Hello,
Don't know if anyone has experienced this one, I have a two node switchless Fas8040 HA setup with three trays attached, One DS2246 populated with 10k SAS owned by Node 1, and two DS4246 Shelfs populated with Sata disk owned by Node 2.
I recently upgraded from On tap 8.3.2P to 9.1P2 successfully after generating the auto support upgrade advisor and following the guide.
However after the upgrade upto a week later I’m still seeing higher than usual CPU utilisation, only on Node1 which prior to the upgrade averaged way below 40% and now averages 80 - 90% with no additional load been placed on the filer.
Before the upgrade
Node1::> node run -node Node1 -command sysstat -c 10 -x 3
CPU %
12
14
13
14
26
21
16
14
19
28
After the upgrade to 9.1 constantly no change after a week with no jobs running out of the norm and only on Node 1
node run -node Node1 sysstat -M 1
ANY1+ ANY2+ ANY3+ ANY4+ ANY5+ ANY6+ ANY7+ ANY8+ AVG CPU0 CPU1 CPU2 CPU3 CPU4 CPU5 CPU6 CPU7 Nwk_Excl Nwk_Lg Nwk_Exmpt Protocol Storage Raid
100% 100% 100% 98% 92% 80% 66% 51% 86% 76% 87% 87% 87% 87% 88% 88% 87% 1% 2% 90% 0% 0% 0%
Raid_Ex Xor_Ex Target Kahuna WAFL_Ex(Kahu) WAFL_MPClean SM_Exempt
3% 0% 9% 2% 21%(14%) 0% 0%
Exempt SSAN_Ex Intr Host Ops/s CP
10% 19% 7% 523% 6673 0%
Command above is truncated for ease of viewing, monitored for a period of time with the values changing marginally but all a lot higher than where it ran before the upgrade.