M. Banatre, G. Muller, B. Rochat, and P. Sanchez. Design decisions for the ftm: a general purpose fault tolerance machine. Technical report, INRIA, Institut National de Recherche en Informatique et en Automatique, 1991.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....the recovery box, although the system detects corruption by maintaining checksums. Banatre et al. implement stable transactional memory, which protects memory contents with dual memory banks, a special memory controller, and explicit calls to allow write access to specified memory blocks [8] [9]. Our work seeks to make all files in memory reliable without special purpose hardware or replication. General mechanisms may be used to help protect memory from software faults. Needham et al. 51] suggest changing a machine s microcode to check certain conditions when writing a memory word. ....

M. Banatre, G. Muller, B. Rochat, and P. Sanchez, "Design Decisions for the FTM: A General Purpose Fault Tolerant Machine," Proc. 1991.

....stable storage. As part of the fault tolerant design effort for MEMSY the checkpointing scheme as well as a stable memory module has been designed [21] The idea of a stable storage was originally proposed in [28] with a disk based solution. Paper [13] describes a memory mapped stable storage and [5] a RAM based stable storage. Our stable storage is also RAM based and accessible by a group of processing nodes (sharing principle) Like the stable memory of the Sequoia [8] multiprocessor it uses dual memory banks, A and B. Memory A is updated by normal accesses of a processing node and memory B ....

M. Bantre, G. Muller, B. Rochat and P. Sanchez, Design Decisions for the FTM: A General Purpose Fault Tolerant Machine, in: Proc. FTCS-21 (1991) 71-78.

....we can expect k = P and O(PN log N ) cost per operation, which will not yield good performance. Similar objections apply to Shavit and Touitou s software implementation [39] of Herlihy and Moss transactional shared memory [29] while proposed hardware implementations are limited in size [9]. Some special purpose wait free data structures have also been introduced, of which the most suitable for sorting are heaps and priority queues. Both data structures use a scheme for announcing pending operations similar to the one proposed by Herlihy, and tend to perform at least part of each ....

Banatre, M., Muller, G., Rochat, B., and Sanchez, P. Design decisions for the FTM: a general purpose fault tolerant machine. 21st Int. Symp. on Fault-Tolerant Computing (FTCS-21) (1991), 71--8.

....k = P , which will not yield good performance. Similar objections apply to Herlihy and Moss transactional shared memory [19] since Shavit and Touitou s lock free software implementation [29] suffers the same drawbacks mentioned above, and proposed hardware implementations are limited in size [5]. Some special purpose wait free data structures have also been introduced, of which the most suitable for sorting are heaps and priority queues. Both data structures use a scheme for announcing pending operations similar to the one proposed by Herlihy, and tend to perform at least part of each ....

Banatre, M., Muller, G., Rochat, B., and Sanchez, P. Design decisions for the FTM: a general purpose fault tolerant machine. 21st Int. Symp. on Fault-Tolerant Computing (FTCS-21) (1991), 71--8.

....that memory can be considered a safe place for permanent data has several implications for architects. A small amount of hardware support at the memory level would make protection easier. An ideal memory controller would enable file system procedures to prevent writes to certain physical pages [Banatre91]. One simple way to implement this is for the controller to store a write permission bit for each memory page and map the write permission bits into the processor s address space. The system could then use these write permission bits to provide fine grained protection at the physical page level, ....

....by maintaining checksums. Banatre, et al. implement stable transactional memory, which protects memory contents with dual The Rio File Cache: Surviving Operating System Crashes 9 memory banks, a special memory controller, and explicit calls to allow write access to specified memory blocks [Banatre91]. Our work seeks to make all files in memory reliable without special purpose hardware or replication. General mechanisms may be used to help protect memory from software faults. Needham83] suggests changing a machine s microcode to check certain conditions when writing a memory word. This is ....

Michel Banatre, Gilles Muller, Bruno Rochat, and Patrick Sanchez. Design decisions for the FTM: a general purpose fault tolerant machine. In Proceedings of the 1991 International Symposium on FaultTolerant Computing, pages 71--78, June 1991.

