公开(公告)号：WO2009022239A2

公开(公告)日：2009-02-19

申请号：PCT/IB2008/003292

申请日：2008-03-26

Applicant: ACUMEM AB ,  VESTERLUND, MAGNUS ,  NILSSON, MATS ,  PETTERSON, MIKAEL ,  HAGERSTEN, ERIK ,  ZEFFER, HAKAN ,  BERG, ERIK

Inventor： VESTERLUND, MAGNUS ,  NILSSON, MATS ,  PETTERSON, MIKAEL ,  HAGERSTEN, ERIK ,  ZEFFER, HAKAN ,  BERG, ERIK

CPC classification number: G06F11/3447 ,  G06F11/3466 ,  G06F2201/88 ,  G06F2201/885

Abstract: A system for, method of and computer program product captures performance- characteristic data from the execution of a program and models system performance based on that data. Performance-characterization data based on easily captured reuse distance metrics is targeted, defined as the total number of memory references between two accesses to the same piece of data. Methods for efficiently capturing this kind of metrics are described. These data can be refined into easily interpreted performance metrics, such as performance data related to caches with LRU replacement and random replacement strategies in combination with fully associative as well as limited associativity cache organizations. Methods for assessing cache utilization as well as parallel execution are covered.

Abstract translation: 系统，方法和计算机程序产品从执行程序捕获性能特征数据，并根据该数据对系统性能进行建模。 基于容易捕获的复用距离度量的性能表征数据被定义为两次访问同一数据块之间的存储器引用的总数。 描述有效捕获这种度量的方法。 这些数据可以被简化为易于解释的性能指标，例如与具有LRU替换的缓存和随机替换策略相关联的性能数据以及完全关联以及有限关联缓存组织。 涵盖了评估缓存利用率和并行执行的方法。

公开(公告)号：WO2007068602A2

公开(公告)日：2007-06-21

申请号：PCT/EP2006069148

申请日：2006-11-30

Applicant: IBM ,  IBM UK ,  VASILE PHIL

Inventor： VASILE PHIL

CPC classification number: G06F11/3409 ,  G06F9/455 ,  G06F11/3495 ,  G06F2201/815 ,  G06F2201/865 ,  G06F2201/885

Abstract: Performance data is received at a Remote Performance Monitor (RPM) Server residing on a target virtual operating system within a virtual data center complex. The performance data is generated, and served at predefined intervals, by a Central Performance Data Server operable for the virtual operating system within the virtual data center complex. At least a portion of the performance data is saved in memory accessible to the RPM Server. Then, responsive to a request form an RPM Client residing on an originating virtual machine within the virtual data center complex, at least a portion of data residing in the memory is extracted by the RPM Server and served to the RPM Client.

Abstract translation: 性能数据在位于虚拟数据中心综合体内的目标虚拟操作系统上的远程性能监视器（RPM）服务器上接收。 性能数据由虚拟数据中心综合体内的虚拟操作系统可操作的中央性能数据服务器以预定间隔生成并提供。 至少有一部分性能数据保存在RPM服务器可访问的内存中。 然后，响应于驻留在虚拟数据中心组合系统内的始发虚拟机上的RPM客户端的请求，驻留在存储器中的至少一部分数据由RPM服务器提取并提供给RPM客户端。

公开(公告)号：WO2007048690A1

公开(公告)日：2007-05-03

申请号：PCT/EP2006/067091

申请日：2006-10-05

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED ,  ALLISON, Brett, Matthew ,  BOBITT, Elise

Inventor： ALLISON, Brett, Matthew ,  BOBITT, Elise

IPC: G06F3/06

CPC classification number: G06F11/3485 ,  G06F3/0613 ,  G06F3/0631 ,  G06F3/0647 ,  G06F3/067 ,  G06F11/3419 ,  G06F11/3433 ,  G06F12/0866 ,  G06F2201/81 ,  G06F2201/885

Abstract: System, method and program for managing a storage server comprising first and second clusters of storage controllers. The first cluster comprises one or more storage controllers each controlling one or more storage arrays. The first cluster also comprises a first cache memory and a first nonvolatile storage ("NVS") shared by the one or more storage controllers of the first cluster. The second cluster comprises one or more storage controllers each controlling one or more storage arrays. The second cluster also comprises a second cache memory and a second nonvolatile storage shared by the one or more storage controllers of the second cluster. There is monitoring of an amount of time that data controlled by each of the clusters is held in the cache memory of the cluster before being outpaged to the storage arrays. There is monitoring of an amount of requests to access storage arrays of a cluster that were delayed due to insufficient NVS. A level of impairment of access to each of the storage arrays is determined based on the amount of time that data controlled by each of the clusters was held in the cache memory of the cluster before being outpaged to the storage arrays, and the amount of requests to access the storage arrays of a cluster that were delayed due to insufficient NVS. When access to a storage array is excessively impaired, data is moved from the access-impaired storage array to another storage array with a lower level of access impairment.

