-
1.发明申请Resource Affinity Via Dynamic Reconfiguration for Multi-Queue Network Adapters 审中-公开通过动态重新配置多队列网络适配器的资源亲和力公开(公告)号：US20150095472A1
公开(公告)日：2015-04-02
申请号：US14566253
申请日：2014-12-10
CPC分类号： H04L61/2015 , G06F9/505 , H04L41/082
摘要： A mechanism is provided for providing resource affinity for multi-queue network adapters via dynamic reconfiguration. A device driver allocates an initial queue pair within a memory. The device driver determines whether workload of the data processing system has risen above a predetermined high threshold. Responsive to the workload rising above the predetermined high threshold, the device driver allocates and initializes an additional queue pair in the memory. The device driver programs a receive side scaling (RSS) mechanism in a network adapter to allow for dynamic insertion of an additional processing engine associated with the additional queue pair. The device driver enables transmit tuple hashing to the additional queue pair.
摘要翻译： 提供了一种通过动态重新配置为多队列网络适配器提供资源亲和力的机制。 设备驱动程序在内存中分配初始队列对。 设备驱动程序确定数据处理系统的工作负荷是否已经升高到高于预定的高阈值。 响应于高于预定高阈值的工作负载，设备驱动程序在存储器中分配和初始化附加的队列对。 设备驱动程序在网络适配器中编程接收侧缩放（RSS）机制，以允许动态插入与附加队列对相关联的附加处理引擎。 设备驱动程序使传输元组哈希附加到附加队列对。
-
公开(公告)号：US09357035B2
公开(公告)日：2016-05-31
申请号：US14470283
申请日：2014-08-27
发明人： Omar Cardona , Matt R. Hogstrom , Rakesh Sharma
IPC分类号： G06F15/173 , H04L29/08 , H04L12/26
CPC分类号： H04L67/32 , H04L41/083 , H04L43/0811 , H04L67/2833 , H04L67/306 , H04L67/325
摘要： A mechanism is provided for optimizing network communications. A first data transfer request is received via a first application level socket connection in an originating computing device. Prior to opening a kernel level socket connection to a destination computing device, a determination is made as to whether a second data transfer request has been received via a second application level socket connection in the originating computing device, the second data transfer request identifying a destination computing device that is the same as the destination computing device as the first data transfer request. Responsive to identifying the second data transfer request, the first data transfer request and the second data transfer request are coalesced into a third data transfer request stored in a single kernel level socket buffer of the originating computing device. The third data transfer request is then sent to the destination computing device via a single TCP/IP stack.
-
公开(公告)号：US09350825B2
公开(公告)日：2016-05-24
申请号：US14305951
申请日：2014-06-16
发明人： Omar Cardona , Matt R. Hogstrom , Rakesh Sharma
IPC分类号： G06F15/173 , H04L29/08 , H04L12/26
CPC分类号： H04L67/32 , H04L41/083 , H04L43/0811 , H04L67/2833 , H04L67/306 , H04L67/325
摘要： A mechanism is provided for optimizing network communications. A first data transfer request is received via a first application level socket connection in an originating computing device. Prior to opening a kernel level socket connection to a destination computing device, a determination is made as to whether a second data transfer request has been received via a second application level socket connection in the originating computing device, the second data transfer request identifying a destination computing device that is the same as the destination computing device as the first data transfer request. Responsive to identifying the second data transfer request, the first data transfer request and the second data transfer request are coalesced into a third data transfer request stored in a single kernel level socket buffer of the originating computing device. The third data transfer request is then sent to the destination computing device via a single TCP/IP stack.
摘要翻译： 提供了一种优化网络通信的机制。 经由始发计算设备中的第一应用级套接字连接接收第一数据传输请求。 在打开到目的地计算设备的内核级套接字连接之前，确定是否已经通过始发计算设备中的第二应用级套接字连接接收到第二数据传输请求，第二数据传输请求标识目的地 计算设备与目的地计算设备相同，作为第一数据传输请求。 响应于识别第二数据传输请求，第一数据传送请求和第二数据传输请求被合并到存储在始发计算设备的单个内核级套接字缓冲器中的第三数据传输请求中。 然后，第三数据传输请求经由单个TCP / IP栈发送到目的地计算设备。
-
公开(公告)号：US20150365494A1
公开(公告)日：2015-12-17
申请号：US14470283
申请日：2014-08-27
发明人： Omar Cardona , Matt R. Hogstrom , Rakesh Sharma
CPC分类号： H04L67/32 , H04L41/083 , H04L43/0811 , H04L67/2833 , H04L67/306 , H04L67/325
摘要： A mechanism is provided for optimizing network communications. A first data transfer request is received via a first application level socket connection in an originating computing device. Prior to opening a kernel level socket connection to a destination computing device, a determination is made as to whether a second data transfer request has been received via a second application level socket connection in the originating computing device, the second data transfer request identifying a destination computing device that is the same as the destination computing device as the first data transfer request. Responsive to identifying the second data transfer request, the first data transfer request and the second data transfer request are coalesced into a third data transfer request stored in a single kernel level socket buffer of the originating computing device. The third data transfer request is then sent to the destination computing device via a single TCP/IP stack.
摘要翻译： 提供了一种优化网络通信的机制。 经由始发计算设备中的第一应用级套接字连接接收第一数据传输请求。 在打开到目的地计算设备的内核级套接字连接之前，确定是否已经通过始发计算设备中的第二应用级套接字连接接收到第二数据传输请求，第二数据传输请求标识目的地 计算设备与目的地计算设备相同，作为第一数据传输请求。 响应于识别第二数据传输请求，第一数据传送请求和第二数据传输请求被合并到存储在始发计算设备的单个内核级套接字缓冲器中的第三数据传输请求中。 然后，第三数据传输请求经由单个TCP / IP栈发送到目的地计算设备。
-
公开(公告)号：US20150365493A1
公开(公告)日：2015-12-17
申请号：US14305951
申请日：2014-06-16
发明人： Omar Cardona , Matt R. Hogstrom , Rakesh Sharma
CPC分类号： H04L67/32 , H04L41/083 , H04L43/0811 , H04L67/2833 , H04L67/306 , H04L67/325
摘要： A mechanism is provided for optimizing network communications. A first data transfer request is received via a first application level socket connection in an originating computing device. Prior to opening a kernel level socket connection to a destination computing device, a determination is made as to whether a second data transfer request has been received via a second application level socket connection in the originating computing device, the second data transfer request identifying a destination computing device that is the same as the destination computing device as the first data transfer request. Responsive to identifying the second data transfer request, the first data transfer request and the second data transfer request are coalesced into a third data transfer request stored in a single kernel level socket buffer of the originating computing device. The third data transfer request is then sent to the destination computing device via a single TCP/IP stack.
-
-
-
-
搜索结果
5 条记录 (耗时 0.018 秒)
