m5.2xlarge
General purpose · Intel Xeon Platinum (x86)
PostgreSQL benchmark results for the m5.2xlarge AWS EC2 instance with 8 vCPU, 32 GiB RAM, and x86-64 architecture.
Compute
- vCPU
- 8
- Memory
- 32 GiB
- Mem / vCPU
- 4 : 1
Platform
- Family
- m5
- Architecture
- x86-64
- Performance
- Fixed
Cost & region
- On-demand
- $0.3840/hr~$280/mo
- Region
- us-east-1
Chart
Change the metric and disk to see how the numbers shift as the dataset grows — and where it stops fitting in memory.
Open markers sit past the RAM limit (~24 GB of 32 GiB): the dataset no longer fits in cache, so the working set spills to disk and throughput drops.
All results
6 of 6 rows
| 1 GB | gp3-baseline | 51,445±0.1% | 126,737 | 0.62±0.1% | 2.01±0.1% | 2.41±0.1% | 6,431 | 1,608 |
| 10 GB | gp3-baseline | 50,632±0.6% | 124,734 | 0.63±0.6% | 2.01±0.4% | 2.41±0.6% | 6,329 | 1,582 |
| 1 GB | gp3-max | 51,430±0.3% | 94,731 | 0.62±0.3% | 2.02±0.3% | 2.42±0.3% | 6,429 | 1,607 |
| 10 GB | gp3-max | 50,525±0.3% | 93,064 | 0.63±0.3% | 2.02±0.0% | 2.42±0.2% | 6,316 | 1,579 |
| 50 GB | gp3-max | 27,315±3.0% | 50,312 | 1.17±3.0% | 2.97±3.2% | 3.91±3.0% | 3,414 | 854 |
| 50 GB | gp3-baseline | 5,267±0.4% | 12,976 | 6.08±0.4% | 17.06±0.6% | 22.94±1.4% | 658 | 165 |