From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 00:44:10 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E4F60171 for ; Sun, 4 Nov 2012 00:44:10 +0000 (UTC) (envelope-from lists@eitanadler.com) Received: from mail-la0-f54.google.com (mail-la0-f54.google.com [209.85.215.54]) by mx1.freebsd.org (Postfix) with ESMTP id 5246B8FC0A for ; Sun, 4 Nov 2012 00:44:09 +0000 (UTC) Received: by mail-la0-f54.google.com with SMTP id e12so4238178lag.13 for ; Sat, 03 Nov 2012 17:44:09 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=eitanadler.com; s=0xdeadbeef; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type; bh=RpkhL/JOmXYlBn8dOlz0L0KJCVHzzUNBozkYkQz+RH0=; b=QBEqujTO5gQGY1mTfTUoXH5AeyMq7n6dgOFOVjmspiu0vanPwMnHQQmCKGnNmEGNok rc/epbjtwQrwtQMMYG0meFey4SlEH2+KpB73W9AZA6HxaKE15e90sRdU+1ZcRS1LAMU2 a8OPLd7Z+gEWAg7zPoRrdf2wJ3dfbjlw30DEU= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type:x-gm-message-state; bh=RpkhL/JOmXYlBn8dOlz0L0KJCVHzzUNBozkYkQz+RH0=; b=ge1A3EE7eCmZxYZ9+7iZGYqaZDV7pYYHg/WSQpTEO7YMVb9z2podQlBFh1xIzW9xug 5RZ5XaqZIp7EOsE/OC8VLNz+Rp5YxC9ODo3DNcpLz1aBSF+ifz/X8R+fu6rKFmxxsf44 3ST+thNC9OsuKyOqa2AB9ORVLurPFCYGdTJICxCpFWYohS6SDfuGbq+HW1AREoUhS5Dx EE3IbR0p19FukWvEMeGkN5U/ZHeSFHQ4WbcZS2HVJprlKnYc9ImW6PuC3F9ATplfS3iD ePzXBUnsO/392OO6QhskPRm45N4nRJTPzbLRT60+HKqN2DZU2oK+rcOJ55zXliWwyPfv NRWw== Received: by 10.152.104.115 with SMTP id gd19mr5497710lab.13.1351989848948; Sat, 03 Nov 2012 17:44:08 -0700 (PDT) MIME-Version: 1.0 Received: by 10.112.25.166 with HTTP; Sat, 3 Nov 2012 17:43:38 -0700 (PDT) In-Reply-To: References: From: Eitan Adler Date: Sat, 3 Nov 2012 20:43:38 -0400 Message-ID: Subject: Re: r2421600 amd64 /var/db/pkg To: Darrel Content-Type: text/plain; charset=UTF-8 X-Gm-Message-State: ALoCoQk5QtkPR8xTSjgQ0Da87CmsYJfUGPKmirThgA10s1Yg+vVFTx+XEzo5Z4ocpPO5RVwDs20c Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 00:44:11 -0000 On 3 November 2012 20:37, Darrel wrote: > >>> Is it possible to regenerate the package database or somehow start over? >>> I >>> am seeing errors like these: >>> >>> pkg_info: Don't use the pkg_ tools if you are using pkgng >>> pkg_info: the package info for package 'ca_root_nss-3.14' is corrupt >> >> >> have you run ever run pkg2ng ? >> > > Hi, Eitan. > > It could be that I had a case of bad luck. About an hour before the > documentation was put into /usr/ports/UPDATING, I noticed that portmaster > was not working and 'make deinstall' and 'make reinstall' and ticked > 'pkgng'. Then portmaster seemed to work alright. > > Then when the UPDATING entry 20121010 happened shortly after, I followed it > exactly- so yes I ran pkg2ng. Somehow my installation has both The moment you run pkg2ng you lose any right to use pkg_* tools - this is what the first warning is telling you. I have a patch awaiting approval which makes the error more clear. -- Eitan Adler From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 00:37:57 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 15C4391 for ; Sun, 4 Nov 2012 00:37:57 +0000 (UTC) (envelope-from levitch@iglou.com) Received: from rdsmtp.iglou.com (rdsmtp.iglou.com [192.107.41.63]) by mx1.freebsd.org (Postfix) with ESMTP id B86988FC0C for ; Sun, 4 Nov 2012 00:37:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=iglou.com; s=alpha; h=Content-Type:MIME-Version:References:Message-ID:In-Reply-To:Subject:cc:To:From:Date; bh=56Qk91atTMqklokM7Tv+Gaqc1qTbTNdnJ//0gbty/FA=; b=uivsU4CeQRC9gDIGhgALc7jy2aMKtNR63KRMarPoVp9NPX6UCQqmGeIhtK8DWd0bVH030yJ+8OMqnAsEuA4xb0I7aAiVElzWfG7aI+ncD1MWWG5uPx10BI2rkozpxd9oHBmKCi1IvxFt47GnbyO8mV3GT7liLeJjbi3sj4TNYsc=; Received: