-
公开(公告)号：US07568030B2
公开(公告)日：2009-07-28
申请号：US12027044
申请日：2008-02-06
IPC分类号： G06F13/00
CPC分类号： G06F9/5027 , G06F9/544 , G06F2209/5018 , G06F2209/508
摘要： A method, system, and program for monitoring thread usage to dynamically control a thread pool are provided. An application running on the server system invokes a listener thread on a listener socket for receiving client requests at the server system and passing the client requests to one of multiple threads waiting in a thread pool. Additionally, the application sends an ioctl call in blocking mode on the listener thread. A TCP layer within the server system detects the listener thread in blocking mode and monitors a thread count of at least one of a number of incoming requests waiting to be processed and a number of said plurality of threads remaining idle in the thread pool over a sample period. Once the TCP layer detects a thread usage event, the ioctl call is returned indicating the thread usage event with the thread count, such that a number of threads in the thread pool may be dynamically adjusted to handle the thread count.
摘要翻译： 提供了一种用于监视线程使用以动态控制线程池的方法，系统和程序。 在服务器系统上运行的应用程序调用侦听器套接字上的侦听器线程，以便在服务器系统上接收客户端请求，并将客户端请求传递给等待线程池的多个线程之一。 此外，应用程序在侦听器线程上以阻塞模式发送ioctl调用。 服务器系统内的TCP层以阻塞模式检测侦听器线程，并且监视等待被处理的多个传入请求中的至少一个的线程计数，并且线程池中的多个线程在一个样本上保持空闲 期。 一旦TCP层检测到线程使用事件，将返回指示线程计数的线程使用事件的ioctl调用，以使线程池中的线程数可以被动态调整以处理线程计数。
-
公开(公告)号：US07363369B2
公开(公告)日：2008-04-22
申请号：US10687236
申请日：2003-10-16
IPC分类号： G06F13/00
CPC分类号： G06F9/5027 , G06F9/544 , G06F2209/5018 , G06F2209/508
摘要： A method, system, and program for monitoring thread usage to dynamically control a thread pool are provided. An application running on the server system invokes a listener thread on a listener socket for receiving client requests at the server system and passing the client requests to one of multiple threads waiting in a thread pool. Additionally, the application sends an ioctl call in blocking mode on the listener thread. A TCP layer within the server system detects the listener thread in blocking mode and monitors a thread count of at least one of a number of incoming requests waiting to be processed and a number of said plurality of threads remaining idle in the thread pool over a sample period. Once the TCP layer detects a thread usage event, the ioctl call is returned indicating the thread usage event with the thread count, such that a number of threads in the thread pool may be dynamically adjusted to handle the thread count.
摘要翻译： 提供了一种用于监视线程使用以动态控制线程池的方法，系统和程序。 在服务器系统上运行的应用程序调用侦听器套接字上的侦听器线程，以便在服务器系统上接收客户端请求，并将客户端请求传递给线程池中等待的多个线程之一。 此外，应用程序在侦听器线程上以阻塞模式发送ioctl调用。 服务器系统内的TCP层以阻塞模式检测侦听器线程，并且监视等待被处理的多个传入请求中的至少一个的线程计数，并且线程池中的多个线程在一个样本上保持空闲 期。 一旦TCP层检测到线程使用事件，将返回指示线程计数的线程使用事件的ioctl调用，以使线程池中的线程数可以被动态调整以处理线程计数。
-
3.发明授权Method, system and article for improved TCP performance during packet reordering 失效方法，系统和文章，用于在数据包重排序期间改进TCP性能公开(公告)号：US07742419B2
公开(公告)日：2010-06-22
申请号：US12101765
申请日：2008-04-11
IPC分类号： H04L1/00
CPC分类号： H04L29/06 , H04L69/16 , H04L69/161 , H04L69/163
摘要： TCP congestion avoidance is implemented upon retransmission of a packet and is reverted back to the original congestion state upon receipt of an early acknowledgement (ACK), indicating reordering of packets, thereby eliminating a needless restriction on TCP bandwidth. Upon receiving an ACK to a retransmitted packet, it is determined if the ACK resulted from receipt of the original reordered packet or the retransmitted packet, based on the arrival time of the ACK at the sender. If the round-trip-time (RTT) for the retransmitted packet is much lower than the average or current calculated RTT for the network link between sender and receiver, then the retransmission occurred as a result of a reordering event, and the congestion window is restored back to its value prior to the retransmission, thereby permitting the network link to continue operating at its original increased throughput.