....the recovery box, although the system detects corruption by maintaining checksums. Banatre, et al. implement stable transactional memory, which protects memory contents with dual memory banks, a special memory controller, and explicit calls to allow write access to specified memory blocks [Banatre86, Banatre88, Banatre91]. Measuring Memory s Resistance to Operating System Crashes 5 General mechanisms may be used to help protect memory from software faults. Needham83] suggests changing a machine s microcode to check certain conditions when writing a memory word; the condition they suggest is that a certain ....

Michel Banatre, Gilles Muller, Bruno Rochat, and Patrick Sanchez. Design decisions for the FTM: a general purpose fault tolerant machine. In Proceedings of the 1991 International Symposium on Fault-Tolerant Computing, pages 71--78, June 1991.

....in case of failure by using a previous image of the system to restart the execution. Most recoverable DSM assume the presence of a stable storage device to ensure the stability of recovery data. These stable storages are usually implemented with specific hardware devices such as stable memories [3, 2], or more conventional devices such as disks. The first solution is efficient but too expensive, especially for large scale systems, whereas the second one is cheap but may rapidly limit the system scalability. In this paper, we propose a backward error recovery implementation that allows the ....

.... protocol based on data replication [13] Many proposed stable storage implementations use either specific hardware devices such as stable memories which are quite expensive, or more conventional devices such as disks which are not very efficient and which limit the scalability of the architecture [3, 2, 4]. Unlike these cases, our approach does not require any specific hardware. Instead, the stable storage needed for recovery data is implemented by using the replication mechanisms provided by the standard memories of a DSM. As node memories can store any shared data, recovery data persistency is ....

M. Banatre, G. Muller, B. Rochat, and P. Sanchez. Design Decisions for the FTM: A General Purpose Fault Tolerant Machine. In 21st International Symposium on FaultTolerant Computing Systems, Montr'eal, Canada, June 1991.

.... or they all reach their final state (all or nothing property) These two properties can be guaranteed by storing recovery points Irisa Tolerating Node Failures in Cache Only Memory Architectures 7 in stable storage [16] for which efficient hardware implementations have already been proposed [2, 3, 4, 7]. In SSMMs, it is however unreasonable to develop specific hardware stable storage implementations as the cost of the architecture would drastically grow. Recovery data persistence, which implies a replication of recovery data on two failure independent physical storages, can be ensured in a COMA ....

M. Banatre, G. Muller, B. Rochat, and P. Sanchez. -- Design Decisions for the FTM : A General Purpose Fault Tolerant Machine. -- In Proc. of 21st International Symposium on Fault-Tolerant Computing Systems, pages 71--78, Montr'eal, Canada, June 1991.

.... establishment, either all recovery data remain in their initial state or they all reach their final state (all or nothing property) These two properties can be guaranteed by storing recovery points in stable storage [16] for which efficient hardware implementations have already been proposed [2, 3, 4, 7]. In SSMMs, it is however unreasonable to develop specific hardware stable storage implementations as the cost of the architecture would drastically grow. Recovery data persistence, which implies a replication of recovery data on two failure independent physical storages, can be ensured in a COMA ....

M. Banatre, G. Muller, B. Rochat, and P. Sanchez. -- Design Decisions for the FTM : A General Purpose Fault Tolerant Machine. -- In Proc. of 21st International Symposium on Fault-Tolerant Computing Systems, pages 71--78, Montr'eal, Canada, June 1991.

No context found.

M. Banatre, G. Muller, B. Rochat, and P. Sanchez. Design decisions for the ftm: a general purpose fault tolerance machine. Technical report, INRIA, Institut National de Recherche en Informatique et en Automatique, 1991.

No context found.

Bantre, M.; Muller, G.; Rochat, B.; Sanchez, P.: Design Decisions for the FTM: A General Purpose Fault Tolerant Machine, Proc. 21th FTCS, pp. 71-78, 1991

No context found.

M. Banatre, G. Muller, et. al., "Design Decisions for the FTM: A General Purpose Fault Tolerant Machine", "Proceedings of the 21st International Symposium on Fault-Tolerant Computing Systems", pp. 71-78, 1991.

No context found.

M. Banatre, G. Muller, B. Rochat, and P. Sanchez. Design Decisions for the FTM: A General Purpose Fault Tolerant Machine. In 21st International Symposium on Fault-Tolerant Computing Systems, Montr'eal, Canada, June 1991.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC