Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Updating dataproc container cost to be multiplied by number of cores #648

Merged
merged 9 commits into from
Nov 3, 2023
Merged

Updating dataproc container cost to be multiplied by number of cores #648

Show file tree
Hide file tree
Changes from 8 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
5915598
Updating dataproc container cost to be multiplied by number of cores
mattahrens Nov 2, 2023
7dcd26c
Simplifying changes for only Dataproc and not Dataproc GKE
mattahrens Nov 2, 2023
a9ceef6
Fixing bug with extraneous dataproc_cost reference
mattahrens Nov 3, 2023
644a2a3
Fixing pylint with lines too long
mattahrens Nov 3, 2023
3697e16
Fixing flake issue with indentation
mattahrens Nov 3, 2023
34bb615
Fixing flake issue with indentation
mattahrens Nov 3, 2023
30d8381
Fixing flake issue with whitespace
mattahrens Nov 3, 2023
a7592b4
Fixing Dataproc GKE costs for dataproc container
mattahrens Nov 3, 2023
b4683c6
Fixing Dataproc GKE costs for dataproc container
mattahrens Nov 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion user_tools/src/spark_rapids_pytools/cloud_api/dataproc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -545,5 +545,7 @@ def _calculate_group_cost(self, cluster_inst: ClusterGetAccessor, node_type: Spa
def _get_cost_per_cluster(self, cluster: ClusterGetAccessor):
master_cost = self._calculate_group_cost(cluster, SparkNodeType.MASTER)
workers_cost = self._calculate_group_cost(cluster, SparkNodeType.WORKER)
dataproc_cost = self.price_provider.get_container_cost()
master_cores = cluster.get_nodes_cnt(SparkNodeType.MASTER) * cluster.get_node_core_count(SparkNodeType.MASTER)
worker_cores = cluster.get_nodes_cnt(SparkNodeType.WORKER) * cluster.get_node_core_count(SparkNodeType.WORKER)
dataproc_cost = self.price_provider.get_container_cost() * (master_cores + worker_cores)
return master_cost + workers_cost + dataproc_cost
5 changes: 2 additions & 3 deletions user_tools/src/spark_rapids_pytools/cloud_api/dataproc_gke.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,7 +194,6 @@ class DataprocGkeSavingsEstimator(DataprocSavingsEstimator):
"""

def _get_cost_per_cluster(self, cluster: ClusterGetAccessor):
master_cost = self._calculate_group_cost(cluster, SparkNodeType.MASTER)
workers_cost = self._calculate_group_cost(cluster, SparkNodeType.WORKER)
dataproc_cost = super()._get_cost_per_cluster()
parthosa marked this conversation as resolved.
Show resolved Hide resolved
dataproc_gke_cost = self.price_provider.get_container_cost()
return master_cost + workers_cost + dataproc_gke_cost
return dataproc_cost + dataproc_gke_cost
6 changes: 5 additions & 1 deletion user_tools/src/spark_rapids_pytools/cloud_api/onprem.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,6 +312,10 @@ def _get_cost_per_cluster(self, cluster: ClusterGetAccessor):
if self.price_provider.name.casefold() == 'dataproc':
master_cost = self.__calculate_dataproc_group_cost(cluster, SparkNodeType.MASTER)
workers_cost = self.__calculate_dataproc_group_cost(cluster, SparkNodeType.WORKER)
dataproc_cost = self.price_provider.get_container_cost()
master_cores = (cluster.get_nodes_cnt(SparkNodeType.MASTER)
* cluster.get_node_core_count(SparkNodeType.MASTER))
worker_cores = (cluster.get_nodes_cnt(SparkNodeType.WORKER)
* cluster.get_node_core_count(SparkNodeType.WORKER))
dataproc_cost = self.price_provider.get_container_cost() * (master_cores + worker_cores)
total_cost = master_cost + workers_cost + dataproc_cost
return total_cost
1 change: 0 additions & 1 deletion user_tools/src/spark_rapids_pytools/pricing/dataproc_gke_pricing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,6 @@ class DataprocGkePriceProvider(DataprocPriceProvider):
name = 'DataprocGke'

def get_container_cost(self) -> float:
dataproc_cost = super().get_container_cost()
gke_container_cost = self.__get_gke_container_cost()
return dataproc_cost + gke_container_cost
parthosa marked this conversation as resolved.
Show resolved Hide resolved

Expand Down