Abstract translation: 用于管理包括第一和第二存储控制器簇的存储服务器的系统，方法和程序。 第一集群包括一个或多个存储控制器，每个存储控制器控制一个或多个存储阵列。 第一集群还包括由第一集群的一个或多个存储控制器共享的第一高速缓存存储器和第一非易失性存储器（“NVS”）。 第二集群包括一个或多个存储控制器，每个存储控制器控制一个或多个存储阵列。 第二集群还包括由第二集群的一个或多个存储控制器共享的第二高速缓存存储器和第二非易失性存储器。 在被分组到存储阵列之前，监视由每个集群控制的数据被保持在集群的高速缓冲存储器中的时间量。 正在监视访问由于NVS不足而延迟的集群存储阵列的请求量。 基于在被分组到存储阵列之前，由每个集群控制的数据被保持在集群的高速缓冲存储器中的时间量以及请求量来确定对每个存储阵列的访问的损害级别 以访问由于NVS不足而延迟的集群的存储阵列。 当对存储阵列的访问过度受损时，数据从访问受损存储阵列移动到具有较低访问损害水平的另一个存储阵列。

公开(公告)号：WO2006130825A2

公开(公告)日：2006-12-07

申请号：PCT/US2006021434

申请日：2006-06-01

Applicant: INTEL CORP ,  NEWBURN CHRIS

Inventor： NEWBURN CHRIS

IPC: G06F17/50

CPC classification number: G06F11/3409 ,  G06F8/41 ,  G06F11/3428 ,  G06F11/3447 ,  G06F11/3457 ,  G06F11/3466 ,  G06F11/348 ,  G06F2201/86 ,  G06F2201/88 ,  G06F2201/885

Abstract: A method and apparatus is described herein for monitoring the performance of a microarchitecture and tuning the microarchitecture based on the monitored performance. Performance is monitored through simulation, analytical reasoning, retirement pushout measure, overall execution time, and other methods of determining per instance event costs. Based on the per instance event costs, the microarchitecture and/or the executing software is tuned to enhance performance.

Abstract translation: 本文描述了一种方法和装置，用于监视微架构的性能，并根据监视的性能调整微体系结构。 通过模拟，分析推理，退休计划，总执行时间以及确定每个事件成本的其他方法监控绩效。 基于事件成本的每一例，微型架构和/或执行软件被调整以增强性能。

公开(公告)号：WO2006028721A2

公开(公告)日：2006-03-16

申请号：PCT/US2005/030266

申请日：2005-08-25

Applicant: CROSSROADS SYSTEMS, INC. ,  EWING, David, B. ,  MARTINDALE, Rick, A.

Inventor： EWING, David, B. ,  MARTINDALE, Rick, A.

IPC: G06F17/00

CPC classification number: H04L67/125 ,  G06F11/3409 ,  G06F11/3495 ,  G06F17/30306 ,  G06F2201/80 ,  G06F2201/81 ,  G06F2201/865 ,  G06F2201/885 ,  Y10S707/99931 ,  Y10S707/99942 ,  Y10S707/99943

Abstract: One embodiment includes a system for application-layer monitoring of communication between one or more database clients and one or more database servers. The system includes one or more decoders residing at a decoding layer above a network layer. The decoders reside at a first network location between one or more database clients residing at one or more second network locations and one or more database servers residing at one or more third network locations. The decoders receive database messages communicated from the database clients and intended for the database servers and database messages communicated from the database servers and intended for the database clients, decode the database messages, and extract query-language statements from the database messages. The system also includes a monitoring application residing at an application layer above the decoding layer. The monitoring application resides at the first network location. The monitoring application receives query-language statements extracted at the decoders and records observations on the database messages based on the query-language statements extracted at the decoders.

