Standard_E32ds_v5 on Databricks
Standard_E32ds_v5 is a memory optimized Azure worker type with 32 vCPUs and 256 GB of memory. On Databricks it uses 11 DBUs an hour, so 1 node on Jobs Compute in East US costs $5.60 an hour: $3.30 for the DBUs and $2.30 to Azure for the machine.
Azure · Memory optimized · Edsv5
Standard_E32ds_v5 at a glance
- vCPUs
- 32
- Memory
- 256 GB
- Own SSD
- 1,200 GB
- DBUs an hour
- 11
- Classic compute
- With Photon
- 27.5
- DBUs an hour, Jobs Compute
- 1 node an hour
- $5.60
- Jobs Compute, East US
1 node an hour on each kind of compute
In East US on the Premium plan. Databricks charges the DBUs, Azure 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 | 11 | $0.30 | $3.30 | $2.30 | $5.60 |
| Jobs Compute + Photon | 27.5 | $0.30 | $8.25 | $2.30 | $10.55 |
| All-Purpose Compute | 11 | $0.55 | $6.05 | $2.30 | $8.35 |
| All-Purpose Compute + Photon | 22 | $0.55 | $12.10 | $2.30 | $14.40 |
| Lakeflow pipelines Core | 11 | $0.30 | $3.30 | $2.30 | $5.60 |
| Lakeflow pipelines Pro | 11 | $0.38 | $4.18 | $2.30 | $6.48 |
| Lakeflow pipelines Advanced | 11 | $0.54 | $5.94 | $2.30 | $8.24 |
In each region
1 node an hour on Jobs Compute, Premium, cheapest first.
| Region | Machine | An hour |
|---|---|---|
| East US | $2.30 | $5.60 |
| East US 2 | $2.30 | $5.60 |
| West US 2 | $2.30 | $5.60 |
| West US 3 | $2.30 | $5.60 |
| Central India | $2.42 | $5.72 |
| Sweden Central | $2.43 | $5.73 |
| Canada Central | $2.53 | $5.83 |
| North Europe | $2.56 | $5.86 |
| Central US | $2.60 | $5.90 |
| UK South | $2.70 | $6.00 |
| France Central | $2.70 | $6.00 |
| West Europe | $2.77 | $6.07 |
| Germany West Central | $2.77 | $6.07 |
| Southeast Asia | $2.78 | $6.08 |
| Japan East | $2.78 | $6.08 |
| Australia East | $2.78 | $6.08 |
| Brazil South | $3.65 | $6.95 |
Other memory optimized sizes
- Standard_E4ds_v54 vCPUs, 32 GB, 1.5 DBUs an hour
- Standard_E8ds_v58 vCPUs, 64 GB, 2.75 DBUs an hour
- Standard_E16ds_v516 vCPUs, 128 GB, 5.5 DBUs an hour
- Standard_E32ds_v532 vCPUs, 256 GB, 11 DBUs an hour
- Standard_E48ds_v548 vCPUs, 384 GB, 16.5 DBUs an hour
- Standard_E64ds_v564 vCPUs, 512 GB, 22 DBUs an hour
- Standard_E96ds_v596 vCPUs, 672 GB, 33 DBUs an hour
Questions
- How many DBUs does Standard_E32ds_v5 use on Databricks?
- Standard_E32ds_v5 uses 11 DBUs an hour on Databricks classic compute without Photon. With Photon it uses 27.5 DBUs an hour on Jobs Compute and 22 on All-Purpose Compute, as Databricks' price list gives them.
- How much does Standard_E32ds_v5 cost an hour on Databricks?
- In East US, 1 Standard_E32ds_v5 node on Jobs Compute costs $5.60 an hour: $3.30 to Databricks for 11 DBUs at $0.30 each, and $2.30 to Azure for the machine. On All-Purpose Compute the same node costs $8.35 an hour, and on Lakeflow pipelines Core $5.60. A cluster pays this for every worker and for the driver.
- Does Photon cost more on Standard_E32ds_v5?
- Yes, by the hour: with Photon, 1 Standard_E32ds_v5 node on Jobs Compute in East US costs $10.55 an hour instead of $5.60, because it uses 27.5 DBUs an hour instead of 11. It saves money only when the job finishes fast enough to make up the difference.
- Which region is cheapest for Standard_E32ds_v5 on Databricks?
- East US, at $5.60 an hour for 1 node on Jobs Compute, against $6.95 in Brazil South, the dearest of the 17 regions listed here that offer it. Databricks charges the same for a DBU of Jobs Compute in every Azure region listed, so the gap is the machine.
- What is the same size as Standard_E32ds_v5 on the other clouds?
- The nearest worker types of the same kind are r6id.8xlarge on AWS and n2-highmem-32 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 Standard_E32ds_v5?
- One size down is Standard_E16ds_v5, at 5.5 DBUs an hour; one size up is Standard_E48ds_v5, at 16.5. 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