Techniques for cache updates based on quality of service

• US 10,229,221 B1
• Filed: 09/13/2012
• Issued: 03/12/2019
• Est. Priority Date: 03/01/2012
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: Tang, Xuan, Pendergraft, James O., Speciner, Norman, Rabe, Bruce R.
• Primary Examiner(s): Hussain, Tauqir
• Assistant Examiner(s): Grijalva Lobos, Boris D
• Application Number:
  US13/613,067
• Time in Patent Office: 2,371 Days
• Field of Search: 709201-203, 709248, 709212-216, 709232-233, 709253, 709226
• CPC Class Codes: G06F 11/30 Monitoring
• CPC Class Codes: G06F 11/3006 where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems multiprogramming arrangements G06F9/46; allocation of resources G06F9/50
• CPC Class Codes: G06F 11/3438 monitoring of user actions tracking the activity of the user H04L67/535
• CPC Class Codes: G06F 12/00 Accessing, addressing or allocating within memory systems or architectures digital input from, or digital output to record carriers, e.g. to disk storage units, G06F3/06
• CPC Class Codes: G06F 12/08 in hierarchically structured memory systems, e.g. virtual memory systems
• CPC Class Codes: G06F 12/0802 Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
• CPC Class Codes: G06F 12/0868 Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
• CPC Class Codes: G06F 12/0871 Allocation or management of cache space
• CPC Class Codes: G06F 12/0875 with dedicated cache, e.g. instruction or stack
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/261 Storage comprising a plurality of storage devices
• CPC Class Codes: G06F 2212/264 Remote server
• CPC Class Codes: G06F 2212/284 being distributed
• CPC Class Codes: H04L 41/0823 characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability for optimising operational conditions of wireless networks H04W24/02
• CPC Class Codes: H04L 41/085 Retrieval of network configuration; Tracking network configuration history
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/2895 Intermediate processing functionally located close to the data provider application, e.g. reverse proxies
• CPC Class Codes: H04L 67/5682 : Policies or rules for updating, deleting or replacing the stored data
• CPC Class Codes: H04L 67/61 : taking into account QoS or priority requirements

Abstract

Described are techniques for processing requests. A profile is recorded comprising a plurality of prior requests from a client to a server. The plurality of prior requests associated with first data. A cached copy of the first data is stored in a cache of the server. A quality of service associated with the received request is determined for affecting when the update is applied to the cached copy of first data. The quality of service associated with the received request is dependent on the prior requests in the profile. The first update is applied to the first data. In accordance with the quality of service, the first update is applied to the cached copy of the first data.

Claims

1. A method for processing requests, the method comprising:

recording a profile comprising information regarding one or more prior requests from a client to a server;

receiving, from the client at the server, a request to apply a first update that updates a primary copy of first data stored on non-volatile storage of the server, a cached copy of the first data additionally being stored in a cache of the server, whereby the server is configured such that said cache is arranged on the server separate to the non-volatile storage and provides quicker client access to the first data than the non-volatile storage;

detecting a behavioral pattern in connection with prior requests by evaluating the information recorded in the profile, wherein the detected behavioral pattern describes an urgency by which a prior request from the client to the server to update data stored on the server was followed by a request from the client to the server to retrieve the updated data;

based on the detected behavioral pattern, determining one of a first or a second quality of service as a quality of service to be applied in connection with the received request, wherein the first quality of service includes applying the first update to both the primary copy of the first data and the cached copy of the first data and notifying the client of completion upon both the primary copy and the cached copy of the first data being updated with the first update, and wherein the second quality of service includes applying the first update to the primary copy of the first data and notifying the client of completion independent of whether or not the cached copy of the first data has been updated with the first update;

performing periodic cache update processing that, at each occurrence of a time interval, updates cached copies of data stored in the cache of the server using corresponding primary copies of data from the server;

responsive to said receiving of the request, applying the first update to the primary copy of the first data stored on non-volatile storage of the server; and

determining, in accordance with the quality of service, whether to perform an additional update to the cache to apply the first update to the cached copy of the first data stored in the cache of the server, wherein said additional update is an out of band cache update operation performed in addition to cache updating performed by said periodic cache update processing.

2. The method of claim 1, wherein the quality of service determined in connection with the received request is one of a plurality of predefined quality of service levels.

3. The method of claim 2, wherein the plurality of predefined quality of service levels includes three predefined quality of service levels, a first of the three predefined quality of service levels denoting a highest quality of service, a second of the three predefined quality of service levels denoting a level lower than the first quality of service level, and a third of the three predefined quality of service levels denoting a level lower than the second quality of service level.

4. The method of claim 3, wherein the first quality of service is the first of the three quality of service levels and the method includes:

performing first processing to apply the first update to the primary copy of the first data;

performing second processing to apply the first update to the cached copy of the first data; and

returning a response to the client that the request has completed after the first update has been applied to both the cached copy and the primary copy of the first data.

5. The method of claim 3, wherein the second quality of service is the second of the three quality of service levels and the method includes:

performing first processing to apply the first update to the primary copy of the first data;

performing second processing to apply the first update to the cached copy of the first data; and

returning a response to the client that the request has completed, wherein the response is returned after the first update has been applied to the primary copy of the first data and without requiring that the first update be applied to the cached copy of the first data.

6. The method of claim 5, wherein the first processing and the second processing are performed concurrently and all of the first processing and at least a portion of the second processing has completed prior to returning the response to the client.

