US 12,267,390 B2
Multi-cluster warehouse
Thierry Cruanes, San Mateo, CA (US); Benoit Dageville, Foster City, CA (US); Florian Andreas Funke, San Francisco, CA (US); and Peter Povinec, Redwood City, CA (US)
Assigned to Snowflake Inc., Bozeman, MT (US)
Filed by Snowflake Inc., Bozeman, MT (US)
Filed on Mar. 26, 2024, as Appl. No. 18/617,083.
Application 18/617,083 is a continuation of application No. 18/139,809, filed on Apr. 26, 2023, granted, now 11,983,198.
Application 18/139,809 is a continuation of application No. 18/102,681, filed on Jan. 27, 2023, granted, now 11,675,815, issued on Jun. 13, 2023.
Application 18/102,681 is a continuation of application No. 16/823,124, filed on Mar. 18, 2020, granted, now 11,593,403, issued on Feb. 28, 2023.
Application 16/823,124 is a continuation of application No. 15/582,071, filed on Apr. 28, 2017, granted, now 11,615,117, issued on Mar. 28, 2023.
Claims priority of provisional application 62/328,943, filed on Apr. 28, 2016.
Prior Publication US 2024/0232226 A1, Jul. 11, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 67/1097 (2022.01); G06F 9/50 (2006.01); G06F 16/2455 (2019.01); G06F 16/28 (2019.01); H04L 41/0896 (2022.01); H04L 41/5025 (2022.01); H04L 43/0817 (2022.01); H04L 67/1008 (2022.01)
CPC H04L 67/1097 (2013.01) [G06F 9/5072 (2013.01); G06F 16/2455 (2019.01); G06F 16/283 (2019.01); H04L 41/0896 (2013.01); H04L 41/5025 (2013.01); H04L 67/1008 (2013.01); H04L 43/0817 (2013.01)] 26 Claims
OG exemplary drawing
 
1. A method of implementing a fault-tolerant data warehouse, comprising:
allocating a plurality of processing units to a data warehouse, the plurality of processing units located in different availability zones, an availability zone comprising one or more data centers;
as a result of monitoring a set of queries running at an input degree of parallelism on the plurality of processing units of the data warehouse, determining that the set of queries is serviceable by one fewer processing unit;
routing, by a processing device, a query from a first processing unit to a second processing unit within the data warehouse, the query having a common session identifier with another query previously provided to the second processing unit, the second processing unit determined to be caching a data segment associated with a cloud storage resource, usable by the query, wherein the cloud storage resource is independent of the plurality of processing units; and
removing the first processing unit from the data warehouse.