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 5276343EB2; Fri, 19 Apr 2024 19:29:58 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id DFF8940A4B; Fri, 19 Apr 2024 19:29:43 +0200 (CEST) Received: from mail-pf1-f181.google.com (mail-pf1-f181.google.com [209.85.210.181]) by mails.dpdk.org (Postfix) with ESMTP id 509B04069F for ; Fri, 19 Apr 2024 19:29:40 +0200 (CEST) Received: by mail-pf1-f181.google.com with SMTP id d2e1a72fcca58-6ecff9df447so2180758b3a.1 for ; Fri, 19 Apr 2024 10:29:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=networkplumber-org.20230601.gappssmtp.com; s=20230601; t=1713547779; x=1714152579; 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=Kg2PCbwdtTsUQ6vMQSsIrhsnoQGMw7xVpkX+ByYWDrw=; b=gioeYdirxpikaShqd9mabqA16Ke2yHVq6jEsTDWC3j+6m+ibHdA08zMXUJI8klwMk4 zPZO+93lAK0mXyHRgomJdzyUo4jWyzwQTnPS8vo1yhQG/wDCakcepYnx8Z89EnOlDHp+ e2+oCFWbuXW2NMRA8Alodsz/7G8WjAw8D96NuhIWvm8wMG5LERkXEyLE47eXiewNy9tr EHYmHcehaagpCPPA2UicSjZxAtc3gvT61tTaHzzjm0JzfuLxeZqyiOUTpI9jtIqmyrI7 Cn9ZOYaPwyG6c6XAgxLXaOsFrkYbKZDeF/xrCnaFqfVx78FUFIjCItbCqe/8vwtsA/hJ VaJw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1713547779; x=1714152579; 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=Kg2PCbwdtTsUQ6vMQSsIrhsnoQGMw7xVpkX+ByYWDrw=; b=CaBs3NqmHjmcHMS3yVAtEDsWX8VVP0nSdeWLtzUfDaStcwSJtjPxRyQRg2RkC4p4AL MwUXTr2M+6y3k6ARyjQPsesmEbG6fiMjx9R1ER2j8LCdDK9g2KzENR27weGssjqGmRy4 InvzMtQ4QPhIxO4La91TaofEc6A6Gu0kflssgkISBoFfb/xm7acPv1BAKsY/jn6BbNdy f2SlN6gB2uyDsF0DwgbEPsUzYhze4i5S4B4akShKIuZ4tRcKKDMdUm5tK4wNTwyc12oE 5BLTwZGoc4X5rEueKdqERaCsTjvevf6n7uj1YCMx+crHKbSbXTcgFZrxGX7mEpHRzivO +M1Q== X-Gm-Message-State: AOJu0YzAn3SXY5F2Alj6J39SMbcV6yspDQZj0ksepKX8FafWA5+BLuU0 UeXvOiUplDoka0am1TrzMjD2Xg3A2S90EAD0Y56LVmiMp4aXDpMuyrqXsQklLniUr9itMoQqsrI p X-Google-Smtp-Source: AGHT+IHyf3vv+6yljEk7tl7msex6FdqSWnhGbtBjFk6GAHQCVUatqlNuZ4SdPWKXMnD4yhOr012Dvg== X-Received: by 2002:a05:6a21:1a9:b0:1a7:91b0:4f14 with SMTP id le41-20020a056a2101a900b001a791b04f14mr3488847pzb.23.1713547779242; Fri, 19 Apr 2024 10:29:39 -0700 (PDT) Received: from hermes.local (204-195-96-226.wavecable.com. [204.195.96.226]) by smtp.gmail.com with ESMTPSA id h16-20020a632110000000b005f3c5cf33b5sm3383074pgh.37.2024.04.19.10.29.38 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 19 Apr 2024 10:29:38 -0700 (PDT) From: Stephen Hemminger To: dev@dpdk.org Cc: Stephen Hemminger , Tyler Retzlaff , Reshma Pattan Subject: [PATCH v4 3/6] latencystats: do not use floating point Date: Fri, 19 Apr 2024 10:28:23 -0700 Message-ID: <20240419172926.55447-4-stephen@networkplumber.org> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20240419172926.55447-1-stephen@networkplumber.org> References: <20240408195036.182545-1-stephen@networkplumber.org> <20240419172926.55447-1-stephen@networkplumber.org> 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 The cycle counts do not need to be stored as floating point. Instead keep track of latency in cycles, and convert to nanoseconds when read. Change Exponential Weighted Moving Average weight from .2 to .25 to avoid use of floating point for that. The average latency took too long to "warm up". Do what RFC 6298 suggests and initialize on first sample. Signed-off-by: Stephen Hemminger Acked-by: Tyler Retzlaff --- lib/latencystats/rte_latencystats.c | 88 +++++++++++++++-------------- 1 file changed, 45 insertions(+), 43 deletions(-) diff --git a/lib/latencystats/rte_latencystats.c b/lib/latencystats/rte_latencystats.c index 55a099c818..6ef8e344bf 100644 --- a/lib/latencystats/rte_latencystats.c +++ b/lib/latencystats/rte_latencystats.c @@ -4,6 +4,7 @@ #include +#include #include #include #include @@ -42,10 +43,10 @@ static uint64_t timer_tsc; static uint64_t prev_tsc; struct rte_latency_stats { - float min_latency; /**< Minimum latency in nano seconds */ - float avg_latency; /**< Average latency in nano seconds */ - float max_latency; /**< Maximum latency