UPDATED 15:12 EDT / APRIL 27 2010

#Datacenter #Metrics – Is 70 Data Center Performance Metrics Enough?

There is a movement in the datacenter circles to rethink metrics.  What are the right metrics for performance?  The industry is moving towards heavily towards Application Performance oriented metrics for better business visibility into their Data Centers and away from traditional “up / down status” reporting.

Faster troubleshooting is increasingly important especially as companies begin to realize how much time and productivity is actually wasted with finger-pointing between Network, Application and Server teams.

These siloed IT teams are all too often using different tools looking at disconnected metrics. Having more decentralized lower cost technologies leads more proliferation within an enterprise and IT.  The big problem is that as the performance and cost of these new technologies increase so does the manual labor to make them all work.  This is compounded by how an IT organization is structured.  If the organization’s are silo’d then those environments are in deep trouble.

Will 70 Metrics Do The Job ?

Metrics Type
Packet Loss (Inbound) % Network Performance
Packet Loss (Outbound) % Network Performance
Packet Retransmission Rate (Inbound) #/sec Network Performance
Packet Retransmission Rate (Outbound) #/sec Network Performance
Retransmission Delay (Inbound) msec Network Performance
Retransmission Delay (Outbound) msec Network Performance
Retransmission Rate (Inbound) Mbits/sec Network Performance
Retransmission Rate (Outbound) Mbits/sec Network Performance
Round Trip Time (Inbound) msec Network Performance
Round  Trip Time (Outbound) msec Network Performance
95th Percentile Throughput (Inbound) kbits/sec Utilization Performance
95th Percentile Throughput (Outbound) kbits/sec Utilization Performance
Goodput (Inbound) kbits/sec Utilization Performance
Goodput (Outbound) kbits/sec Utilization Performance
Packet Payload (TCP Clients) # Utilization Performance
Packet Payload (TCP Servers) # Utilization Performance
Packet Throughput (Inbound) #/sec Utilization Performance
Packet Throughput (Outbound) #/sec Utilization Performance
Packet Traffic (Inbound) # Utilization Performance
Packet Traffic (Outbound) # Utilization Performance
Payload (TCP Clients) kB Utilization Performance
Payload (TCP Servers) kB Utilization Performance
Throughput (Inbound and Outbound) kbits/sec Utilization Performance
Throughput (Inbound) kbits/sec Utilization Performance
Throughput (Outbound) kbits/sec Utilization Performance
Traffic (Inbound and Outbound) MB Utilization Performance
Traffic (Inbound) MB Utilization Performance
Traffic (Oubound) MB Utilization Performance
AS Description AS Information Metrics
AS Name AS Information Metrics
AS Number AS Information Metrics
Group AS Information Metrics
Ground Defined AS Information Metrics
Group Membership Information AS Information Metrics
ISP Peering Point Roundtrip Time msec Traceroute Metrics
Traceroute Round Trip Time msec Traceroute Metrics
Trans-ISP Round Trip Time msec Traceroute Metrics
Client Reset Rate (TCP Clients) #/sec Application Performance Metrics
Client Reset Rate (TCP Servers) #/sec Application Performance Metrics
Connection Duration (TCP Clients) sec Application Performance Metrics
Connection Duration (TCP Servers) sec Application Performance Metrics
Connection Rate (TCP Clients) #/sec Application Performance Metrics
Connection Rate (TCP Servers) #/sec Application Performance Metrics
Connection Request Rate (TCP Clients) #/sec Application Performance Metrics
Connection Request Rate (TCP Servers) #/sec Application Performance Metrics
Connection Requests (TCP Clients) # Application Performance Metrics
Connection Requests (TCP Servers) # Application Performance Metrics
Connection Setup Time (TCP Clients) msec Application Performance Metrics
Connection Setup Time (TCP Servers) msec Application Performance Metrics
Connections (TCP Clients) # Application Performance Metrics
Connections (TCP Servers) # Application Performance Metrics
Connections Failed (TCP Clients) # Application Performance Metrics
Connections Failed (TCP Servers) # Application Performance Metrics
Connections Failed Rate (TCP Clients) #/sec Application Performance Metrics
Connections Failed Rate (TCP Servers) #/sec Application Performance Metrics
Data Transfer Time (TCP Clients) sec Application Performance Metrics
Data Transfer Time (TCP Servers) sec Application Performance Metrics
Initial Application Response Time (TCP Clients) msec Application Performance Metrics
Initial Application Response Time (TCP Servers) msec Application Performance Metrics
Payload Transfer Time (Clients) Application Performance Metrics
Payload Transfer Time (Servers) Application Performance Metrics
Server Reset Rate (TCP Clients) #/sec Application Performance Metrics
Server Reset Rate (TCP Servers) #/sec Application Performance Metrics
Server Response Time (Clients) msec Application Performance Metrics
Server Response Time (Servers) msec Application Performance Metrics
Time to First Byte (TCP Clients) msec Application Performance Metrics
Time to First Byte (TCP Servers) msec Application Performance Metrics
Turn Rate Clients) #/sec Application Performance Metrics
(Turn Rate (Servers) #/sec Application Performance Metrics
Turns (Clients) # Application Performance Metrics
Turns (Servers) # Application Performance Metrics
User Response Time (Clients) Application Performance Metrics
User Response Time (Servers) Application Performance Metrics

A primary goal should be to get them all working from the same sheet of music leveraging best of breed and Integrated tools to troubleshoot performance problems at lightning speed completely across network and server environments.  Also, “metric reporting” is almost becoming a commodity market; solutions that actually offer advanced analytics and a co-relational understanding of these metrics offer key differentiators for datacenter performance management.

Enterprises and IT have to align their business objectives with real IT metrics not some narrow spec traditionally employed by IT.

{Editors note:  Andy Fields @painpoint contributed to this post. – thanks Andy}


A message from John Furrier, co-founder of SiliconANGLE:

Support our open free content by sharing and engaging with our content and community.

Join theCUBE Alumni Trust Network

Where Technology Leaders Connect, Share Intelligence & Create Opportunities

11.4k+  
CUBE Alumni Network
C-level and Technical
Domain Experts
15M+ 
theCUBE
Viewers
Connect with 11,413+ industry leaders from our network of tech and business leaders forming a unique trusted network effect.

SiliconANGLE Media is a recognized leader in digital media innovation serving innovative audiences and brands, bringing together cutting-edge technology, influential content, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — such as those established in Silicon Valley and the New York Stock Exchange (NYSE) — SiliconANGLE Media operates at the intersection of media, technology, and AI. .

Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a powerful ecosystem of industry-leading digital media brands, with a reach of 15+ million elite tech professionals. The company’s new, proprietary theCUBE AI Video cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.