RHEL5.8: NFS server (nfsd) panics in tcp_sendpage because of overrun of rq_pages array
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, tools, and much more.