公开(公告)号：US20160077946A1

公开(公告)日：2016-03-17

申请号：US14846870

申请日：2015-09-07

Applicant: Mellanox Technologies Ltd.

Inventor： Shlomo Raikin ,  Shachar Raindel ,  Noam Bloch ,  Liran Liss

IPC: G06F11/30 ,  G06F13/38 ,  G06F12/08 ,  G06F13/16 ,  G11C7/10 ,  G06F12/10

CPC classification number: G06F11/3065 ,  G06F12/0891 ,  G06F12/1009 ,  G06F12/109 ,  G06F13/1663 ,  G06F13/385 ,  G06F2212/653 ,  G06F2212/657

Abstract: A method for data transfer includes receiving in a data transfer operation data to be written by a peripheral device to a specified virtual address in a random access memory (RAM) of a host computer. Upon receiving the data, it is detected that a page that contains the specified virtual address is marked as not present in a page table of the host computer. The peripheral device receives a notification that the page is not present and an estimate of a length of time that will be required to make the page available and selects a mode for handling of the data transfer operation depending upon the estimate.

Abstract translation: 一种用于数据传送的方法包括：在主机计算机的随机存取存储器（RAM）中，在数据传送操作中接收要由外围设备写入的指定虚拟地址的数据。 在接收到数据时，检测到包含指定的虚拟地址的页面被标记为不存在于主计算机的页表中。 外围设备接收到页面不存在的通知以及使页面可用所需的时间长度的估计，并且根据估计选择用于处理数据传送操作的模式。

公开(公告)号：US20150293881A1

公开(公告)日：2015-10-15

申请号：US14644400

申请日：2015-03-11

Applicant: Mellanox Technologies Ltd.

Inventor： Shlomo Raikin ,  Shachar Raindel ,  Michael Kagan

IPC: G06F15/167 ,  H04L29/08

CPC classification number: H04L67/02 ,  G06F9/5016 ,  G06F12/023 ,  G06F12/0811 ,  G06F12/0813 ,  G06F12/0862 ,  G06F12/1072 ,  G06F12/123 ,  G06F15/17331 ,  G06F2212/1024 ,  G06F2212/163 ,  H04L67/10

Abstract: A method for memory access is applied in a cluster of computers linked by a network. For a given computer, a respective physical memory range is defined including a local memory range within the local RAM of the given computer and a remote memory range allocated to the given compute within the local RAM of at least one other computer in the cluster, which is accessible via the network using the network interface controllers of the computers. When a memory operation is requested at a given address in the respective physical memory range, the operation is executed on the data in the local RAM of the given computer when the data at the given address are valid in the local memory range. Otherwise the data are fetched from the given address in the remote memory range to the local memory range before executing the operation on the data.

Abstract translation: 用于存储器访问的方法被应用于由网络链接的计算机的集群中。 对于给定的计算机，定义相应的物理存储器范围，其包括给定计算机的本地RAM内的本地存储器范围和分配给集群中的至少另一台计算机的本地RAM内的给定计算的远程存储器范围， 可通过网络使用计算机的网络接口控制器访问。 当在相应物理存储器范围内的给定地址处请求存储器操作时，当给定地址的数据在本地存储器范围内有效时，对给定计算机的本地RAM中的数据执行操作。 否则，在对数据执行操作之前，将数据从远程存储器范围中的给定地址提取到本地存储器范围。

公开(公告)号：US20150288624A1

公开(公告)日：2015-10-08

申请号：US14247255

申请日：2014-04-08

Applicant: Mellanox Technologies Ltd.

Inventor： Shachar Raindel ,  Yaniv Saar ,  Haggai Eran ,  Yishai Israel Hadas ,  Ari Zigler

IPC: H04L12/861 ,  H04L29/08

CPC classification number: H04L49/90 ,  G06F13/382 ,  H04L49/9047

Abstract: A method in a network node that includes a host and an accelerator, includes holding a work queue that stores work elements, a notifications queue that stores notifications of the work elements, and control indices for adding and removing the work elements and the notifications to and from the work queue and the notifications queue, respectively. The notifications queue resides on the accelerator, and at least some of the control indices reside on the host. Messages are exchanged between a network and the network node using the work queue, the notifications queue and the control indices.

Abstract translation: 包括主机和加速器的网络节点中的方法包括保存存储工作元素的工作队列，存储工作元素的通知的通知队列，以及用于将工作元素和通知添加到和 分别从工作队列和通知队列。 通知队列驻留在加速器上，并且至少一些控制索引驻留在主机上。 使用工作队列，通知队列和控制索引，在网络和网络节点之间交换消息。

公开(公告)号：US08914458B2

公开(公告)日：2014-12-16

申请号：US13628075

申请日：2012-09-27

Applicant: Mellanox Technologies Ltd.

