Skip to content

Instantly share code, notes, and snippets.

@MarkPryceMaherMSFT
Last active December 6, 2024 16:02
Show Gist options
  • Save MarkPryceMaherMSFT/04939610b48df6a8b79d18ec46485dfd to your computer and use it in GitHub Desktop.
Save MarkPryceMaherMSFT/04939610b48df6a8b79d18ec46485dfd to your computer and use it in GitHub Desktop.
This script can be used to find the size of a workspace, lakehouse , warehouse or table
Display the source blob
Display the rendered blob
Raw
{"cells":[{"cell_type":"code","source":["from notebookutils import mssparkutils\n","\n","def scan_folder(folder,total_size):\n"," #print(f\" folder = {folder}\")\n"," l0 = notebookutils.fs.ls(folder)\n"," for l1 in l0:\n"," if l1.isDir==False:\n"," #print(f\" name = {l1.name} : {l1.size/ 1024/1024:.2f} MB\")\n"," total_size = total_size + l1.size\n"," \n"," for l1 in l0: \n"," if l1.isDir:\n"," dirsize = scan_folder(l1.path, 0);\n"," #print(f\"{l1.path} : {dirsize/ 1024/1024:.2f} MB\")\n"," total_size = total_size + dirsize\n"," \n"," return total_size\n","\n","total_size=0.00;\n","\n","# Warehouse\n","#delta_table_path = f\"abfss://[workspace]@onelake.dfs.fabric.microsoft.com/[warehouse name].Datawarehouse/dbo/[table name]\"\n","\n","# lakehouse\n","#delta_table_path = \"abfss://[workspace]@onelake.dfs.fabric.microsoft.com/[lakehouse name].Lakehouse/Tables/[table name]\"\n","\n","# Workspace\n","delta_table_path = \"abfss://[workspace]@onelake.dfs.fabric.microsoft.com/\"\n","\n","total_size = scan_folder(delta_table_path, total_size)\n","total_size = total_size/ 1024/1024\n","print(f\" Total Workspace Size: {total_size:.2f} MB\")\n"],"outputs":[],"execution_count":null,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"377c1f19-92bc-4562-a8de-f9088a4ee999"}],"metadata":{"kernel_info":{"name":"synapse_pyspark"},"kernelspec":{"name":"synapse_pyspark","display_name":"synapse_pyspark"},"language_info":{"name":"python"},"microsoft":{"language":"python","language_group":"synapse_pyspark","ms_spell_check":{"ms_spell_check_language":"en"}},"nteract":{"version":"[email protected]"},"spark_compute":{"compute_id":"/trident/default","session_options":{"conf":{"spark.synapse.nbs.session.timeout":"1200000"}}},"dependencies":{}},"nbformat":4,"nbformat_minor":5}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment