Re: [PATCH v2] Make VM_MAX_READAHEAD a kernel parameter

[Nikanth Karthikesan]

On Monday 15 February 2010 03:07:24 Dave Chinner wrote:
> On Thu, Feb 11, 2010 at 05:15:03PM +0530, Nikanth Karthikesan wrote:
> > On Thursday 11 February 2010 16:45:24 Ankit Jain wrote:
> > > > +static int __init readahead(char *str)
> > > > +{
> > > > +       if (!str)
> > > > +               return -EINVAL;
> > > > +       vm_max_readahead_kb = memparse(str, &str) / 1024ULL;
> > >
> > > Just wondering, shouldn't you check whether the str had a valid value
> > > [memparse (str, &next); next > str ..] and if it didn't, then use the
> > > DEFAULT_VM_MAX_READAHEAD ? Otherwise, incase of a invalid
> > > value, the readahead value will become zero.
> >
> > Thanks for the review. Here is the fixed patch that checks whether all of
> > the parameters value is consumed.
> >
> > Thanks
> > Nikanth
> >
> > From: Nikanth Karthikesan <knikanth@xxxxxxx>
> >
> > Add new kernel parameter "readahead", which would be used instead of the
> > value of VM_MAX_READAHEAD. If the parameter is not specified, the default
> > of 128kb would be used.
> >
> > Signed-off-by: Nikanth Karthikesan <knikanth@xxxxxxx>
> >
> > ---
> >
> > diff --git a/Documentation/kernel-parameters.txt
> > b/Documentation/kernel-parameters.txt index 736d456..354e6f1 100644
> > --- a/Documentation/kernel-parameters.txt
> > +++ b/Documentation/kernel-parameters.txt
> > @@ -2148,6 +2148,8 @@ and is between 256 and 4096 characters. It is
> > defined in the file Format: <reboot_mode>[,<reboot_mode2>[,...]]
> >  			See arch/*/kernel/reboot.c or arch/*/kernel/process.c
> >
> > +	readahead=	Default readahead value for block devices.
> > +
> 
> I think the description should define the units (kb) and valid value
> ranges e.g. page size to something not excessive - say 65536kb.  The
> above description is, IMO, useless without refering to the source to
> find out this information....
> 

The parameter can be specified with/without any suffix(k/m/g) that memparse() 
helper function can accept. So it can take 1M, 1024k, 1050620. I checked other 
parameters that use memparse() to get similar values and they didn't document 
it. May be this should be described here.

> [snip]
> 
> > @@ -249,6 +250,24 @@ static int __init loglevel(char *str)
> >
> >  early_param("loglevel", loglevel);
> >
> > +static int __init readahead(char *str)
> > +{
> > +	unsigned long readahead_kb;
> > +
> > +	if (!str)
> > +		return -EINVAL;
> > +	readahead_kb = memparse(str, &str) / 1024ULL;
> > +	if (*str != '\0')
> > +		return -EINVAL;
>  		
> And readahead_kb needs to be validated against the range of
> valid values here.
> 

I didn't want to impose artificial restrictions. I think Wu's patch set would 
be adding some restrictions, like minimum readahead. He could fix it when he 
modifies the patch to include in his patch set.

> > +
> > +	vm_max_readahead_kb = readahead_kb;
> > +	default_backing_dev_info.ra_pages = vm_max_readahead_kb
> > +						* 1024 / PAGE_CACHE_SIZE;
> > +	return 0;
> > +}
> > +
> > +early_param("readahead", readahead);
> > +
> 

Thanks for reviewing.

Thanks
Nikanth
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/