Revision 494de90098784b8e2797598cefdd34188884ec2e authored by Mel Gorman on 03 July 2008, 04:27:51 UTC, committed by Linus Torvalds on 03 July 2008, 16:22:59 UTC
The non-NUMA case of build_zonelist_cache() would initialize the zlcache_ptr for both node_zonelists[] to NULL. Which is problematic, since non-NUMA only has a single node_zonelists[] entry, and trying to zero the non-existent second one just overwrote the nr_zones field instead. As kswapd uses this value to determine what reclaim work is necessary, the result is that kswapd never reclaims. This causes processes to stall frequently in low-memory situations as they always direct reclaim. This patch initialises zlcache_ptr correctly. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Tested-by: Dan Williams <dan.j.williams@intel.com> [ Simplified patch a bit ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent c461a97
File | Mode | Size |
---|---|---|
Makefile | -rw-r--r-- | 247 bytes |
asm-offsets.c | -rw-r--r-- | 2.3 KB |
entry.S | -rw-r--r-- | 8.2 KB |
gpio.c | -rw-r--r-- | 3.6 KB |
h8300_ksyms.c | -rw-r--r-- | 2.6 KB |
init_task.c | -rw-r--r-- | 1.0 KB |
irq.c | -rw-r--r-- | 4.5 KB |
module.c | -rw-r--r-- | 2.9 KB |
process.c | -rw-r--r-- | 5.3 KB |
ptrace.c | -rw-r--r-- | 5.5 KB |
setup.c | -rw-r--r-- | 6.6 KB |
signal.c | -rw-r--r-- | 13.8 KB |
sys_h8300.c | -rw-r--r-- | 6.3 KB |
syscalls.S | -rw-r--r-- | 12.9 KB |
time.c | -rw-r--r-- | 1.6 KB |
traps.c | -rw-r--r-- | 3.8 KB |
vmlinux.lds.S | -rw-r--r-- | 2.7 KB |
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...