You are tasked with setting up a cluster of EC2 Instances for a NoSQL database. The database requires random
read IO disk performance up to a 100,000 IOPS at 4KB block side per node.
Which of the following EC2 instances will perform the best for this workload?
A.
A High-Memory Quadruple Extra Large (m2.4xlarge) with EBS-Optimized set to true and a PIOPs EBS volume
B.
A Cluster Compute Eight Extra Large (cc2.8xlarge) using instance storage
C.
High I/O Quadruple Extra Large (hi1.4xlarge) using instance storage
D.
A Cluster GPU Quadruple Extra Large (cg1.4xlarge) using four separate 4000 PIOPS EBS volumes in a RAID 0
configuration
Explanation:
http://aws.amazon.com/ec2/instance-types/
Seems like A would be the right answer as there is no indication in the question that a GPU instance is required and the other options are using Instance Storage which doesn’t make sense for a Database.
PIOPS are limited to 20,000 which is why C is the better option
Answer: C
The question refers to a cluster of EC2 instances. So even a failure of single instance shouldn’t matter, additionally it can always be backed up to S3.
https://aws.amazon.com/blogs/aws/new-high-io-ec2-instance-type-hi14xlarge/
“The SSD storage is local to the instance. Using PV virtualization, you can expect 120,000 random read IOPS (Input/Output Operations Per Second) and between 10,000 and 85,000 random write IOPS, both with 4K blocks. For HVM and Windows AMIs, you can expect 90,000 random read IOPS and 9,000 to 75,000 random write IOPS”
C.
High I/O Quadruple Extra Large (hi1.4xlarge) using instance storage
c
C