摘要翻译： TCP拥塞避免在分组重传时实现，并且在接收到指示重新排序分组的早期确认（ACK）时被恢复到原始拥塞状态，从而消除对TCP带宽的不必要的限制。 在向重传的分组接收到ACK时，基于ACK在发送方的到达时间确定ACK是否从接收到原始重新排序的分组或重传分组而产生。 如果重发分组的往返时间（RTT）远低于发送方和接收方之间的网络链路的平均或当前计算的RTT，则重新发送作为重排序事件的结果，拥塞窗口为 在重传之前恢复其值，从而允许网络链路以其原始增加的吞吐量继续运行。
-
4.发明授权Method, system, and computer program product for delivering data to a storage buffer assigned to an application 失效用于将数据传送到分配给应用程序的存储缓冲区的方法，系统和计算机程序产品公开(公告)号：US07519699B2
公开(公告)日：2009-04-14
申请号：US10912498
申请日：2004-08-05
IPC分类号： G06F15/173
CPC分类号： H04L67/2842 , H04L49/90 , H04L49/9036 , H04L69/16 , H04L69/161 , H04L69/32
摘要： A method, system, and computer program product in a computer-readable medium for delivering data, received from a network, to a storage buffer assigned to an application is proposed. An application designates a communication buffer within a local data processing system for buffering data communicated with an application. The local data processing system reports to a network interface of the local data processing system a memory address of the designated communication buffer, and the data processing system creates a cookie containing the memory address. The data processing system then sends the cookie form the local data processing system to a remote data processing system, such that the remote data processing system may address data directly to the designated communication buffer.
摘要翻译： 提出了一种用于将从网络接收的数据传送到分配给应用的存储缓冲器的计算机可读介质中的方法，系统和计算机程序产品。 应用程序指定本地数据处理系统内的通信缓冲器，用于缓冲与应用程序通信的数据。 本地数据处理系统向本地数据处理系统的网络接口报告指定通信缓冲器的存储器地址，并且数据处理系统创建包含存储器地址的cookie。 然后，数据处理系统将本地数据处理系统的cookie发送到远程数据处理系统，使得远程数据处理系统可以直接将数据寻址到指定的通信缓冲器。
-
5.发明授权Method, apparatus, and program for informing a client when a server is busy in the transfer control protocol 有权用于在服务器忙于传输控制协议时通知客户端的方法，装置和程序公开(公告)号：US07483990B2
公开(公告)日：2009-01-27
申请号：US10443667
申请日：2003-05-22
IPC分类号： G06F15/16
CPC分类号： H04L47/263 , H04L47/10 , H04L47/193 , H04L47/30 , H04L67/14 , H04L69/16 , H04L69/163 , H04L69/329
摘要： The server side Transfer Control Protocol is modified so that the server returns a SYNACK message with the window size equal to zero if the server is busy. When a client sends a TCP connection request and receives a synchronization acknowledgement message with the window size equal to zero, the client knows that the server received the connection request and that the server is busy. The client may then send an acknowledgement message to complete the three-way synchronization handshake, thus successfully completing the connection. Thereafter, the client side TCP may probe the server side TCP until a window update message is received from the server. When the server sends a window update message to set the window size to a non-zero size, the client knows that the server is no longer busy and the client application may then use the TCP connection.
摘要翻译： 修改服务器端传输控制协议，以便服务器返回SYNACK消息，如果服务器正忙，则窗口大小等于零。 当客户端发送TCP连接请求并接收到窗口大小等于零的同步确认消息时，客户端知道服务器接收到连接请求，并且服务器正忙。 然后，客户端可以发送确认消息以完成三次同步握手，从而成功地完成连接。 此后，客户端TCP可以探测服务器端TCP，直到从服务器接收到窗口更新消息。 当服务器发送窗口更新消息以将窗口大小设置为非零大小时，客户端知道服务器不再忙，客户端应用程序可能会使用TCP连接。
-
6.发明申请METHOD, SYSTEM AND ARTICLE FOR IMPROVED TCP PERFORMANCE DURING PACKET REORDERING 失效方法，系统和文章提高分组后的TCP性能公开(公告)号：US20080186863A1
公开(公告)日：2008-08-07
申请号：US12101765
申请日：2008-04-11
IPC分类号： G08C15/00
CPC分类号： H04L29/06 , H04L69/16 , H04L69/161 , H04L69/163
摘要： TCP congestion avoidance is implemented upon retransmission of a packet and is reverted back to the original congestion state upon receipt of an early acknowledgement (ACK), indicating reordering of packets, thereby eliminating a needless restriction on TCP bandwidth. Upon receiving an ACK to a retransmitted packet, it is determined if the ACK resulted from receipt of the original reordered packet or the retransmitted packet, based on the arrival time of the ACK at the sender. If the round-trip-time (RTT) for the retransmitted packet is much lower than the average or current calculated RTT for the network link between sender and receiver, then the retransmission occurred as a result of a reordering event, and the congestion window is restored back to its value prior to the retransmission, thereby permitting the network link to continue operating at its original increased throughput.