from iglou1.iglou.com ([192.107.41.3]:43488 helo=mail.iglou.com) by rdsmtp.iglou.com with esmtpa (Exim MTA/8.19.3) (envelope-from ) id 1TUoDs-0003XR-4X by authid with igloumta_auth for current@freebsd.org; Sat, 03 Nov 2012 20:37:56 -0400 Received: from shell1.iglou.com ([192.107.41.17]:36178 helo=shell1) by mail.iglou.com with esmtps (TLS cipher TLSv1:AES256-SHA:256) (Exim MTA/8.19.3) (envelope-from ) id 1TUoDr-0007Wp-MG; Sat, 03 Nov 2012 20:37:55 -0400 Date: Sat, 3 Nov 2012 20:37:55 -0400 (EDT) From: Darrel X-X-Sender: levitch@shell1 To: Eitan Adler Subject: Re: r2421600 amd64 /var/db/pkg In-Reply-To: Message-ID: References: User-Agent: Alpine 2.00 (GSO 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Originating-IP: 192.107.41.17 X-IgLou-Customer: 3cb6f76205bd20f518810676a67a982b X-Mailman-Approved-At: Sun, 04 Nov 2012 00:48:37 +0000 Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 00:37:57 -0000 >> Is it possible to regenerate the package database or somehow start over? I >> am seeing errors like these: >> >> pkg_info: Don't use the pkg_ tools if you are using pkgng >> pkg_info: the package info for package 'ca_root_nss-3.14' is corrupt > > have you run ever run pkg2ng ? > Hi, Eitan. It could be that I had a case of bad luck. About an hour before the documentation was put into /usr/ports/UPDATING, I noticed that portmaster was not working and 'make deinstall' and 'make reinstall' and ticked 'pkgng'. Then portmaster seemed to work alright. Then when the UPDATING entry 20121010 happened shortly after, I followed it exactly- so yes I ran pkg2ng. Somehow my installation has both portmaster-3.14 *and* portmaster-3.14_7 installed. Perhaps my portmaster upgrade prior to following the UPDATING entry 20121010 broke something. I can guess that my database is messed up. Thanks for your reply, Darrel From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 01:14:08 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B4417DA0; Sun, 4 Nov 2012 01:14:08 +0000 (UTC) (envelope-from null@pozo.com) Received: from pozo.com (pozo.com [216.101.162.50]) by mx1.freebsd.org (Postfix) with ESMTP id 813798FC0C; Sun, 4 Nov 2012 01:14:08 +0000 (UTC) Received: from T61p.pozo.com (t61p.pozo.com [192.168.0.4]) (authenticated bits=0) by pozo.com (8.14.5/8.14.5) with ESMTP id qA41DfLn001577 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NOT); Sat, 3 Nov 2012 18:13:41 -0700 (PDT) (envelope-from null@pozo.com) Message-Id: <201211040113.qA41DfLn001577@pozo.com> X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Sat, 03 Nov 2012 18:13:20 -0700 To: Adrian Chadd From: Manfred Antar Subject: Re: weird network problems on current since 10/28/2012 In-Reply-To: References: <201211031740.qA3HeqVX001622@pozo.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" X-Spam-Status: No, score=-0.9 required=5.0 tests=ALL_TRUSTED,MISSING_MID autolearn=no version=3.3.2, No X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on pozo.com X-pozocom-MailScanner-Information: Please contact the ISP for more information X-pozocom-MailScanner-ID: qA41DfLn001577 X-pozocom-MailScanner: Found to be clean X-pozocom-MailScanner-From: null@pozo.com Cc: freebsd-current@freebsd.org, andre@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 01:14:08 -0000 At 03:29 PM 11/3/2012, Adrian Chadd wrote: >On 3 November 2012 10:40, Manfred Antar wrote: >> i have problem connecting to freebsd box on local network since last sunday. >> the last kernel that works: >> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >> anything after that, sometimes i can connect, other times just hangs. >> any