Return-Path: X-Original-To: apmail-trafficserver-users-archive@www.apache.org Delivered-To: apmail-trafficserver-users-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 63BB710EC5 for ; Sat, 10 Aug 2013 16:16:15 +0000 (UTC) Received: (qmail 49355 invoked by uid 500); 10 Aug 2013 16:16:14 -0000 Delivered-To: apmail-trafficserver-users-archive@trafficserver.apache.org Received: (qmail 46562 invoked by uid 500); 10 Aug 2013 16:16:10 -0000 Mailing-List: contact users-help@trafficserver.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: users@trafficserver.apache.org Delivered-To: mailing list users@trafficserver.apache.org Received: (qmail 46000 invoked by uid 99); 10 Aug 2013 16:16:08 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Sat, 10 Aug 2013 16:16:08 +0000 X-ASF-Spam-Status: No, hits=-0.7 required=5.0 tests=RCVD_IN_DNSWL_LOW,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (nike.apache.org: domain of h.reindl@thelounge.net designates 91.118.73.15 as permitted sender) Received: from [91.118.73.15] (HELO mail.thelounge.net) (91.118.73.15) by apache.org (qpsmtpd/0.29) with ESMTP; Sat, 10 Aug 2013 16:16:02 +0000 Received: from srv-rhsoft.rhsoft.net (openvpn-rh.thelounge.net [10.0.0.241]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by mail.thelounge.net (THELOUNGE MTA) with ESMTPSA id 3cC7ht0v4pz2k for ; Sat, 10 Aug 2013 18:15:42 +0200 (CEST) Message-ID: <5206672D.6080603@thelounge.net> Date: Sat, 10 Aug 2013 18:15:41 +0200 From: Reindl Harald Organization: the lounge interactive design User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130805 Thunderbird/17.0.8 MIME-Version: 1.0 To: users@trafficserver.apache.org Subject: Re: 3.3.5: performance regression? References: <52063E61.8090201@thelounge.net> <153920A9-F441-4991-8034-A2D9DAB46FF0@apache.org> <520658DF.7010402@thelounge.net> <52065F3B.4050109@thelounge.net> In-Reply-To: X-Enigmail-Version: 1.5.2 OpenPGP: id=7F780279; url=http://arrakis.thelounge.net/gpg/h.reindl_thelounge.net.pub.txt Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="Cqc14N8CWPlcBpIOESNW12E0dNm7RuOCi" X-Virus-Checked: Checked by ClamAV on apache.org This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --Cqc14N8CWPlcBpIOESNW12E0dNm7RuOCi Content-Type: text/plain; charset=GB2312 Content-Transfer-Encoding: quoted-printable Am 10.08.2013 18:09, schrieb Yongming Zhao: >=20 > =D4=DA 2013-8-10=A3=AC=CF=C2=CE=E711:41=A3=ACReindl Harald =D0=B4=B5=C0=A3=BA >=20 >> >> Am 10.08.2013 17:32, schrieb Yongming Zhao: >>> if your requested URL is expires very often, then you may hit the=20 >>> read-while-writer performance issue, we have fixed that read-while-wr= iter >>> in V3.3 that will make it really work. >> >> but every 60 seconds is not that often in case of a apache-benchmark >> it's a simple calculation how many cache-hits you can have within >> this 60 seconds by 200 parallel requests of the same URL >> >=20 > we care of the performance, but your case is mixing with the feature=20 > of read-while-writer, if you get to know that read-while-writer may=20 > affect your performance result, that will help us compare the result,=20 > in the better understanding. CONFIG proxy.config.cache.enable_read_while_writer INT 0 does not change anything >>> please compare the Origin Side traffic during the test >> >> the origin is 127.0.0.1:80 but 6 prefork-processes >> while "ab -c 200" is running indicates pretty clear >> that all the work is ATS >> >> [root@testserver:~]$ ps aux | grep httpd | wc -l >> 6 >=20 > I mean, how many requests you get from the origin side during your test= ing, or hit ratio *none* which is pretty clear in case of a preforking-httpd StartServers 3 MinSpareServers 3 MaxSpareServers 5 so the 6 httpd-processes are the master-process and 5 idle workers >>> and you'd better try the compare without expire issue, to make sure w= e have=20 >>> not make critical regression there. >> >> no - if this is a problem now *it is* a critical regression >> >> the only reason trafficserver exists in our infrastructure >> is to buffer high-traffic sites with a lot of images and >> hold back the image-count multiplied with users requests >> from teh preforking-apache >=20 > if you want to enable read while writer, that means you care of the ori= gin side traffic,=20 > and you may need to pay for the performance drop in speed(response time= ) on the proxy,=20 > when that url is getting fetched from the origin please stop to insist in "read while writer" * disable it does not change anything * 100000 requests with 200 parallel are done within the 60 seconds expire= * hence we speak about *one* single URL, only *one* object requested and = cached --Cqc14N8CWPlcBpIOESNW12E0dNm7RuOCi Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.14 (GNU/Linux) Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iEYEARECAAYFAlIGZy0ACgkQhmBjz394AnknRACcDPjyc7N21LL8EQUAzNTbPIxe ILcAn2IBTgIDXJ7zxQ4WYol/xRYkv+bD =hDxq -----END PGP SIGNATURE----- --Cqc14N8CWPlcBpIOESNW12E0dNm7RuOCi--