A user has submitted a trouble ticket complaining that the email server VM has become very
sluggish. After looking at the logs, the vSphere administrator suspects the iSCSI network is
experiencing congestion.
What esxtop statistic should the administrator examine in order to validate that the guest OS is
experiencing performance degradation?
A.
GAVG/wr
B.
%ACTV
C.
PATH
D.
PKTRXMUL/s
Explanation:
http://kb.vmware.com/selfservice/microsites/search.do?language=en_US&cmd=displayKC&externalId=1008205
GAVG/wr stands for GuestOS Average Writes
GAVG is the only valid esxtop listed. Can anyone confirm this plz?
GAVG/wr – Average guest operating system write latency per write operation in milliseconds.
%ACTV – Percentage of guest physical memory that is being referenced by the guest. This is an instantaneous value.
PATH – Storage path name. This name is only visible if the corresponding adapter is expanded. See interactive command e in Storage Adapter Panel Interactive Commands.
PKTRXMUL/s – Number of multicast packets received per second.
http://pubs.vmware.com/vsphere-55/index.jsp?topic=%2Fcom.vmware.vsphere.monitoring.doc%2FGUID-A27C3166-DBD1-4E0B-917B-67EF56864F9B.html&resultof=%22GAVG%2fwr%22%20
GAVG is the sum of KAVG(latency experimented by the host) + DADG(latency experimented in the actual device) so this will result in the comulative latency experimented by the actual guest VM.
I would go with A