network connection hangs ===== pop httpd ssh etc etc. >> anyone have any ideas ? >> i can checkout different sources and see if i can locate the changes that cause this. > >Please do! > > > >adrian OK Here is what I found doing : setenv CVSROOT /usr/home/ncvs cvs co -D"October 28, 2012 12:14:38 PDT" sys A kernel from that time works fine. doing: cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later the following files were changed: sys/netinet/tcp_input.c sys/netinet/tcp_timer.c sys/netinet/tcp_var.h Building a kernel from these new files is when the problem starts. ======================== || null@pozo.com || || Ph. (415) 681-6235 || ======================== -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 03:30:26 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D7F6786C for ; Sun, 4 Nov 2012 03:30:26 +0000 (UTC) (envelope-from bright@mu.org) Received: from elvis.mu.org (elvis.mu.org [192.203.228.196]) by mx1.freebsd.org (Postfix) with ESMTP id B207C8FC08 for ; Sun, 4 Nov 2012 03:30:26 +0000 (UTC) Received: from kruse-124.4.ixsystems.com (drawbridge.ixsystems.com [206.40.55.65]) by elvis.mu.org (Postfix) with ESMTPSA id F34D11A3C1C; Sat, 3 Nov 2012 20:30:24 -0700 (PDT) Message-ID: <5095E156.7000309@mu.org> Date: Sat, 03 Nov 2012 20:30:30 -0700 From: Alfred Perlstein User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7; rv:16.0) Gecko/20121026 Thunderbird/16.0.2 MIME-Version: 1.0 To: "Samuel J. Greear" Subject: Re: DragonFly vs FreeBSD scheduler References: <509531DF.6050108@mu.org> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-current@freebsd.org, Alie Tan X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 03:30:27 -0000 On 11/3/12 7:02 PM, Samuel J. Greear wrote: >> Looks like a few specific benchmarks that DragonFly aimed to do well at that >> we were unawares of. >> > Unawares of? http://bsd.slashdot.org/story/08/03/06/1313218/freebsd-70-bests-linux-in-smp-performance > The FreeBSD project made hay with sysbench and pgbench not that long ago. > >> Not sure, didn't see DragonFly sharing the results with us until this paper >> was published although I may have missed that. >> > Is the DragonFly project under some obligation to share its results > with the FreeBSD developers? My takeaway is that this conversation is dumb. -Alfred From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 01:15:08 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B870BEB3 for ; Sun, 4 Nov 2012 01:15:08 +0000 (UTC) (envelope-from levitch@iglou.com) Received: from rdsmtp.iglou.com (rdsmtp.iglou.com [192.107.41.63]) by mx1.freebsd.org (Postfix) with ESMTP id 6E0878FC15 for ; Sun, 4 Nov 2012 01:15:08 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=iglou.com; s=alpha; h=Content-Type:MIME-Version:References:Message-ID:In-Reply-To:Subject:cc:To:From:Date; bh=5L1O6R+tN6xSU6OUKTh+MOR/eQ3VrlUcKwmV2BzW/GY=; b=EMr3ZpBgIWdRIDPQ98PvuWja4KaikLtwmY1xMZQFils7KyjIfgtZDxG3BiLzZhpJxXDSAsQiraOpa7mLJzhknr91wRmk0SAzw/6TirEvtHBDJie9c5zf0/C8ufBzGjqAT4oWZw7rPouSwY8Q2cd4pPjmmwk2eDUMij4nLxjhLTo=; Received: from iglou1.iglou.com ([192.107.41.3]:50456 helo=mail.iglou.com) by rdsmtp.iglou.com with esmtpa (Exim MTA/8.19.3) (envelope-from ) id 1TUonr-0005wZ-Rn by authid with igloumta_auth for current@freebsd.org; Sat, 03 Nov 2012 21:15:07 -0400 Received: from shell1.iglou.com ([192.107.41.17]:36239 helo=shell1) by mail.iglou.com with esmtps (TLS cipher TLSv1:AES256-SHA:256) (Exim MTA/8.19.3) (envelope-from ) id 1TUonr-0002CZ-Cy; Sat, 03 Nov 2012 21:15:07 -0400 Date: Sat, 3 Nov 2012 21:15:07 -0400 (EDT) From: Darrel X-X-Sender: levitch@shell1 