[dpdk-dev] [PATCH v3 1/3] lib/lpm: not inline unnecessary functions

Ruifeng Wang (Arm Technology China) Ruifeng.Wang at arm.com
Fri Jun 28 07:48:13 CEST 2019


Hi Stephen,

> -----Original Message-----
> From: Stephen Hemminger <stephen at networkplumber.org>
> Sent: Friday, June 28, 2019 12:35
> To: Ruifeng Wang (Arm Technology China) <Ruifeng.Wang at arm.com>
> Cc: bruce.richardson at intel.com; vladimir.medvedkin at intel.com;
> dev at dpdk.org; Honnappa Nagarahalli <Honnappa.Nagarahalli at arm.com>;
> Gavin Hu (Arm Technology China) <Gavin.Hu at arm.com>; nd <nd at arm.com>
> Subject: Re: [dpdk-dev] [PATCH v3 1/3] lib/lpm: not inline unnecessary
> functions
> 
> On Fri, 28 Jun 2019 02:44:54 +0000
> "Ruifeng Wang (Arm Technology China)" <Ruifeng.Wang at arm.com> wrote:
> 
> > >
> > > > Tests showed that the function inlining caused performance drop on
> > > > some x86 platforms with the memory ordering patches applied.
> > > > By force no-inline functions, the performance was better than
> > > > before on x86 and no impact to arm64 platforms.
> > > >
> > > > Suggested-by: Medvedkin Vladimir <vladimir.medvedkin at intel.com>
> > > > Signed-off-by: Ruifeng Wang <ruifeng.wang at arm.com>
> > > > Reviewed-by: Gavin Hu <gavin.hu at arm.com>
> > >  {
> > >
> > > Do you actually need to force noinline or is just taking of inline enough?
> > > In general, letting compiler decide is often best practice.
> >
> > The force noinline is an optimization for x86 platforms to keep
> > rte_lpm_add() API performance with memory ordering applied.
> 
> I don't think you answered my question. What does a recent version of GCC
> do if you drop the inline.
> 
GCC still inlines it when inline is dropped. So we need the force noinline.
See Vladmir's comment in http://patches.dpdk.org/patch/54936/.

> Actually all the functions in rte_lpm should drop inline.
> 
I don't know if we have guideline on use of 'inline'.
In general, 'inline' is not used and it is upon compiler to decide?
Is it reasonable to use force inline or force noinline for performance tunning?

