How to use Valgrind to troubleshoot memory leaks in Gluster?

Solution Verified - Updated -

Issue

  • Sometimes, the information provided by an statedump ( please refer to section 19.8 of the Administration Guide regarding the steps on how to capture an statedump) is not sufficient to diagnose the cause of a memory leak.

  • Let's consider the following example, were the structure nfs3_call_state_t is allocating 9.3 GB of memory:

    pool-name=nfs3_call_state_t                                            
    active-count=143041                                                                                                    
    sizeof-type=44640                                                      
    padded-sizeof=65536                                                    
    size=9374334976                                                                                                              
    shared-pool=0x7f289a8490e8          
    
  • This structure is being used by many NFS functions in gNFS. How to narrow down which exact function is responsible for this leak?

Environment

Red Hat Gluster Storage 3.X

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.

Current Customers and Partners

Log in for full access

Log In

New to Red Hat?

Learn more about Red Hat subscriptions

Using a Red Hat product through a public cloud?

How to access this content