公开(公告)号：US08006169B2

公开(公告)日：2011-08-23

申请号：US11843938

申请日：2007-08-23

申请人： Giora Biran ,  Zorik Machulsky ,  Vadim Makhervaks

发明人： Giora Biran ,  Zorik Machulsky ,  Vadim Makhervaks

IPC分类号： H03M13/00

CPC分类号： H03M13/00

摘要： An RNIC implementation that performs direct data placement to memory where all segments of a particular connection are aligned, or moves data through reassembly buffers where all segments of a particular connection are non-aligned. The type of connection that cuts-through without accessing the reassembly buffers is referred to as a “Fast” connection because it is highly likely to be aligned, while the other type is referred to as a “Slow” connection. When a consumer establishes a connection, it specifies a connection type. The connection type can change from Fast to Slow and back. The invention reduces memory bandwidth, latency, error recovery using TCP retransmit and provides for a “graceful recovery” from an empty receive queue. The implementation also may conduct CRC validation for a majority of inbound DDP segments in the Fast connection before sending a TCP acknowledgement (Ack) confirming segment reception.

摘要翻译： 执行直接数据放置到特定连接的所有段对齐的存储器的RNIC实现，或者通过重组缓冲区移动数据，其中特定连接的所有段都不对齐。 在不访问重组缓冲区的情况下，直接连接的类型被称为“快速”连接，因为它很可能被对齐，而另一种类型被称为“慢速”连接。 当消费者建立连接时，它指定一个连接类型。 连接类型可以从快速变慢到慢。 本发明减少了内存带宽，延迟，使用TCP重传的错误恢复，并提供了从空接收队列的“优雅恢复”。 在确认段接收之前，实现还可以在Fast连接中的大部分入站DDP段进行CRC校验。

公开(公告)号：US07779182B2

公开(公告)日：2010-08-17

申请号：US12342030

申请日：2008-12-22

申请人： Richard Louis Arndt ,  Giora Biran ,  Harvey Gene Kiel ,  Vadim Makhervaks ,  Renato John Recio ,  Leah Shaley ,  Jaya Srikrishnan

发明人： Richard Louis Arndt ,  Giora Biran ,  Harvey Gene Kiel ,  Vadim Makhervaks ,  Renato John Recio ,  Leah Shaley ,  Jaya Srikrishnan

IPC分类号： G06F13/12 ,  G06F13/28 ,  G06F12/00 ,  H04L12/28 ,  H04J3/16

CPC分类号： H04L49/901 ,  H04L49/90

摘要： A computer program product and distributed data processing system that allows a single physical I/O adapter, such as a PCI, PCI-X, or PCI-E adapter, to validate that a direct memory access address referenced by an incoming I/O transaction that was initiated through a memory mapped I/O operation are associated with a virtual adapter or virtual resource that is referenced by the incoming memory mapped I/O operation is provided. Specifically, the present invention is directed to a mechanism for sharing conventional PCI (Peripheral Component Interconnect) I/O adapters, PCI-X I/O Adapters, PCI-Express I/O Adapters, and, in general, any I/O adapter that uses a memory mapped I/O interface for communications. A single physical I/O adapter validates that one or more direct memory access addresses referenced by an incoming I/O transaction initiated through a memory mapped I/O operation are associated with a virtual adapter or virtual resource that is referenced by the incoming memory mapped I/O operation.

摘要翻译： 计算机程序产品和分布式数据处理系统，允许单个物理I / O适配器（例如PCI，PCI-X或PCI-E适配器）验证输入I / O事务引用的直接存储器访问地址 通过内存映射的I / O操作启动的虚拟适配器或虚拟资源与由进入的内存映射I / O操作引用的虚拟资源相关联。 具体来说，本发明涉及用于共享常规PCI（外围组件互连）I / O适配器，PCI-X I / O适配器，PCI-Express I / O适配器的机制，并且一般地，任何I / O适配器 它使用内存映射的I / O接口进行通信。 单个物理I / O适配器验证通过内存映射I / O操作启动的传入I / O事务引用的一个或多个直接内存访问地址与由映射的进入内存映射的虚拟适配器或虚拟资源相关联 I / O操作。

