[duplicte of #657] vHive Latency components

[niravnshah]

Hi,

While experimenting with vhive cluster, I wanted to get the benchmark latency components for various functions that has been published in ASPLOS 21 paper
I am trying to benchmark following two charts mentioned in the paper..

To capture the data, I am using following command.

sudo env "PATH=$PATH" go test -v -run TestBenchServe -args -iter 10 -benchDirTest /home/user/vhive/logs -metricsTest -funcName pyaes -snapshotsTest -upfTest 1>/home/user/vhive/logs/pyaes.out 2>/home/user/vhive/logs/pyaes.err

With this command I am getting the following components.

• AddInstance
• FetchState
• LoadVMM
• InstallWS
• ServeUnique
• ConnectFuncClient
• FuncInvocation

From the charts, can you please confirm which of the above component correspond to the following? Or else, how to obtain these?

• Function Start-up (in Figure 7)
• Connection restoration (in Figure 8)
• Function Processing (in Figure 8)

Also, it would be nice if you can provide a brief explanation on what each of the following component would mean in the context of a cluster. A more precise explanation about starting and ending point for these time components would be helpful.

• AddInstance
• ConnectFuncClient
• FuncInvocation

Thanks in advance,
Nirav.

[niravnshah]

Sorry for the repetition of the question. I did not realize @ustiugov has already replied for some of the answers on another thread here in #657. Continuing the discussion there.