公开(公告)号：US06700876B1

公开(公告)日：2004-03-02

申请号：US09354750

申请日：1999-07-29

申请人： Paul D. DiNicola ,  Rama Krishna Govindaraju ,  Mandayam Thondanur Raghunath ,  Gautam H. Shah

发明人： Paul D. DiNicola ,  Rama Krishna Govindaraju ,  Mandayam Thondanur Raghunath ,  Gautam H. Shah

IPC分类号： H04J116

CPC分类号： H04L47/283 ,  H04L47/10 ,  H04L47/115

摘要： Method, system and program storage device are provided for monitoring and ameliorating congestion in a tightly coupled network. Commensurate with sending a packet into the network, a first time stamp is recorded. Upon receipt of an acknowledgment back across the network responsive to sending of the packet, a second time stamp is recorded. The round trip time of the packet is determined and an amount of congestion is estimated using the determined round trip time and a statically predetermined round trip representative of at least one of no network congestion or a known degree of network congestion. The number of flow control tokens for the destination node can be dynamically varied in response to the estimate of the amount of network congestion. If desired, monitoring and estimating of network congestion can be initiated only after identifying the existence of network congestion, for example, represented by a lack of flow control tokens at a sender node for a destination node.

摘要翻译： 提供方法，系统和程序存储设备用于监视和改善紧耦合网络中的拥塞。 相当于将数据包发送到网络中，记录第一个时间戳。 响应于分组的发送而在通过网络接收到确认后，记录第二时间戳。 确定分组的往返时间，并且使用所确定的往返时间和代表无网络拥塞或已知的网络拥塞程度中的至少一个的静态预定往返行程来估计拥塞量。 可以响应于网络拥塞量的估计来动态地改变目的地节点的流控制令牌的数量。 如果需要，可以仅在识别出网络拥塞的存在之后才能启动网络拥塞的监视和估计，例如，由目的地节点的发送方节点缺乏流量控制令牌来表示。

公开(公告)号：US06389478B1

公开(公告)日：2002-05-14

申请号：US09365696

申请日：1999-08-02

申请人： Robert Sidney Blackmore ,  Xin Chen ,  Rama Krishna Govindaraju ,  Anan Vishwanath Hudli

发明人： Robert Sidney Blackmore ,  Xin Chen ,  Rama Krishna Govindaraju ,  Anan Vishwanath Hudli

IPC分类号： G06F1500

CPC分类号： H04L29/06 ,  H04L67/10 ,  H04L69/22 ,  H04L69/329

摘要： A method for grouping I/O vectors to be transferred across a distributed computing environment comprising a plurality of processing nodes coupled together over a network. The method reduces the number of packets transmitted over a network between two or more nodes. The method includes the grouping of two or more I/O vectors into a single message, consisting of one packet with a predetermined maximum size, provided the sizes of the vectors are small enough to be placed into a single packet. The grouping method finds an efficient collection of vectors to form groups that fit inside a single packet. If two or more of the vectors can be combined so that the resulting single packet size does not exceed the predetermined maximum size, the vectors are grouped accordingly. Vectors whose size approach the predetermined maximum packet size are sent as a separate message.

摘要翻译： 一种用于分组要在分布式计算环境中传送的I / O向量的方法，包括通过网络耦合在一起的多个处理节点。 该方法减少了两个或多个节点之间通过网络传输的数据包数量。 该方法包括将两个或更多个I / O向量分组为单个消息，由具有预定最大大小的一个分组组成，只要向量的大小足够小以便放置在单个分组中。 分组方法找到有效的向量集合以形成适合单个数据包内的组。 如果可以组合两个或更多个向量，使得所得到的单个分组大小不超过预定的最大大小，则矢量被相应地分组。 大小接近预定最大数据包大小的向量作为单独消息发送。