公开(公告)号：US07496698B2

公开(公告)日：2009-02-24

申请号：US11086713

申请日：2005-03-22

申请人： Giora Biran ,  John Lewis Hufferd ,  Zorik Machulsky ,  Vadim Makhervaks ,  Renato John Recio

发明人： Giora Biran ,  John Lewis Hufferd ,  Zorik Machulsky ,  Vadim Makhervaks ,  Renato John Recio

IPC分类号： G06F3/00 ,  G06F5/00

CPC分类号： G06F13/1657

摘要： A method, computer program product, and a data processing system for posting and retrieving WQEs to a shared receive queue in a manner that alleviates head-of-line blocking issues is provided. The present invention provides a shared receive queue and a posting routine for allowing non-sequential work request postings in the shared receive queue. Additionally, a fetch routine is provided for non-sequential fetching of work queue elements from the shared receive queue.

摘要翻译： 提供了一种方法，计算机程序产品和用于以减轻线头阻塞问题的方式将WQE发布和检索到共享接收队列的数据处理系统。 本发明提供一种共享接收队列和用于允许在共享接收队列中的非顺序工作请求过帐的发布例程。 另外，提供了一个提取例程，用于从共享接收队列中非连续获取工作队列元素。

公开(公告)号：US20080037555A1

公开(公告)日：2008-02-14

申请号：US11839185

申请日：2007-08-15

申请人： Giora Biran ,  Vadim Makhervaks

发明人： Giora Biran ,  Vadim Makhervaks

IPC分类号： H04L12/28

CPC分类号： H04L69/16 ,  H04L49/90 ,  H04L69/161 ,  H04L69/163

摘要： A method and system for completion coalescing by a Transmission Control Protocol (TCP) receiver (e.g., in a TCP/IP offload engine (TOE)). The method comprises: processing inbound TCP segments; and performing completion processing of received TCP ACKS and/or RDMA Read Requests independently of the processing of the inbound TCP segments.

摘要翻译： 用于由传输控制协议（TCP）接收机（例如，在TCP / IP卸载引擎（TOE）中）完成合并的方法和系统。 该方法包括：处理入站TCP段; 并且独立于入站TCP段的处理执行接收的TCP ACKS和/或RDMA读取请求的完成处理。

公开(公告)号：US20060168094A1

公开(公告)日：2006-07-27

申请号：US10905814

申请日：2005-01-21

申请人： Vadim Makhervaks ,  Giora Biran ,  Zorik Machulsky ,  Kalman Meth ,  Renato Recio

发明人： Vadim Makhervaks ,  Giora Biran ,  Zorik Machulsky ,  Kalman Meth ,  Renato Recio

IPC分类号： G06F15/167

CPC分类号： H04L67/1097

摘要： A method and system for directly accessing a SCSI buffer by a RDMA ATP (Address Translation and Protection) mechanism used in at least one of an iSCSI initiator function and an iSCSI target function. A preregistered SCSI buffer may be identified by means of an ITT (initiator task tag) or TTT (target transfer tag) used as a Stag (steering tag).

摘要翻译： 一种用于通过在iSCSI启动器功能和iSCSI目标功能中的至少一个中使用的RDMA ATP（地址转换和保护）机制来直接访问SCSI缓冲器的方法和系统。 可以通过用作Stag（转向标签）的ITT（发起者任务标签）或TTT（目标传送标签）来识别预注册的SCSI缓冲器。

公开(公告)号：US20050149817A1

公开(公告)日：2005-07-07

申请号：US10733588

申请日：2003-12-11

申请人： Giora Biran ,  Zorik Machulsky ,  Vadim Makhervaks

发明人： Giora Biran ,  Zorik Machulsky ,  Vadim Makhervaks

IPC分类号： H03M13/00

CPC分类号： H03M13/00

摘要： An RNIC implementation that performs direct data placement to memory where all segments of a particular connection are aligned, or moves data through reassembly buffers where all segments of a particular connection are non-aligned. The type of connection that cuts-through without accessing the reassembly buffers is referred to as a “Fast” connection because it is highly likely to be aligned, while the other type is referred to as a “Slow” connection. When a consumer establishes a connection, it specifies a connection type. The connection type can change from Fast to Slow and back. The invention reduces memory bandwidth, latency, error recovery using TCP retransmit and provides for a “graceful recovery” from an empty receive queue. The implementation also may conduct CRC validation for a majority of inbound DDP segments in the Fast connection before sending a TCP acknowledgement (Ack) confirming segment reception.

