Abstract: A method and apparatus performs peer-to-peer file transfers on a High Performance Computing (HPC) cluster such as a Beowulf cluster. A peer-to-peer file tracker (PPFT) allows operating system, application and data files to be moved from a pre-loaded node to another node of the HPC cluster. A peer-to-peer (PTP) client is loaded into the nodes to facilitate PTP file transfers to reduce loading on networks, network switches and file servers to reduce the time needed to load the nodes with these files to increase overall efficiency of the multi-node computing system. The selection of the nodes participating in file transfers can be based on network topology, network utilization, job status and predicted network/computer utilization. This selection can be dynamic, changing during the file transfers as resource conditions change. The policies used to choose resources can be configured by an administrator.

Abstract: Embodiments of the invention provide techniques for generating statistics for optimizing database queries containing user-defined functions (UDFs). In general, the statistics may be generated based on output values produced during past executions of a UDF. The statistics may also be generated based on input values received during past executions of the UDF. Additionally, the statistics may include input and output value pairs, such that a UDF output may be determined based on a UDF input. The generated statistics may be used by a query optimizer to determine an efficient query plan for executing the database query.

Abstract: Embodiments of the invention provide techniques for generating statistics for optimizing database queries containing user-defined functions (UDFs). In general, the statistics may be generated based on output values produced during past executions of a UDF. The statistics may also be generated based on input values received during past executions of the UDF. Additionally, the statistics may include input and output value pairs, such that a UDF output may be determined based on a UDF input. The generated statistics may be used by a query optimizer to determine an efficient query plan for executing the database query.

Abstract: Embodiments of the invention enhance a garbage collection process running on a parallel system or distributed computing environment. Using a garbage collector in such an environment allows a more in-depth analysis to be performed than is possible on other systems. This is because the number of compute nodes present in many parallel systems, and the connections between them, allows the overhead of doing advanced analysis to be spread across the nodes and the results of that analysis to be shared among the nodes.

Abstract: An apparatus, program product and method for determining a cost for using a standby resource that accounts for the cause for the resource's usage. A standby resource, such as a processor, is activated in response to a resource requirement. The cause of the resource requirement is automatically determined. The result of that automatic determination is used to determine a charge indicator for using the standby resource. For instance, performance code associated with a failure may be associated with a charge indicator. A user may later be billed according to the determined charge indicator, i.e., according to their actual use of the standby resource and/or their usage status.

Abstract: A database partial compression mechanism compresses only part of a database table based on historical information regarding how the database table has been accessed in the past. The function of the database partial compression mechanism may also be governed by a user-specified partial compression policy. When the historical information indicates a portion of a table is not frequently used, the portion of the table is compressed without compressing other portions of the table. The result is a table that is uncompressed for portions that are accessed often and compressed for portions that are accessed less often.

Abstract: A multiprocessing uncompression mechanism takes advantage of existing multiprocessing capability within a database to perform dynamic uncompression of portions of a partially compressed database table that satisfy a query using processes that may be executed in parallel. Historical information is gathered for each query. Uncompression advice includes user-specified parameters that determine how the multiprocessing uncompression mechanism functions. The multiprocessing uncompression mechanism processes the historical information and uncompression advice to determine an appropriate task count for performing uncompression in parallel processes. The existing multiprocessing capability within the database then processes the tasks that perform the uncompression in parallel.

Abstract: A database dynamic partial uncompression mechanism determines when to dynamically uncompress one or more compressed portions of a database table that also includes uncompressed portions. A query may include an express term that specifies whether or not to skip compressed portions. In addition, a query may include associated information that specifies whether or not to skip compressed portions, and one or more thresholds that may be used to determine if the system is too busy to perform uncompression. A display mechanism may also determine whether or not to display compressed portions. The uncompression may occur at the database server or at a client. The database dynamic partial uncompression mechanism thus performs dynamic uncompression in a way that preferably uncompresses one or more compressed portions of a partially compressed database table only when the compressed portions satisfy a query and/or need to be displayed.

Abstract: Embodiments of the invention may be used to distribute a database across a plurality of compute nodes of a parallel computing system. That is, to a method for creating a fully in-memory database on the parallel computing system. Further, data compression techniques may be used increase the performance of the in-memory database by compressing some portions of the database to fit within a single node or a logically or physically related group of nodes.

Abstract: A database engine and optimizer framework support creation of a series of profiling indices over a column having character string data, such as a traditional “varchar” data type. The profiling indices result in a reduction of the number of records that are searched when searching for a sub-string match within that column. In some embodiments, the series of indices are created over a column that is typically searched using the LIKE predicate or some similar technique; these indices indicate for each record whether certain sub-strings may exist in that record's value in the column. Thus, the indices are used to find the rows that may match one or more portions of the particular term being queried or, in other words, eliminate those records that do not have at least a portion of the term to be matched. The number of records actually retrieved and searched for the query sub-string is thereby reduced.

