I see this in the client data for example
[iostatdisk]
extended device statistics
device,r/s,w/s,kr/s,kw/s,wait,actv,svc_t,%w,%b,
sd0,a,0.2,3.4,24.0,118.4,0.0,0.1,30.2,0,2
sd0,c,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
sd1,a,0.2,3.4,24.1,118.4,0.0,0.1,28.4,0,2
sd1,c,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
nfs3,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
nfs4,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
extended device statistics
device,r/s,w/s,kr/s,kw/s,wait,actv,svc_t,%w,%b,
sd0,a,0.0,3.2,1.1,99.2,0.0,0.1,26.8,0,2
sd0,c,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
sd1,a,0.0,3.2,0.6,99.2,0.0,0.1,23.9,0,1
sd1,c,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
nfs3,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
nfs4,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0,0
I am interested in a iostatdisk graph.
Also my customer wants to be alerted for some of this issues on above iostat
- A service time value of more than 30ms on a disk that is more than 10% busy
- disk is more than 60% busy
- average wait time of more than 5
Also wants to be alerted for vmstat sr
- scan rate greater than 200 pages per second
Even after these patches there seems to be a parsing issue on some filesystems. ie. some filesystems get a solid graph line, some filesystems are a broken line. "Random" data seems to be missing from the rrd's. I have not located where the bug is yet though.
Craig Cook
--
Asif Iqbal
PGP Key: 0xE62693C5 KeyServer: pgp.mit.edu
A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?