| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <361B12F0-625B-4148-91EC-A2217679C723@gmail.com>
Date: Fri, 18 Oct 2019 13:45:47 -0700
From: "Jonathan Lemon" <jonathan.lemon@...il.com>
To: "Jesper Dangaard Brouer" <brouer@...hat.com>
Cc: ilias.apalodimas@...aro.org, saeedm@...lanox.com,
tariqt@...lanox.com, netdev@...r.kernel.org, kernel-team@...com
Subject: Re: [PATCH 09/10 net-next] net/mlx5: Add page_pool stats to the
Mellanox driver
On 17 Oct 2019, at 4:09, Jesper Dangaard Brouer wrote:
> On Wed, 16 Oct 2019 15:50:27 -0700
> Jonathan Lemon <jonathan.lemon@...il.com> wrote:
>
>> Replace the now deprecated inernal cache stats with the page pool
>> stats.
>
> I can see that the stats you introduced are useful, but they have to
> be
> implemented in way that does not hurt performance.
They're not noticeable, but even if they were, they are needed
for production, otherwise there's no way to identify problems.
I can separate the ring consume/produce counters so they
are always separated by a cache line distance.
>> # ethtool -S eth0 | grep rx_pool
>> rx_pool_cache_hit: 1646798
>> rx_pool_cache_full: 0
>> rx_pool_cache_empty: 15723566
>> rx_pool_ring_produce: 474958
>> rx_pool_ring_consume: 0
>> rx_pool_ring_return: 474958
>> rx_pool_flush: 144
>> rx_pool_node_change: 0
>>
>> Showing about a 10% hit rate for the page pool.
>
> What is the workload from above stats?
Network traffic from a proxygen load balancer. From
this, we see the ptr_ring is completely unused except
for flushing operations.
--
Jonathan
>
>
>> Signed-off-by: Jonathan Lemon <jonathan.lemon@...il.com>
>> ---
>> drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 +
>> .../net/ethernet/mellanox/mlx5/core/en_main.c | 1 +
>> .../ethernet/mellanox/mlx5/core/en_stats.c | 39
>> ++++++++++++-------
>> .../ethernet/mellanox/mlx5/core/en_stats.h | 19 +++++----
>> 4 files changed, 35 insertions(+), 25 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h
>> b/drivers/net/ethernet/mellanox/mlx5/core/en.h
>> index 2e281c755b65..b34519061d12 100644
>> --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
>> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
>> @@ -50,6 +50,7 @@
>> #include <net/xdp.h>
>> #include <linux/dim.h>
>> #include <linux/bits.h>
>> +#include <net/page_pool.h>
>> #include "wq.h"
>> #include "mlx5_core.h"
>> #include "en_stats.h"
>> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
>> b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
>> index 2b828de1adf0..f10b5838fb17 100644
>> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
>> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
>> @@ -551,6 +551,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel
>> *c,
>> pp_params.nid = cpu_to_node(c->cpu);
>> pp_params.dev = c->pdev;
>> pp_params.dma_dir = rq->buff.map_dir;
>> + pp_params.stats = &rq->stats->pool;
>>
>> /* page_pool can be used even when there is no rq->xdp_prog,
>> * given page_pool does not handle DMA mapping there is no
>> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
>> b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
>> index ac6fdcda7019..ad42d965d786 100644
>> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
>> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
>> @@ -102,11 +102,14 @@ static const struct counter_desc
>> sw_stats_desc[] = {
>> { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
>> { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks)
>> },
>> { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts)
>> },
>> - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_reuse) },
>> - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_full) },
>> - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
>> - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
>> - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_cache_hit) },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_cache_full) },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_cache_empty) },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_ring_produce)
>> },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_ring_consume)
>> },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_ring_return) },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_flush) },
>> + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pool_node_change) },
>> { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
>> { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
>> { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
>> @@ -214,11 +217,14 @@ static void mlx5e_grp_sw_update_stats(struct
>> mlx5e_priv *priv)
>> s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
>> s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
>> s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
>> - s->rx_cache_reuse += rq_stats->cache_reuse;
>> - s->rx_cache_full += rq_stats->cache_full;
>> - s->rx_cache_empty += rq_stats->cache_empty;
>> - s->rx_cache_busy += rq_stats->cache_busy;
>> - s->rx_cache_waive += rq_stats->cache_waive;
>> + s->rx_pool_cache_hit += rq_stats->pool.cache_hit;
>> + s->rx_pool_cache_full += rq_stats->pool.cache_full;
>> + s->rx_pool_cache_empty += rq_stats->pool.cache_empty;
>> + s->rx_pool_ring_produce += rq_stats->pool.ring_produce;
>> + s->rx_pool_ring_consume += rq_stats->pool.ring_consume;
>> + s->rx_pool_ring_return += rq_stats->pool.ring_return;
>> + s->rx_pool_flush += rq_stats->pool.flush;
>> + s->rx_pool_node_change += rq_stats->pool.node_change;
>> s->rx_congst_umr += rq_stats->congst_umr;
>> s->rx_arfs_err += rq_stats->arfs_err;
>> s->rx_recover += rq_stats->recover;
>> @@ -1446,11 +1452,14 @@ static const struct counter_desc
>> rq_stats_desc[] = {
>> { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
>> { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks)
>> },
>> { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts)
>> },
>> - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_reuse) },
>> - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_full) },
>> - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
>> - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
>> - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.cache_hit) },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.cache_full) },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.cache_empty) },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.ring_produce)
>> },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.ring_consume)
>> },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.ring_return) },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.flush) },
>> + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pool.node_change) },
>> { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
>> { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
>> { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
>> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
>> b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
>> index 79f261bf86ac..7d6001969400 100644
>> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
>> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
>> @@ -109,11 +109,14 @@ struct mlx5e_sw_stats {
>> u64 rx_buff_alloc_err;
>> u64 rx_cqe_compress_blks;
>> u64 rx_cqe_compress_pkts;
>> - u64 rx_cache_reuse;
>> - u64 rx_cache_full;
>> - u64 rx_cache_empty;
>> - u64 rx_cache_busy;
>> - u64 rx_cache_waive;
>> + u64 rx_pool_cache_hit;
>> + u64 rx_pool_cache_full;
>> + u64 rx_pool_cache_empty;
>> + u64 rx_pool_ring_produce;
>> + u64 rx_pool_ring_consume;
>> + u64 rx_pool_ring_return;
>> + u64 rx_pool_flush;
>> + u64 rx_pool_node_change;
>> u64 rx_congst_umr;
>> u64 rx_arfs_err;
>> u64 rx_recover;
>> @@ -245,14 +248,10 @@ struct mlx5e_rq_stats {
>> u64 buff_alloc_err;
>> u64 cqe_compress_blks;
>> u64 cqe_compress_pkts;
>> - u64 cache_reuse;
>> - u64 cache_full;
>> - u64 cache_empty;
>> - u64 cache_busy;
>> - u64 cache_waive;
>> u64 congst_umr;
>> u64 arfs_err;
>> u64 recover;
>> + struct page_pool_stats pool;
>> };
>>
>> struct mlx5e_sq_stats {
>
>
>
> --
> Best regards,
> Jesper Dangaard Brouer
> MSc.CS, Principal Kernel Engineer at Red Hat
> LinkedIn: http://www.linkedin.com/in/brouer
Powered by blists - more mailing lists