Error Message

$ cat messages | grep "page allocation"| grep vx
May  5 17:52:37 esesslx0077b kernel: [255432.921856] vx_worklist_thr: page allocation failure. order:1, mode:0x5050, alloc_flags:0x40 pflags:0x602040

May  6 16:20:33 esesslx0077b kernel: [342008.067116] vx_worklist_thr: page allocation failure. order:1, mode:0x5050, alloc_flags:0x40 pflags:0x602040
May  6 16:20:58 esesslx0077b kernel: [342008.954549] vx_worklist_thr: page allocation failure. order:1, mode:0x5050, alloc_flags:0x40 pflags:0x602040
 

O/S tunning

Since memory management is done by Linux kernel, the error is coming from the O/S. The Netbackup application is not at fault
Virtual memory systems separate the memory addresses used by a process from actual physical addresses, allowing separation of processes and increasing the effective available amount of RAM using disk swapping. The quality of the virtual memory manager can have a big impact on overall system performance. This error related to memory fragmentation i.e. a new job / process cannot be loaded into memory due to fragmentation issue.

To get rid of this problem please try all of the following with the guidance from SUSE:

Upgrade kernel to latest version

Set VM kernel variables using sysctl or /etc/sysctl.conf file.

The /proc/sys/vm file is used for the virtual memory subsystem. You can setup following two variables:

vm.lower_zone_protection=N :  Try setting /proc/sys/vm/lower_zone_protection to a value of 250 or more.
This will cause the kernel to try to be more aggressive in defending the low zone from allocating memory that could potentially be allocated in the high memory zone. This option may not be available until the 2.6.x kernel.

vm.vfs_cache_pressure=N : Controls the tendency of the kernel to reclaim the memory which is used for caching of directory and inode objects. At the default value of vfs_cache_pressure=100 the kernel will attempt to reclaim dentries and inodes at a "fair" rate with respect to pagecache and swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100
causes the kernel to prefer to reclaim dentries and inodes.

Please seek further guidance from SUSE on the above tunable's.

Applies To

SF 5.1 SP1 for Linux SUSE 11 SP1