c6id.24xlarge on Databricks
c6id.24xlarge is a compute optimized AWS worker type with 96 vCPUs and 192 GB of memory. On Databricks it uses 16.69 DBUs an hour, so 1 node on Jobs Compute in US East (N. Virginia) costs $7.34 an hour: $2.50 for the DBUs and $4.84 to AWS for the machine.
AWS · Compute optimized · c6id
c6id.24xlarge at a glance
- vCPUs
- 96
- Memory
- 192 GB
- Own SSD
- 5,700 GB
- DBUs an hour
- 16.69
- Classic compute
- With Photon
- 48.4
- DBUs an hour, Jobs Compute
- 1 node an hour
- $7.34
- Jobs Compute, US East (N. Virginia)
1 node an hour on each kind of compute
In US East (N. Virginia) on the Premium plan. Databricks charges the DBUs, AWS the machine. A cluster pays this for every worker and for the driver.
| Compute | DBUs an hour | A DBU | Databricks | Machine | An hour |
|---|---|---|---|---|---|
| Jobs Compute | 16.69 | $0.15 | $2.50 | $4.84 | $7.34 |
| Jobs Compute + Photon | 48.4 | $0.15 | $7.26 | $4.84 | $12.10 |
| All-Purpose Compute | 16.69 | $0.55 | $9.18 | $4.84 | $14.02 |
| All-Purpose Compute + Photon | 33.38 | $0.55 | $18.36 | $4.84 | $23.20 |
| Lakeflow pipelines Core | 16.69 | $0.20 | $3.34 | $4.84 | $8.18 |
| Lakeflow pipelines Core + Photon | 48.4 | $0.20 | $9.68 | $4.84 | $14.52 |
| Lakeflow pipelines Pro | 16.69 | $0.25 | $4.17 | $4.84 | $9.01 |
| Lakeflow pipelines Pro + Photon | 48.4 | $0.25 | $12.10 | $4.84 | $16.94 |
| Lakeflow pipelines Advanced | 16.69 | $0.36 | $6.01 | $4.84 | $10.85 |
| Lakeflow pipelines Advanced + Photon | 48.4 | $0.36 | $17.42 | $4.84 | $22.26 |
In each region
1 node an hour on Jobs Compute, Premium, cheapest first.
| Region | Machine | An hour |
|---|---|---|
| US East (N. Virginia) | $4.84 | $7.34 |
| US East (Ohio) | $4.84 | $7.34 |
| US West (Oregon) | $4.84 | $7.34 |
| Canada (Central) | $5.34 | $7.85 |
| Europe (Ireland) | $5.49 | $8.00 |
| Asia Pacific (Seoul) | $5.54 | $8.05 |
| Europe (Frankfurt) | $5.59 | $8.10 |
| Asia Pacific (Singapore) | $5.64 | $8.15 |
| Europe (London) | $5.80 | $8.30 |
| Europe (Paris) | $5.80 | $8.30 |
| Asia Pacific (Tokyo) | $6.15 | $8.65 |
| Asia Pacific (Sydney) | $6.35 | $8.85 |
| South America (São Paulo) | $7.51 | $10.01 |
Other compute optimized sizes
- c6id.xlarge4 vCPUs, 8 GB, 0.7 DBUs an hour
- c6id.2xlarge8 vCPUs, 16 GB, 1.39 DBUs an hour
- c6id.4xlarge16 vCPUs, 32 GB, 2.78 DBUs an hour
- c6id.8xlarge32 vCPUs, 64 GB, 5.56 DBUs an hour
- c6id.12xlarge48 vCPUs, 96 GB, 8.34 DBUs an hour
- c6id.16xlarge64 vCPUs, 128 GB, 11.13 DBUs an hour
- c6id.24xlarge96 vCPUs, 192 GB, 16.69 DBUs an hour
- c6id.32xlarge128 vCPUs, 256 GB, 22.25 DBUs an hour
Questions
- How many DBUs does c6id.24xlarge use on Databricks?
- c6id.24xlarge uses 16.69 DBUs an hour on Databricks classic compute without Photon. With Photon it uses 48.4 DBUs an hour on Jobs Compute and 33.38 on All-Purpose Compute, as Databricks' price list gives them.
- How much does c6id.24xlarge cost an hour on Databricks?
- In US East (N. Virginia), 1 c6id.24xlarge node on Jobs Compute costs $7.34 an hour: $2.50 to Databricks for 16.69 DBUs at $0.15 each, and $4.84 to AWS for the machine. On All-Purpose Compute the same node costs $14.02 an hour, and on Lakeflow pipelines Core $8.18. A cluster pays this for every worker and for the driver.
- Does Photon cost more on c6id.24xlarge?
- Yes, by the hour: with Photon, 1 c6id.24xlarge node on Jobs Compute in US East (N. Virginia) costs $12.10 an hour instead of $7.34, because it uses 48.4 DBUs an hour instead of 16.69. It saves money only when the job finishes fast enough to make up the difference.
- Which region is cheapest for c6id.24xlarge on Databricks?
- US East (N. Virginia), at $7.34 an hour for 1 node on Jobs Compute, against $10.01 in South America (São Paulo), the dearest of the 13 regions listed here that offer it. Databricks charges the same for a DBU of Jobs Compute in every AWS region listed, so the gap is the machine. US West (N. California), Asia Pacific (Mumbai) and Asia Pacific (Jakarta) do not offer it.
- What is the same size as c6id.24xlarge on the other clouds?
- The nearest worker types of the same kind are Standard_D96ds_v5 on Azure and n2-highcpu-80 on Google Cloud. Each cloud gives its own DBUs an hour for its types, so compare what a cluster costs in the calculator, not the DBUs alone.
- What is the next size up or down from c6id.24xlarge?
- One size down is c6id.16xlarge, at 11.13 DBUs an hour; one size up is c6id.32xlarge, at 22.25. Within a family, DBUs and the machine price grow with the vCPUs, so 2 nodes of a size cost about what 1 node of twice the size costs.
Sources
Where each fact comes from
- 1Databricks: pricing calculator and instance types (the DBUs an hour of each worker type, with and without Photon)
- 2Databricks: pricing on AWS (the price of a DBU for each kind of compute and plan)
- 3AWS: Amazon EC2 on-demand pricing
- 4Databricks: compute configuration reference (the driver is the workers' type by default)
- 5Databricks: Photon
- 6AWS: c6id sizes