What do we mean by "top percentile" or TP based latency?

latency distributed-system performance
user1071840 picture user1071840 · Jul 2, 2013 · Viewed 41.9k times · Source

When we discuss performance of a distributed system we use the terms tp50, tp90, tp99.99 TPS. Could someone explain what do we mean by those?

Answer

Sergey Romanovsky picture Sergey Romanovsky · Jul 3, 2013

tp90 is a minimum time under which 90% of requests have been served. Imagine you have times:

10s
1000s
100s
2s

Calculating TP is very simple:

  • sort all times in ascending order: [2s, 10s, 100s, 1000s]
  • find latest item in portion you need to calculate. For TP50 it will ceil(4*.5)=2 requests. You need 2nd request. For TP90 it will be ceil(4*.9)=4. You need 4th request.
  • get time for the item found above. TP50=10s. TP90=1000s

Related questions

How do I simulate a low bandwidth, high latency environment?

I need to simulate a low bandwidth, high latency connection to a server in order to emulate the conditions of a VPN at a remote site. The bandwidth and latency should be tweakable so I can discover the best combination …

Read More
Approximate cost to access various caches and main memory?

Can anyone give me the approximate time (in nanoseconds) to access L1, L2 and L3 caches, as well as main memory on Intel i7 processors? While this isn't specifically a programming question, knowing these kinds of speed details is neccessary …

Read More
How does LMAX's disruptor pattern work?

I am trying to understand the disruptor pattern. I have watched the InfoQ video and tried to read their paper. I understand there is a ring buffer involved, that it is initialized as an extremely large array to take advantage …

Read More