in nano seconds */ - float jitter; /** Latency variation */ + uint64_t min_latency; /**< Minimum latency */ + uint64_t avg_latency; /**< Average latency */ + uint64_t max_latency; /**< Maximum latency */ + uint64_t jitter; /** Latency variation */ rte_spinlock_t lock; /** Latency calculation lock */ }; @@ -77,13 +78,12 @@ int32_t rte_latencystats_update(void) { unsigned int i; - float *stats_ptr = NULL; uint64_t values[NUM_LATENCY_STATS] = {0}; int ret; for (i = 0; i < NUM_LATENCY_STATS; i++) { - stats_ptr = RTE_PTR_ADD(glob_stats, - lat_stats_strings[i].offset); + const uint64_t *stats_ptr + = RTE_PTR_ADD(glob_stats, lat_stats_strings[i].offset); values[i] = floor(*stats_ptr / cycles_per_ns); } @@ -100,11 +100,10 @@ static void rte_latencystats_fill_values(struct rte_metric_value *values) { unsigned int i; - float *stats_ptr = NULL; for (i = 0; i < NUM_LATENCY_STATS; i++) { - stats_ptr = RTE_PTR_ADD(glob_stats, - lat_stats_strings[i].offset); + const uint64_t *stats_ptr + = RTE_PTR_ADD(glob_stats, lat_stats_strings[i].offset); values[i].key = i; values[i].value = floor(*stats_ptr / cycles_per_ns); } @@ -151,15 +150,9 @@ calc_latency(uint16_t pid __rte_unused, void *_ __rte_unused) { unsigned int i; - uint64_t now; - float latency; - static float prev_latency; - /* - * Alpha represents degree of weighting decrease in EWMA, - * a constant smoothing factor between 0 and 1. The value - * is used below for measuring average latency. - */ - const float alpha = 0.2; + uint64_t now, latency; + static uint64_t prev_latency; + static bool first_sample = true; now = rte_rdtsc(); @@ -170,32 +163,41 @@ calc_latency(uint16_t pid __rte_unused, latency = now - *timestamp_dynfield(pkts[i]); - /* - * The jitter is calculated as statistical mean of interpacket - * delay variation. The "jitter estimate" is computed by taking - * the absolute values of the ipdv sequence and applying an - * exponential filter with parameter 1/16 to generate the - * estimate. i.e J=J+(|D(i-1,i)|-J)/16. Where J is jitter, - * D(i-1,i) is difference in latency of two consecutive packets - * i-1 and i. - * Reference: Calculated as per RFC 5481, sec 4.1, - * RFC 3393 sec 4.5, RFC 1889 sec. - */ - glob_stats->jitter += (fabsf(prev_latency - latency) - - glob_stats->jitter)/16; - if (glob_stats->min_latency == 0) - glob_stats->min_latency = latency; - else if (latency < glob_stats->min_latency) + if (unlikely(first_sample)) { + first_sample = false; + glob_stats->min_latency = latency; - else if (latency > glob_stats->max_latency) glob_stats->max_latency = latency; - /* - * The average latency is measured using exponential moving - * average, i.e. using EWMA - * https://en.wikipedia.org/wiki/Moving_average - */ - glob_stats->avg_latency += - alpha * (latency - glob_stats->avg_latency); + glob_stats->avg_latency = latency; + glob_stats->jitter = latency / 2; + } else { + /* + * The jitter is calculated as statistical mean of interpacket + * delay variation. The "jitter estimate" is computed by taking + * the absolute values of the ipdv sequence and applying an + * exponential filter with parameter 1/16 to generate the + * estimate. i.e J=J+(|D(i-1,i)|-J)/16. Where J is jitter, + * D(i-1,i) is difference in latency of two consecutive packets + * i-1 and i. + * Reference: Calculated as per RFC 5481, sec 4.1, + * RFC 3393 sec 4.5, RFC 1889 sec. + */ + glob_stats->jitter += ((prev_latency - latency) + - glob_stats->jitter) / 16; + if (latency < glob_stats->min_latency) + glob_stats->min_latency = latency; + if (latency > glob_stats->max_latency) + glob_stats->max_latency = latency; + /* + * The average latency is measured using exponential moving + * average, i.e. using EWMA + * https://en.wikipedia.org/wiki/Moving_average + * + * Alpha is .25 + */ + glob_stats->avg_latency += (latency - glob_stats->avg_latency) / 4; + } + prev_latency = latency; } rte_spinlock_unlock(&glob_stats->lock); -- 2.43.0