From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 3FDD345A9E; Wed, 2 Oct 2024 18:58:56 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 7740C4064C; Wed, 2 Oct 2024 18:58:52 +0200 (CEST) Received: from mail-wr1-f51.google.com (mail-wr1-f51.google.com [209.85.221.51]) by mails.dpdk.org (Postfix) with ESMTP id B6F5240616 for ; Wed, 2 Oct 2024 18:58:51 +0200 (CEST) Received: by mail-wr1-f51.google.com with SMTP id ffacd0b85a97d-37ce8458ae3so28460f8f.1 for ; Wed, 02 Oct 2024 09:58:51 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1727888331; x=1728493131; darn=dpdk.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=097tv44whgm8NlW4/pvNtBVFjTfAKs/+i9ES/OkSWXw=; b=PDiBZ6RMh/DLLIntRGJamwzzKTp5EZw/bkyGvVObLwYaneFr3VwlyvOkkBMHPFk7ik 23pP+X7DxYREtCcAWFnkcEtizEpRyFkYS+x+IhbVv4kF9qVh+9FCJr39K5rrdH8rXxMS mkNqwaCLrne9f/AanU+OHuF4saEmB0g8Df/aiohNS/12P/JTrOVhzCpsgiP/KpBIl7tl +DTaeTpXwhF+9EomHUjYvEseGkPWSyWPuuHpi2qjSuO9dtC1vms4t0C+T2TUZUZTkChL K0QsLYEL8J/uBHBB32Qnyl0HiW9jPwvPz0clyq2/NH9s1do+wEsfZl0tugVCI/ummnrQ RZdA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1727888331; x=1728493131; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=097tv44whgm8NlW4/pvNtBVFjTfAKs/+i9ES/OkSWXw=; b=OnSaTPQjWu7D1q65D8hA/gaQHUVASWV0xcedo+r2Vq4IkmfajH/z4/IAflkzzONyPe LBoq2zXbrAJOfz230XSlndK7ykSM7m5vBiZmlHWdn1vUHP07kQ6x7U9ZgFXEnQIej1oD toKR3ktREyhfRg1f5fda1Y8YY9h7gR5AneUjfQD1XlS2yE9XPRM+TPEnkUTi7t/TPNls 4b8k+D8Fi2p8O1iiSKFmTI5KVzcaTKLuyXS5mQqiZPD1vuJ5KzC/h7eKAIPMjmJ1DTdL cUk9tXN6cv1kq1NgciI2i4XGp3wE1QVnUpuYiPdnbRsL2GRL0WE48ZGT7dYoEKk6RKyT pFgQ== X-Gm-Message-State: AOJu0YwPMK2geAD2C93707XafHDoSxa6/iwiK0b/GZCSn+FTKFLqU/TQ GT3SYuysPSgt35iW7iHbDULqLzv8+rewfnE3GB3iLFcTFnNW+KV+iC0MHZcJ X-Google-Smtp-Source: AGHT+IGsyK5bYtLQrdMLDqq3LcvLIGvZxaLpA326GfJbJoBRICWbmCTl7ddTasaYvZ0SFrbzZd/H/w== X-Received: by 2002:adf:e712:0:b0:37c:d1c6:7e45 with SMTP id ffacd0b85a97d-37cfba0a614mr2971517f8f.40.1727888330679; Wed, 02 Oct 2024 09:58:50 -0700 (PDT) Received: from localhost.localdomain (85-250-29-188.bb.netvision.net.il. [85.250.29.188]) by smtp.googlemail.com with ESMTPSA id a640c23a62f3a-a93c2777254sm889947166b.9.2024.10.02.09.58.49 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 02 Oct 2024 09:58:50 -0700 (PDT) From: Isaac Boukris To: dev@dpdk.org Cc: stephen@networkplumber.org, bruce.richardson@intel.com, roretzla@linux.microsoft.com, dmitry.kozliuk@gmail.com, david.marchand@redhat.com, Isaac Boukris Subject: [PATCH v4 1/2] timer: lower rounding of TSC estimation to 100KHz Date: Wed, 2 Oct 2024 19:56:35 +0300 Message-ID: <20241002165840.341116-2-iboukris@gmail.com> X-Mailer: git-send-email 2.45.0 In-Reply-To: <20241002165840.341116-1-iboukris@gmail.com> References: <20240921140022.107239-1-iboukris@gmail.com> <20241002165840.341116-1-iboukris@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org In practice, the frequency is often not a nice round number, while the estimation results are rather accurate, just a couple of KHz away from the kernel's tsc_khz value, so it should suffice. Rounding to 10MHz can cause a significant drift from real time, up to a second per 10 minutes. See also bugzilla: 959 Signed-off-by: Isaac Boukris --- lib/eal/linux/eal_timer.c | 6 +++--- lib/eal/windows/eal_timer.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/lib/eal/linux/eal_timer.c b/lib/eal/linux/eal_timer.c index 1cb1e92193..f56a7ae15b 100644 --- a/lib/eal/linux/eal_timer.c +++ b/lib/eal/linux/eal_timer.c @@ -192,7 +192,7 @@ get_tsc_freq(void) { #ifdef CLOCK_MONOTONIC_RAW #define NS_PER_SEC 1E9 -#define CYC_PER_10MHZ 1E7 +#define CYC_PER_100KHZ 1E5 struct timespec sleeptime = {.tv_nsec = NS_PER_SEC / 10 }; /* 1/10 second */ @@ -209,8 +209,8 @@ get_tsc_freq(void) double secs = (double)ns/NS_PER_SEC; tsc_hz = (uint64_t)((end - start)/secs); - /* Round up to 10Mhz. 1E7 ~ 10Mhz */ - return RTE_ALIGN_MUL_NEAR(tsc_hz, CYC_PER_10MHZ); + /* Round up to 100Khz. 1E5 ~ 100Khz */ + return RTE_ALIGN_MUL_NEAR(tsc_hz, CYC_PER_100KHZ); } #endif return 0; diff --git a/lib/eal/windows/eal_timer.c b/lib/eal/windows/eal_timer.c index b070cb7751..4003541b08 100644 --- a/lib/eal/windows/eal_timer.c +++ b/lib/eal/windows/eal_timer.c @@ -12,7 +12,7 @@ #include "eal_private.h" #define US_PER_SEC 1E6 -#define CYC_PER_10MHZ 1E7 +#define CYC_PER_100KHZ 1E5 void rte_delay_us_sleep(unsigned int us) @@ -81,8 +81,8 @@ get_tsc_freq(void) double secs = ((double)elapsed_us.QuadPart)/US_PER_SEC; tsc_hz = (uint64_t)((end - start)/secs); - /* Round up to 10Mhz. 1E7 ~ 10Mhz */ - return RTE_ALIGN_MUL_NEAR(tsc_hz, CYC_PER_10MHZ); + /* Round up to 100Khz. 1E5 ~ 100Khz */ + return RTE_ALIGN_MUL_NEAR(tsc_hz, CYC_PER_100KHZ); } -- 2.45.0