From owner-freebsd-performance@FreeBSD.ORG Wed Aug 19 10:13:41 2009 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 81E00106568F for ; Wed, 19 Aug 2009 10:13:41 +0000 (UTC) (envelope-from fabrizio.invernizzi@telecomitalia.it) Received: from GRFEDG702BA020.telecomitalia.it (grfedg702ba020.telecomitalia.it [156.54.233.201]) by mx1.freebsd.org (Postfix) with ESMTP id D2C3B8FC15 for ; Wed, 19 Aug 2009 10:13:40 +0000 (UTC) Content-Type: multipart/mixed; boundary="_845582a1-7dd3-48da-9f34-4f3673aeb813_" Received: from GRFHUB701BA020.griffon.local (10.188.101.111) by GRFEDG702BA020.telecomitalia.it (10.188.45.101) with Microsoft SMTP Server (TLS) id 8.1.340.0; Wed, 19 Aug 2009 12:13:38 +0200 Received: from GRFMBX702BA020.griffon.local ([10.188.101.12]) by grfhub701ba020.griffon.local ([10.188.101.111]) with mapi; Wed, 19 Aug 2009 12:13:38 +0200 From: Invernizzi Fabrizio To: "freebsd-performance@freebsd.org" Date: Wed, 19 Aug 2009 12:13:37 +0200 Thread-Topic: Strange CPU distributionat very high level bandwidth Thread-Index: AcogtbfR8rs1r71cRa6H+ejVJ74Tug== Message-ID: <36A93B31228D3B49B691AD31652BCAE9A456967AF4@GRFMBX702BA020.griffon.local> Accept-Language: it-IT, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: acceptlanguage: it-IT, en-US MIME-Version: 1.0 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Subject: Strange CPU distributionat very high level bandwidth X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 19 Aug 2009 10:13:41 -0000 --_845582a1-7dd3-48da-9f34-4f3673aeb813_ Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Hi all i am going on with some performance tests on a 10gbe network card with Free= BSD. I am doing this test: I send UDP traffic to be forwarded to the other port = of the card on both the card ports. Using 1492-long packets i am uppering the number of packets per second i s= ent In order to see wich is the maximum bandwidth (or pps) the system can s= upport without losses. The limit seems to be about 1890Mbps per port (3870 Mbps total). Looking more in deep the CPU behaviour i see this : - uppering the sent pps results in uppering the intterrupt time (about 90= %) - when i am very strict to the limit, interrupt time falls to about 10% a= nd CPU is always (85%) in system (rx/tx driver procedure) Questions: - Is not the AIM intended to contrast this behaviour to limit interrupts se= nt to CPU? (nothing changes if i disable it) - Why does the system start loosing pkts in that condition? - Why does the system seem to perform better when it is managing more conte= xt switches? These are my system details: - HP 380 G5 (XEON X5420, CPU speed: 2.50GHz, BUS speed: 1333 MHz, L2 cache = size: 12 MB, L2 cache speed: 2,5 GHz) with 1 quad-core installed. - Network card: Silicom PE10G2i-LR - Dual Port Fiber (LR) 10 Gigabit Ethern= et PCI Express Server Adapter Intel(r) based (chip 82598EB). - FreeBSD 7.2-RELEASE (64 bit) Driver ixgbe-1.8.6 hw.intr_storm_threshold:2000000 dev.ix.0.low_latency: 128 dev.ix.0.ave_latency: 400 dev.ix.0.bulk_latency: 1200 dev.ix.1.low_latency: 128 dev.ix.1.ave_latency: 400 dev.ix.1.bulk_latency: 1200 ------------------------------------------------------------------ Telecom Italia Fabrizio INVERNIZZI Technology - TILAB Accesso Fisso e Trasporto Via Reiss Romoli, 274 10148 Torino Tel. +39 011 2285497 Mob. +39 3316001344 Fax +39 06 41867287 Questo messaggio e i suoi allegati sono indirizzati esclusivamente alle per= sone indicate. La diffusione, copia o qualsiasi altra azione derivante dall= a conoscenza di queste informazioni sono rigorosamente vietate. Qualora abb= iate ricevuto questo documento per errore siete cortesemente pregati di dar= ne immediata comunicazione al mittente e di provvedere alla sua distruzione= , Grazie. This e-mail and any attachments is confidential and may contain privileged = information intended for the addressee(s) only. Dissemination, copying, pri= nting or use by anybody else is unauthorised. If you are not the intended r= ecipient, please delete this message and any attachments and advise the sen= der by return e-mail, Thanks. [cid:00000000000000000000000000000001@TI.Disclaimer]Rispetta l'ambiente. No= n stampare questa mail se non ? necessario. --_845582a1-7dd3-48da-9f34-4f3673aeb813_--