International Business Machines Corporation

Sigfox

Marc Philippe Vertes

Philippe Bergheaud

Dinesh Kumar Subhraveti

Christophe Fourtet

Laurent Dufour

Cèdric Artigue

Nicolas Chalbos

Cédric Artigue

Cedric Le Goater

Francois Richard

Gregory Kurz

An access network for terminals of a digital telecommunications system includes base stations adapted for receiving radiofrequency signals emitted by the terminals, each terminal a physical layer processing module adapted to form a radiofrequency signal on the basis of binary data in accordance with a predefined physical layer protocol. Moreover, for at least one base station, termed the 'partial station', an inverse physical layer processing, making it possible to extract binary data from a radiofrequency signal, is distributed between the partial station and a processing server distinct from the partial station, an inverse physical layer processing module being made up of a first inverse processing module, integrated into the partial station, and a second inverse processing module, integrated into the processing server. The invention also relates to a method of digital telecommunications.

Access network for digital telecommunications system and method of digital telecommunications

A method for transmitting useful information between a transmitting terminal and a receiving terminal connected via a transmission channel. The transmitting terminal defines control information for the useful information, and searches in an association table, which is accessible from the transmitting terminal, for a frame-synchronization word associated with the control information. The transmitting terminal generates a frame of data from the useful information, and transmits, over the transmission channel, a data stream that includes the frame-synchronization word and the frame of data.

Method for transmitting useful information between two terminals and method for generating an association table used in the context of the transmission

A method, computer program and system for controlling accesses to memory by threads created by a process executing on a multiprocessor computer. A page table structure is allocated for each new thread and copied from the existing threads. The page access is controlled by a present bit and a writable bit. Upon a page fault the access is provided to one thread. The kernel handles the new page entry creation process and set the page present bits to zero which creates page faults. In a second embodiment, two page table structures are created, one for one thread having access to the address space and the other page table structure shared by all the other threads not having access to the address space.

Method and system to manage memory accesses from multithread programs on multiprocessor systems

The invention relates to a method for estimating frequency bias negatively affecting a digital signal representative of a symbol frame, wherein said method comprises the steps of: generating the digital signal at a sampling period Te that is shorter than a predefined period of each of the symbols of the frame; calculating values for a plurality of pairs of samples of the digital signal, each value being representative of a phase difference between the samples of a pair; estimating the frequency bias negatively affecting the digital signal on the basis of the values calculated for Np pairs of samples selected such that a plurality of said Np pairs belong strictly to a single symbol in the frame. The present invention also relates to a module for implementing the estimation method, as well as to a telecommunication method and system.

Method and module for estimating frequency bias in a digital-telecommunications system

A mechanism for replicating programs executing on a computer system having a first storage means is provided. The mechanism identifies the events corresponding to requests from one executing program, which may be different from the executing program to be replicated, which are non-deterministic and identifies the 'Non Abortable Events' (NAE's), which change irremediably the state of the external world that need to be reproduced in the replay of the programs. These events are immediately transferred for replay and the executing program is blocked until the transfer is acknowledged. For the other non-deterministic events, they are logged and sent to the executing program, the executing programs remaining blocked only if the log is full and/or if a timer between two NAEs expires, in this case a log transfer to the standby machine is performed to prepare replication before unblocking of the executing program.

Transfer of event logs for replication of executing programs

A method and computer system logs events occurring in an application in a single or multi-computer environment, functioning non-intrusively and transparently vis-&#xe1;-vis this application. A first computer node receives a communication from a client; the first computer node executes a transactional application that provides services to the client. A process of the transactional application includes a call to a first function. In response to the call to the first function, a modified function is executed that calls both the first function and second recording function. The call to the recording function is detected at a secondary computer node, different from the first computer node. The recording function executes at the second node to store logged data at the second computer node, the logged data representing execution of the first process.

Non-intrusive method for logging of internal events within an application process, and system implementing this method

This invention relates to a management method, more particularly by recording or external control, of software operations performed within the execution of an application process executed on a computer. This management applies in particular to the recording of operations in the form of logging data, or to a replay of operations according to a given execution corresponding to a running previously logged running This method applies in particular to operations returning at least one result datum to the managed process, and comprises the carrying out of at least one complementary management phase for the managed operation, this complementary management depending on the deterministic or non deterministic nature of the managed operation or of its result.

