From: "Zhang, Qi Z" <qi.z.zhang@intel.com>
To: "Jiang, JunyuX" <junyux.jiang@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Cc: "Yang, Qiming" <qiming.yang@intel.com>,
"stable@dpdk.org" <stable@dpdk.org>
Subject: Re: [dpdk-stable] [PATCH v2] net/ice: fix incorrect Rx/Tx bytes statistics
Date: Mon, 20 Jul 2020 09:50:49 +0000 [thread overview]
Message-ID: <039ED4275CED7440929022BC67E7061154862515@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <20200717021747.52132-1-junyux.jiang@intel.com>
> -----Original Message-----
> From: Jiang, JunyuX <junyux.jiang@intel.com>
> Sent: Friday, July 17, 2020 10:18 AM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z <qi.z.zhang@intel.com>; Yang, Qiming
> <qiming.yang@intel.com>; Jiang, JunyuX <junyux.jiang@intel.com>;
> stable@dpdk.org
> Subject: [PATCH v2] net/ice: fix incorrect Rx/Tx bytes statistics
>
> This patch fixed the issue that rx/tx bytes overflowed on 40 bit limitation by
> enlarging the limitation.
>
> Fixes: a37bde56314d ("net/ice: support statistics")
> Cc: stable@dpdk.org
>
> Signed-off-by: Junyu Jiang <junyux.jiang@intel.com>
> ---
> drivers/net/ice/ice_ethdev.c | 36 ++++++++++++++++++++++++++++++++++++
> drivers/net/ice/ice_ethdev.h | 4 ++++
> 2 files changed, 40 insertions(+)
>
> diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c index
> 3534d18ca..85aa6cfe6 100644
> --- a/drivers/net/ice/ice_ethdev.c
> +++ b/drivers/net/ice/ice_ethdev.c
> @@ -4139,6 +4139,10 @@ ice_stat_update_40(struct ice_hw *hw, static
> void ice_update_vsi_stats(struct ice_vsi *vsi) {
> + uint64_t old_rx_bytes_h = vsi->old_rx_bytes & ~ICE_40_BIT_MASK;
> + uint64_t old_rx_bytes_l = vsi->old_rx_bytes & ICE_40_BIT_MASK;
> + uint64_t old_tx_bytes_h = vsi->old_tx_bytes & ~ICE_40_BIT_MASK;
> + uint64_t old_tx_bytes_l = vsi->old_tx_bytes & ICE_40_BIT_MASK;
Could you use a macro to replace above variable? so above variable is not necessary
#define ICE_RXTX_BYTES_LOW(bytes) ((bytes) & ICE_40_BIT_MASK);
#define ICE_RXTX_BYTES_HIGH ....
> struct ice_eth_stats *oes = &vsi->eth_stats_offset;
> struct ice_eth_stats *nes = &vsi->eth_stats;
> struct ice_hw *hw = ICE_VSI_TO_HW(vsi); @@ -4156,6 +4160,13 @@
> ice_update_vsi_stats(struct ice_vsi *vsi)
> ice_stat_update_40(hw, GLV_BPRCH(idx), GLV_BPRCL(idx),
> vsi->offset_loaded, &oes->rx_broadcast,
> &nes->rx_broadcast);
> + /* enlarge the limitation when rx_bytes overflowed */
> + if (vsi->offset_loaded) {
> + if (old_rx_bytes_l > nes->rx_bytes)
> + old_rx_bytes_h += (uint64_t)1 << ICE_40_BIT_WIDTH;
> + nes->rx_bytes += old_rx_bytes_h;
> + }
> + vsi->old_rx_bytes = nes->rx_bytes;
> /* exclude CRC bytes */
> nes->rx_bytes -= (nes->rx_unicast + nes->rx_multicast +
> nes->rx_broadcast) * RTE_ETHER_CRC_LEN; @@ -4182,6
> +4193,13 @@ ice_update_vsi_stats(struct ice_vsi *vsi)
> /* GLV_TDPC not supported */
> ice_stat_update_32(hw, GLV_TEPC(idx), vsi->offset_loaded,
> &oes->tx_errors, &nes->tx_errors);
> + /* enlarge the limitation when tx_bytes overflowed */
> + if (vsi->offset_loaded) {
> + if (old_tx_bytes_l > nes->tx_bytes)
> + old_tx_bytes_h += (uint64_t)1 << ICE_40_BIT_WIDTH;
> + nes->tx_bytes += old_tx_bytes_h;
> + }
> + vsi->old_tx_bytes = nes->tx_bytes;
> vsi->offset_loaded = true;
>
> PMD_DRV_LOG(DEBUG, "************** VSI[%u] stats start
