ndctl: fail NUMA filtering when unsupported
PATCH 1/1 ndctl: fail NUMA filtering when unsupported
For systems that don't support NUMA, numactl gives a loud and fatal error:
# numactl -N 0 ls numactl: This system does not support NUMA policy
Follow this model in ndctl for NUMA based filtering:
# ./ndctl/ndctl list --numa-node=0
Error: This system does not support NUMAThis is done instead of just quietly filtering out all dimms, regions and namespaces because the NUMA node they were trying to match didn't exist in the system.
--- util/filter.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
util/filter.c +10 -0
@@ -14,7 +14,10 @@#include <string.h> #include <stdlib.h> #include <limits.h> +#include <unistd.h> +#include <sys/stat.h> #include <util/util.h> +#include <sys/types.h> #include <ndctl/ndctl.h> #include <util/filter.h> #include <ndctl/libndctl.h>
@@ -328,6 +331,13 @@ int util_filter_walk(struct ndctl_ctx *ctx, struct util_filter_ctx *fctx, }if (param->numa_node &&strcmp (param->numa_node,"all" ) !=0 ) { +struct stat st; + +if (stat ("/sys/devices/system/node" , &st)) { +error ("This system does not support NUMA\n" ); +return -EINVAL ; + } + numa_node =strtol (param->numa_node, &end,0 );if (end == param->numa_node || end[0 ]) {error ("invalid numa_node: '%s'\n" , param->numa_node);
Signature · 6 lines
2.14.3 _______________________________________________ Linux-nvdimm mailing list [email protected] https://lists.01.org/mailman/listinfo/linux-nvdimm
Verma, Vishal L
maintainerQuoted 41 lines · Ross Zwisler
For systems that don't support NUMA, numactl gives a loud and fatal error:
# numactl -N 0 ls numactl: This system does not support NUMA policyFollow this model in ndctl for NUMA based filtering:
# ./ndctl/ndctl list --numa-node=0 Error: This system does not support NUMAThis is done instead of just quietly filtering out all dimms, regions and
namespaces because the NUMA node they were trying to match didn't exist in
the system.Signed-off-by Ross Zwisler <[email protected]>Suggested-by Dan Williams <[email protected]>--- util/filter.c | 10 ++++++++++ 1 file changed, 10 insertions(+)util/filter.c +3
-0@@ -14,7 +14,10 @@#include <string.h> #include <stdlib.h> #include <limits.h> +#include <unistd.h> +#include <sys/stat.h> #include <util/util.h> +#include <sys/types.h> #include <ndctl/ndctl.h> #include <util/filter.h> #include <ndctl/libndctl.h> @@ -328,6 +331,13 @@ int util_filter_walk(struct ndctl_ctx *ctx, struct util_filter_ctx *fctx, }
util/filter.c int util_filter_walk(struct ndctl_ctx *ctx, · line 342
Quoted 10 lines
util/filter.c +6
-0if (param->numa_node &&strcmp (param->numa_node,"all" ) !=0 ) { +struct stat st; + +if (stat ("/sys/devices/system/node" , &st)) { +error ("This system does not support NUMA\n"); +return -EINVAL ; + }
Is it ok to just directly read sysfs here? Alternatively we could use the get_mempolicy syscall (like libnuma does) but that requires linking with -lnuma..
https://github.com/numactl/numactl/blob/master/libnuma.c#L800
Quoted 5 lines
util/filter.c +1
-0+util/filter.c +0
-0numa_node =strtol (param->numa_node, &end,0 );if (end == param->numa_node || end[0 ]) { error("invalid numa_node: '%s'\n", param-Quoted 1 line
numa_node);
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm
Quoted 58 lines · Vishal L
Quoted 41 lines · Ross Zwisler
For systems that don't support NUMA, numactl gives a loud and fatal error:
# numactl -N 0 ls numactl: This system does not support NUMA policyFollow this model in ndctl for NUMA based filtering:
# ./ndctl/ndctl list --numa-node=0 Error: This system does not support NUMAThis is done instead of just quietly filtering out all dimms, regions and
namespaces because the NUMA node they were trying to match didn't exist in
the system.Signed-off-by Ross Zwisler <[email protected]>Suggested-by Dan Williams <[email protected]>--- util/filter.c | 10 ++++++++++ 1 file changed, 10 insertions(+)util/filter.c +3
-0@@ -14,7 +14,10 @@#include <string.h> #include <stdlib.h> #include <limits.h> +#include <unistd.h> +#include <sys/stat.h> #include <util/util.h> +#include <sys/types.h> #include <ndctl/ndctl.h> #include <util/filter.h> #include <ndctl/libndctl.h> @@ -328,6 +331,13 @@ int util_filter_walk(struct ndctl_ctx *ctx, struct util_filter_ctx *fctx, }util/filter.c int util_filter_walk(struct ndctl_ctx *ctx, · line 342
Quoted 10 lines
util/filter.c +6
-0if (param->numa_node &&strcmp (param->numa_node,"all" ) !=0 ) { +struct stat st; + +if (stat ("/sys/devices/system/node" , &st)) { +error ("This system does not support NUMA\n"); +return -EINVAL ; + }Is it ok to just directly read sysfs here? Alternatively we could use the
get_mempolicysyscall (like libnuma does) but that requires linking with -lnuma..
I don't mind linking against libnuma if the goal is to mimic the behavior of numactl.
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm