摘要:
Techniques are provided for managing, within a storage system, the sequence in which I/O requests are processed by the storage system based, at least in part, on a one or more logical characteristics of the I/O requests. The logical characteristics may include, for example, the identity of the user for whom the I/O request was submitted, the service that submitted the I/O request, the database targeted by the I/O request, an indication of a consumer group to which the I/O request maps, the reason why the I/O request was issued, a priority category of the I/O request, etc. Techniques are also provided for automatically establishing a scheduling policy within a storage system, and for dynamically changing the scheduling policy in response to changes in workload.
摘要:
An approach for providing efficient network data transfer service is provided. In one embodiment, a first database server receives, from a second database server, a first request to access a first storage subsystem. Here, the second database server cannot access first data in the first storage subsystem without another database server transmitting the first data to the second database server. In response, the first database server provides the second database server a first set of access primitives. Using the first set of access primitives, the second database server may access data stored in the first storage subsystem that may be otherwise not accessible. As a result, the first database server receives, from the second database server, a first data access request to access first data stored in the first storage subsystem.
摘要:
A method, system, and computer program product forcost based analysis for data access in a database management system. In one approach, the method, system, and computer program productperforms identifying data to access, determining a first cost for direct I/O storage access and a second cost for cache access, performing a comparison between the first cost and the second cost, and accessing a first portion of identified data based upon the comparison.
摘要翻译:一种用于数据库管理系统中数据访问的方法,系统和计算机程序产品forcost based analysis。 在一种方法中,方法,系统和计算机程序产品实现识别要访问的数据,确定用于直接I / O存储访问的第一成本和用于高速缓存访问的第二成本,执行第一成本和第二成本之间的比较,以及 基于比较来访问所识别的数据的第一部分。
摘要:
A method, system, and computer program product for cost based analysis for data access in a database management system. In one approach, the method, system, and computer program product identifies data to access. A first cost for direct I/O storage access and a second cost for cache access are then determined for accessing the data. A comparison between the first cost and the second cost is then performed. Finally, a first portion of identified data is accessed based at least in part upon the comparison.
摘要:
An approach for providing efficient network data transfer service is provided. In one embodiment, a first database server receives, from a second database server, a first request to access a first storage subsystem. Here, the second database server cannot access first data in the first storage subsystem without another database server transmitting the first data to the second database server. In response, the first database server provides the second database server a first set of access primitives. Using the first set of access primitives, the second database server may access data stored in the first storage subsystem that may be otherwise not accessible. As a result, the first database server receives, from the second database server, a first data access request to access first data stored in the first storage subsystem.
摘要:
A computer system having a kernel for mapping virtual memory address space to physical memory address space. The computer system uses a method for performing an input/output operation. A physical memory buffer is registered with a subsystem, and the physical memory buffer is associated with a first virtual address, a size and a key. The physical memory buffer is dynamically associated with a second virtual address which is different from the first virtual address. As part of an application program an input/output operation is requested regarding the second virtual address. An application table is used to obtain the first virtual address, the key and the size. The first virtual address, the key and the size are supplied to the subsystem. The subsystem uses the first virtual address, the key and the size, to determine the physical memory buffer and performs an input/output operation using the physical memory buffer without intervention of the kernel.
摘要:
Automated management of shared I/O resources involves use of a policy engine for implementing I/O scheduling group I/O policies. The I/O policies are used for determining whether corresponding I/O requests should be issued to a shared storage system immediately or should be delayed via corresponding policy-based queues. In the context of database systems, a database administrator can specify policies regarding how I/O resources should be used and the database system itself enforces the policies, rather than requiring the database administrator enforce the I/O usage of the database and of the individual users.
摘要:
A database management system (DBMS) maintains a clone database in a clone space without storing an entire copy of the database and without requiring a snapshot function from an underlying storage device. This DBMS may receive a database command to access a data block of the clone database, and may determine whether the data block is stored in the clone space. If the data block is not stored in the local clone space, the DBMS may receive the data block from a backup copy of the database. If the database command comprises a write operation, the DBMS may perform the write operation to update the data block, and may store the updated data block in the clone space. Also, if the database command comprises a read operation, the DBMS may perform the read operation on the data block received from the backup copy of the database.
摘要:
Techniques are provided for managing, within a storage system, the sequence in which I/O requests are processed by the storage system based, at least in part, on one or more logical characteristics of the I/O requests. The logical characteristics may include, for example, the identity of the user for whom the I/O request was submitted, the service that submitted the I/O request, the database targeted by the I/O request, an indication of a consumer group to which the I/O request maps, the reason why the I/O request was issued, a priority category of the I/O request, etc. Techniques are also provided for automatically establishing a scheduling policy within a storage system, and for dynamically changing the scheduling policy in response to changes in workload.
摘要:
A computer-implemented method of implementing a network file system may include steps of providing a host, the host including an Operating System (OS) that includes a kernel and a first client implementing the Network File System (NFS) protocol in the kernel, and a database server process. A second NFS client may be provided in the database server process. A NFS server may be provided, coupled to the host. A device implementing the Network Attached Storage (NAS) protocol may also be provided, coupled to the NFS server. NFS requests to access data stored in the NAS server may then be generated and sent from the second NFS client in the database server process directly to the NFS server, bypassing the first NFS client in the OS kernel of the host. NFS File handles obtained by one database process may be shared with other database processes through a shared memory area.