7. The method of claim 3, wherein a third quality of service associated with the request is the third of the three quality of service levels and the method includes:

performing first processing to apply the first update to the primary copy of the first data; and

returning a response to the client that the request has completed after the first update has been applied to the first data and prior to commencing second processing to apply the first update to the cached copy.

8. The method of claim 7, wherein the second processing is performed at an occurrence of a predetermined time interval.

9. The method as claimed in claim 1, wherein the quality of service determined in connection with the received request is dependent on the behavior with respect to similar prior requests in the profile.

10. The method as claimed in claim 2, wherein the server performs first processing to determine the quality of service level for the request by determining a likelihood of similar behavior applying to the received request as with respect to similar prior requests, wherein a policy specifies a quality of service level for the received request based on the likelihood.

11. The method as claimed in claim 10, wherein the policy specifies different quality of service levels for different likelihoods of similar behavior applying to the received request as with respect to similar prior requests.

12. The method as claimed in claim 10, wherein the behavior relates to a pattern of prior requests from the client to the server in which a similar request to the received request is one of the pattern of requests.

13. The method as claimed in claim 1, wherein the received request is recorded in the profile for assisting in the determination of a quality of service for future requests for updating first data.

14. The method of claim 1, wherein the client issues a second request to read at least a portion of the first data and the second request is serviced by the server using the cached copy of the first data.

15. The method of claim 1, wherein all requests to read first data are serviced using the cached copy of the first data and not serviced using the primary copy of the first data.

16. The method of claim 1, wherein the first data is data storage configuration data, the client issues the request to modify the data storage configuration data, the server is the data storage system having a configuration described by the data storage configuration data and wherein the data storage configuration data is stored on a storage device of the data storage system.

17. A non-transitory computer readable medium comprising code stored thereon for processing requests, the computer readable medium comprising code stored thereon for:

recording a profile comprising information regarding one or more prior requests from a client to a server;

receiving, from the client at the server, a request to apply a first update that updates a primary copy of first data stored on non-volatile storage of the server, a cached copy of the first data additionally being stored in a cache of the server, whereby the server is configured such that said cache is arranged on the server separate to the non-volatile storage and provides quicker client access to the first data than the non-volatile storage;

detecting a behavioral pattern in connection with prior requests by evaluating the information recorded in the profile, wherein the detected behavioral pattern describes an urgency by which a prior request from the client to the server to update data stored on the server was followed by a request from the client to the server to retrieve the updated data;

based on the detected behavioral pattern, determining one of a first or a second quality of service as a quality of service to be applied in connection with the received request, wherein the first quality of service includes applying the first update to both the primary copy of the first data and the cached copy of the first data and notifying the client of completion upon both the primary copy and the cached copy of the first data being updated with the first update, and wherein the second quality of service includes applying the first update to the primary copy of the first data and notifying the client of completion independent of whether or not the cached copy of the first data has been updated with the first update;

performing periodic cache update processing that, at each occurrence of a time interval, updates cached copies of data stored in the cache of the server using corresponding primary copies of data from the server;

responsive to said receiving of the request, applying the first update to the primary copy of the first data stored on non-volatile storage of the server; and

determining, in accordance with the quality of service, whether to perform an additional update to the cache to apply the first update to the cached copy of the first data stored in the cache of the server, wherein said additional update is an out of band cache update operation performed in addition to cache updating performed by said periodic cache update processing.

18. The computer readable medium of claim 17, wherein the quality of service determined in connection with the received request is one of a plurality of predefined quality of service levels.

19. The computer readable medium of claim 18, wherein the plurality of predefined quality of service levels includes three predefined quality of service levels, a first of the three predefined quality of service levels denoting a highest quality of service, a second of the three predefined quality of service levels denoting a level lower than the first quality of service level, and a third of the three predefined quality of service levels denoting a level lower than the second quality of service level.

20. A system comprising:

a client; and

a server in communication with said client, the server including a memory comprising code stored therein for processing requests, the memory comprising code stored therein for;

recording a profile comprising information regarding one or more prior requests from the client to the server;

receiving, from the client at the server, a request to apply a first update that updates a primary copy of first data stored on non-volatile storage of the server, a cached copy of the first data additionally being stored in a cache of the server, whereby the server is configured such that said cache is arranged on the server separate to the non-volatile storage and provides quicker client access to the first data than the non-volatile storage;

detecting a behavioral pattern in connection with prior requests by evaluating the information recorded in the profile, wherein the detected behavioral pattern describes an urgency by which a prior request from the client to the server to update data stored on the server was followed by a request from the client to the server to retrieve the updated data;

based on the detected behavioral pattern, determining one of a first or a second quality of service as a quality of service to be applied in connection with the received request, wherein the first quality of service includes applying the first update to both the primary copy of the first data and the cached copy of the first data and notifying the client of completion upon both the primary copy and the cached copy of the first data being updated with the first update, and wherein the second quality of service includes applying the first update to the primary copy of the first data and notifying the client of completion independent of whether or not the cached copy of the first data has been updated with the first update;

performing periodic cache update processing that, at each occurrence of a time interval, updates cached copies of data stored in the cache of the server using corresponding primary copies of data from the server;

responsive to said receiving of the request, applying the first update to the primary copy of the first data stored on non-volatile storage of the server; and

determining, in accordance with the quality of service, whether to perform an additional update to the cache to apply the first update to the cached copy of the first data stored in the cache of the server, wherein said additional update is an out of band cache update operation performed in addition to cache updating performed by said periodic cache update processing.