此告警信息是在11.2.3.3.1之后出现，主要是防止Exadata 存储节点 I/O 读取数据达到 latency capping （延时上限)时会读取尝试读取其它镜像。是一个Exadata的自动调整策略，有效的提高的读取的数据的速度。
从错误信息来进程在读取asm 镜像块的时候发现比较慢从而去读取另外一个镜像块。建议检测cell节点是否有异常。
MOS 对此错误详细解释:
This is a new feature now available in 11.2.3.3.1 called 'Exadata I/O Latency Capping'.
This feature helps eliminate any outliers due to slow reads and prevents read outliers that would otherwise have been visible to applications.
It's possible that on rare occasion, disk drives or flash drives can display high latencies for a small duration while an internal recovery operation is running.
With Exadata I/O Latency Capping enabled, the software automatically cancels the slow read and ASM will redirect the read to a mirror copy as long as it's not the very last copy.
If no further I/O messages are reported in the RDBMS alert log, this means that I/O redirection was successful.
「喜欢这篇文章，您的关注和赞赏是给作者最好的鼓励」
关注作者
【版权声明】本文为墨天轮用户原创内容，转载时必须标注文章的来源（墨天轮），文章链接，文章作者等基本信息，否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容，欢迎发送邮件至：contact@modb.pro进行举报，并提供相关证据，一经查实，墨天轮将立刻删除相关内容。
