主节点system io比较高,而第二个节点正常,请教大师怎么排查?
本帖最后由 lxhbww 于 2013-12-23 20:36 编辑主节点system io比较高,而第二个节点正常,请教大师怎么排查?见图...
现在没什么应用.节点一alert.log没有报错,也不会频繁切换日志.
oracle11.2.0.2.0 rac oel5.5 x64
主节点iostat比较高,而二节点同样看盘阵这些io都很低.
awr见桌面.rar 最少提供:
业务高峰期的两个节点的awr,系统监控类似ows数据
看 第三条 sql, 还有 顶级会话。 IO 量 几乎一样:
1节点
IOStat by Function summary
'Data' columns suffixed with M,G,T,P are in multiples of 1024 other columns suffixed with K,M,G,T,P are in multiples of 1000
ordered by (Data Read + Write) desc
Function Name Reads: Data Reqs per sec Data per sec Writes: Data Reqs per sec Data per sec Waits: Count Avg Tm(ms)
Others 928M 5.65 .128470 527M 2.18 .072956 48.2K 89.24
DBWR 0M 0.00 0M 480M 3.00 .066450 0
LGWR 0M 0.01 0M 478M 36.78 .066173 132.8K 18.26
Buffer Cache Reads 72M 0.64 .009967 0M 0.00 0M 4269 77.34
Direct Reads 6M 0.05 .000830 1M 0.02 .000138 0
Direct Writes 0M 0.00 0M 1M 0.01 .000138 0
TOTAL: 1006M 6.35 .139268 1.5G 41.99 .205856 185.3K 38.09
2节点
Function Name Reads: Data Reqs per sec Data per sec Writes: Data Reqs per sec Data per sec Waits: Count Avg Tm(ms)
Others 1002M 5.11 .138716 698M 2.88 .096630 46.7K 0.74
LGWR 1M 0.01 .000138 715M 47.21 .098984 170.5K 2.36
DBWR 0M 0.00 0M 676M 4.43 .093584 0
Buffer Cache Reads 92M 0.81 .012736 0M 0.00 0M 5752 5.30
Direct Reads 5M 0.04 .000692 1M 0.01 .000138 0
Direct Writes 0M 0.00 0M 2M 0.01 .000276 0
TOTAL: 1.1G 5.97 .152283 2G 54.55 .289615 222.9K 2.09
Operating System Statistics - Detail
Snap Time Load %busy %user %sys %idle %iowait
23-12月 18:00:16 1.56
23-12月 19:00:07 1.95 1.80 1.31 0.43 98.20 5.44
23-12月 20:00:40 1.89 2.10 1.65 0.39 97.90 6.39
但1节点的延迟明显较高
需要从OS层/通道层/存储层获得更多数据, 先上OSW 谢谢飞哥和刘大,问题找到了,是由于节点一所连光纤模块出了问题,现硬件正在联系采购更换.
页:
[1]