n2-highmem-80 on Databricks
n2-highmem-80 is a memory optimized Google Cloud worker type with 80 vCPUs and 640 GB of memory. On Databricks it uses 19.2 DBUs an hour, so 1 node on Jobs Compute in Iowa (us-central1) costs $8.12 an hour: $2.88 for the DBUs and $5.24 to Google Cloud for the machine.
Google Cloud · Memory optimized · n2-highmem
n2-highmem-80 at a glance
- vCPUs
- 80
- Memory
- 640 GB
- Own SSD
- None
- Local SSDs are added in the compute settings
- DBUs an hour
- 19.2
- Classic compute
- With Photon
- 48
- DBUs an hour, Jobs Compute
- 1 node an hour
- $8.12
- Jobs Compute, Iowa (us-central1)
1 node an hour on each kind of compute
In Iowa (us-central1) on the Premium plan. Databricks charges the DBUs, Google Cloud 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 | 19.2 | $0.15 | $2.88 | $5.24 | $8.12 |
| Jobs Compute + Photon | 48 | $0.15 | $7.20 | $5.24 | $12.44 |
| All-Purpose Compute | 19.2 | $0.55 | $10.56 | $5.24 | $15.80 |
| All-Purpose Compute + Photon | 38.4 | $0.55 | $21.12 | $5.24 | $26.36 |
| Lakeflow pipelines Core | 19.2 | $0.20 | $3.84 | $5.24 | $9.08 |
| Lakeflow pipelines Core + Photon | 48 | $0.20 | $9.60 | $5.24 | $14.84 |
| Lakeflow pipelines Pro | 19.2 | $0.25 | $4.80 | $5.24 | $10.04 |
| Lakeflow pipelines Pro + Photon | 48 | $0.25 | $12.00 | $5.24 | $17.24 |
| Lakeflow pipelines Advanced | 19.2 | $0.36 | $6.91 | $5.24 | $12.15 |
| Lakeflow pipelines Advanced + Photon | 48 | $0.36 | $17.28 | $5.24 | $22.52 |
In each region
1 node an hour on Jobs Compute, Premium, cheapest first.
| Region | Machine | An hour |
|---|---|---|
| Iowa (us-central1) | $5.24 | $8.12 |
| South Carolina (us-east1) | $5.24 | $8.12 |
| Oregon (us-west1) | $5.24 | $8.12 |
| Belgium (europe-west1) | $5.76 | $8.64 |
| Montréal (northamerica-northeast1) | $5.77 | $8.65 |
| Las Vegas (us-west4) | $5.90 | $8.78 |
| Northern Virginia (us-east4) | $5.90 | $8.78 |
| Mumbai (asia-south1) | $6.29 | $9.17 |
| Singapore (asia-southeast1) | $6.46 | $9.34 |
| Tokyo (asia-northeast1) | $6.72 | $9.60 |
| London (europe-west2) | $6.75 | $9.63 |
| Frankfurt (europe-west3) | $6.75 | $9.63 |
| Sydney (australia-southeast1) | $7.44 | $10.32 |
| São Paulo (southamerica-east1) | $8.32 | $11.20 |
| Dammam (me-central2) | $8.38 | $11.26 |
Other memory optimized sizes
- n2-highmem-44 vCPUs, 32 GB, 0.96 DBUs an hour
- n2-highmem-88 vCPUs, 64 GB, 1.92 DBUs an hour
- n2-highmem-1616 vCPUs, 128 GB, 3.84 DBUs an hour
- n2-highmem-3232 vCPUs, 256 GB, 7.68 DBUs an hour
- n2-highmem-4848 vCPUs, 384 GB, 11.52 DBUs an hour
- n2-highmem-6464 vCPUs, 512 GB, 15.36 DBUs an hour
- n2-highmem-8080 vCPUs, 640 GB, 19.2 DBUs an hour
Questions
- How many DBUs does n2-highmem-80 use on Databricks?
- n2-highmem-80 uses 19.2 DBUs an hour on Databricks classic compute without Photon. With Photon it uses 48 DBUs an hour on Jobs Compute and 38.4 on All-Purpose Compute, as Databricks' price list gives them.
- How much does n2-highmem-80 cost an hour on Databricks?
- In Iowa (us-central1), 1 n2-highmem-80 node on Jobs Compute costs $8.12 an hour: $2.88 to Databricks for 19.2 DBUs at $0.15 each, and $5.24 to Google Cloud for the machine. On All-Purpose Compute the same node costs $15.80 an hour, and on Lakeflow pipelines Core $9.08. A cluster pays this for every worker and for the driver.
- Does Photon cost more on n2-highmem-80?
- Yes, by the hour: with Photon, 1 n2-highmem-80 node on Jobs Compute in Iowa (us-central1) costs $12.44 an hour instead of $8.12, because it uses 48 DBUs an hour instead of 19.2. It saves money only when the job finishes fast enough to make up the difference.
- Which region is cheapest for n2-highmem-80 on Databricks?
- Iowa (us-central1), at $8.12 an hour for 1 node on Jobs Compute, against $11.26 in Dammam (me-central2), the dearest of the 15 regions listed here that offer it. Databricks charges the same for a DBU of Jobs Compute in every Google Cloud region listed, so the gap is the machine.
- What is the same size as n2-highmem-80 on the other clouds?
- The nearest worker types of the same kind are r6id.24xlarge on AWS and Standard_E96ds_v5 on Azure. 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 down from n2-highmem-80?
- n2-highmem-80 is the largest size of its family listed here. One size down is n2-highmem-64, at 15.36 DBUs an hour.
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 Google Cloud
- 3Google Cloud: general-purpose machine pricing
- 4Databricks: compute configuration reference (the driver is the workers' type by default)
- 5Databricks: Photon
- 6Google Cloud: n2-highmem sizes