Been working as SAN consultant, I am always curious to know the various parameters which a Sr. SAN Consultant/Oncall person study/review when there are any issues/alerts reported on SAN storage to them critical with less time.
I am curious to take up the responsiblities from oncall perceptive and seeking guidance on the major factor one consideres while isolating an issue related to SAN Performace degrade.
what are specific values (threshold, eg 15 ios/sec, 30% cache writing pending etc ) which are the watermarks for those specific paramteres one reviews from monitoring tool like HTm, SMC, Perf Advisor.
( Eg. Read cache Pending, write cache pending, IOS/sec, back end and front end adapters ).
And are these values same across all vendor arrays.