Abstract translation: 一个实施例包括用于应用层监视一个或多个数据库客户端与一个或多个数据库服务器之间的通信的系统。 该系统包括位于网络层上方的解码层的一个或多个解码器。 解码器驻留在驻留在一个或多个第二网络位置的一个或多个数据库客户端和驻留在一个或多个第三网络位置的一个或多个数据库服务器之间的第一网络位置。 解码器接收从数据库客户端传送的数据库消息，并且用于从数据库服务器传送的数据库服务器和数据库消息，并且用于数据库客户端，解码数据库消息，以及从数据库消息中提取查询语言语句。 该系统还包括驻留在解码层上方的应用层的监视应用。 监控应用程序位于第一个网络位置。 监控应用程序接收在解码器处提取的查询语言语句，并根据在解码器中提取的查询语言语句记录关于数据库消息的观察。

公开(公告)号：WO2005098626A2

公开(公告)日：2005-10-20

申请号：PCT/EP2005/051531

申请日：2005-04-06

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED ,  CHILDRESS, Rhonda ,  KUMHYR, David Bruce ,  PENNELL, Neil Raymond

Inventor： CHILDRESS, Rhonda ,  KUMHYR, David Bruce ,  PENNELL, Neil Raymond

IPC: G06F11/34

CPC classification number: G06F11/3495 ,  G06F9/5033 ,  G06F9/505 ,  G06F11/3419 ,  G06F11/3433 ,  G06F2201/81 ,  G06F2201/875 ,  G06F2201/88 ,  G06F2201/885

Abstract: A monitoring program contains a method for detecting a load imbalance in a group of servers and providing notification so that corrections can be made. An embodiment of the invention reads from the address resolution protocol (ARP) cache to determine which server addresses are present, then clears the ARP cache. The address resolution protocol will repopulate the cache from traffic it snoops and from new requests. By performing this query and clear operation pe­riodically, the tracking program can form a picture of the activity levels of the servers. When a significant imbalance exists, the program notifies a control console for human intervention to solve the problem. The tracking program will periodically write its results to a log file, allowing reports for various time periods to be produced as needed. By this mechanism, not only can an imbalance be quickly detected, but underutilization can be picked up by comparing known capability of a resource to its actual usage.

Abstract translation: 监视程序包含用于检测一组服务器中的负载不平衡的方法，并提供通知，以便进行校正。 本发明的实施例从地址解析协议（ARP）缓存读取以确定哪些服务器地址存在，然后清除ARP缓存。 地址解析协议将从其侦听的流量和新的请求重新填充缓存。 通过定期执行查询和清除操作，跟踪程序可以形成服务器活动级别的图片。 当存在显着的不平衡时，程序通知控制台进行人为干预来解决问题。 跟踪程序将定期将其结果写入日志文件，以便根据需要生成各种时间段的报告。 通过这种机制，不仅可以快速检测到不平衡，而且可以通过将资源的已知能力与其实际使用进行比较来获取利用不足。

公开(公告)号：WO2004095282A1

公开(公告)日：2004-11-04

申请号：PCT/GB2004/001586

申请日：2004-04-14

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED ,  ARMSTRONG, William, Joseph ,  FLOYD, Michael, Stephen ,  LEITNER, Larry, Scott ,  KALLA, Ronald, Nick ,  SINHAROY, Balaram

Inventor： ARMSTRONG, William, Joseph ,  FLOYD, Michael, Stephen ,  LEITNER, Larry, Scott ,  KALLA, Ronald, Nick ,  SINHAROY, Balaram

IPC: G06F11/34

CPC classification number: G06F9/3851 ,  G06F9/50 ,  G06F11/3419 ,  G06F11/348 ,  G06F2201/88 ,  G06F2201/885

Abstract: An accounting method and logic for determining per-thread processor resource utilization in a simultaneous multi-threaded (SMT) processor provides a mechanism for accounting for processor resource usage by programs and threads within programs. Relative resource use is determined by detecting instruction dispatches for multiple threads active within the processor, which may include idle threads that are still occupying processor resources. If instructions are dispatched for all threads or no threads, the processor cycle is accounted equally to all threads. Alternatively if no threads are in a dispatch state, the accounting may be made using a prior state, or in conformity with ratios of the threads' priority levels. If only one thread is dispatching, that thread is accounted the entire processor cycle. If multiple threads are dispatching, but less than all threads are dispatching (in processors supporting more than two threads), the processor cycle is billed evenly across the dispatching threads. Multiple dispatches may be detected for the threads and a fractional resource usage determined for each thread and the counters may be updated in accordance with their fractional usage.

