memhog mmaps a memory region for a given size and sets the numa
policy (if specified). It then updates the memory region for the
given number of iterations using memset.
-r<num> Repeat memset NUM times
-f<file> Open file for mmap backing
-H Disable transparent hugepages
-size Allocation size in bytes, may have case-insensitive order
suffix (G=gigabyte, M=megabyte, K=kilobyte)
Memory will be allocated using round robin on nodes. When
memory cannot be allocated on the current interleave,
target fall back to other nodes. Multiple nodes may be
Only allocate memory from nodes. Allocation will fail
when there is not enough memory available on these nodes.
Multiple nodes may be specified.
Preferably allocate memory on node, but if memory cannot
be allocated there fall back to other nodes. This
option takes only a single node number.
Memory will be allocated on the local node (the node the
thread is running on)
# Allocate a 1G region, mmap backed by memhog.mmap file, membind
to node 0, repeat test 6 times
memhog -r6 1G --membind 0 -fmemhog.mmap
# Allocate a 1G region, iterleave across nodes 0,1,2,3, repeat
test 4 times
memhog -r4 1G --interleave 0-3
# Allocate a 1G region, (implicit) default policy, repeat test 8
memhog -r8 1G
This page is part of the numactl (NUMA commands) project.
Information about the project can be found at
⟨http://oss.sgi.com/projects/libnuma/⟩. If you have a bug report
for this manual page, send it to email@example.com.
This page was obtained from the project's upstream Git repository
⟨https://github.com/numactl/numactl.git⟩ on 2021-08-27. (At that
time, the date of the most recent commit that was found in the
repository was 2021-08-25.) If you discover any rendering
problems in this HTML version of the page, or you believe there
is a better or more up-to-date source for the page, or you have
corrections or improvements to the information in this COLOPHON
(which is not part of the original manual page), send a mail to
SuSE Labs 2003,2004 MEMHOG(8)