On April 22, 2017, SAS learned that NO version of RHEL is supported on the AWS EC2 I3 instance. This has to do with the lack of drivers for the NVMe SSD drives and the new Elastic Network Adapters. Please note Red Hat is aggressively working on resolving this issue, but in the meantime SAS strongly encourages SAS 9.4 customers to use the EC2 I2 instance.
We understand that these are older instances, but they are still available from AWS via this previous generation instances link.
For maximum IO throughput, we strongly recommend that you use the i2.8xlarge instance for your SAS compute node(s). This instance has 16 physical cores (32 vCPUs), 244 GB of RAM, and 8 – 800GB internal SSD drives (these drives are ephemeral and all data on them will be erased during a reboot/restart of your instance) and a single 10 GB NIC card. Amazon configured several storage scenarios and gathered IO throughput statistics on them. Please see Appendix A for the details.
We suggest that you stripe the 8 – 800GB internal SSD drives to get the best IO throughput for your SAS WORK and UTILLOC file systems. Please note with striped SSD drives, you can leave UTILLOC in its default location, which is SAS WORK.
We also suggest that the RHEL administrator reads the Optimizing SAS on RHEL paper and apply the tuning recommendations in the paper.
Permanent SAS data, SAS binaries, SAS configuration files, home directories, etc. should be housed on EBS storage for your single SAS compute server instance or in Lustre for your SAS Grid infrastructures (see this paper for how to configure SAS Grid on the Amazon cloud).
As a reminder, it is advisable for all instances used by SAS (metadata tiers, mid-tier, compute tier, and external database tier) to be located in the same Amazon Region and Availability Zone.
Appendix A
To help with getting the best IO throughput, Amazon set up four different storage configuration with an i2.8xlarge instance type running RHEL-7.3_HVM_GA-20161026-x86_64-1-Hourly2-GP2 (ami-b63769a1) and got the following IO throughput numbers using the rhel_iotest.sh test from SAS:
Configuration 1:
- (4) 7965 GiB ST1 EBS Volumes with expected throughput of 312MiB/s per volume in a RAID 0 set named md0.
- (8) ephemeral SSD’s configured as RAID 0 set named md1.
Ephemeral SSD (local)
- read throughput rate: 232.25 megabytes/second per physical core
- write throughput rate: 82.94 megabytes/second per physical core
EBS
- read throughput rate: 71.00 megabytes/second per physical core
- write throughput rate: 70.07 megabytes/second per physical core
Configuration 2:
- (3) 12800GiB ST1 EBS Volumes, pushing the expected throughput of 500MiB/s per volume, in a RAID0 set named raidvol
EBS
- read throughput rate: 72.06 megabytes/second per physical core
- write throughput rate: 70.37 megabytes/second per physical core
Configuration 3:
- (8) ephemeral SSD’s configured as RAID 0 names raidvol
Ephemeral SSD (local)
- read throughput rate: 230.44 megabytes/second per physical core
- write throughput rate: 86.22 megabytes/second per physical core
Configuration 4:
- (4) ephemeral SSD’s configured as RAID 0
- (8) 2TB st1 EBS volumes
Ephemeral SSD (local)
- read throughput rate: 136.48 megabytes/second per physical core
- write throughput rate: 96.45 megabytes/second per physical core
EBS
- read throughput rate: 72.14 megabytes/second per physical core
- write throughput rate: 70.71 megabytes/second per physical core
