Skip to contentSkip to conversation

sched_domain-handle-kmalloc-failure-fix

PATCH In review Lee Schermerhorn 2 participants 2 messages Apr 6, 2006 – Apr 7, 2006

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 sched_domain-handle-kmalloc-failure-fix

[PATCH] sched_domain-handle-kmalloc-failure-fix

2.6.17-rc1-mm1 hangs during boot on HP rx8620 and dl585 -- both 4 node NUMA platforms. Problem is in build_sched_domains() setting up the sched_group_nodes[] lists, resulting from patch:
sched_domain-handle-kmalloc-failure.patch

The referenced patch does not propagate the "next" pointer from the head of the list, resulting in a loop between the last 2 groups in the list. This causes a tight loop/hang in init_numa_sched_groups_power() because 'sg->next' never == 'group_head' when you have > 2 nodes.

This patch seems to fix the problem.

kernel/sched.c +1 -1
Index: linux-2.6.17-rc1-mm1/kernel/sched.c
===================================================================
@@ -6360,7 +6360,7 @@ static int build_sched_domains(const cpu
 			}
 			sg->cpu_power = 0;
 			sg->cpumask = tmp;
-			sg->next = prev;
+			sg->next = prev->next;
 			cpus_or(covered, covered, tmp);
 			prev->next = sg;
 			prev = sg;
#1 lore raw
Quoted 9 lines · Lee Schermerhorn

2.6.17-rc1-mm1 hangs during boot on HP rx8620 and dl585 -- both 4 node NUMA platforms. Problem is in build_sched_domains() setting up the sched_group_nodes[] lists, resulting from patch:
sched_domain-handle-kmalloc-failure.patch

The referenced patch does not propagate the "next" pointer from the head of the list, resulting in a loop between the last 2 groups in the list. This causes a tight loop/hang in init_numa_sched_groups_power() because 'sg->next' never == 'group_head' when you have > 2 nodes.

Wow. I'm incredibly impressed that you tracked that down. I can't believe how horribly unintelligible that code is.

I ran into the same freeze on a 4-node NUMA-Q. Your patch fixed it.

Is there any good reason that sched domains has to roll its own linked lists? Why not use list_heads? Seems like it would avoid crappy problems like this.

-- Dave