摘要翻译： TCP拥塞避免在分组重传时实现，并且在接收到指示重新排序分组的早期确认（ACK）时被恢复到原始拥塞状态，从而消除对TCP带宽的不必要的限制。 在向重传的分组接收到ACK时，基于ACK在发送方的到达时间确定ACK是否从接收到原始重新排序的分组或重传分组而产生。 如果重发分组的往返时间（RTT）远低于发送方和接收方之间的网络链路的平均或当前计算的RTT，则重新发送作为重排序事件的结果，拥塞窗口为 在重传之前恢复其值，从而允许网络链路以其原始增加的吞吐量继续运行。
-
7.发明授权Method, system and article for improved TCP performance during packet reordering 失效方法，系统和文章，用于在数据包重排序期间改进TCP性能公开(公告)号：US07385923B2
公开(公告)日：2008-06-10
申请号：US10640818
申请日：2003-08-14
IPC分类号： H04L1/00
CPC分类号： H04L29/06 , H04L69/16 , H04L69/161 , H04L69/163
摘要： TCP congestion avoidance is implemented upon retransmission of a packet and is reverted back to the original congestion state upon receipt of an early acknowledgement (ACK), indicating reordering of packets, thereby eliminating a needless restriction on TCP bandwidth. Upon receiving an ACK to a retransmitted packet, it is determined if the ACK resulted from receipt of the original reordered packet or the retransmitted packet, based on the arrival time of the ACK at the sender. If the round-trip-time (RTT) for the retransmitted packet is much lower than the average or current calculated RTT for the network link between sender and receiver, then the retransmission occurred as a result of a reordering event, and the congestion window is restored back to its value prior to the retransmission, thereby permitting the network link to continue operating at its original increased throughput.
摘要翻译： TCP拥塞避免在分组重传时实现，并且在接收到指示重新排序分组的早期确认（ACK）时被恢复到原始拥塞状态，从而消除对TCP带宽的不必要的限制。 在向重传的分组接收到ACK时，基于ACK在发送方的到达时间确定ACK是否从接收到原始重新排序的分组或重传分组而产生。 如果重发分组的往返时间（RTT）远低于发送方和接收方之间的网络链路的平均或当前计算的RTT，则重新发送作为重排序事件的结果，拥塞窗口为 在重传之前恢复其值，从而允许网络链路以其原始增加的吞吐量继续运行。
-
8.发明授权Method, system and computer program product for delivering data to a storage buffer assigned to an application 失效用于将数据传送到分配给应用程序的存储缓冲区的方法，系统和计算机程序产品公开(公告)号：US07562133B2
公开(公告)日：2009-07-14
申请号：US12060650
申请日：2008-04-01
IPC分类号： G06F15/173
CPC分类号： H04L67/2842 , H04L49/90 , H04L49/9036 , H04L69/16 , H04L69/161 , H04L69/32
摘要： A method, system, and computer program product in a computer-readable medium for delivering data, received from a network, to a storage buffer assigned to an application is proposed. An application designates a communication buffer within a local data processing system for buffering data communicated with an application. The local data processing system reports to a network interface of the local data processing system a memory address of the designated communication buffer, and the data processing system creates a cookie containing the memory address. The data processing system then sends the cookie form the local data processing system to a remote data processing system, such that the remote data processing system may address data directly to the designated communication buffer.
