US 12,265,742 B2
Quality of service management in a distributed storage system
Maor Ben Dayan, Tel Aviv (IL); Omri Palmon, Tel Aviv (IL); Liran Zvibel, Tel Aviv (IL); Kanael Arditti, Tel Aviv (IL); and Tomer Filiba, Tel Aviv (IL)
Assigned to Weka.IO Ltd., (IL)
Filed by Weka.IO Ltd., Tel Aviv (IL)
Filed on Nov. 21, 2023, as Appl. No. 18/515,570.
Application 18/515,570 is a continuation of application No. 17/529,357, filed on Nov. 18, 2021, granted, now 11,899,987.
Application 17/529,357 is a continuation of application No. 16/149,444, filed on Oct. 2, 2018, granted, now 11,210,033, issued on Dec. 28, 2021.
Application 16/149,444 is a continuation of application No. 15/599,737, filed on May 19, 2017, granted, now 10,133,516, issued on Nov. 20, 2018.
Application 15/599,737 is a continuation in part of application No. 15/075,129, filed on Mar. 19, 2016, granted, now 9,686,359, issued on Jun. 20, 2017.
Claims priority of provisional application 62/366,297, filed on Jul. 25, 2016.
Claims priority of provisional application 62/288,106, filed on Jan. 28, 2016.
Prior Publication US 2024/0086117 A1, Mar. 14, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/00 (2019.01); G06F 3/06 (2006.01); G06F 16/182 (2019.01); H04L 47/12 (2022.01); H04L 67/01 (2022.01); H04L 67/06 (2022.01); H04L 67/1097 (2022.01); H04L 47/11 (2022.01); H04L 47/24 (2022.01); H04L 47/30 (2022.01)
CPC G06F 3/067 (2013.01) [G06F 16/182 (2019.01); H04L 47/12 (2013.01); H04L 67/01 (2022.05); H04L 67/06 (2013.01); H04L 67/1097 (2013.01); H04L 47/11 (2013.01); H04L 47/24 (2013.01); H04L 47/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors operable to generate a current choking level according to a plurality of file system requests, wherein:
each of the plurality of file system requests is associated with a priority level of a plurality priority levels,
the current choking level is determined according to a normalization of the plurality of file system requests and a plurality of individual loads on a plurality of respective resources,
the normalization is relative to a number of input/output operations (IOPs), and
the number of IOPs is dynamically updated according to a machine learning algorithm.