> diff --git a/lib/librte_lpm/rte_lpm.c b/lib/librte_lpm/rte_lpm.c index
> 6b7b28a2e431..ffe07e980864 100644
> --- a/lib/librte_lpm/rte_lpm.c
> +++ b/lib/librte_lpm/rte_lpm.c
> @@ -399,7 +399,7 @@ MAP_STATIC_SYMBOL(void rte_lpm_free(struct
> rte_lpm *lpm),
>   * are stored in the rule table from 0 - 31.
>   * NOTE: Valid range for depth parameter is 1 .. 32 inclusive.
>   */
> -static inline int32_t
> +static int32_t
>  rule_add_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked, uint8_t depth,
>  	uint8_t next_hop)
>  {
> @@ -471,7 +471,7 @@ rule_add_v20(struct rte_lpm_v20 *lpm, uint32_t
> ip_masked, uint8_t depth,
>  	return rule_index;
>  }
> 
> -static inline int32_t
> +static int32_t
>  rule_add_v1604(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth,
>  	uint32_t next_hop)
>  {
> @@ -547,7 +547,7 @@ rule_add_v1604(struct rte_lpm *lpm, uint32_t
> ip_masked, uint8_t depth,
>   * Delete a rule from the rule table.
>   * NOTE: Valid range for depth parameter is 1 .. 32 inclusive.
>   */
> -static inline void
> +static void
>  rule_delete_v20(struct rte_lpm_v20 *lpm, int32_t rule_index, uint8_t depth)
> {
>  	int i;
> @@ -570,7 +570,7 @@ rule_delete_v20(struct rte_lpm_v20 *lpm, int32_t
> rule_index, uint8_t depth)
>  	lpm->rule_info[depth - 1].used_rules--;  }
> 
> -static inline void
> +static void
>  rule_delete_v1604(struct rte_lpm *lpm, int32_t rule_index, uint8_t depth)  {
>  	int i;
> @@ -597,7 +597,7 @@ rule_delete_v1604(struct rte_lpm *lpm, int32_t
> rule_index, uint8_t depth)
>   * Finds a rule in rule table.
>   * NOTE: Valid range for depth parameter is 1 .. 32 inclusive.
>   */
> -static inline int32_t
> +static int32_t
>  rule_find_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked, uint8_t depth)
> {
>  	uint32_t rule_gindex, last_rule, rule_index; @@ -618,7 +618,7 @@
> rule_find_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked, uint8_t depth)
>  	return -EINVAL;
>  }
> 
> -static inline int32_t
> +static int32_t
>  rule_find_v1604(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth)  {
>  	uint32_t rule_gindex, last_rule, rule_index; @@ -642,7 +642,7 @@
> rule_find_v1604(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth)
>  /*
>   * Find, clean and allocate a tbl8.
>   */
> -static inline int32_t
> +static int32_t
>  tbl8_alloc_v20(struct rte_lpm_tbl_entry_v20 *tbl8)  {
>  	uint32_t group_idx; /* tbl8 group index. */ @@ -669,7 +669,7 @@
> tbl8_alloc_v20(struct rte_lpm_tbl_entry_v20 *tbl8)
>  	return -ENOSPC;
>  }
> 
> -static inline int32_t
> +static int32_t
>  tbl8_alloc_v1604(struct rte_lpm_tbl_entry *tbl8, uint32_t number_tbl8s)  {
>  	uint32_t group_idx; /* tbl8 group index. */ @@ -709,7 +709,7 @@
> tbl8_free_v1604(struct rte_lpm_tbl_entry *tbl8, uint32_t tbl8_group_start)
>  	tbl8[tbl8_group_start].valid_group = INVALID;  }
> 
> -static inline int32_t
> +static int32_t
>  add_depth_small_v20(struct rte_lpm_v20 *lpm, uint32_t ip, uint8_t depth,
>  		uint8_t next_hop)
>  {
> @@ -777,7 +777,7 @@ add_depth_small_v20(struct rte_lpm_v20 *lpm,
> uint32_t ip, uint8_t depth,
>  	return 0;
>  }
> 
> -static inline int32_t
> +static int32_t
>  add_depth_small_v1604(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
>  		uint32_t next_hop)
>  {
> @@ -846,7 +846,7 @@ add_depth_small_v1604(struct rte_lpm *lpm,
> uint32_t ip, uint8_t depth,
>  	return 0;
>  }
> 
> -static inline int32_t
> +static int32_t
>  add_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked, uint8_t
> depth,
>  		uint8_t next_hop)
>  {
> @@ -971,7 +971,7 @@ add_depth_big_v20(struct rte_lpm_v20 *lpm,
> uint32_t ip_masked, uint8_t depth,
>  	return 0;
>  }
> 
> -static inline int32_t
> +static int32_t
>  add_depth_big_v1604(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t
> depth,
>  		uint32_t next_hop)
>  {
> @@ -1244,7 +1244,7 @@ BIND_DEFAULT_SYMBOL(rte_lpm_is_rule_present,
> _v1604, 16.04);  MAP_STATIC_SYMBOL(int rte_lpm_is_rule_present(struct
> rte_lpm *lpm, uint32_t ip,
>  		uint8_t depth, uint32_t *next_hop),
> rte_lpm_is_rule_present_v1604);
> 
> -static inline int32_t
> +static int32_t
>  find_previous_rule_v20(struct rte_lpm_v20 *lpm, uint32_t ip, uint8_t depth,
>  		uint8_t *sub_rule_depth)
>  {
> @@ -1266,7 +1266,7 @@ find_previous_rule_v20(struct rte_lpm_v20 *lpm,
> uint32_t ip, uint8_t depth,
>  	return -1;
>  }
> 
> -static inline int32_t
> +static int32_t
>  find_previous_rule_v1604(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
>  		uint8_t *sub_rule_depth)
>  {
> @@ -1288,7 +1288,7 @@ find_previous_rule_v1604(struct rte_lpm *lpm,
> uint32_t ip, uint8_t depth,
>  	return -1;
>  }
> 
> -static inline int32_t
> +static int32_t
>  delete_depth_small_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked,
>  	uint8_t depth, int32_t sub_rule_index, uint8_t sub_rule_depth)
> { @@ -1381,7 +1381,7 @@ delete_depth_small_v20(struct rte_lpm_v20
> *lpm, uint32_t ip_masked,
>  	return 0;
>  }
> 
> -static inline int32_t
> +static int32_t
>  delete_depth_small_v1604(struct rte_lpm *lpm, uint32_t ip_masked,
>  	uint8_t depth, int32_t sub_rule_index, uint8_t sub_rule_depth)
> { @@ -1483,7 +1483,7 @@ delete_depth_small_v1604(struct rte_lpm *lpm,
> uint32_t ip_masked,
>   * Return of value > -1 means tbl8 is in use but has all the same values and
>   * thus can be recycled
>   */
> -static inline int32_t
> +static int32_t
>  tbl8_recycle_check_v20(struct rte_lpm_tbl_entry_v20 *tbl8,
>  		uint32_t tbl8_group_start)
>  {
> @@ -1530,7 +1530,7 @@ tbl8_recycle_check_v20(struct
> rte_lpm_tbl_entry_v20 *tbl8,
>  	return -EINVAL;
>  }
> 
> -static inline int32_t
> +static int32_t
>  tbl8_recycle_check_v1604(struct rte_lpm_tbl_entry *tbl8,
>  		uint32_t tbl8_group_start)
>  {
> @@ -1577,7 +1577,7 @@ tbl8_recycle_check_v1604(struct
> rte_lpm_tbl_entry *tbl8,
>  	return -EINVAL;
>  }
> 
> -static inline int32_t
> +static int32_t
>  delete_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked,
>  	uint8_t depth, int32_t sub_rule_index, uint8_t sub_rule_depth)
> { @@ -1655,7 +1655,7 @@ delete_depth_big_v20(struct rte_lpm_v20 *lpm,
> uint32_t ip_masked,
>  	return 0;
>  }
> 
> -static inline int32_t
> +static int32_t
>  delete_depth_big_v1604(struct rte_lpm *lpm, uint32_t ip_masked,
>  	uint8_t depth, int32_t sub_rule_index, uint8_t sub_rule_depth)  {


More information about the dev mailing list