Computational instance batching and automation orchestration based on resource usage and availability

Patent metadata

Field	Value
Publication number	US-11520621-B2
Application number	US-201916551416-A
Country	US
Kind code	B2
Filing date	Aug 26, 2019
Priority date	Aug 26, 2019
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

An embodiment may involve server devices arranged into pods, each server device hosting computational instances, and a central computational instance configured to: (i) obtain per-pod lists of the instances hosted by the pods; (ii) determine a maximum number of the instances to arrange into batches; (iii) determine a group size for groups of the instances that are to be placed into the batches; (iv) execute a first phase that involves removing per-pod groups from the per-pod lists and adding them to the batches, until less of the instances than the group size remains in each of the per-pod lists; (v) execute a second phase that involves removing one of the instances from the per-pod lists and adding it to the batches, until none of the instances remains in any of the per-pod lists; and (vi) schedule one or more of the automations to take place in the data center.

First claim

What is claimed is:

1. A data center comprising:
a plurality of server devices arranged into pods, the plurality of server devices hosting computational instances, wherein the computational instances utilize application and database resources of the plurality of server devices and are associated with managed networks; and
a central computational instance, operational on one or more computing devices, and configured to:
obtain per-pod lists of the computational instances hosted by the plurality of server devices of the pods;
determine a maximum number of the computational instances to arrange into each of a plurality of batches, wherein the batches are used for scheduling automations in the data center;
determine a group size for groups of the computational instances that are to be placed into the batches, wherein one group at a time is placed into the batches, and wherein the group size is greater than one;
execute a first assignment phase that involves iteratively removing per-pod groups of the computational instances, each of the group size, from the per-pod lists and adding them to the batches, until less of the computational instances than the group size remains in each of the per-pod lists;
execute a second assignment phase that involves iteratively removing one of the computational instances from the per-pod lists and adding it to the batches, until none of the computational instances remains in any of the per-pod lists;
schedule one or more automations of the automations to take place in the data center, wherein the automations are initiated one batch at a time; and
execute the one or more automations scheduled to take place in the data center, wherein the one or more automations comprise restarting an application node, restoring a database node, failing a computational instance of the computational instances over to another data center, moving the computational instance over to the other data center, or upgrading the computational instance, or any combination thereof.

2. The data center of claim 1 , wherein there are fewer pods than the plurality of server devices.

3. The data center of claim 1 , wherein, prior to executing the first assignment phase, the per-pod lists are each sorted, per server device, in descending order of the computational instances therein.

4. The data center of claim 1 , wherein, prior to executing the first assignment phase, the per-pod lists are each sorted, per server device, in descending order of network traffic involving the computational instances therein.

5. The data center of claim 1 , wherein, prior to executing the first assignment phase, the per-pod lists are each sorted, per server device, in descending order of service-level agreement importance of the computational instances therein.

6. The data center of claim 1 , wherein the maximum number is pre-determined.

7. The data center of claim 1 , wherein the group size is based on the maximum number divided by a count of the pods.

8. The data center of claim 1 , wherein adding the per-pod groups of the computational instances to the batches comprises adding up to the maximum number of the computational instances in each batch, then creating a new batch for addition of further computational instances.

9. The data center of claim 1 , wherein scheduling the one or more automations to take place in the data center comprises scheduling all of the automations involving a first of the batches to take place prior to any of the automations involving a second of the batches.

10. The data center of claim 9 , wherein scheduling all of the automations involving the first of the batches to take place prior to any of the automations involving the second of the batches comprises:
scheduling all of the automations involving the first of the batches to take place substantially simultaneously; and
waiting for all of the automations involving the first of the batches to complete prior to initiating any of the automations involving the second of the batches.

11. The data center of claim 9 , wherein scheduling all of the automations involving the first of the batches to take place prior to any of the automations involving the second of the batches comprises:
scheduling all of the automations involving the first of the batches to take place substantially simultaneously; and
scheduling the automations of the second of the batches to begin at a fixed interval after the automations of the first of the batches begin.

12. A computer-implemented method comprising:
obtaining, in a data center, per-pod lists of computational instances hosted by server devices arranged into pods, wherein the server devices host the computational instances, and wherein the computational instances utilize application and database resources of the server devices and are associated with managed networks;
determining a maximum number of the computational instances to arrange into each of a plurality of batches, wherein the batches are used for scheduling automations in the data center;
determining a group size for groups of the computational instances that are to be placed into the batches, wherein one group at a time is placed into the batches, and wherein the group size is greater than one;
executing a first assignment phase that involves iteratively removing per-pod groups of the computational instances, each of the group size, from the per-pod lists and adding them to the batches, until less of the computational instances than the group size remains in each of the per-pod lists;
executing a second assignment phase that involves iteratively removing one of the computational instances from the per-pod lists and adding it to the batches, until none of the computational instances remains in any of the per-pod lists;
scheduling one or more automations of the automations to take place in the data center, wherein the automations are initiated one batch at a time; and
executing the one or more automations scheduled to take place in the data center, wherein the one or more automations comprise restarting an application node, restoring a database node, failing a computational instance of the computational instances over to another data center, moving the computational instance over to the other data center, or upgrading the computational instance, or any combination thereof.

13. The computer-implemented method of claim 12 , wherein, prior to executing the first assignment phase, the per-pod lists are each sorted, per server device, in descending order of the computational instances therein.

14. One or more non-transitory computer-readable medium comprising computer readable instructions, that when executed by one or more processors, cause the one or more processors to perform operations comprising:
obtaining, via a central instance operational on one or more computing devices, per-pod lists of computational instances hosted by respective server devices of a plurality of server devices arranged into pods, each respective server device hosting one or more computational instances, wherein the computational instances utilize application and database resources of the server devices and are associated with managed networks;
determining, via the central instance, a maximum number of the computational instances to arrange into each of a plurality of batches, wherein the batches are used for scheduling automations in a data center;
determining, via the central instance, a group size for groups of the computational instances that are to be placed into the batches, wherein one group at a time is placed into the batches, and wherein the group size is greater than one;
executing, via the central in

Assignees

• Servicenow Inc

Inventors

• Goudarzi Khashayar
• Li Wenhui
• Vaddempudi Sharath
• Jain Kavish
• Zou Shaoying
• Khurmyetbyek Yerjan
• Pattapu Swathi

Classifications

• H04L67/10

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title

• G06F9/5088 Primary

  involving task migration · CPC title

• H04L67/01

  Protocols · CPC title

• G06F9/4881 Primary

  Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues · CPC title