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.
---
src/haproxy.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/src/haproxy.c b/src/haproxy.c
index 8785b9f94..0c823c497 100644
--- a/src/haproxy.c
+++ b/src/haproxy.c
@@ -2837,7 +2837,7 @@ int main(int argc, char **argv)
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 @@ int main(int argc, char **argv)
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);
--
2.11.0
