Short-circuiting normal grace-period computations in the presence of expedited grace periods

• US 10,353,748 B2
• Filed: 08/30/2016
• Issued: 07/16/2019
• Est. Priority Date: 08/30/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: McKenney, Paul E.
• Primary Examiner(s): Skhoun, Hicham
• Application Number:
  US15/252,160
• Publication Number:
  US 20180060140A1
• Time in Patent Office: 1,050 Days
• Field of Search: 707687
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 2212/60 Details of cache memory
• CPC Class Codes: G06F 2212/62 Details of cache specific to multiprocessor cache arrangements
• CPC Class Codes: G06F 9/4418 Suspend and resume; Hibernate and awake
• CPC Class Codes: G06F 9/526 Mutual exclusion algorithms

Abstract

A technique for short-circuiting normal read-copy update (RCU) grace period computations in the presence of expedited RCU grace periods. The technique may include determining during normal RCU grace period processing whether at least one expedited RCU grace period elapsed during a normal RCU grace period. If so, the normal RCU grace period is ended. If not, the normal RCU grace period processing is continued. Expedited RCU grace periods may be implemented by expedited RCU grace period processing that periodically awakens a kernel thread that implements the normal RCU grace period processing. The expedited RCU grace period processing may conditionally throttle wakeups to the kernel thread based on CPU utilization.

Claims

1. A system, comprising:

a plurality of CPUs;

a memory coupled to said CPUs, said memory including a computer readable storage medium tangibly embodying at least one program of instructions executable by said CPUs to perform operations for short-circuiting normal read-copy update (RCU) grace period computations in the presence of expedited RCU grace periods, said operations comprising;

determining during normal RCU grace period processing whether at least one expedited RCU grace period has elapsed during a normal RCU grace period;

if at least one expedited RCU grace period has elapsed during said normal RCU grace period, ending said normal RCU grace period;

if at least one expedited RCU grace period has not elapsed during said normal RCU grace period, continuing said normal RCU grace period processing;

said expedited RCU grace periods being implemented by expedited RCU grace period processing that periodically awakens a kernel thread that implements said normal RCU grace period processing;

said expedited RCU grace period processing conditionally throttling wakeups to said kernel thread based on CPU utilization.

2. The system of claim 1, wherein said conditional throttling is conditioned on said CPU utilization reaching a predetermined level.

3. The system of claim 2, wherein said CPU utilization is periodically updated using a CPU utilization calculation that includes filtering to avoid rapid cycling between throttling and not throttling.

4. The system of claim 3, wherein said filtering weights historical CPU utilization calculations.

5. The system of claim 1, wherein said CPU utilization is periodically calculated at a rate that is inversely proportional to a number of CPUs.

6. The system of claim 1, wherein said CPU utilization is calculated using a combining tree, and wherein individual CPUs report per-CPU utilization to leaf nodes of said combining tree and said per-CPU utilizations are propagated to a root node of said combining tree.

7. The system of claim 1, wherein said CPU utilization represents a fraction of time that a CPU is non-idle and comprises a value between 0-100%, with 100% CPU utilization being represented by a scaled value that can be divided using integer division to determine rates of CPU utilization that are less than 100%.

8. A computer program product, comprising:

one or more computer readable data storage media;

program instructions stored on said one or more computer readable data storage media for programming a data processing platform having a plurality of CPUs to perform operations for short-circuiting normal read-copy update (RCU) grace period computations in the presence of expedited RCU grace periods, said operations comprising;

determining during normal RCU grace period processing whether at least one expedited RCU grace period has elapsed during a normal RCU grace period;

if at least one expedited RCU grace period has elapsed during said normal RCU grace period, ending said normal RCU grace period;

if at least one expedited RCU grace period has not elapsed during said normal RCU grace period, continuing said normal RCU grace period processing;

said expedited RCU grace periods being implemented by expedited RCU grace period processing that periodically awakens a kernel thread that implements said normal RCU grace period processing;

said expedited RCU grace period processing conditionally throttling wakeups to said kernel thread based on CPU utilization.

9. The computer program product of claim 8, wherein said conditional throttling is conditioned on said CPU utilization reaching a predetermined level.

10. The computer program product of claim 9, wherein said CPU utilization is periodically updated using a CPU utilization calculation that includes filtering to avoid rapid cycling between throttling and not throttling.

11. The computer program product of claim 10, wherein said filtering weights historical CPU utilization calculations.

12. The computer program product of claim 8, wherein said CPU utilization is periodically calculated at a rate that is inversely proportional to a number of CPUs.

13. The computer program product of claim 8, wherein said CPU utilization is calculated using a combining tree, and wherein individual CPUs report per-CPU utilization to leaf nodes of said combining tree and said per-CPU utilizations are propagated to a root node of said combining tree.