Re: [PATCH v4 1/3] qspinlock: Introducing a 4-byte queue spinlock implementation

[Peter Zijlstra]

On Mon, Feb 17, 2014 at 03:41:22PM -0500, Waiman Long wrote:
> +/*
> + * The queue node structure
> + *
> + * This structure is essentially the same as the mcs_spinlock structure
> + * in mcs_spinlock.h file. This structure is retained for future extension
> + * where new fields may be added.
> + */
> +struct qnode {
> +	u32		 wait;		/* Waiting flag		*/
> +	struct qnode	*next;		/* Next queue node addr */
> +};
> +
> +struct qnode_set {
> +	int		node_idx;	/* Current node to use */
> +	struct qnode	nodes[MAX_QNODES];
> +};
> +
> +/*
> + * Per-CPU queue node structures
> + */
> +static DEFINE_PER_CPU(struct qnode_set, qnset) ____cacheline_aligned
> +	= { 0 };

You really didn't pay attention did you.

That should be DEFINE_PER_CPU_ALIGNED()

Furthermore, your structure is bigger than 1 cacheline; your struct
qnode is 16 bytes, 4*16=64, and then you add that int.
--
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/