BUG/MEDIUM: fix a 100% cpu usage with cpu-map and nbthread/nbproc
Krishna Kumar reported a 100% cpu usage with a configuration using
cpu-map and a high number of threads,
Indeed, this minimal configuration to reproduce the issue :
global
nbthread 40
cpu-map auto:1/1-40 0-39
frontend test
bind :8000
This is due to a wrong type in a shift operator (int vs unsigned long int),
causing an endless loop while applying the cpu affinity on threads. The same
issue may also occur with nbproc under FreeBSD. This commit addresses both
cases.
This patch must be backported to 1.8.
diff --git a/src/haproxy.c b/src/haproxy.c
index 8785b9f..0c823c4 100644
--- a/src/haproxy.c
+++ b/src/haproxy.c
@@ -2837,7 +2837,7 @@
CPU_ZERO(&cpuset);
while ((i = ffsl(cpu_map)) > 0) {
CPU_SET(i - 1, &cpuset);
- cpu_map &= ~(1 << (i - 1));
+ cpu_map &= ~(1UL << (i - 1));
}
ret = cpuset_setaffinity(CPU_LEVEL_WHICH, CPU_WHICH_PID, -1, sizeof(cpuset), &cpuset);
}
@@ -3037,7 +3037,7 @@
while ((j = ffsl(cpu_map)) > 0) {
CPU_SET(j - 1, &cpuset);
- cpu_map &= ~(1 << (j - 1));
+ cpu_map &= ~(1UL << (j - 1));
}
pthread_setaffinity_np(threads[i],
sizeof(cpuset), &cpuset);