Inventor： Shachar Raindel ,  Haggai Eran ,  Liran Liss ,  Noam Bloch

IPC: G06F15/167

CPC classification number: G06F3/067 ,  G06F3/061 ,  G06F3/0656 ,  G06F3/0659

Abstract: A method for data transfer includes receiving in an input/output (I/O) operation a first segment of data to be written to a specified virtual address in a host memory. Upon receiving the first segment of the data, it is detected that a first page that contains the specified virtual address is swapped out of the host memory. At least one second page of the host memory is identified, to which a second segment of the data is expected to be written. Responsively to detecting that the first page is swapped out and to identifying the at least one second page, at least the first and second pages are swapped into the host memory. After swapping at least the first and second pages into the host memory, the data are written to the first and second pages.

Abstract translation: 一种用于数据传输的方法包括在输入/输出（I / O）操作中接收要写入主机存储器中的指定虚拟地址的第一数据段。 在接收到数据的第一段时，检测到包含指定虚拟地址的第一页被转换出主机存储器。 标识主机存储器的至少一个第二页，期望数据的第二段被写入到其上。 响应于检测到第一页面被换出并且识别至少一个第二页面，至少第一页面和第二页面被交换到主机存储器中。 至少将第一页和第二页交换到主机存储器之后，数据被写入第一页和第二页。

公开(公告)号：US20140089528A1

公开(公告)日：2014-03-27

申请号：US13628187

申请日：2012-09-27

Applicant: MELLANOX TECHNOLOGIES LTD.

Inventor： Noam Bloch ,  Shachar Raindel ,  Haggai Eran ,  Liran Liss

IPC: G06F3/00

CPC classification number: H04L49/9089 ,  G06F12/08 ,  H04L69/321

Abstract: A method for data transfer includes receiving in an input/output (I/O) operation data to be written to a specified virtual address in a host memory. Upon receiving the data, it is detected that a first page that contains the specified virtual address is swapped out of the host memory. Responsively to detecting that the first page is swapped out, the received data are written to a second, free page in the host memory, and the specified virtual address is remapped to the free page.

Abstract translation: 一种用于数据传输的方法包括在主机存储器中接收要写入指定虚拟地址的输入/输出（I / O）操作数据。 在接收到数据时，检测到包含指定的虚拟地址的第一页被转换出主机存储器。 响应于检测到第一页被换出，所接收的数据被写入主机存储器中的第二个空闲页面，并且将指定的虚拟地址重新映射到空闲页面。

公开(公告)号：US20160342547A1

公开(公告)日：2016-11-24

申请号：US15154945

申请日：2016-05-14

Applicant: Mellanox Technologies Ltd.

Inventor： Liran Liss ,  Shachar Raindel ,  Shlomo Raikin ,  Adi Menachem ,  Yuval Itkin

IPC: G06F13/38 ,  G06F13/40 ,  G06F15/173 ,  H04L12/861 ,  G06F13/42 ,  G06F13/28

CPC classification number: G06F13/385 ,  G06F13/28 ,  G06F13/4022 ,  G06F13/4282 ,  H04L49/3009 ,  H04L49/9068

Abstract: Peripheral apparatus for use with a host computer includes an add-on device, which includes a first network port coupled to one end of a packet communication link and add-on logic, which is configured to receive and transmit packets containing data over the packet communication link and to perform computational operations on the data. A network interface controller (NIC) includes a host bus interface, configured for connection to the host bus of the host computer and a second network port, coupled to the other end of the packet communication link. Packet processing logic in the NIC is coupled between the host bus interface and the second network port, and is configured to translate between the packets transmitted and received over the packet communication link and transactions executed on the host bus so as to provide access between the add-on device and the resources of the host computer.

Abstract translation: 用于主计算机的外围设备包括附加设备，其包括耦合到分组通信链路的一端的第一网络端口和附加逻辑，其被配置为通过分组通信来接收和发送包含数据的分组 链接并对数据执行计算操作。 网络接口控制器（NIC）包括主机总线接口，被配置为连接到主计算机的主机总线和耦合到分组通信链路的另一端的第二网络端口。 NIC中的分组处理逻辑耦合在主机总线接口和第二网络端口之间，并且被配置为在通过分组通信链路发送和接收的分组之间转换和在主机总线上执行的事务之间的转换，以便在加法 - 设备和主机的资源。

公开(公告)号：US09497125B2

公开(公告)日：2016-11-15

申请号：US14338488

申请日：2014-07-23

Applicant: Mellanox Technologies Ltd.

Inventor： Shachar Raindel ,  Noam Bloch ,  Liran Liss ,  Diego Crupnicoff ,  Marina Lipshteyn ,  Adi Menachem

IPC: H04L12/801 ,  H04L12/931 ,  H04L12/46 ,  H04L12/851 ,  G06F3/06

CPC classification number: H04L47/127 ,  G06F3/0662 ,  G06F3/0664 ,  H04L12/4633 ,  H04L47/2441 ,  H04L49/50 ,  H04L49/70

Abstract: In a data network congestion control in a virtualized environment is enforced in packet flows to and from virtual machines in a host. A hypervisor and network interface hardware in the host are trusted components. Enforcement comprises estimating congestion states in the data network attributable to respective packet flows, recognizing a new packet that belongs to one of the data packet flows, and using one or more of the trusted components and to make a determination based on the congestion states that the new packet belongs to a congestion-producing packet flow. A congestion-control policy is applied by one or more of the trusted components to the new packet responsively to the determination.

