Re: [PATCH] kernel/fork: declare max_threads __read_mostly

[Lorenzo Stoakes]

On Tue, 07 Jul 2026 17:23:54 +0800, JianChunfu <jansef.jian@xxxxxxxxxxxx> wrote:
> [...]
> after patch:
> 	hachbench -g    100      500      1000      2000
>                     0.823    4.487    11.107    32.987
> 
> Above data are the average values obtained from multiple tests, and
> there was indeed some fluctuation in the data during the tests.

Seems nice though you do wonder if there's other factors at play on the
delta.

> 
> Signed-off-by: JianChunfu <jansef.jian@xxxxxxxxxxxx>

It does seem nr_threads is very rarely written too so read mostly is valid,
and given observed improvement even if there's noise this seems legit so:

>
>
> diff --git a/kernel/fork.c b/kernel/fork.c
> index f0e2e131a9a5..516faec8efb8 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -143,7 +143,7 @@
>  unsigned long total_forks;	/* Handle normal Linux uptimes. */
>  int nr_threads;			/* The idle threads do not count.. */
>  
> -static int max_threads;		/* tunable limit on nr_threads */
> +static int max_threads __read_mostly;		/* tunable limit on nr_threads */
>  
>  #define NAMED_ARRAY_INDEX(x)	[x] = __stringify(x)
>  

Cheers, Lorenzo

Reviewed-by: Lorenzo Stoakes <ljs@xxxxxxxxxx>

-- 
Lorenzo Stoakes <ljs@xxxxxxxxxx>