From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 3FC3DA04C8; Fri, 18 Sep 2020 15:37:23 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 1E8C31C2FB; Fri, 18 Sep 2020 15:37:23 +0200 (CEST) Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) by dpdk.org (Postfix) with ESMTP id 523B31C2F0; Fri, 18 Sep 2020 15:37:21 +0200 (CEST) IronPort-SDR: rSPIXw7EHwY2I4CKrlTdnwjFRJmOt87n0bmqF6K99jVuC+mxeEg5tmE6Do2l6J2xNDRf96X5Ap JVd/1+Ay7cWA== X-IronPort-AV: E=McAfee;i="6000,8403,9747"; a="139935959" X-IronPort-AV: E=Sophos;i="5.77,274,1596524400"; d="scan'208";a="139935959" X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga107.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 18 Sep 2020 06:37:19 -0700 IronPort-SDR: MYzO/8wK0GoNpvadvxTu5oSC192QirfvGMqHix+lz6a/iN+okZ+N1mGawn+5U319OVnw5zGK0H vQrYRSsE7vLA== X-IronPort-AV: E=Sophos;i="5.77,274,1596524400"; d="scan'208";a="484213247" Received: from fyigit-mobl1.ger.corp.intel.com (HELO [10.213.227.248]) ([10.213.227.248]) by orsmga005-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 18 Sep 2020 06:37:18 -0700 To: "Jiang, JunyuX" , "dev@dpdk.org" Cc: "Guo, Jia" , "Xing, Beilei" , "stable@dpdk.org" References: <20200910015426.3140-1-junyux.jiang@intel.com> <20200916015105.39815-1-junyux.jiang@intel.com> <295e61ad-cbc5-3fbe-c996-c3f9a11b34d6@intel.com> From: Ferruh Yigit Message-ID: <29409c0f-d679-d702-e78e-3cb4def8a92d@intel.com> Date: Fri, 18 Sep 2020 14:37:14 +0100 User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Thunderbird/78.2.2 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 8bit Subject: Re: [dpdk-dev] [dpdk-stable] [PATCH v2] net/i40e: fix incorrect byte counters X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On 9/18/2020 4:44 AM, Jiang, JunyuX wrote: > Hi Ferruh, > >> -----Original Message----- >> From: Ferruh Yigit >> Sent: Wednesday, September 16, 2020 8:31 PM >> To: Jiang, JunyuX ; dev@dpdk.org >> Cc: Guo, Jia ; Xing, Beilei ; >> stable@dpdk.org >> Subject: Re: [dpdk-stable] [PATCH v2] net/i40e: fix incorrect byte counters >> >> On 9/16/2020 2:51 AM, Junyu Jiang wrote: >>> This patch fixed the issue that rx/tx bytes overflowed >> >> "Rx/Tx statistics counters overflowed"? >> > Yes, the rx_bytes and tx_bytes counter in X710 cards is 48-bit long, if keep sending packets for a log time, the register will overflow. > >>> on 48 bit limitation by enlarging the limitation. >>> >>> Fixes: 4861cde46116 ("i40e: new poll mode driver") >>> Cc: stable@dpdk.org >>> >>> Signed-off-by: Junyu Jiang >>> --- >>> drivers/net/i40e/i40e_ethdev.c | 47 >> ++++++++++++++++++++++++++++++++++ >>> drivers/net/i40e/i40e_ethdev.h | 9 +++++++ >>> 2 files changed, 56 insertions(+) >>> >>> diff --git a/drivers/net/i40e/i40e_ethdev.c >>> b/drivers/net/i40e/i40e_ethdev.c index 563f21d9d..4d4ea9861 100644 >>> --- a/drivers/net/i40e/i40e_ethdev.c >>> +++ b/drivers/net/i40e/i40e_ethdev.c >>> @@ -3073,6 +3073,13 @@ i40e_update_vsi_stats(struct i40e_vsi *vsi) >>> i40e_stat_update_48(hw, I40E_GLV_BPRCH(idx), >> I40E_GLV_BPRCL(idx), >>> vsi->offset_loaded, &oes->rx_broadcast, >>> &nes->rx_broadcast); >>> + /* enlarge the limitation when rx_bytes overflowed */ >>> + if (vsi->offset_loaded) { >>> + if (I40E_RXTX_BYTES_LOW(vsi->old_rx_bytes) > nes- >>> rx_bytes) >>> + nes->rx_bytes += (uint64_t)1 << I40E_48_BIT_WIDTH; >>> + nes->rx_bytes += I40E_RXTX_BYTES_HIGH(vsi- >>> old_rx_bytes); >>> + } >>> + vsi->old_rx_bytes = nes->rx_bytes; >> >> >> Can you please describe this logic? (indeed better to describe it in the >> commit log) >> >> 'nes->rx_bytes' is diff in the stats register since last read. >> 'old_rx_bytes' is the previous stats diff. >> >> Why/how "I40E_RXTX_BYTES_LOW(vsi->old_rx_bytes) > nes->rx_bytes" has >> a meaning? Isn't this very depends on the read frequency? >> >> I guess I am missing something but please help me understand. >> > This patch fixes the issue of rx/tx bytes counter register overflow: > The counter register in i40e is 48-bit long, when overflow, nes->rx_bytes becomes less than old_rx_bytes, the correct value of nes->rx_bytes should be plused 1 << 48. > Use I40E_RXTX_BYTES_HIGH() to remember the MSB, nes->rx_bytes plus the MSB is the correct value, So that using uint64_t to enlarge the 48 bit limitation of register . > My bad, 'nes->rx_bytes' is NOT diff in the stats register since last read, it is accumulated stats value since last reset. Above logic make sense now. What do you think creating a function something like 'i40e_stat_update_48_in_64()' and hide all the extension inside it? I think it reduces the clutter. > >> Also can you please confirm the initial value of the "vsi->offset_loaded" is >> correct. >> > offset_loaded will be true when get statistics of port and offset_loaded will be false when reset or clear the statistics, > so if offset_loaded is false, shouldn't to calculate the value of nes->rx_bytes, it will be 0. > >> <....> >> >>> @@ -282,6 +282,9 @@ struct rte_flow { >>> #define I40E_ETH_OVERHEAD \ >>> (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + >> I40E_VLAN_TAG_SIZE * 2) >>> >>> +#define I40E_RXTX_BYTES_HIGH(bytes) ((bytes) & ~I40E_48_BIT_MASK) >>> +#define I40E_RXTX_BYTES_LOW(bytes) ((bytes) & I40E_48_BIT_MASK) >>> + >> >> HIGH/LOW is a little misleading, for 64Bits it sounds like it is getting low 32 bits >> and high 32 bits, can you please clarify macro masks out >> 48/16 bits. >> > Yes, I will change the macro name in V3. >> >>> struct i40e_adapter; >>> struct rte_pci_driver; >>> >>> @@ -399,6 +402,8 @@ struct i40e_vsi { >>> uint8_t vlan_anti_spoof_on; /* The VLAN anti-spoofing enabled */ >>> uint8_t vlan_filter_on; /* The VLAN filter enabled */ >>> struct i40e_bw_info bw_info; /* VSI bandwidth information */ >>> + uint64_t old_rx_bytes; >>> + uint64_t old_tx_bytes; >> >> 'prev' seems better naming than 'old', what do you think renaming >> 'old_rx_bytes' -> 'prev_rx_bytes' (for all variables)? > Yes, it's better, I will fix it in V3. >