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 DE77443C40; Sat, 2 Mar 2024 17:37:38 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 6E3134025C; Sat, 2 Mar 2024 17:37:38 +0100 (CET) Received: from mail-pl1-f174.google.com (mail-pl1-f174.google.com [209.85.214.174]) by mails.dpdk.org (Postfix) with ESMTP id 8E211400D5 for ; Sat, 2 Mar 2024 17:37:36 +0100 (CET) Received: by mail-pl1-f174.google.com with SMTP id d9443c01a7336-1dcd0431f00so22466635ad.3 for ; Sat, 02 Mar 2024 08:37:36 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=networkplumber-org.20230601.gappssmtp.com; s=20230601; t=1709397456; x=1710002256; darn=dpdk.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:from:to:cc:subject:date :message-id:reply-to; bh=ku37BJ2OTC1/pKgUizgXAZlUrNlvEyI5UAmOxOdYtCg=; b=pAslHPUb9k6mXTKOSDNyjjIRNGdYcBdzVNCUIasvySiGz8D4QOzyVXsm2LXqRY6/lP oVUvdwNZI5acenI+jbCYN4dEYTZcMar4Kl+GmHpCLdKabComXeb2qhcscPtOq9bR4SyL psLSB0CeBsI/8G4EE1KhkrwV7Qq5d7oyUQAdCrlBhFMSY0EIEF/ZfsC1V2PFoNTpu+I7 iluFi9odLfwPOvJ0abyxl3YXXsBHa7yhYSqasWaSmutsgTTkrm+L5n3jdqY87oIHvLm3 rlav4oPRkCIDV4iuNDWEiWOPIRq2nAKXKsknW+w7tog+/Q+jvknRyokXyEKs1zShoTxD ssiw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1709397456; x=1710002256; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=ku37BJ2OTC1/pKgUizgXAZlUrNlvEyI5UAmOxOdYtCg=; b=O5nvqt9+Zg6jdHxtYhw5pJBaqlAbjd1U/k5C+Ce5sHVjNiItvFFruwG8Yd+u1rdmls waSyKoXyha7xmEZMD6XaOEivjydbjynMywLj3xR70pI2x7phhZjKlA9Z0ujWLO7djdP0 tbEDyoO6tUIRAFXvFM15YhpcZta+b7+dP0Y6lShM4igKMDGvHLaaqjUrwkK8kXM/5Wfh YPuZDQjs/RA+wA2abnV9iWrqTBKl9v6c4lQTuMdpTRefT1TWZwFiMzOvUDrNyiaZd/vb fcKRhECB4YHEaDmEQkziz4iQZI2U84oZ3wnyq3GSx6utYLY4IgHJexCuuxyoyHN1q3So utyw== X-Forwarded-Encrypted: i=1; AJvYcCWCsxbgx/PlVg8HBd7TY3cqp1TdVSx3lrQ2EE290qGmdf05FM1FayPTbgrp8v1WXl+KXfhK5aJVZS8NVNg= X-Gm-Message-State: AOJu0Yye7OyDptg0QfCL90ATOla6XHBwFB7skEyvNddEfnlgQ+VjNPTa 93W1LSwmy4lwcalV8FSpWFfSBzxSMLV7hY7B9ZYnTL27GY56LdXRVKN/qIRuFnw= X-Google-Smtp-Source: AGHT+IF/w4EqNIkfhrT4033V0tGOEt3N9HZovL08QFK0TXvBoRgOYDHPYKOQmL1ZiFajJ/wv6rsJkw== X-Received: by 2002:a17:902:d503:b0:1dc:dfb7:a6e0 with SMTP id b3-20020a170902d50300b001dcdfb7a6e0mr5292514plg.50.1709397455622; Sat, 02 Mar 2024 08:37:35 -0800 (PST) Received: from hermes.local (204-195-123-141.wavecable.com. [204.195.123.141]) by smtp.gmail.com with ESMTPSA id k12-20020a170902c40c00b001db5ca97817sm5415374plk.68.2024.03.02.08.37.35 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 02 Mar 2024 08:37:35 -0800 (PST) Date: Sat, 2 Mar 2024 08:37:34 -0800 From: Stephen Hemminger To: Morten =?UTF-8?B?QnLDuHJ1cA==?= Cc: Mattias =?UTF-8?B?UsO2bm5ibG9t?= , Subject: Re: [PATCH v2 00/71] replace use of fixed size rte_mempcy Message-ID: <20240302083734.61f40f71@hermes.local> In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35E9F294@smartserver.smartshare.dk> References: <20240229225936.483472-1-stephen@networkplumber.org> <20240301171707.95242-1-stephen@networkplumber.org> <91b581bb-e181-4eac-879c-afd20b7bd6c4@lysator.liu.se> <98CBD80474FA8B44BF855DF32C47DC35E9F294@smartserver.smartshare.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable 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 On Sat, 2 Mar 2024 14:05:45 +0100 Morten Br=C3=B8rup wrote: > > =20 > > > My experience with replacing rte_memcpy() with memcpy() (or vice =20 > > versa) =20 > > > is mixed. > > > > > > I've also tried just dropping the DPDK-custom memcpy() implementation > > > altogether, and that caused a performance drop (in a particular app, = =20 > > on =20 > > > a particular compiler and CPU). =20 >=20 > I guess the compilers are just not where we want them to be yet. >=20 > I don't mind generally replacing rte_memcpy() with memcpy() in the contro= l plane. > But we should use whatever is more efficient in the data plane. >=20 > We must also keep in mind that DPDK supports old distros with old compile= rs. We should not remove a superfluous hand crafted optimization if a suppo= rted old compiler hasn't caught up with it yet, i.e. if it isn't superfluou= s on some of the old compilers supported by DPDK. When I scanned the result. 1. Most copies were small (like Ether address or IPv6 address) and compiler inlining should beat a function call every time. 2. Larger structure copies were in control path.