Abstract:
The present invention provides a method and a caching node entity for ensuring at least a predetermined number of a content object to be kept stored in a network, comprising a plurality of cache nodes for storing copies of content objects. The present invention makes use of ranking states values, deletable or non-deletable, which when assigned to copies of content objects are indicating whether a copy is either deletable or non-deletable. At least one copy of each content object is assigned the value non-deletable. The value for a copy of a content object changing from deletable to non-deletable in one cache node of the network, said copy being a candidate for the value non-deletable, if a certain condition is fulfilled.
Abstract:
To provide an approach to software update with scaleable disturbance there is proposed a state copying method for a computation system with at least two logic partitions wherein a state of new software in a standby partition (6, 16) is updated to the state of old software in an executing partition (16, 6) while continuing execution of the old software. Data is transferred from the executing partition to the standby partition in a scaleable way and as soon as the same state is achieved for the standby partition (6, 16) and the executing partition (16, 6) the execution is switched to the new software. This allows to scale the degree of disturbance due to the software update to what is deemed suitable.
Abstract:
To improve the efficiency for an update process in a software processing device with a plurality of memory partitions (4, 14), it is proposed to continue the execution of old software on original data stored in a first memory partition (4) and to update new software and related data in a second memory partition (14). In case the same state for data of old and new software is achieved (S4), an instant switch of services to the new software as far as the same state is achieved (S5) takes place. This processing is repeated (S6) until no data to be transferred remains (S6) in the first memory partition. Thus, the present invention allows for a considerable improvement of the update efficiency with reduced disturbances during data transfer.
Abstract:
To achieve a highly efficient update of software in computer based systems, there is provided a software processing system comprising two partitions (A, B) that are connected through a linking means (24). The two partitions (A, B) are adapted to update a state of new software in one memory means (12) to the sate of old software in the other memory means (32) during the execution of the old software. In particular, the transfer of data from old software to new software is supported by a data conversions support device (50) adapted to output the start address of a conversion program being related to a data variable to be converted.
Abstract:
To achieve a highly efficient upgrade of software in computer based systems a message conversion apparatus (34) comprises an interface unit (36) for message conversion information (MCI) describing at least one message being exchanged in a software processing system before and after an upgrade of the software processing system. Also, a message conversion means (38, 40) is provided to convert the message between old and new representation for the upgraded software processing system in compliance with the specifications given in the message conversion information (MCI). Therefore, it is possible to introduce a disturbance free upgrade of software in computer based systems with minimized system downtime.
Abstract:
In general, the invention is directed towards a multiprocessing system in which jobs are speculatively executed in parallel by multiple processors (30-1, 30-2, ..., 30-N). By speculating on the existence of more coarse-grained parallelism, so-called job-level parallelism, and backing of to sequential execution only in cases where dependencies that prevent parallel execution of jobs are detected, a high degree of parallelism can be extracted. According to the invention a private memory buffer is speculatively allocated for holding results, such as a communication message, an operation system call or a new job signal, of a speculatively executed job, and these results are speculatively written directly into the allocated memory buffer. When commit priority is assigned to the speculatively executed job, a pointer referring to the allocated memory buffer is transferred to an input/output (10) device which may access the memory buffer by means of the transferred pointer. In this way, by speculatively writing messages and signals into private memory buffers, even further parallelism can be extracted.
Abstract:
The invention relates to a method and an access means for determining the storage address of a predetermined data value in a memory device. The data values are stored in an increasing order sequentially in a column direction according to a binary tree data structure. A new subtree root node is calculated from the previous leaf node address when the data value to be searched is not located in the previous subtree. Since a new subtree root node is always calculated from a previous leaf node address and the comparison result between the searched and read out value, the number of row address changes can be kept to a minimum whilst a high speed for the subtree searching is maintained. The search method and the access means is memory efficient since no pointers are used and fast, since the address of a next memory location to be investigated can always be calculated from the previous address and the last comparison result.
Abstract:
PCT No. PCT/SE87/00437 Sec. 371 Date May 17, 1988 Sec. 102(e) Date May 17, 1988 PCT Filed Sep. 28, 1987 PCT Pub. No. WO88/02513 PCT Pub. Date Apr. 7, 1988.A data processing system which executes two instruction sequences in an order determined in advance. With the aid of instructions, a main memory common to both sequences is activated for data information reading/writing. Increased data handling capacity is achieved in the following manner: both sequences are executed in parallel to start with. During execution of the first sequence, the main memory is prevented from being activated for writing due to the second sequence write instructions. A write address and data information included in a write instruction associated with the second sequence are intermediately stored. The intermediately stored write address is compared with the read addresses of the second sequence, and data information is prevented from being read from the main memory in response to an identity of the addresses, the intermediately stored data information being read instead. An address included in a read instruction associated with the second sequence is intermediately stored if this address has not been previously selected in conjuction with a write instruction associated with the second sequence. The intermediately stored read address is compared with the write address of the first sequence and execution of the second sequence is restarted in response to an identity of the addresses.