This document discusses node level parallelism and dynamic controlling of container creation services (CCS) on nodes. It proposes using a proportional-derivative (PD) controller to dynamically tune CCS based on metrics like CPU utilization, blocked I/O processes, and context switches. The PD approach is shown to provide faster performance and better resource utilization compared to manual tuning or a static best practice CCS value. Experimental results on 10 node clusters demonstrate the PD approach improves application completion times by 7-31% over static approaches.
5. RM
NM
NM
NM
Wait queue
Ready Queue
Uses existing ccs to allocate containers.
Periodically compute CCS value - API
IF { New CCS < Old CCS }
Suspend Containers
IF
{ New CCS > Old CCS & Suspended containers }
Then
{ Resume old containers before new containers spawn }
IF
{ New CCS > Old CCS & no Suspended containers }
Then
{ assign new containers }
CCS Alloted = 7
CCS Alloted = 14
CCS Alloted =21
CCS Alloted = 14
8. Experimental Setup
Ten IBM Power PC Machines
10 GBPS Ethernet network B/w RM & NM’s
16 cores
64 CPU Threads
124 GB RAM
For each node
RM
NM 9
NM 2
NM 1
1
9. Applications used for Testing
Applications are selected based on two factors
CPU Utilization
IO Demand
10. Performance Comparison
• Default Configuration is at least 50% slower for all applications
• All three dynamic approaches are much better than best practices (7-31% better)
• PD is better than WaterLevel and PD+pruning except for grep application
Tuning Methods to be Compared
• Default
• Best practice
• Three Dynamic Controlling Methods (PD,WL & PD+pruning)
Table: Relative Comparison of map completion time for various tuning methods
11. Performance Comparison
• Default, best case, and exhaustive search have
static CCS value
• Among dynamic approaches PD and
WaterLevel changes CCS
• PD+pruning changes CCS initially, but
stabilizes CCS to a fixed value after 350 second
mark
Fig : Change of CCS value of all tuning approaches
• Dynamic tuning achieves the most satisfactory
performance as well as CCS responsiveness
13. Conclusion
Does not under utilize resources
In Performance comparison PD based dynamic controller showed improvement
compared to best Practice method and Default method
Dynamic approach change the CCS value dynamically for efficient utilization of
resources
Dynamic approach suspends the container when it has less CCS value which reduce
CPU contention