Abstract:
A data store comprises a commit management map including an identifier of a distributed transaction. A control method executed by an adapter coupled to the data store includes: alternate processing of, temporarily storing the reception query, and causing a transaction on the data store side to execute the reception query; perpetuation processing of determining whether or not commit is possible using lock information and perpetuating the GXID to be committed and the temporarily stored reception query in a case where commit is possible; settlement processing of causing the transaction on the data store side to execute a GXID addition query that is a query that adds the GXID to be committed to the commit management map and committing the transaction on the data store side; and store restart processing of the adapter starting a new transaction at the data store for a distributed transaction in an in-doubt state.
Abstract:
A computer system includes a plurality of processes which execute processing requests, a control unit, and an all-order distribution unit. When the control unit determines execution of a second processing request with a lower priority order than a first processing request, the control unit creates a divided second processing request based on the second processing request in accordance with a division size determined in advance. The all-order distribution unit determines an execution order of one or more processing requests including at least one of one or more divided second processing requests corresponding to one or more second processing requests and one or more first processing requests, and respectively causes the plurality of processes to execute the one or more processing requests in the determined execution order.
Abstract:
This computer system includes a plurality of nodes for forming a distributed KVS. The plurality of nodes have a plurality of key ranges to which upper-limit data amounts are set, each upper-limit data amounts being an upper limit of an amount of manageable data. When a new key range is created, the plurality of nodes lowers an upper-limit data amount of an existing key range so that the sum of an upper-limit data amount of the new key range and an upper-limit data amount of the existing key range does not exceed a maximum amount which is the amount based on the volume of the memory of the computer apparatus.
Abstract:
A computer system includes a node including a plurality of processes, an instruction unit that designates a key range of data processed by the process, and a distribution unit. When a first key range is processed by a first process and a third key range, which is a portion of the first key range, is processed by a second process that processes a second key range, the instruction unit transmits a first updated key range to the first process, transmits a second updated key range to the second process, and transmits third range update information including first and second new ranges to the distribution unit. When receiving the third range update information, the distribution unit changes the distribution of the data to be processed. The first process performs data processing in the first updated key range and the second process performs data processing in the second updated key range.