NFS Server - running Solaris 10 or earlier - experiences a low memory condition (Doc ID 2086383.1)

Last updated on JANUARY 24, 2017

Applies to:

Solaris Operating System - Version 8 6/00 U1 to 10 1/13 U11 [Release 8.0 to 10.0]
Information in this document applies to any platform.

Symptoms

An NFS server was effectively hung - not responding to NFS clients.   Activity even from the system console was very sluggish at best.

The system was actively swapping, and was very low on free memory.  Overall the system was basically unusable.

Even network communications have been seen to be affected, with messages such as this having been logged:

    NOTICE: ixgbe1: ixgbe_rx_copy: allocate buffer failed

    LLT INFO V-14-1-10063 llt_send_port: no memory to xmit

The system in this case was a Veritas Cluster node - and the VCS software took the system down (initiated a panic) due to the inability to communicate.

Per the crash dump, many threads were waiting for memory in page_create_throttle() calls - and a lot of threads were waiting on those threads. 

Exact symptoms may vary, but the underlying cause in situations like this comes down to a serious - if not fatal - shortage of free memory. 

Cause

Sign In with your My Oracle Support account

Don't have a My Oracle Support account? Click to get started

My Oracle Support provides customers with access to over a
Million Knowledge Articles and hundreds of Community platforms