[Devel] [PATCH VZ10 v8 6/7] ve: Introduce per-VE failcount

[Vasileios Almpanis]

> It may be useful to have a history of resource limit hits for every VE,
> this may simplify debugging and provide some information about the
> resources usage.
> 
> This information is provided by ve.failcount file, any write to it
> resets all failcounts.
> 
> To add a new failcounter we need to create a new atomic_t field
> name_failcount in ve structure and add a new VE_FC_ENTRY in
> ve_failcounts array.
> 
> One change, unrelated to failcounts: aio fields are now initialized
> in ve0.
> 
> https://virtuozzo.atlassian.net/browse/VSTOR-135520
> 
> Feature: per-ve failcounters
> Signed-off-by: Vladimir Riabchun <vladimir.riabchun at virtuozzo.com>
>
> diff --git a/fs/aio.c b/fs/aio.c
> index cb63416af135..4ae06bcd47f2 100644
> --- a/fs/aio.c
> +++ b/fs/aio.c
> @@ -814,6 +814,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
>  	spin_lock(&ve->aio_nr_lock);
>  	if (ve->aio_nr + ctx->max_reqs > ve->aio_max_nr ||
>  	    ve->aio_nr + ctx->max_reqs < ve->aio_nr) {
> +		ve_failcount_inc(ve, aio);
>  		spin_unlock(&ve->aio_nr_lock);
>  		err = -EAGAIN;
>  		goto err_ctx;
> diff --git a/fs/namespace.c b/fs/namespace.c
> index 1d6e66cd7174..ea01664ff5f2 100644
> --- a/fs/namespace.c
> +++ b/fs/namespace.c
> @@ -3380,6 +3380,8 @@ static inline int ve_try_reserve_mount(struct ve_struct *ve)
>  
>  	if (ret)
>  		get_ve(ve);
> +	else
> +		ve_failcount_inc(ve, mnt);
>  	return ret;
>  }
>  
> diff --git a/include/linux/ve.h b/include/linux/ve.h
> index fabc608e31f5..065129b42768 100644
> --- a/include/linux/ve.h
> +++ b/include/linux/ve.h
> @@ -80,12 +80,15 @@ struct ve_struct {
>  	struct kmapset_key	proc_perms_key;
>  
>  	atomic_t		netns_avail_nr;
> +	atomic_t		netns_failcount;
>  	int			netns_max_nr;
>  
>  	atomic_t		netif_avail_nr;
> +	atomic_t		netif_failcount;
>  	int			netif_max_nr;
>  
>  	atomic_t		bpf_prog_avail_nr;
> +	atomic_t		bpf_prog_failcount;
>  	int			bpf_prog_max_nr;
>  
>  	atomic64_t		_uevent_seqnum;
> @@ -94,6 +97,7 @@ struct ve_struct {
>  
>  	atomic_t		arp_neigh_nr;
>  	atomic_t		nd_neigh_nr;
> +	atomic_t		neigh_tbl_failcount;
>  	unsigned long		meminfo_val;
>  
>  	/*
> @@ -102,6 +106,7 @@ struct ve_struct {
>  	 * other containers.
>  	 */
>  	atomic_t		mnt_avail_nr; /* number of available VE mounts */
> +	atomic_t		mnt_failcount;
>  	int			mnt_max_nr;
>  
>  #ifdef CONFIG_COREDUMP
> @@ -129,6 +134,7 @@ struct ve_struct {
>  	spinlock_t		aio_nr_lock;
>  	unsigned long		aio_nr;
>  	unsigned long		aio_max_nr;
> +	atomic_t		aio_failcount;
>  #endif
>  	struct vfsmount		*devtmpfs_mnt;
>  };
> @@ -151,6 +157,16 @@ extern int nr_ve;
>  #define BPF_PROG_MAX_NR_DEFAULT	256	/* number of loaded BPF progs per-VE */
>  #define MNT_MAX_NR_DEFAULT	4096	/* number of mounts per-VE */
>  
> +#define ve_failcount_inc(ve, name)					\
> +do {									\
> +	struct ve_struct *__ve = (ve);					\
> +									\
> +	atomic_inc(&__ve->name##_failcount);				\
> +	ve_pr_warn_ratelimited(VE_LOG_BOTH, "CT%s: hits the " #name	\
> +		" limit, see the '" #name "' counter in ve.failcount "	\
> +		"of the container's ve cgroup\n", ve_name(__ve));	\

If this is called in softirq context for example like neigh_alloc it
will print into ve of whatever task was just interrupted. So a random ve
will receive this warning into its dmesg. I don't think this is good.

-- 
Vasileios Almpanis <vasileios.almpanis at virtuozzo.com>