RHEL5.8: NFS server (nfsd) panics in tcp_sendpage because of overrun of rq_pages array

Solution Verified - Updated -

Issue

  • Customer recently installed a DL980 G7, RHEL6 2.6.32-131.0.15.el6.x86_64, and when it attempts to connect to either of two RHEL 5.8 ia64 NFS servers, eventually and fairly quickly, the NFS server crashes.
  • After updating NFS server to RHEL 5.8, the server panics after being accessed by a client with rsize/wsize 1048576
  • Kernel panic due to nfsd crash in tcp_sendpage

Environment

  • Red Hat Enterprise Linux 5.8 NFS server with /proc/fs/nfsd/max_block_size set to 1048576
    • kernel at least 2.6.18-308.el5 and earlier than 2.6.18-308.11.1.el5
  • NFS client mounting an export on the NFS server using an rsize/wsize of 1048576
  • TCP being used for NFS communication

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase of over 48,000 articles and solutions.

Current Customers and Partners

Log in for full access

Log In