Abstract: A method, apparatus and program product for allocating resources in a logically partitioned multiprocessor environment. Resource usage is monitored in a first logical partition in the logically partitioned multiprocessor environment to predict a future underutilization of a resource in the first logical partition. An application executing in a second logical partition in the logically partitioned multiprocessor environment is configured for execution in the second logical partition with an assumption made that at least a portion of the underutilized resource is allocated to the second logical partition during at least a portion of the predicted future underutilization of the resource.

Abstract: An enhanced space allocation mechanism (ESAM) for dynamically allocating space for a fixed length part of variable length fields, such as VARCHAR fields, in database tables. Each record in such a variable length field has a fixed length part, a variable length part, and a pointer to the variable length part. The ESAM determines how much space to allocate based on the data that was historically put into these tables. In one embodiment, a database management system (DBMS) maintains a historical record that includes fields identifying the table, column and application ID, as well as fields that track a count and a total length.

Abstract: A load balancer detects a server failure, and sends a failure notification message to the remaining servers. In response, one or more of the remaining servers may autonomically adjust their configuration parameters, thereby allowing the remaining servers to better handle the increased load caused by the server failure. One or more of the servers may also include a performance measurement mechanism that measures performance before and after an autonomic adjustment of the configuration parameters to determine whether and how much the autonomic adjustments improved the system performance. In this manner server computer systems may autonomically compensate for the failure of another server computer system that was sharing the workload.

Abstract: A method, apparatus, system, and signal-bearing medium that in an embodiment determine whether a block of code associated with a copy-and-paste operation or a punch-out operation has a size greater than a threshold. If the size is greater than the threshold, then a method is created and the block of code is pasted into the method. Also, an invocation to the newly created method is added at the copied-from location and the intended pasted-to location (in the case of the copy-and-paste operation) or an invocation to the newly created method is added at the copied-from location (in the case of the punch-out operation). In this way, future modifications to the block of code need only be made in one place: the method, instead of at all locations where duplicate code exists. Thus, embodiments of the invention may reduce the fragility of the code.

Abstract: A database engine and optimizer framework support creation of a series of profiling indices over a column having character string data, such as a traditional “varchar” data type. The profiling indices result in a reduction of the number of records that are searched when searching for a sub-string match within that column. In some embodiments, the series of indices are created over a column that is typically searched using the LIKE predicate or some similar technique; these indices indicate for each record whether certain sub-strings may exist in that record's value in the column. Thus, the indices are used to find the rows that may match one or more portions of the particular term being queried or, in other words, eliminate those records that do not have at least a portion of the term to be matched. The number of records actually retrieved and searched for the query sub-string is thereby reduced.

Abstract: An apparatus, system, and storage medium that in an embodiment collect a performance metric of a first partition in a logically-partitioned computer. If the difference between the performance metric and an expected performance metric exceeds a threshold, then a job or another partition is shut down or suspended. The expected performance metric is calculated based on the performance that is expected if the first partition is the only partition.

Abstract: A load balancer detects a server failure, and sends a failure notification message to the remaining servers. In response, one or more of the remaining servers may autonomically adjust their configuration parameters, thereby allowing the remaining servers to better handle the increased load caused by the server failure. One or more of the servers may also include a performance measurement mechanism that measures performance before and after an autonomic adjustment of the configuration parameters to determine whether and how much the autonomic adjustments improved the system performance. In this manner server computer systems may autonomically compensate for the failure of another server computer system that was sharing the workload.

Abstract: A load balancer detects a server failure, and sends a failure notification message to the remaining servers. In response, one or more of the remaining servers may autonomically adjust their configuration parameters, thereby allowing the remaining servers to better handle the increased load caused by the server failure. One or more of the servers may also include a performance measurement mechanism that measures performance before and after an autonomic adjustment of the configuration parameters to determine whether and how much the autonomic adjustments improved the system performance. In this manner server computer systems may autonomically compensate for the failure of another server computer system that was sharing the workload.

Abstract: A performance monitor reports SAN performance so that issues within the SAN are not masked from the client. Accesses to the SAN may be grouped into the categories of SAN logical or SAN physical. In one specific embodiment, the ranges of service times for accesses to the SAN are determined by monitoring service times of accesses to the SAN from the client perspective. In another specific embodiment, the ranges of service times for the SAN are determined by the SAN returning data with each request that indicates the service time from the SAN perspective. This allows reporting not only SAN logical and SAN physical accesses, but also allows reporting SAN service time. By specifying SAN service time, the client is able to better determine network delays. In yet another embodiment, information is returned by the SAN to indicate whether the access is SAN logical or SAN physical.

Abstract: A load balancer detects a server failure, and sends a failure notification message to the remaining servers. In response, one or more of the remaining servers may autonomically adjust their configuration parameters, thereby allowing the remaining servers to better handle the increased load caused by the server failure. One or more of the servers may also include a performance measurement mechanism that measures performance before and after an autonomic adjustment of the configuration parameters to determine whether and how much the autonomic adjustments improved the system performance. In this manner server computer systems may autonomically compensate for the failure of another server computer system that was sharing the workload.