> **************", @@ -4206,6 +4224,10 @@ ice_update_vsi_stats(struct
> ice_vsi *vsi) static void ice_read_stats_registers(struct ice_pf *pf, struct
> ice_hw *hw) {
> + uint64_t old_rx_bytes_h = pf->old_rx_bytes & ~ICE_40_BIT_MASK;
> + uint64_t old_rx_bytes_l = pf->old_rx_bytes & ICE_40_BIT_MASK;
> + uint64_t old_tx_bytes_h = pf->old_tx_bytes & ~ICE_40_BIT_MASK;
> + uint64_t old_tx_bytes_l = pf->old_tx_bytes & ICE_40_BIT_MASK;
> struct ice_hw_port_stats *ns = &pf->stats; /* new stats */
> struct ice_hw_port_stats *os = &pf->stats_offset; /* old stats */
>
> @@ -4229,6 +4251,13 @@ ice_read_stats_registers(struct ice_pf *pf, struct
> ice_hw *hw)
> ice_stat_update_32(hw, PRTRPB_RDPC,
> pf->offset_loaded, &os->eth.rx_discards,
> &ns->eth.rx_discards);
> + /* enlarge the limitation when rx_bytes overflowed */
> + if (pf->offset_loaded) {
> + if (old_rx_bytes_l > ns->eth.rx_bytes)
> + old_rx_bytes_h += (uint64_t)1 << ICE_40_BIT_WIDTH;
> + ns->eth.rx_bytes += old_rx_bytes_h;
> + }
> + pf->old_rx_bytes = ns->eth.rx_bytes;
>
> /* Workaround: CRC size should not be included in byte statistics,
> * so subtract RTE_ETHER_CRC_LEN from the byte counter for each rx
> @@ -4259,6 +4288,13 @@ ice_read_stats_registers(struct ice_pf *pf, struct
> ice_hw *hw)
> GLPRT_BPTCL(hw->port_info->lport),
> pf->offset_loaded, &os->eth.tx_broadcast,
> &ns->eth.tx_broadcast);
> + /* enlarge the limitation when tx_bytes overflowed */
> + if (pf->offset_loaded) {
> + if (old_tx_bytes_l > ns->eth.tx_bytes)
> + old_tx_bytes_h += (uint64_t)1 << ICE_40_BIT_WIDTH;
> + ns->eth.tx_bytes += old_tx_bytes_h;
> + }
> + pf->old_tx_bytes = ns->eth.tx_bytes;
> ns->eth.tx_bytes -= (ns->eth.tx_unicast + ns->eth.tx_multicast +
> ns->eth.tx_broadcast) * RTE_ETHER_CRC_LEN;
>
> diff --git a/drivers/net/ice/ice_ethdev.h b/drivers/net/ice/ice_ethdev.h index
> 2bff735ca..69fd35b47 100644
> --- a/drivers/net/ice/ice_ethdev.h
> +++ b/drivers/net/ice/ice_ethdev.h
> @@ -248,6 +248,8 @@ struct ice_vsi {
> struct ice_eth_stats eth_stats_offset;
> struct ice_eth_stats eth_stats;
> bool offset_loaded;
> + uint64_t old_rx_bytes;
> + uint64_t old_tx_bytes;
> };
>
> enum proto_xtr_type {
> @@ -391,6 +393,8 @@ struct ice_pf {
> struct ice_parser_list perm_parser_list;
> struct ice_parser_list dist_parser_list;
> bool init_link_up;
> + uint64_t old_rx_bytes;
> + uint64_t old_tx_bytes;
> };
>
> #define ICE_MAX_QUEUE_NUM 2048
> --
> 2.17.1
next prev parent reply other threads:[~2020-07-20 9:50 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20200715070307.36814-1-junyux.jiang@intel.com>
2020-07-15 7:03 ` [dpdk-stable] [PATCH 1/2] net/ice: fix incorrect Rx " Junyu Jiang
2020-07-15 7:03 ` [dpdk-stable] [PATCH 2/2] net/ice: fix incorrect Tx " Junyu Jiang
2020-07-17 2:17 ` [dpdk-stable] [PATCH v2] net/ice: fix incorrect Rx/Tx " Junyu Jiang
2020-07-20 9:50 ` Zhang, Qi Z [this message]
2020-07-21 7:20 ` [dpdk-stable] [PATCH v3] " Junyu Jiang
2020-07-22 5:19 ` Zhang, Qi Z
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=039ED4275CED7440929022BC67E7061154862515@SHSMSX103.ccr.corp.intel.com \
--to=qi.z.zhang@intel.com \
--cc=dev@dpdk.org \
--cc=junyux.jiang@intel.com \
--cc=qiming.yang@intel.com \
--cc=stable@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).