Re: [PATCH] Bring numastat up to revision 20130723

[Cliff Wickman <cpw@sgi.com>]

Thanks Bill.
I added your patch.


There have been only 2 patches since the release of 2.0.8 last October:
this one, and the add of 1 prototype statement.
These are now part of numactl-2.0.9-rc2.tar.gz on
ftp://oss.sgi.com/www/projects/libnuma/download/

I ran the regression tests successfully on ia64 and a large x86_64
(though I did disable the regress-io test as it is known to fail).
More testing is welcome.

Even with so few changes I'll probably declare it as version 2.0.9 this
fall.

-Cliff



On Thu, Jul 25, 2013 at 10:10:26AM -0400, Bill Gray wrote:
>
> This patch fixes issues (detailed below) in numastat.c and numastat.8,
> and brings numastat up to revision 20130723.
>
> numastat.8 |   18 +++++++-----------
> numastat.c |    4 ++--
> 2 files changed, 9 insertions(+), 13 deletions(-)
>
> numastat.c:
> - fix bug preventing correct static huge page quantities
> - update version number
>
> numastat.8:
> - remove redundant "interleave hit" description
> - remove extraneous leading spaces and blank lines
> - enhance explanation of correct placement for "-s" option
>
> Signed-off-by: Bill Gray <bgray@redhat.com>
>
>
> diff -purN numactl-2.0.8-orig/numastat.8 numactl-2.0.8-new/numastat.8
> --- numactl-2.0.8-orig/numastat.8	2012-10-11 16:52:25.000000000 -0400
> +++ numactl-2.0.8-new/numastat.8	2013-07-24 17:54:36.570307058 -0400
> @@ -36,26 +36,20 @@ on another node.
>  .LP
>  .B numa_foreign
>  is memory intended for this node, but actually allocated on some  
> different node.  Each
> - .I numa_foreign
> +.I numa_foreign
>  has a
> - .I numa_miss
> -  on another node.
> +.I numa_miss
> +on another node.
>  .LP
>  .B interleave_hit
>  is interleaved memory successfully allocated on this node as intended.
>  .LP
> -.B interleave_hit
> -is the number of interleave policy allocations that were intended for a
> -specific node and succeeded there.
> -
>  .B local_node
>  is memory allocated on this node while a process was running on it.
>  .LP
> -
>  .B other_node
>  is memory allocated on this node while a process was running on some  
> other node.
>  .LP
> -
>  Any supplied options or arguments with the \fBnumastat\fP command will
>  significantly change both the content and the format of the display.  
> Specified
>  options will cause display units to change to megabytes of memory, and  
> will
> @@ -100,7 +94,10 @@ memory consumers are listed first.  With
>  sorted by the total column.  If the optional <node> argument is  
> supplied, the
>  data will be sorted by the <node> column.  Note that <node> must follow 
> the
>  \fB\-s\fP immediately with no intermediate white space (e.g., \fBnumastat
> -\-s2\fP).
> +\-s2\fP). Because \fB\-s\fP can allow an optional argument, it must  
> always be
> +the last option character in a compound option character string. For  
> example,
> +instead of \fBnumastat \-msc\fP (which probably will not work as you  
> expect),
> +use \fBnumastat \-mcs\fP
>  .TP
>  \fB\-v\fR
>  Make some reports more verbose.  In particular, process information for
> @@ -139,7 +136,6 @@ NUMASTAT_WIDTH
>  \fI/sys/devices/system/node/node*/meminfo\fP
>  .br
>  \fI/sys/devices/system/node/node*/numastat\fP
> -
>  .SH "EXAMPLES"
>  .I numastat \-c \-z \-m \-n
>  .br
> diff -purN numactl-2.0.8-orig/numastat.c numactl-2.0.8-new/numastat.c
> --- numactl-2.0.8-orig/numastat.c	2012-10-11 16:52:25.000000000 -0400
> +++ numactl-2.0.8-new/numastat.c	2013-07-24 17:50:02.845242848 -0400
> @@ -724,7 +724,7 @@ double huge_page_size_in_bytes = 0;
>
>
>  void display_version_and_exit() {
> -	char *version_string = "20120821";
> +	char *version_string = "20130723";
>  	printf("%s version: %s: %s\n", prog_name, version_string, __DATE__);
>  	exit(EXIT_SUCCESS);
>  }
> @@ -880,7 +880,7 @@ void show_info_from_system_file(char *fi
>  				double value = (double)atol(tok[1 + tok_offset]);
>  				if (!compatibility_mode) {
>  					double multiplier = 1.0;
> -					if (tokens < 5) {
> +					if (tokens < 4) {
>  						multiplier = page_size_in_bytes;
>  					} else if (!strncmp("HugePages", tok[2], 9)) {
>  						multiplier = huge_page_size_in_bytes;

-- 
Cliff Wickman
SGI
cpw@sgi.com
(651) 683-3824