From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-wm1-f48.google.com (mail-wm1-f48.google.com [209.85.128.48]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id AF58119ABD4 for ; Thu, 3 Apr 2025 17:35:34 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.48 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1743701737; cv=none; b=h7aS3ywjBEWC09zyUulmffVHpQTYUIhGcsKWZacw0upvu+NhY+lVOlwal6Zb3mCMmwn+ps3D/OsLnkZnHO0iwAo68+ZqzkGhE9pOduzeR4wwJK1aAEUcPGjKXCpOqKkeEgR2MD2WPt5GAkIIJTk1FSXjt7130Z0u9KQOcT94drU= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1743701737; c=relaxed/simple; bh=kU3chiQMtLw4Ewijb6//EiNc1pBxUeMTs6ROcMUU6Ks=; h=Message-ID:Date:MIME-Version:Subject:To:Cc:References:From: In-Reply-To:Content-Type; b=nutnvynIW5PHgc38rQgGUcnT+P9zWlw5tRc/3VFazKMl5uP1CpJP1Dc9fgrWnoeFJihP2cMDqB8NidHVDdJEA1UrjmWgexJmt9gtFpwEBJxwIuGmIkGWMP7A9QVsA742lDdw+tRcWTHFVMgdpcaIywhcG7B2Q8Zl9i++MuELGfg= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=XzaJU8hv; arc=none smtp.client-ip=209.85.128.48 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="XzaJU8hv" Received: by mail-wm1-f48.google.com with SMTP id 5b1f17b1804b1-43cebe06e9eso7679185e9.3 for ; Thu, 03 Apr 2025 10:35:34 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1743701733; x=1744306533; darn=vger.kernel.org; h=content-transfer-encoding:in-reply-to:from:content-language :references:cc:to:subject:user-agent:mime-version:date:message-id :from:to:cc:subject:date:message-id:reply-to; bh=rhzKKJXBgb1TBIoFe7QKSNj6y3DYctsVlZae2Uegqx0=; b=XzaJU8hvuHsU1upBSY7Imv0HHsp+fXPdCXYqxGCwtgqQmsPmGz5dnmfOmeGxHsibBN TskoQREn1YAwDtG7V/jn4dZw6RUy/OwUeUVF19Wu2sPtz/BjxKAEHvH+WQjuMpupQQsb v1D06RnPhARIHxpARj858j0HY8fY/YG9+69EpFQLN7LEg9Ct+qR2WHeWV4ZSsgPW8NbE vH4X0ODLONzieexkYz8Wce9dlsFU+2682AYeBHH6Gulh2urNrgIkLIS1CCR/bysmfIRm O84KfHUKygbWclk8xccp5VnC5Z+leVVYBOTP0TYzTtREpp/oNSzVD8TSt805m2L3wK8h 8L3w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1743701733; x=1744306533; h=content-transfer-encoding:in-reply-to:from:content-language :references:cc:to:subject:user-agent:mime-version:date:message-id :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=rhzKKJXBgb1TBIoFe7QKSNj6y3DYctsVlZae2Uegqx0=; b=ci0OAdqz+zDnnkLOJKxEsoZUf0Rk3BEbVr1hPfhiAAznWDhXZ/wTDCHmMFuJ5TCmec 8PFVyjwbRLEEHLx1p7bkMsXqgpa6dH4qSpLijNBhUusluIkKpnk+Xm+g3ysQUYb8kvNJ wnEjaGc01jEWSCdkwQn8DGYnC6bJdcua7WsFlL3XM1rbAjL2gIBuDm/XHHlhgKlzfRXG K9HWCYjZY1p6DcHErV08w2k/YQTJpd8ZWUyc4QMZdfcgddSvJVhZv0YNdHeDM6tzxw3g RmWWwBQgINyO0CfFL6ujgOh0IAoLCR9Y7eB1DlxgKVd03O3L62GN3cpGi1rUbDG4hBt6 Svqg== X-Gm-Message-State: AOJu0YylaVWP8C7gxo1J0vi1tQP3AnpjcYDQfB4g6Fof0bStMh4zHB+A TUO9UgjTS+zCFyl5jAkQ6J0tdSUlm7ruGS+KywgnnVRhPHGTGQW+ X-Gm-Gg: ASbGnctI+zc+p93LRg0s/CvelALcuiFqqQMhuPpu4WCQHKYkR78U0dRcgAtX6NqAEEf SR6FSGeoutmaeyOQ6gUlcpjfmnp4m09VRMCpI3hjANF3/xYNYxnKz6MjIZJc1IqZclF2KVMDZr7 sci89Nj9Z3IOC3kYj3X15U5+vvz/7EuzUMjTG1hqx4gDUwuA6jGkzq5Ufp3lXRLG4DFclyzaKzX RW4Xg+nUXbbqZaShfwU4b2nwT7Go4a6YsQrA632OaP1Vauc/cAb7xvWL5+NkylROsZVSN5gZi01 KE6huB/1BqxUfKHxBm62EszUBZ/kRNZ/6pv5/xdbSAIl5X9mge1L/Y7+UGT1kL6tcucc5D/wY3Y = X-Google-Smtp-Source: AGHT+IEXVNDkb/52ahY7iLo/XYVOiwBAzv9wii66ftxibDb0F/PSMvrhFgJaXWffn4bIh4oWak/u2A== X-Received: by 2002:a05:6000:2506:b0:390:df75:ddc4 with SMTP id ffacd0b85a97d-39cba93377bmr178933f8f.44.1743701732679; Thu, 03 Apr 2025 10:35:32 -0700 (PDT) Received: from [192.168.0.107] (83-228-63-123.ip.btc-net.bg. [83.228.63.123]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-39c30096923sm2378358f8f.17.2025.04.03.10.35.31 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Thu, 03 Apr 2025 10:35:32 -0700 (PDT) Message-ID: Date: Thu, 3 Apr 2025 20:35:30 +0300 Precedence: bulk X-Mailing-List: linux-trace-devel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101 Thunderbird/102.15.1 Subject: Re: [PATCH v3] kernel-shark: Multi-thread the computaion of stream/combo plots To: Libo Chen Cc: linux-trace-devel@vger.kernel.org References: <20250327002133.135719-1-libo.chen@oracle.com> Content-Language: en-US From: Yordan Karadzhov In-Reply-To: <20250327002133.135719-1-libo.chen@oracle.