Abstract translation: 用于确定同时多线程（SMT）处理器中的每线程处理器资源利用的计费方法和逻辑提供了一种用于计算程序内的程序和线程的处理器资源使用的机制。 通过检测处理器内活动的多个线程的指令分派来确定相对资源使用，这可能包括仍占用处理器资源的空闲线程。 如果为所有线程或没有线程调度指令，则处理器周期与所有线程相等。 或者，如果没有线程处于调度状态，则可以使用先前状态进行计费，或者根据线程的优先级的比率来进行计费。 如果只调度一个线程，则该线程将占整个处理器周期。 如果多个线程正在调度，但是少于所有线程的调度（在支持多于两个线程的处理器中），处理器周期将在调度线程之间平均计费。 可以为线程检测多个调度，并且为每个线程确定的分数资源使用，并且可以根据其分数使用来更新计数器。

公开(公告)号：WO02054245A8

公开(公告)日：2002-09-12

申请号：PCT/US0144083

申请日：2001-11-26

Applicant: INTEL CORP

Inventor： CRANFORD MICHAEL ,  RODGERS SCOTT D ,  KALAFATIS STAVOS

IPC: G06F11/34

CPC classification number: G06F11/3466 ,  G06F11/3409 ,  G06F11/348 ,  G06F2201/86 ,  G06F2201/88 ,  G06F2201/885

Abstract: A method and apparatus for monitoring the performance characteristics of a multithreaded processor (10) executing instructions from two or more threads simultaneously. Event detectors detect the occurrence of specific processor events (20) during the execution of instructions from threads of a multithreaded processor. Specialized event select controls registers (30) are programmed to control the selection, masking and qualifying of events to be monitored. Events arequalified according to their thread ID and thread current privilege level (CPL). Each event that is qualified is counted by one of several programmable event counters (70) that keep track of all processor events being monitored. The contents of the event counters can then be accessed and sampled via a program instruction.

Abstract translation: 一种用于监视同时执行来自两个或多个线程的指令的多线程处理器（10）的性能特征的方法和装置。 在从多线程处理器的线程执行指令期间，事件检测器检测特定处理器事件（20）的发生。 专门的事件选择控制寄存器（30）被编程为控制要监视的事件的选择，屏蔽和限定。 事件根据其线程ID和线程当前权限级别（CPL）进行资格认证。 每个符合条件的事件都由几个可编程事件计数器（70）之一进行计数，这些可编程事件计数器（70）跟踪所有被监视的处理器 然后可以通过程序指令访问和采样事件计数器的内容。

公开(公告)号：WO99009481A1

公开(公告)日：1999-02-25

申请号：PCT/DE1998/001708

申请日：1998-06-22

IPC: G06F11/34

CPC classification number: G06F11/3409 ,  G06F11/3466 ,  G06F11/3476 ,  G06F2201/86 ,  G06F2201/865 ,  G06F2201/885

Abstract: The invention concerns the acquisition of event-related data occurring during the execution of a user programme, two mutually related processes being formed. The first of said processes consists in detecting event-related data and the second is replaced by the user programme. A clock signal is iteratively activated by the first process, and the process goes into stand-by mode. While the clock signal lasts, the first process blocks the second process and acquires the event-related data of the second process stored by the operational system during the time interval which has elapsed.

Abstract translation: 一种用于检测在一个用户程序，其特征在于，形成有两个相关的过程，其中所述第一过程检测到事件数据和所述第二处理的执行中发生的事件的数据的方法被替换为用户程序，并重复一定时器由第一工序和所述激活 过程进入等待状态，第一过程继续在该定时器的期满第二，和检测由操作系统用于第二进程事件数据的经过时间部分存储的数据。

公开(公告)号：WO1998026571A2

公开(公告)日：1998-06-18

申请号：PCT/US1997022444

申请日：1997-12-10

Applicant: AT & T CORP.

Inventor： AT & T CORP. ,  FRANKLIN, Matthew, Keith ,  MALKHI, Dahlia

IPC: H04M15/00

CPC classification number: G06F11/3438 ,  G06F2201/805 ,  G06F2201/86 ,  G06F2201/875 ,  G06F2201/885 ,  H04M15/00 ,  H04M2215/0176

Abstract: A compact metering scheme meters visits to a web site. A proxy module intercepts traffic between a client and a server. The proxy module appends a metering module to the body of information sent from the server to the client. The metering module measures the duration of each visit using a timing function F and a unique seed generated for each visit. The metering module returns an auditable result when the client ends the visit. A log keeper module is used to store each result.

Abstract translation: 紧凑的计量方案可以访问网站。 代理模块拦截客户端和服务器之间的流量。 代理模块将测量模块附加到从服务器发送到客户端的信息主体。 计量模块使用定时函数F和为每次访问生成的唯一种子来测量每次访问的持续时间。 当客户端结束访问时，计量模块返回可审核的结果。 日志保持模块用于存储每个结果。