欢迎大家赞助一杯啤酒🍺 我们准备了下酒菜:Formal mathematics/Isabelle/ML, Formal verification/Coq/ACL2, C++/F#/Lisp
Red Hat Enterprise Linux/6
来自开放百科 - 灰狐
http://www.redhat.com/about/news/prarchive/2010/new-standard.html 红帽企业 Linux 6.0 正式版已发布] (2010.11.10)
红帽企业 Linux 6.0 正式版有以下技术更新与创新:
高效性,可伸缩,可靠性
可伸缩
- Red Hat Enterprise Linux 6 supports more sockets, more cores, more threads, and more memory.
Efficient Scheduling
- The CFS schedules the next task to be run based on which task has consumed the least time, task prioritization, and other factors. Using hardware awareness and multi-core topologies, the CFS optimizes task performance and power consumption.
Reliability, Availability, and Serviceability (RAS)
- RAS hardware-based hot add of CPUs and memory is enabled.
- When supported by machine check hardware, the system can recover from some previously fatal hardware errors with minimal disruption.
- Memory pages with errors can be declared as "poisoned", and will be avoided.
文件系统
- The new default file system, ext4, is faster, more robust, and scales to 16TB.
- The Scalable File System Add-On contains the XFS file system, which scales to 100TB.
- The Resilient Storage Add-On includes the high availability, clustered GFS2 file system.
- NFSv4 is significantly improved over NFSv3, and is backwards compatible.
- Fuse allows filesystems to run in user space allowing testing and development on newer fused-based filesystems (such as cloud filesystems).
高可用性
- The web interface based on Conga has been re-designed for added functionality and ease of use.
- The cluster group communication system, Corosync, is mature, secure, high performance, and light-weight.
- Nodes can re-enable themselves after failure without administrative intervention using unfencing.
- Unified logging and debugging simplifies administrative work.
- Virtualized KVM guests can be run as managed services which enables fail-over, including between physical and virtual hosts.
- Centralized configuration and management is provided by Conga.
- A single cluster command can be used to manage system logs from different services, and the logs have a consistent format that is easier to parse.
能量管理
- The tickless kernel feature keeps systems in the idle state longer, resulting in net power savings.
- Active State Power Management and Aggressive Link Power Management provide enhanced system control, reducing the power consumption of I/O subsystems. Administrators can actively throttle power levels to reduce consumption.
- Realtime drive access optimization reduces filesystem metadata write overhead.
资源管理
<discussion>characters_max=300</discussion>
分享您的观点