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit The patch is applied. Thanks! Yordan On 3/27/25 02:21, Libo Chen wrote: > Parallelize _newCPUGraph() and _newTaskGraph() calls to dramatically > speed up graph rendering particularly for traces from very large systems. > > OpenMP technically is a new dependency here, but it's part of GCC, so long > as your GCC >= v4.9, the libgomp library will make the code compiled. > > Signed-off-by: Libo Chen > --- > CMakeLists.txt | 6 ++++++ > src/KsGLWidget.cpp | 30 ++++++++++++++++++++++++++---- > 2 files changed, 32 insertions(+), 4 deletions(-) > > diff --git a/CMakeLists.txt b/CMakeLists.txt > index 988bfd6..7847177 100644 > --- a/CMakeLists.txt > +++ b/CMakeLists.txt > @@ -84,6 +84,12 @@ set(EXECUTABLE_OUTPUT_PATH "${KS_DIR}/bin") > set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wall -Wextra -pthread -fPIC -fno-common") > set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall -Wextra -pthread -fPIC -fno-common") > > +find_package(OpenMP 3.2.5) > +if (OPENMP_FOUND) > + set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}") > + set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}") > +endif(OPENMP_FOUND) > + > set(CMAKE_CXX_STANDARD 17) > set(CMAKE_CXX_STANDARD_REQUIRED ON) > set(CMAKE_CXX_EXTENSIONS OFF) > diff --git a/src/KsGLWidget.cpp b/src/KsGLWidget.cpp > index 9311d98..7f2001c 100644 > --- a/src/KsGLWidget.cpp > +++ b/src/KsGLWidget.cpp > @@ -13,6 +13,9 @@ > #include > #include > > +// OpenMP > +#include > + > // KernelShark > #include "libkshark-plugin.h" > #include "KsGLWidget.hpp" > @@ -54,6 +57,7 @@ KsGLWidget::KsGLWidget(QWidget *parent) > > connect(&_model, &QAbstractTableModel::modelReset, > this, qOverload<>(&KsGLWidget::update)); > + omp_set_num_threads(omp_get_num_procs()); > } > > void KsGLWidget::_freeGraphs() > @@ -690,23 +694,41 @@ void KsGLWidget::_makeGraphs() > > for (auto it = _streamPlots.begin(); it != _streamPlots.end(); ++it) { > sd = it.key(); > + size_t nCpus = it.value()._cpuList.count(); > + size_t nTasks = it.value()._taskList.count(); > + QVector cpuGraphs(nCpus); > + QVector taskGraphs(nTasks); > + > /* Create CPU graphs according to the cpuList. */ > it.value()._cpuGraphs = {}; > - for (auto const &cpu: it.value()._cpuList) { > - g = lamAddGraph(sd, _newCPUGraph(sd, cpu), _vSpacing); > + #pragma omp parallel for > + for (size_t idx = 0; idx < nCpus; ++idx) { > + int cpu = it.value()._cpuList[idx]; > + cpuGraphs[idx] = _newCPUGraph(sd, cpu); > + } > + QVectorIterator itCpuGraphs(cpuGraphs); > + while (itCpuGraphs.hasNext()) { > + g = lamAddGraph(sd, itCpuGraphs.next(), _vSpacing); > it.value()._cpuGraphs.append(g); > } > > /* Create Task graphs according to the taskList. */ > it.value()._taskGraphs = {}; > - for (auto const &pid: it.value()._taskList) { > - g = lamAddGraph(sd, _newTaskGraph(sd, pid), _vSpacing); > + #pragma omp parallel for > + for (size_t idx = 0; idx < nTasks; ++idx) { > + int pid = it.value()._taskList[idx]; > + taskGraphs[idx] = _newTaskGraph(sd, pid); > + } > + QVectorIterator itTaskGraphs(taskGraphs); > + while (itTaskGraphs.hasNext()) { > + g = lamAddGraph(sd, itTaskGraphs.next(), _vSpacing); > it.value()._taskGraphs.append(g); > } > } > > for (auto &c: _comboPlots) { > int n = c.count(); > + #pragma omp parallel for > for (int i = 0; i < n; ++i) { > sd = c[i]._streamId; > if (c[i]._type & KSHARK_TASK_DRAW) {