To: Eitan Adler Subject: Re: r2421600 amd64 /var/db/pkg In-Reply-To: Message-ID: References: User-Agent: Alpine 2.00 (GSO 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Originating-IP: 192.107.41.17 X-IgLou-Customer: 3cb6f76205bd20f518810676a67a982b X-Mailman-Approved-At: Sun, 04 Nov 2012 04:50:21 +0000 Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 01:15:08 -0000 >>>> >>>> pkg_info: Don't use the pkg_ tools if you are using pkgng >>>> pkg_info: the package info for package 'ca_root_nss-3.14' is corrupt >>> >>> >>> have you run ever run pkg2ng ? >>> >> >> Hi, Eitan. >> >> It could be that I had a case of bad luck. About an hour before the >> documentation was put into /usr/ports/UPDATING, I noticed that portmaster >> was not working and 'make deinstall' and 'make reinstall' and ticked >> 'pkgng'. Then portmaster seemed to work alright. >> >> Then when the UPDATING entry 20121010 happened shortly after, I followed it >> exactly- so yes I ran pkg2ng. Somehow my installation has both > > The moment you run pkg2ng you lose any right to use pkg_* tools - > this is what the first warning is telling you. > I have a patch awaiting approval which makes the error more clear. > Yes, the existing man 8 pkg does not seem to match all of the facts. Darrel From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 04:56:09 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id F42332A5 for ; Sun, 4 Nov 2012 04:56:08 +0000 (UTC) (envelope-from yanegomi@gmail.com) Received: from mail-oa0-f54.google.com (mail-oa0-f54.google.com [209.85.219.54]) by mx1.freebsd.org (Postfix) with ESMTP id ABFDE8FC0A for ; Sun, 4 Nov 2012 04:56:08 +0000 (UTC) Received: by mail-oa0-f54.google.com with SMTP id n9so6053372oag.13 for ; Sat, 03 Nov 2012 21:56:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=SOmagVgc5CliEay+7kxRhK33aBwS94zBmAhFPkdt3kk=; b=Lu+75mLB5/3YVJ8BFbHCQxxx3GdJOsCnk8b+e3iTYmgfxA5KHlispETnGTKdS8I8R2 T0aCgTEOYjalvk484ZZNROyQtFCAirG9FfAfdg8liglt9HK/fOJsnwyV4/1LPfj3srko BbcH3X3WkY8+8OmeT9mzx5Yp4RjCbOm3Nu/K4uU7QP7C9HMOeyBPPtCIoMriCO+maUHb KzZjXYDbI6+Jc4EpKpvxpt4XeeSkvr3nU5gBCjZuR9KuDggDSwE7ePpOpxUuG6kCZn80 n/yukrXnX9Q+ukCSdaRJRi6jIUw2cufbiguj/mPksCFwfl+Sl1Ia1DycWm+tOTLW2CP2 Wxhg== MIME-Version: 1.0 Received: by 10.182.131.100 with SMTP id ol4mr4959181obb.38.1352004967863; Sat, 03 Nov 2012 21:56:07 -0700 (PDT) Received: by 10.76.143.33 with HTTP; Sat, 3 Nov 2012 21:56:07 -0700 (PDT) In-Reply-To: References: Date: Sat, 3 Nov 2012 21:56:07 -0700 Message-ID: Subject: Re: r2421600 amd64 /var/db/pkg From: Garrett Cooper To: Darrel Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: Eitan Adler , current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 04:56:09 -0000 On Sat, Nov 3, 2012 at 6:15 PM, Darrel wrote: ... > Yes, the existing man 8 pkg does not seem to match all of the facts. > What you probably ran into is the common chicken and egg problem where if pkgng is upgraded ports, it blows up when it tries to deinstall the package, or similarly, when portmaster is upgraded, it doesn't halt the upgrade and restart it properly. It's most likely still a problem; I'm going to doublecheck to make sure that's the case and file PRs if it is. Thanks, -Garrett From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 02:02:03 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4B39DB84 for ; Sun, 4 Nov 2012 02:02:03 +0000 (UTC) (envelope-from sjg@evilcode.net) Received: from mail-vb0-f54.google.com (mail-vb0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id ED7A78FC18 for ; Sun, 4 Nov 2012 02:02:02 +0000 (UTC) Received: by mail-vb0-f54.google.com