Method for the management, logging or replay of the execution of an application process

Mechanisms for managing task events during the scheduling period of a task executing on a processor. Only events of specific portions of the scheduling period are logged, wherein a first shared resource access has been granted for the task, this portion of the scheduling period involving gathering all the non-deterministic events which cannot be replayed by simple task re-execution. Other independent non-deterministic event records are still logged as usual when they occur out of the portion of the scheduling period for which a record has been created. This limits the number of logged events during a recording session of an application and limits the frequency of events to transmit from the production machine to the replay machine.

Optimizing deterministic event record and replay operations

A method is provided which includes: facilitating intercepting a system call in user space by setting up signal handler code for executing operations related to the system call, and performing in the executing process, before execution of the system call, a SELF PTRACE request which sets system and self trace flags in the operating system kernel, wherein the self trace flag facilitates self-notifying the executing process whenever the executing process executes the system call; and intercepting the system call, including: verifying by the kernel that the system and self trace flags are set; saving and sending a signal to the signal handler conveying system call information to the user space; starting execution in user space of the signal handler; and at the end of signal handler execution, re-starting execution of the executing process, while providing system call return information to code of the executing process making the system call.

Method for system call interception in user space

This invention relates to a management method, more particularly by logging and replay, for software operations performed during the execution of an application process executed on a computer. The method applies in particular to internal operations sending a result datum to the managed process, and comprises the following steps: &#x2014;carrying out a deterministic software processing, termed prediction function (FH), based on the state of a managed process or of the application (AOP, ASB), to provide a predict result (RP) for said operation; &#x2014;comparative test to establish whether the value of the predict result (RP) corresponds or does not correspond to the value of the actual result (DR, RRJ); &#x2014;performance of a complementary management depending on the result of the preceding test.

Predictive method for managing logging or replaying non-deterministic operations within the execution of an application process

A method and system for providing a virtual clock on a computer by multiplying the number of instructions executed by the average instruction execution time. It is however not reliable to use this generic computation for virtualization of application in a fault tolerant system because the virtual clock computed like this quickly deviates from the system clock. A virtual clock computation is provided which includes periodic readjustment of the virtual to the system clock. Also, the errors coming from rounding of the number of executing instruction are suppressed. Taking the assumption that the user instruction counters are maintained synchronized in the operational and the replication computers, replacing the system clock access by a virtual clock when virtualizing applications thus turning the system clock acquisition into a deterministic event. Replicating the system clock access can be thus done by re-executing the application code in the replication machine avoiding transfer of information at each system clock access of the virtualized application programs.

Method and system for providing a deterministic virtual clock

This invention relates to a method for dynamic insertion of a computer code processing within a running computer task in a transparent fashion for this target task. It also relates to a method using such a dynamic insertion in order to execute a multi-task application in a virtual container forming a virtualized environment session. This method comprises the following steps of storing by a manager task of a hooking datum representing the code processing to be inserted; executing, within the execution of a system routine called by the target task, a hooking instruction initiating a test of the hooking datum; and executing the inserted code, according to the result of said test and instead of the program instruction following the hooking instruction in the execution of said system routine.

Method for executing an application in a virtual container forming a virtualized environment session

Provided are a method, system, and article of manufacture for providing a process exclusive access to a page including a memory address to which a lock is granted to the process. A request is received for a memory address in a memory device from a requesting process. A lock is granted to the requested memory address to the requesting process. The requesting process is provided exclusive access to a page including the requested memory address for a page access time period. The exclusive access to the page provided to the requesting process is released in response to an expiration of the page access time period.

Providing a process exclusive access to a page including a memory address to which a lock is granted to the process

This invention relates to a management method, during a logging or a replay, of software operations returning a non-deterministic result within the execution of an application process within a computer (OP). This method comprising the following steps:

Growing community of inventors

Plaisance du Touch, France

Marc Philippe Vertes