US 12,711,108 B2Granted

Compact representation of object store workloads

AssigneeNetApp, Inc.

InventorMorgan Mears

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and techniques that facilitate compact representation of object store workloads are provided. In various embodiments, a system can access a stream of object-storage operation requests associated with an object store. In various aspects, the system can identify a set of repeating object-storage operation sequences, based on the stream of object-storage operation requests. In various instances, the system can generate a set of distribution ensembles that quantify variation of first attributes associated with respective ones of the set of repeating object-storage operation sequences. In various cases, the stream of object-storage operation requests can be considered as fully and/or bulkily representing the workload experienced by the object store. In contrast, the set of distribution ensembles can be considered as compactly representing the workload experienced by the object store (e.g., the set of distribution ensembles can take up far less memory space than the stream of object-storage operation requests).

Claims18

Dependent claims

A system, comprising:

a processor that executes computer-executable components stored in a computer-readable memory, the computer-executable components comprising:
an access component that accesses a stream of object-storage operation requests associated with an object store;
a bin component that segments the stream of object-storage operation requests into a set of bins, based on first attributes of the stream of object-storage operation requests;
a sequence component that identifies a set of repeating object-storage operation sequences for at least one bin in the set of bins, based on the stream of object-storage operation requests in a bin-wise fashion, wherein identifying the set of repeating object-storage operation sequences comprises:
for each bin in the set of bins, selecting an object-storage operation request that has not been assigned to a repeating object-storage operation sequence for that bin and has an object identifier;
and
for each bin in the set of bins, creating a new repeating object-storage operation sequence for that bin that corresponds to the object identifier or replacing an existing repeating object-storage operation sequence with the new repeating object-storage operation sequence based on available memory slots;
a model component that generates a set of distribution ensembles for at least one bin in the set of bins that quantify variation of second attributes associated with respective ones of the set of repeating object-storage operation sequences in that bin;
and
an execution component that reconfigures the object store to handle a current workload based on the set of distribution ensembles.

7 more elements

A computer-implemented method, comprising:

accessing, by a device operatively coupled to a processor, a stream of object-storage operation requests received by an object store from one or more client devices;
segmenting, by the device, the stream of object-storage operation requests into a set of bins, based on first attributes associated with the stream of object-storage operation requests;
identifying, by the device, a set of repeating object-storage operation sequences within the stream of object-storage operation requests for at least one bin in the set of bins in a bin-wise fashion, wherein identifying the set of repeating object-storage operation sequences comprises:
for each bin in the set of bins, selecting an object-storage operation request that has not been assigned to a repeating object-storage operation sequence for that bin and has an object identifier;
and
for each bin in the set of bins, creating a new repeating object-storage operation sequence that corresponds to the object identifier or replacing an existing repeating object-storage operation sequence with the new repeating object-storage operation sequence based on available memory slots;
generating, by the device, a set of distribution ensembles for at least one bin in the set of bins that describe how second attributes associated with respective ones of the set of repeating object-storage operation sequences in that bin vary, wherein the set of distribution ensembles collectively represent a current workload of the object store;
and
reconfiguring, by the device, the object store to handle the current workload based on the set of distribution ensembles.

6 more elements

A computer program product for facilitating compact representation of object store workloads, the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

access a stream of object-storage operation requests of an object store;
segment the stream of object-storage operation requests into a set of bins, based on first attributes of the stream of object-storage operation requests;
identify, for at least one bin in the set of bins, a set of repeating object-storage operation sequences within the stream of object-storage operation requests for the object-storage operations requests in a bin-wise fashion, wherein identifying the set of repeating object-storage operation sequences comprises:
for each bin in the set of bins, selecting an object-storage operation request that has not been assigned to a repeating object-storage operation sequence for that bin and has an object identifier;
and
for each bin in the set of bins, creating a new repeating object-storage operation sequence that corresponds to the object identifier or replacing an existing repeating object-storage operation sequence with the new repeating object-storage operation sequence based on available memory slots;
generate, for at least one bin in the set of bins, a set of distribution ensembles conveying how second attributes of the set of repeating object-storage operation sequences in that bin vary, wherein the set of distribution ensembles collectively represent a current workload of the object store, and wherein the set of distribution ensembles take up less memory than the stream of object-storage operation requests;
and
reconfigure the object store to handle the current workload based on the set of distribution ensembles.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/653,011Filed 1 Mar 2022
Published: US 2023/0281170 A17 Sep 2023
Granted: 18 Aug 2026
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G06F 16/21
Of structured data, e.g. relational data: design, administration or maintenance of databases
G06F 16/289
Databases characterised by their database models, e.g. relational or object models: object oriented databases
G06F 11/3034
Monitoring arrangements specially adapted to the computing system or computing system component being monitored: where the computing system…
G06F 11/3466
Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of…:…