with SMTP id l1so6360173vba.13 for ; Sat, 03 Nov 2012 19:02:01 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:x-gm-message-state; bh=LSCxwJOODqBdnWn7MxoxxxAPja9BkrQjcmu2MSyMy7M=; b=Nash+NbO+4GZhTf9UYG89OSSHUpBwJfocY3WMJ7Xu+0q6SrrgUg4ItOj2isu2y85v5 4Drk1ME/O1522otKbT6jOd41La6PZBYhjyI0wZscmnnPmOR7xPPj8lzFTjXQkrHgLlkf jAzlStqwjMbG1NVWzAGJaz+PKCjJUs0m6wpd9Iu3Q6O4RmRg2lWw3tVWBtaOsI8VTs5Q 4mCbKkUc5NHWD4RuXvXqTflbNkYZNhLj0sjx193VnXstx87vw3K9ceYRsyjIClgnVt7R m0YoGBEy1KIznW/Nw3jrNzEzU5PrP8P6Nih/MlMs9R0am/xB0Mg6oz6oFFyr50WMFPdB sI3w== MIME-Version: 1.0 Received: by 10.52.92.97 with SMTP id cl1mr5097183vdb.65.1351994521744; Sat, 03 Nov 2012 19:02:01 -0700 (PDT) Received: by 10.220.3.136 with HTTP; Sat, 3 Nov 2012 19:02:01 -0700 (PDT) In-Reply-To: <509531DF.6050108@mu.org> References: <509531DF.6050108@mu.org> Date: Sat, 3 Nov 2012 20:02:01 -0600 Message-ID: Subject: Re: DragonFly vs FreeBSD scheduler From: "Samuel J. Greear" To: Alfred Perlstein Content-Type: text/plain; charset=ISO-8859-1 X-Gm-Message-State: ALoCoQnCgJG+OtbazJ68YlAZePhgpOzyDljCKhzmtBqsCsd+OZP0UcDY4RE480e0l/ZIUwSYG7lD X-Mailman-Approved-At: Sun, 04 Nov 2012 04:57:46 +0000 Cc: freebsd-current@freebsd.org, Alie Tan X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 02:02:03 -0000 > Looks like a few specific benchmarks that DragonFly aimed to do well at that > we were unawares of. > Unawares of? http://bsd.slashdot.org/story/08/03/06/1313218/freebsd-70-bests-linux-in-smp-performance The FreeBSD project made hay with sysbench and pgbench not that long ago. > Not sure, didn't see DragonFly sharing the results with us until this paper > was published although I may have missed that. > Is the DragonFly project under some obligation to share its results with the FreeBSD developers? > -Alfred From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 09:43:21 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 86580530 for ; Sun, 4 Nov 2012 09:43:21 +0000 (UTC) (envelope-from swhetzel@gmail.com) Received: from mail-ea0-f182.google.com (mail-ea0-f182.google.com [209.85.215.182]) by mx1.freebsd.org (Postfix) with ESMTP id 08BF58FC12 for ; Sun, 4 Nov 2012 09:43:20 +0000 (UTC) Received: by mail-ea0-f182.google.com with SMTP id c10so2362061eaa.13 for ; Sun, 04 Nov 2012 01:43:14 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=TecccP5x4jGkK4VydkAsstm/6mbxWZFcJSO5h8U0Vk0=; b=Ij9Vqy05w6sV79GQ6KHGRQWk3i9YWqKnh46wW6tyF4yI2DdDbyAwtF2DAqr2lNXoFz uR71JPxQKJ5ZfGCg71R0Od8g6fBF5lFd7+BgC9UQky6K3CRftPExdXF9tVf2tCVghVEr oG0+hIdXg9cdpKmyTkYtlawu6tqGDOFLB4XmL+sILenrKpvg56i3vO8GKSt7NoDFMc9p FqMyhFFMiIx3vs3xVcat9LQ2558er2/SRto/AUDtJ1g67pI0sP1JyEqdod0VKPgF7PRG b27g9tbub4cAjuYwdxJ6IOyuyY/Rq6/9aTodEnGAcNBeZzAxMQAqVRkhelBbSNXVnDz0 2c9A== MIME-Version: 1.0 Received: by 10.14.182.9 with SMTP id n9mr25052665eem.24.1352022193991; Sun, 04 Nov 2012 01:43:13 -0800 (PST) Received: by 10.14.188.136 with HTTP; Sun, 4 Nov 2012 01:43:13 -0800 (PST) In-Reply-To: <20121103232433.00005eee@unknown> References: <20121103232433.00005eee@unknown> Date: Sun, 4 Nov 2012 03:43:13 -0600 Message-ID: Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? From: Scot Hetzel To: Alexander Leidinger Content-Type: text/plain; charset=ISO-8859-1 Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 09:43:21 -0000 On Sat, Nov 3, 2012 at 5:24 PM, Alexander Leidinger wrote: > Hi, > > while trying to update from r239708 to r242511 (amd64 arch) I tried to > compile the world with "make -j8". After a short while I got an > internal error in the clang compile (this is a gcc-compiled system, I > don't use clang). The CFLAGS/COPTFLAGS are -O2 -pipe. > > Without the -j8 it compiles just fine. > Without the CPUTYPE?