摘要翻译： 执行直接数据放置到特定连接的所有段对齐的存储器的RNIC实现，或者通过重组缓冲区移动数据，其中特定连接的所有段都不对齐。 在不访问重组缓冲区的情况下，直接连接的类型被称为“快速”连接，因为它很可能被对齐，而另一种类型被称为“慢速”连接。 当消费者建立连接时，它指定一个连接类型。 连接类型可以从快速变慢到慢。 本发明减少了内存带宽，延迟，使用TCP重传的错误恢复，并提供了从空接收队列的“优雅恢复”。 在确认段接收之前，实现还可以在Fast连接中的大部分入站DDP段进行CRC校验。

公开(公告)号：US20050120360A1

公开(公告)日：2005-06-02

申请号：US10725740

申请日：2003-12-02

申请人： Vadim Makhervaks ,  Giora Biran ,  Zorik Machulsky

发明人： Vadim Makhervaks ,  Giora Biran ,  Zorik Machulsky

IPC分类号： G06F3/00 ,  G06F9/44 ,  G06F9/46 ,  G06F13/00 ,  G06F15/16 ,  H04L29/06 ,  H04L29/08

CPC分类号： H04L29/06 ,  H04L67/1097 ,  H04L69/329

摘要： A system and method for maintaining ordering in completion and retransmit operations in an RDMA environment. A system is provided for handling a completion process in an remote data memory access (RDMA) environment having a RequestOut channel and a ResponseOut channel, comprising: a descriptor list for each channel, wherein each descriptor list includes a message descriptor for each message in the channel; an update mechanism for updating a message length field in the message descriptor with a sequence number of a last byte in the message whenever a channel swap occurs between the RequestOut channel and the ResponseOut channel; an acknowledgement (Ack) completion system that examines values in a completion context and compares a sequence number of a next to complete message with a last acknowledged sequence number to determine if the message should be completed; and a read request completion system that performs completion of a read request.

摘要翻译： 用于在RDMA环境中完成和重新传输操作的维护顺序的系统和方法。 提供了一种用于处理具有RequestOut信道和ResponseOut信道的远程数据存储器访问（RDMA）环境中的完成过程的系统，包括：每个信道的描述符列表，其中每个描述符列表包括用于每个信息的每个消息的消息描述符 渠道; 一种更新机制，用于在所述RequestOut信道和所述ResponseOut信道之间发生信道交换时，用消息描述符中的消息长度字段更新所述消息中的最后一个字节的序列号; 确认（Ack）完成系统，其检查完成上下文中的值，并将下一个完成消息的序列号与最后确认的序列号进行比较，以确定消息是否应该完成; 以及执行完读取请求的读请求完成系统。

公开(公告)号：US20060221946A1

公开(公告)日：2006-10-05

申请号：US10907507

申请日：2005-04-04

申请人： Leah Shalev ,  Giora Biran

发明人： Leah Shalev ,  Giora Biran

IPC分类号： H04L12/56

CPC分类号： H04L69/16 ,  H04L69/12 ,  H04L69/163 ,  H04L69/326

摘要： A method for performing connection establishment in TCP (transmission control protocol), the method including sending a SYN segment from a sender to a TCP offload engine (TOE), the SYN segment comprising a TCP packet adapted to synchronize sequence numbers on connecting computers, creating a connection context, acknowledging receipt of the SYN segment by sending a SYN/ACK segment to the sender, and sending an ACK segment from the sender to the TOE to acknowledge receipt of the SYN/ACK segment. Alternatively, the method may include sending a SYN segment from a sender to a computer, acknowledging receipt of the SYN segment by sending a SYN/ACK segment to the TOE, creating a connection context, and sending an ACK segment from the TOE to acknowledge receipt of the SYN/ACK segment.