Abstract translation: 在数据网络中，虚拟化环境中的拥塞控制在来自主机中的虚拟机的数据包流中实施。 主机中的管理程序和网络接口硬件是可信组件。 执行包括估计可归因于相应分组流的数据网络中的拥塞状态，识别属于数据分组流之一的新分组，以及使用一个或多个可信组件，并基于拥塞状态进行确定 新分组属于产生拥塞的分组流。 响应于该确定，拥塞控制策略由一个或多个可信任组件应用于新分组。

公开(公告)号：US20160330301A1

公开(公告)日：2016-11-10

申请号：US15146013

申请日：2016-05-04

Applicant: Mellanox Technologies Ltd.

Inventor： Shachar Raindel ,  Shlomo Raikin ,  Liran Liss

IPC: H04L29/06 ,  H04L12/851 ,  G06F21/60 ,  H04L12/801

Abstract: Data processing apparatus includes a host processor and a network interface controller (NIC), which is configured to couple the host processor to a packet data network. A memory holds a flow state table containing context information with respect to computational operations to be performed on multiple packet flows conveyed between the host processor and the network. Acceleration logic is coupled to perform the computational operations on payloads of packets in the multiple packet flows using the context information in the flow state table.

Abstract translation: 数据处理装置包括主处理器和网络接口控制器（NIC），其被配置为将主机处理器耦合到分组数据网络。 存储器保存流状态表，该流状态表包含关于在主处理器和网络之间传送的多个分组流执行的计算操作的上下文信息。 加速逻辑被耦合以使用流状态表中的上下文信息对多个分组流中的分组的有效载荷执行计算操作。

公开(公告)号：US20160294715A1

公开(公告)日：2016-10-06

申请号：US14673892

申请日：2015-03-31

Applicant: Mellanox Technologies Ltd.

Inventor： Shachar Raindel ,  Idan Burstein ,  Noam Bloch ,  Benny Koren ,  Barak Gafni ,  Dror Goldenberg ,  Liran Liss

IPC: H04L12/801 ,  H04L12/721 ,  H04L12/803 ,  H04L12/707

CPC classification number: H04L47/34 ,  H04L45/22 ,  H04L45/38 ,  H04L47/122

Abstract: A method in a network element that includes multiple interfaces for connecting to a communication network includes receiving from the communication network via an ingress interface a flow including a sequence of packets, and routing the packets to a destination of the flow via a first egress interface. A permission indication for re-routing the flow is received in the ingress interface. In response to receiving the permission indication, subsequent packets of the flow are re-routed via a second egress interface that is different from the first egress interface. Further re-routing of the flow is refrained from, until receiving another permission indication.

Abstract translation: 包括用于连接到通信网络的多个接口的网络元件中的方法包括经由入口接口从通信网络接收包括一系列分组的流，以及经由第一出口接口将分组路由到流的目的地。 在入口接口中接收到重新路由流量的许可指示。 响应于接收到许可指示，流的后续分组经由与第一出口接口不同的第二出口接口重新路由。 直到收到另一个许可指示为止，进一步重新路由流。

公开(公告)号：US20140269271A1

公开(公告)日：2014-09-18

申请号：US13803144

申请日：2013-03-14

Applicant: MELLANOX TECHNOLOGIES, LTD.

Inventor： Barak Gafni ,  Benny Koren ,  Freddy Gabbay ,  Zachy Hamamaty ,  Shachar Raindel

IPC: H04L12/801

CPC classification number: H04L47/35 ,  H04L47/32 ,  H04W28/0242 ,  H04W28/0284

Abstract: Methods and systems are disclosed for network congestion management. The methods and systems receive a first packet complying with a first network protocol comprising a first congestion indicator representative of a presence or absence of network congestion and further comprising a first set of data associated with a second network protocol, and provide an indication of the presence or absence of network congestion generated based, at least in part, on the first congestion indicator. The methods and systems also receive a first packet complying with a first network protocol comprising a first set of data associated with a second network protocol, and output a second packet complying with the first network protocol comprising a first congestion indicator representative of a presence of network congestion.

Abstract translation: 公开了用于网络拥塞管理的方法和系统。 所述方法和系统接收符合第一网络协议的第一分组，所述第一分组包括表示网络拥塞存在或不存在的第一拥塞指示符，并且还包括与第二网络协议相关联的第一组数据，并且提供存在 或者至少部分地基于第一拥塞指示生成网络拥塞。 所述方法和系统还接收符合第一网络协议的第一分组，所述第一网络协议包括与第二网络协议相关联的第一组数据，并且输出符合所述第一网络协议的第二分组，所述第二分组包括表示网络存在的第一拥塞指示符 拥塞。