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 5BAF1A0503 for ; Fri, 20 May 2022 10:35:01 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id E4B3F427ED; Fri, 20 May 2022 10:35:00 +0200 (CEST) Received: from mail-oi1-f181.google.com (mail-oi1-f181.google.com [209.85.167.181]) by mails.dpdk.org (Postfix) with ESMTP id B362B40222 for ; Fri, 20 May 2022 10:34:58 +0200 (CEST) Received: by mail-oi1-f181.google.com with SMTP id v66so9220887oib.3 for ; Fri, 20 May 2022 01:34:58 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=mime-version:from:date:message-id:subject:to; bh=jgVbeW/l5d+JANsbkIoEvPXDNXLGeOL/7+e7dwLqsKU=; b=RbLvIjujNh9/c5xQgDSaQCpsh3gMWYOwIvzWSUui86CropanoXqaaQnDkRCXBB31vv zjDLMXcSAgZs0hfRsJNthMXJl1AbPyJqwrhbLpR59ApBMFQzvvjFCiMjfaaULaq+vTWt 2z77hQx8n8i3Bt02oJhH3A1TiV69foWe6kPNQV4wyynpMmV6GFOcpsrEsIDnZU2mg51c yhG7Hrum7qsiBuA/9cLGkCswxvyz6rrXAA0lJaSJPoy0l335EvzicZUgW5RmVDw/rlzF aNQQXxxG4JmL0ErfvkxTsHPzpE0DjMk4m+Ev7rezIK6ZOvabDEol2Cc08yWyemSh27iI 3aWg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:mime-version:from:date:message-id:subject:to; bh=jgVbeW/l5d+JANsbkIoEvPXDNXLGeOL/7+e7dwLqsKU=; b=0u182HyL/gR19O9lO6zPbOstvR2nEV9n8Wd/kN01+xdnLgq+yeFAooLdIl79qEM9mv JImDRmkbqo6tuZmCjA/iirAg8puyY4YNtLL0tT4PAZREyVyvjxDgUJyF8YYHVLRF8+1X BRtfkicrj6TEVDuftAcpk32GrWIKUNZTr9iN1+lsZtrxrzg6gqP9zcCc6gpeWdtFn2qV Z//8hM/x9R5JFgDUbMHRDWTmPiyu9VnvtPd9ur/xAuyoD8OaRCLYRUtR9y2yNJdIHVnR 0NQNi+or/bKm77jtIFYVubsNYc1gdowsq/7tfyUEsxgGLLA07YYn5i9sS/W/SJODDkRI JS7g== X-Gm-Message-State: AOAM531CEzxj+y5JiC1A+xvjki1Sey2DpXanNOx+LD898XGD65acCN1p NaBd5FrYC47eMpKqgZjg5kYcxeUJR16X2aGYqZHbZjsb7WQ= X-Google-Smtp-Source: ABdhPJzq7eU6aowThAUgtGg8O3qEOzTrJRquwIzV9iv9f266brYtvYZJkjHLL9R9j0zJwegm0lggpIjTGCluWNrvfAE= X-Received: by 2002:aca:a8d7:0:b0:328:b19f:dbac with SMTP id r206-20020acaa8d7000000b00328b19fdbacmr4980547oie.243.1653035697513; Fri, 20 May 2022 01:34:57 -0700 (PDT) MIME-Version: 1.0 From: Antonio Di Bacco Date: Fri, 20 May 2022 10:34:46 +0200 Message-ID: Subject: Optimizing memory access with DPDK allocated memory To: users@dpdk.org Content-Type: multipart/alternative; boundary="0000000000008d28c705df6d5d49" X-BeenThere: users@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK usage discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: users-bounces@dpdk.org --0000000000008d28c705df6d5d49 Content-Type: text/plain; charset="UTF-8" Let us say I have two memory channels each one with its own 16GB memory module, I suppose the first memory channel will be used when addressing physical memory in the range 0 to 0x4 0000 0000 and the second when addressing physical memory in the range 0x4 0000 0000 to 0x7 ffff ffff. Correct? Now, I need to have a 2GB buffer with one "writer" and one "reader", the writer writes on half of the buffer (call it A) and, in the meantime, the reader reads on the other half (B). When the writer finishes writing its half buffer (A), signal it to the reader and they swap, the reader starts to read from A and writer starts to write to B. If I allocate the whole buffer (on two 1GB hugepages) across the two memory channels, one half of the buffer is allocated on the end of first channel while the other half is allocated on the start of the second memory channel, would this increase performances compared to the whole buffer allocated within the same memory channel? --0000000000008d28c705df6d5d49 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Let us say I have two memory channels each one with its ow= n 16GB memory module,=C2=A0I suppose the first memory channel will be used = when addressing physical memory in the range 0 to 0x4 0000 0000 and the sec= ond when addressing physical=C2=A0memory in the range 0x4 0000 0000 to=C2= =A0 0x7 ffff ffff.=C2=A0 Correct?
Now, I need to have a 2GB buffer with= one "writer" and one "reader", the writer writes on ha= lf of the buffer (call it A) and, in the meantime, the reader reads on the = other half (B). When the writer finishes writing its half buffer (A), signa= l it to the reader and they swap,=C2=A0 the reader starts to read from A an= d writer starts to write to B.
If I allocate the whole=C2=A0buffer (on = two 1GB hugepages) across the two memory channels, one half of the buffer i= s allocated on the end of first channel while the other half is allocated o= n the start of the second memory channel, would this increase performances= =C2=A0compared to the whole buffer allocated within the same memory channel= ?


--0000000000008d28c705df6d5d49--