Hi David,
On Sun, Mar 12, 2017 at 09:11:53AM +, David Howells wrote:
> Eric Biggers wrote:
>
> > +static int cp_statx(const struct kstat *stat, struct statx __user *buffer)
> > ...
> > + struct statx tmp;
>
> This function needs to be "noinline" as tmp is big.
>
> >
Hi David,
On Sun, Mar 12, 2017 at 09:11:53AM +, David Howells wrote:
> Eric Biggers wrote:
>
> > +static int cp_statx(const struct kstat *stat, struct statx __user *buffer)
> > ...
> > + struct statx tmp;
>
> This function needs to be "noinline" as tmp is big.
>
> > - return
Eric Biggers wrote:
> +static int cp_statx(const struct kstat *stat, struct statx __user *buffer)
> ...
> + struct statx tmp;
This function needs to be "noinline" as tmp is big.
> - return statx_set_result(, buffer);
> +
> + return cp_statx(, buffer);
Can you
Eric Biggers wrote:
> +static int cp_statx(const struct kstat *stat, struct statx __user *buffer)
> ...
> + struct statx tmp;
This function needs to be "noinline" as tmp is big.
> - return statx_set_result(, buffer);
> +
> + return cp_statx(, buffer);
Can you leave it as
From: Eric Biggers
I found that statx() was significantly slower than stat(). As a
microbenchmark, I compared 10,000,000 invocations of fstat() on a tmpfs
file to the same with statx() passed a NULL path:
$ time ./stat_benchmark
real0m1.464s
From: Eric Biggers
I found that statx() was significantly slower than stat(). As a
microbenchmark, I compared 10,000,000 invocations of fstat() on a tmpfs
file to the same with statx() passed a NULL path:
$ time ./stat_benchmark
real0m1.464s
user0m0.275s
6 matches
Mail list logo