traffic for the VLANs.

Controller driven designated forwarder election in EVPN networks for optimized load distribution

A performance metric of a data shard stored in a first storage portion is monitored. It is determined that the performance metric of the data shard exceeds a threshold. In response to the determination that the performance metric exceeds the threshold, the data shard is reassigned to a second storage portion selected based on an over-provisioning bias of the second storage portion that is different than an over-provisioning bias of the first storage portion or the over-provisioning bias of the first storage portion is increased.

Shard rebalancing based on over-provisioning

A method for allocating workloads based on a total cost of ownership (TCO) model includes receiving a workload; estimating a cost for allocating the workload to each disk of disks in a disk pool based on a TCO model; determining a disk among the disks in the disk pool that minimizes a TCO; and allocating the workload to the disk. The TCO model incorporates a plurality of cost factors for estimating costs for each disk in the disk pool for allocating the workload.

Online flash resource allocation manager based on a TCO model

A method for migrating disks includes: dividing a disk pool including a plurality of disks into a random zone and a sequential zone based on sequentiality and randomness of workloads running on the plurality of disks; monitoring a status of each disk in the disk pool based on a total cost of ownership (TCO); migrating one or more workloads of an overheated disk to an idle disk based on the status of each disk. The overheated disk has a first TCO higher than a migration threshold, and the idle disk has a second TCO lower than an idling threshold.

Online flash resource migration, allocation, retire and replacement manager based on a cost of ownership model

Embodiments of the inventive concept include a solid state drive (SSD) shared array memory cache system including memory cache occupancy prediction. The system can include multiple SSD modules each including a non-volatile memory section, a cache, and a prediction agent generator logic section. The system can further include a host agent including an occupancy prediction logic section that can receive prediction agents from the prediction agent generator logic section of each of the SSD modules, and predict content occupancy of the cache based at least on the prediction agents. A method for predicting SSD memory cache occupancy can include processing write requests, predicting content occupancy of an SSD's cache, determining whether an address in the cache is probably logically contiguous to the logical memory address, re-directing at least one write request, and coalescing multiple write requests including the re-directed write request into a single I/O for storage on the non-volatile memory of the SSD.

Growing community of inventors

Milpitas, CA, United States of America

Mrinmoy Ghosh