摘要翻译： 一种用于在TCP（传输控制协议）中执行连接建立的方法，所述方法包括从发送方向TCP卸载引擎（TOE）发送SYN段，所述SYN段包括适于在连接计算机上同步序列号的TCP分组， 连接上下文，通过向发送者发送SYN / ACK段来确认SYN段的接收，以及从发送方向TOE发送ACK段以确认接收到SYN / ACK段。 或者，该方法可以包括从发送方发送SYN分段到计算机，通过向TOE发送SYN / ACK分段来确认接收到SYN分段，创建连接上下文，以及从TOE发送ACK分段以确认接收 的SYN / ACK段。

公开(公告)号：US20050117582A1

公开(公告)日：2005-06-02

申请号：US10724960

申请日：2003-12-01

申请人： Giora Biran ,  Leah Shalev

发明人： Giora Biran ,  Leah Shalev

IPC分类号： H04L12/56 ,  H04L29/06 ,  H04L29/08 ,  H04L12/28

CPC分类号： H04L69/16 ,  H04L69/12 ,  H04L69/161 ,  H04L69/28 ,  H04L69/326

摘要： A system and method for providing parallel implementation of a TCP sender comprising a transmit request handler and a transmitter. A transfer control protocol (TCP) transmission system is provided, comprising: a transmit request handler that receives request events, records the event information into a connection context and either schedules a connection in a ready queue or places the connection in a pending queue; and a transmitter that operates in parallel with the transmit request handler, wherein the transmitter dequeues connections from the ready queue and prepares packets for transmission based on information recorded in the connection context.

摘要翻译： 一种用于提供包括发送请求处理器和发送器的TCP发送器的并行实现的系统和方法。 提供了一种传输控制协议（TCP）传输系统，包括：接收请求事件的发送请求处理器，将事件信息记录到连接上下文中，并且调度可用队列中的连接或将连接置于等待队列中; 以及与所述发送请求处理器并行操作的发射机，其中所述发射机基于所述准备队列中的连接进行出队，并且基于在所述连接上下文中记录的信息来准备用于传输的分组。

公开(公告)号：US07543037B2

公开(公告)日：2009-06-02

申请号：US10725740

申请日：2003-12-02

申请人： Vadim Makhervaks ,  Giora Biran ,  Zorik Machulsky

发明人： Vadim Makhervaks ,  Giora Biran ,  Zorik Machulsky

IPC分类号： G06F15/167 ,  G06F3/00 ,  H04L12/56 ,  H04L12/54

CPC分类号： H04L29/06 ,  H04L67/1097 ,  H04L69/329

摘要： A system and method for maintaining ordering in completion and retransmit operations in an RDMA environment. A system is provided for handling a completion process in an remote data memory access (RDMA) environment having a RequestOut channel and a ResponseOut channel, comprising: a descriptor list for each channel, wherein each descriptor list includes a message descriptor for each message in the channel; an update mechanism for updating a message length field in the message descriptor with a sequence number of a last byte in the message whenever a channel swap occurs between the RequestOut channel and the ResponseOut channel; an acknowledgement (Ack) completion system that examines values in a completion context and compares a sequence number of a next to complete message with a last acknowledged sequence number to determine if the message should be completed; and a read request completion system that performs completion of a read request.

摘要翻译： 用于在RDMA环境中完成和重新传输操作的维护顺序的系统和方法。 提供了一种用于处理具有RequestOut信道和ResponseOut信道的远程数据存储器访问（RDMA）环境中的完成过程的系统，包括：每个信道的描述符列表，其中每个描述符列表包括用于每个信息的每个消息的消息描述符 渠道; 一种更新机制，用于在所述RequestOut信道和所述ResponseOut信道之间发生信道交换时，用消息描述符中的消息长度字段更新所述消息中的最后一个字节的序列号; 确认（Ack）完成系统，其检查完成上下文中的值，并将下一个完成消息的序列号与最后确认的序列号进行比较，以确定消息是否应该完成; 以及执行完读取请求的读请求完成系统。