摘要翻译： 提出了一种用于将从网络接收的数据传送到分配给应用的存储缓冲器的计算机可读介质中的方法，系统和计算机程序产品。 应用程序指定本地数据处理系统内的通信缓冲器，用于缓冲与应用程序通信的数据。 本地数据处理系统向本地数据处理系统的网络接口报告指定通信缓冲器的存储器地址，并且数据处理系统创建包含存储器地址的cookie。 然后，数据处理系统将本地数据处理系统的cookie发送到远程数据处理系统，使得远程数据处理系统可以直接将数据寻址到指定的通信缓冲器。
-
公开(公告)号：US07571247B2
公开(公告)日：2009-08-04
申请号：US11301106
申请日：2005-12-12
IPC分类号： G06F15/16
CPC分类号： H04L47/10 , H04L47/266 , H04L47/30 , H04L49/90 , H04L49/901
摘要： A method, system, and program provide for efficient send socket call handling by a transport layer. A transport layer of a network protocol stack receives a send socket call for data of a specified length from an application layer. Responsive to detecting that there is insufficient memory for a single memory allocation to a buffer in the transport layer for at least the specified length, the transport layer blocks the send socket call. The transport layer only wakes the send socket call upon detection of sufficient memory for the single memory allocation within the buffer of the transport layer for at least the specified length, wherein waking the send socket call triggers a kernel to perform the single memory allocation in the buffer and to write the data to the single memory allocation in a single pass.
摘要翻译： 方法，系统和程序提供传输层有效的发送套接字呼叫处理。 网络协议栈的传输层从应用层接收指定长度的数据的发送套接字调用。 响应于检测到对于至少指定长度的传输层中的缓冲器的单个存储器分配没有足够的存储器，传输层阻止发送套接字调用。 检测到传输层缓冲区内单个内存分配的足够内存至少达到指定长度时，传输层只会唤醒发送套接字调用，其中唤醒发送套接字调用会触发内核执行单个内存分配 缓冲区，并将数据写入单次存储器分配。
-
10.发明授权Method, system and article for rapid detection and avoidance of high data corrupting routes within a network 有权用于快速检测和避免网络内高数据损坏路由的方法，系统和文章公开(公告)号：US07394769B2
公开(公告)日：2008-07-01
申请号：US10640819
申请日：2003-08-14
IPC分类号： H04J1/16
CPC分类号： H04L1/0061 , H04L1/0072 , H04L1/08 , H04L1/16 , H04L1/1809 , H04L45/00 , H04L45/22 , H04L45/28 , H04L69/16 , H04L69/161 , H04L69/163 , H04L69/22 , H04L69/40
摘要： A receiving host in a TCP/IP network sends an acknowledgment indicating a received data packet is corrupt. The sending host will begin transmitting with a new field set in the IP header called a check-TCP-checksum bit, thereby requesting that all routers in the TCP/IP network perform a checksum on the entire received packet. Routers in the TCP/IP network will perform a complete checksum on an entire packet with the check-TCP-checksum bit set, and not just on the IP header. The routers continuously monitor the ratio of corrupt packets received on a particular port that fail the entire packet checksum to the total number of packets received on that port. If the ratio of corrupt-to-received packets exceeds a corruption threshold, the router assumes that the associated link is causing data corruption and issues a routing update indicating that the link is bad and should be avoided. Once the retransmission rate between the sender and receiver drops below a threshold level, the bad link has been detected and avoided within the TCP/IP network and the check-TCP-checksum option in the IP header is no longer set in data packets transmitted to the receiver host.
摘要翻译： TCP / IP网络中的接收主机发送指示接收到的数据包已损坏的确认。 发送主机将开始使用称为检查TCP校验和位的IP报头中设置的新字段进行发送，从而请求TCP / IP网络中的所有路由器对整个接收到的数据包执行校验和。 TCP / IP网络中的路由器将对整个数据包执行完整的校验和，同时检查TCP-checksum位，而不仅仅是在IP报头上。 路由器连续监视在特定端口上接收的损坏数据包的总数与在该端口上接收的数据包的总数之间的比例。 如果损坏的数据包的比例超过了破坏阈值，则路由器假设相关联的链路导致数据损坏，并发出路由更新，指示链路不良，应该避免。 一旦发送方和接收方之间的重传速率下降到阈值以下，就会在TCP / IP网络内检测并避免不良链路，并且IP报头中的check-TCP-checksum选项不再被设置在发送到 接收主机。
-
-
-
-
-
-
-
-
-
搜索结果
185 条记录 (耗时 0.044 秒)
