Fujitsu Corporation

Georgia Tech Research Corporation

Yasuhiko Kanemasa

Motoyuki Kawaba

Calton Pu

Qingyang Wang

Takafumi Onishi

Yuji Nomura

Riichiro Take

Miwa Okabayashi

Hisatoshi Yamaoka

Hirokazu Iwakura

Atsushi Kubota

Junichi Higuchi

Julius Michaelis

Gaku Nakagawa

Masazumi Matsubara

Toshihiro Shimizu

Yuuji Hotta

Naoyoshi Ohkawa

A method for creating an entry is performed by a computer. The method includes: determining a first time width equal to or longer than a longest time width among time widths to be read based on a read request from each program to a key-value store that holds data that corresponds to time, as a time width to be associated with one entry in the key-value store; and creating the entry that corresponds to a plurality of data that belongs to a time range of the first time width based on the data for each time and storing the entry in the key-value store.

Entry creation method and entry creation program

A data processing system configured to perform processing including: each time when data that includes time information is received, inputting the received data to each of a first processing system of a switching source and a second processing system of a switching destination; comparing the time information of the data with a switching time set as a time to switch a processing system in the first processing system; outputting a processing result of processing that uses the data from the first processing system in a case where a time indicated by the time information is before the switching time; comparing the time information of the data with the switching time in the second processing system; and outputting the processing result of processing that uses the data from the second processing system in a case where the time indicated by the time information is the switching time or time after the switching time.

Computer-readable recording medium storing data processing program, data processing method, and data processing system

A data management method causes a computer to execute processing including: creating, when a predetermined data processing program performs data processing, based on an access frequency to a data store, high-frequency state item list information obtained by listing high-frequency state items of which the access frequency is high; determining, when state information that includes a value of the high-frequency state item is written to the data store, whether or not the state information corresponds to the high-frequency state item with reference to the high-frequency state item list information; grouping and writing pieces of the state information of a plurality of the high-frequency state item.

Data management method for writing state information in data store and computer-readable recording medium storing data management program for writing state information in data store

An event stream processing system having a processor, wherein the processor registers a temporary object when the object of an event message is unregistered in response to the event message from an event generating device, stores the event message in a pending manner, and Issues an error message. The processor converts the temporary object to a permanent object in response to an automatically-issued event generation message in response to the error message, updates state of the object with state value of the held event message, and executes plug-in corresponding to the updated state.

Event stream processing system, event stream processing method, event stream processing program

An information processing device includes a processor configured to observe an actual load measurement value of each of change target components that have a dependency relationship with each other from among a plurality of components arranged in a distributed processing system. The processor is configured to calculate a load prediction value until completion of a change processing of all of the change target components based on the actual load measurement value of each of the change target components. The processor is configured to adjust a transmission interval of a change instruction for instructing start of the change processing to each unchanged change target component that has not started the change processing when the load prediction value exceeds a predetermined threshold value. The processor is configured to transmit the change instruction to each unchanged change target component that has not started the change processing at the adjusted transmission interval.

Information processing device and distributed system

An execution control method that causes a computer to execute a process, the process includes generating a first regression line that indicates a correlation between a reception time point of each of a plurality of event messages received in a first time period and a generation time point of each of the plurality of event messages, calculating, for each of the plurality of the event messages, a first difference between the generation time point of each event message and a value on the first regression line corresponding to the reception time point of each event message, and determining, based on a margin time in accordance with the calculated first difference, a notification time point to be added to a control message indicating a communication state of the plurality of event messages.

Execution control method and information processing apparatus

An event processing method includes storing in a storage unit, upon receipt of a control message representing information indicating a type of an event to be an execution condition for a plug-in and information regarding the plug-in, in association with each other, the information indicating the type of the event specified from the received control message and the plug-in, in association with each other. The method also includes executing the plug-in upon receipt of an event message representing the information indicating the type of the event. The plug-in being stored in the storage unit in association with the information indicating the type of the event specified from the received event message.

