[PATCH] cyclictest: avoid using libnuma cpumask parsing functions

From: Clark Williams
Date: Wed Apr 13 2016 - 16:37:14 EST


John,

I ran into issues with parsing cpu masks when trying to run this command:

sudo ./cyclictest -i100 -qmu -h 2000 -p95 -t1 -a3

I had previously booted a 4-core system with these boot options:

isolcpus=3 nohz_full=3 rcu_nocbs=3

The intent was to run loads on cpus 0-2 while running cyclictest on the isolated cpu 3.

Unfortunately, the libnuma function numa_parse_cpumask() (which we use when it's available) seems to check the current affinity mask and fails the parse if any of the cpus in the input string are not in the current affinity mask. I find this "unhelpful" when trying to place a measurement thread on an isolated cpu.

This patch removes the wrapper function which uses libnuma cpumask parsing functions and instead uses the parser function we wrote for when libnuma is not available.

Signed-off-by: Clark Williams <williams@xxxxxxxxxx>
---
src/cyclictest/rt_numa.h | 82 ++++++++++++++++++++++--------------------------
1 file changed, 38 insertions(+), 44 deletions(-)

diff --git a/src/cyclictest/rt_numa.h b/src/cyclictest/rt_numa.h
index ec2994314e80..d65cd421863b 100644
--- a/src/cyclictest/rt_numa.h
+++ b/src/cyclictest/rt_numa.h
@@ -32,6 +32,12 @@ static int numa = 0;
#define LIBNUMA_API_VERSION 1
#endif

+#ifndef BITS_PER_LONG
+#define BITS_PER_LONG (8*sizeof(long))
+#endif
+
+
+
static void *
threadalloc(size_t size, int node)
{
@@ -89,22 +95,6 @@ static inline unsigned int rt_numa_bitmask_isbitset( const struct bitmask *mask,
return numa_bitmask_isbitset(mask,i);
}

-static inline struct bitmask* rt_numa_parse_cpustring(const char* s,
- int max_cpus)
-{
-#ifdef HAVE_PARSE_CPUSTRING_ALL /* Currently not defined anywhere. No
- autotools build. */
- return numa_parse_cpustring_all(s);
-#else
- /* We really need numa_parse_cpustring_all(), so we can assign threads
- * to cores which are part of an isolcpus set, but early 2.x versions of
- * libnuma do not have this function. A work around should be to run
- * your command with e.g. taskset -c 9-15 <command>
- */
- return numa_parse_cpustring((char *)s);
-#endif
-}
-
static inline void rt_bitmask_free(struct bitmask *mask)
{
numa_bitmask_free(mask);
@@ -157,32 +147,6 @@ static inline unsigned int rt_numa_bitmask_isbitset( const struct bitmask *mask,
return (bit != 0);
}

-static inline struct bitmask* rt_numa_parse_cpustring(const char* s,
- int max_cpus)
-{
- int cpu;
- struct bitmask *mask = NULL;
- cpu = atoi(s);
- if (0 <= cpu && cpu < max_cpus) {
- mask = malloc(sizeof(*mask));
- if (mask) {
- /* Round up to integral number of longs to contain
- * max_cpus bits */
- int nlongs = (max_cpus+BITS_PER_LONG-1)/BITS_PER_LONG;
-
- mask->maskp = calloc(nlongs, sizeof(long));
- if (mask->maskp) {
- mask->maskp[cpu/BITS_PER_LONG] |=
- (1UL << (cpu % BITS_PER_LONG));
- mask->size = max_cpus;
- } else {
- free(mask);
- mask = NULL;
- }
- }
- }
- return mask;
-}

static inline void rt_bitmask_free(struct bitmask *mask)
{
@@ -204,8 +168,6 @@ struct bitmask {
unsigned long size; /* number of bits in the map */
unsigned long *maskp;
};
-#define BITS_PER_LONG (8*sizeof(long))
-
static inline void *threadalloc(size_t size, int n) { return malloc(size); }
static inline void threadfree(void *ptr, size_t s, int n) { free(ptr); }
static inline void rt_numa_set_numa_run_on_node(int n, int c) { }
@@ -280,4 +242,36 @@ static inline unsigned int rt_numa_bitmask_count(const struct bitmask *mask)
return num_bits;
}

+/*
+ * Use this instead of a wrapper for libnuma functions.
+ * The libnuma function numa_parse_cpustring() checks the affinity mask
+ * and fails if an input cpu is not in the mask. This of course sucks when
+ * trying to place a thread on an isolated cpu. Avoid libnuma parsing functions
+ */
+static inline struct bitmask* rt_numa_parse_cpustring(const char* s,
+ int max_cpus)
+{
+ int cpu;
+ struct bitmask *mask = NULL;
+ cpu = atoi(s);
+ if (0 <= cpu && cpu < max_cpus) {
+ mask = malloc(sizeof(*mask));
+ if (mask) {
+ /* Round up to integral number of longs to contain
+ * max_cpus bits */
+ int nlongs = (max_cpus+BITS_PER_LONG-1)/BITS_PER_LONG;
+
+ mask->maskp = calloc(nlongs, sizeof(long));
+ if (mask->maskp) {
+ mask->maskp[cpu/BITS_PER_LONG] |=
+ (1UL << (cpu % BITS_PER_LONG));
+ mask->size = max_cpus;
+ } else {
+ free(mask);
+ mask = NULL;
+ }
+ }
+ }
+ return mask;
+}
#endif /* _RT_NUMA_H */
--
2.5.5

Attachment: pgp_YdZvXA8QC.pgp
Description: OpenPGP digital signature