Re: [PATCH 5/5] Update huge pages kernel documentation

[David Rientjes <rientjes@google.com>]

On Tue, Jun 16, 2009 at 6:53 AM, Lee
Schermerhorn<lee.schermerhorn@hp.com> wrote:
> @@ -67,26 +65,76 @@ use either the mmap system call or share
>  the huge pages.  It is required that the system administrator preallocate
>  enough memory for huge page purposes.
>
> -Use the following command to dynamically allocate/deallocate hugepages:
> +The administrator can preallocate huge pages on the kernel boot command line by
> +specifying the "hugepages=N" parameter, where 'N' = the number of huge pages
> +requested.  This is the most reliable method for preallocating huge pages as
> +memory has not yet become fragmented.
> +
> +Some platforms support multiple huge page sizes.  To preallocate huge pages
> +of a specific size, one must preceed the huge pages boot command parameters
> +with a huge page size selection parameter "hugepagesz=<size>".  <size> must
> +be specified in bytes with optional scale suffix [kKmMgG].  The default huge
> +page size may be selected with the "default_hugepagesz=<size>" boot parameter.
> +
> +/proc/sys/vm/nr_hugepages indicates the current number of configured [default
> +size] hugetlb pages in the kernel.  Super user can dynamically request more
> +(or free some pre-configured) hugepages.
> +
> +Use the following command to dynamically allocate/deallocate default sized
> +hugepages:
>
>        echo 20 > /proc/sys/vm/nr_hugepages
>
> -This command will try to configure 20 hugepages in the system.  The success
> -or failure of allocation depends on the amount of physically contiguous
> -memory that is preset in system at this time.  System administrators may want
> -to put this command in one of the local rc init files.  This will enable the
> -kernel to request huge pages early in the boot process (when the possibility
> -of getting physical contiguous pages is still very high). In either
> -case, administrators will want to verify the number of hugepages actually
> -allocated by checking the sysctl or meminfo.
> +This command will try to configure 20 default sized hugepages in the system.
> +On a NUMA platform, the kernel will attempt to distribute the hugepage pool
> +over the nodes specified by the /proc/sys/vm/hugepages_nodes_allowed node mask.
> +hugepages_nodes_allowed defaults to all on-line nodes.
> +
> +To control the nodes on which huge pages are preallocated, the administrator
> +may set the hugepages_nodes_allowed for the default huge page size using:
> +
> +       echo <nodelist> >/proc/sys/vm/hugepages_nodes_allowed
> +

This probably also needs an update to
Documentation/ABI/testing/sysfs-kernel-mm-hugepages for the
non-default hstate nodes_allowed.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>