Event processing method, non-transitory computer-readable storage medium for storing program

A disclosed information processing apparatus includes a memory and a processor. And the processor is coupled to the memory and configured to: detect a first virtual node that is a bottleneck from among plural virtual nodes included in a virtual system; and identify a second virtual node that is a bottleneck based on a first number of cache misses that occurred when a first program for realizing the first virtual node was executed and a second number of cache misses that occurred when a second program for realizing a second virtual node that is other than the first virtual node was executed.

Analysis method and analysis apparatus

A performance diagnostic server acquires time series data that indicates the number of executions per time from a multi-tier system and calculates, on the basis of the time series data, a correlation coefficient of processing types that are executed by a server in each tier. The performance diagnostic server calculates, from a correlation coefficient of processing types, a partial correlation coefficient by removing the effect of the trend of the entire multi tiers and updates the correlation coefficient of the processing types on the basis of the calculated partial correlation coefficient.

Correlation coefficient calculation method, computer-readable recording medium, and correlation coefficient calculation device

A method includes: extracting a partial character string including a reserved word and a character string immediately previous or subsequent to the reserved word from each of a plurality of pieces of target data, the plurality of pieces of target data conforming to a first pattern character string including the reserved word defined by a protocol; detecting target data including the partial character string among the plurality of pieces of target data; specifying a first partial character string from the extracted partial character string based on the detected target data; and creating, by a processor, a second pattern character string for classifying the plurality of pieces of target data based on the first pattern character string and the first partial character string.

Method of creating classification pattern, apparatus, and recording medium

A first memory stores requester event records describing events that occurred in relation to processes executed in a first server. A second memory stores requestee event records describing events that occurred in relation to processes executed in a second server in response to execution requests issued from the first server. An associating unit searches the first and second memories for requester event records and requestee event records whose transaction identifiers are identical and associates the found records together. A determining unit compares the associated event records with each other in terms of their time information. Based on this comparison, the determining unit determines a correction value for correcting time differences between requester event records in the first memory and requestee event records in the second memory.

Information processing apparatus and method for determining time correction values

A physical machine calculates, for each virtual switch, an increment of a usage of a processor in accordance with the number of packets to be collected, by using a usage of the processor by a virtual switch and a number of packets passing through each port when mirroring is executed and when mirroring is not executed, respectively. For each of candidates for capture point, the physical machine calculates, for each physical machine, a usage of the processor by a hypervisor when mirroring is executed, by using an increment of a usage of the processor by the virtual switch and a usage of the processor by the hypervisor when mirroring is not executed. The physical machine determines a combination of ports used for collection of packets from among the candidates for capture point, in accordance with a deviation of the calculated usage of the processor by each hypervisor.

Capture point determination method and capture point determination system

An information processing apparatus includes a processor that is capable of switching a performance level to one of a plurality of performance levels with different power consumption, and a storage unit that stores a program for controlling the performance level of the processor. The processor executing the program detects the periodicity of load variation of the information processing apparatus, and changes, according to the periodicity of the load variation, a determination interval for determining whether to switch the performance level of the processor.

Information processing apparatus and load control method

In an information processing apparatus, a calculation unit retrieves data that indicates processing periods of processes executed in each time window constituting an analysis period. The calculation unit then calculates a total processing time for each time window by adding up processing times spent for execution of processes. The calculation unit also calculates a total progress quantity for each time window by adding up progress quantities of the processes. A determination unit determines, based on the total processing time and total progress quantity of each time window, a threshold of the total processing times at which the ratio of an increase of the total progress quantity to an increase of the total processing time is equal to or smaller than a predetermined value. A detection unit detects time windows whose total processing times are equal to or longer than the threshold.

Method, computer program, and information processing apparatus for analyzing performance of computer system

An information processing apparatus submits jobs for execution on a server. Jobs are classified into a plurality of groups, and these groups are ranked in ascending order of workload that the groups of jobs impose on the server. A processor in the information processing apparatus counts ongoing jobs that are currently executed on the server and belong to a specified number of top-ranked groups. The processor designates pending jobs that belong to other groups than the specified number of top-ranked groups and suspends submission of processing requests of the designated pending jobs to the server, when the number of ongoing jobs is greater than or equal to a threshold and when there are one or more pending jobs that belong to the specified number of top-ranked groups.

Growing community of inventors

Kawasaki, Japan

Yasuhiko Kanemasa