=native it compiles even with -j8. > > The CPU is an Intel(R) Xeon(R) CPU (L5630) with ECC ram. > > The r239708 world runs stable since I installed it (build with > CPUTYPE=native). The r242511 world (no CPUTYPE set) doesn't run stable > (not only the watchdogd segfault I reported in another mail some minutes > ago, but also some other kind of reboot every X minutes I haven't > investigated yet). > > Does someone run -current on a similar system on a similar revision and > can comment about the stability? > Not sure if your hitting the same bug, that was found in PR 112997. When you set CPUTYPE?=native, bsd.cpu.mk doesn't set MACHINE_CPU to the correct values for your CPUTYPE. See http://www.freebsd.org/cgi/query-pr.cgi?pr=conf/112997 for a patch to bsd.cpu.mk. Does your system compile correctly, if you specify the CPUTYPE? Scot From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 11:21:35 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 03A9DB9C; Sun, 4 Nov 2012 11:21:35 +0000 (UTC) (envelope-from dimitry@andric.com) Received: from tensor.andric.com (tensor.andric.com [87.251.56.140]) by mx1.freebsd.org (Postfix) with ESMTP id AC61C8FC0A; Sun, 4 Nov 2012 11:21:34 +0000 (UTC) Received: from [IPv6:2001:7b8:3a7:0:d48d:da6b:2080:d1e7] (unknown [IPv6:2001:7b8:3a7:0:d48d:da6b:2080:d1e7]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by tensor.andric.com (Postfix) with ESMTPSA id 3C0C65C59; Sun, 4 Nov 2012 12:21:33 +0100 (CET) Message-ID: <50964FBB.4010600@andric.com> Date: Sun, 04 Nov 2012 12:21:31 +0100 From: Dimitry Andric User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:17.0) Gecko/17.0 Thunderbird/17.0 MIME-Version: 1.0 To: Manfred Antar Subject: Re: weird network problems on current since 10/28/2012 References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> In-Reply-To: <201211040113.qA41DfLn001577@pozo.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Adrian Chadd , freebsd-current@freebsd.org, Andre Oppermann X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 11:21:35 -0000 On 2012-11-04 02:13, Manfred Antar wrote: > At 03:29 PM 11/3/2012, Adrian Chadd wrote: >> On 3 November 2012 10:40, Manfred Antar wrote: >>> i have problem connecting to freebsd box on local network since last sunday. >>> the last kernel that works: >>> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >>> anything after that, sometimes i can connect, other times just hangs. >>> any network connection hangs ===== pop httpd ssh etc etc. >>> anyone have any ideas ? >>> i can checkout different sources and see if i can locate the changes that cause this. >> >> Please do! ... > Here is what I found doing : > setenv CVSROOT /usr/home/ncvs > > cvs co -D"October 28, 2012 12:14:38 PDT" sys > > A kernel from that time works fine. > > doing: > > cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later > the following files were changed: > sys/netinet/tcp_input.c > sys/netinet/tcp_timer.c > sys/netinet/tcp_var.h > > Building a kernel from these new files is when the problem starts. So, your problems seem to have been introduced by this commit by Andre: http://svn.freebsd.org/changeset/base/242266 Increase the initial CWND to 10 segments as defined in IETF TCPM draft-ietf-tcpm-initcwnd-05. It explains why the increased initial window improves the overall performance of many web services without risking congestion collapse. As long as it remains a draft it is placed under a sysctl marking it as experimental: net.inet.tcp.experimental.initcwnd10 = 1 When it becomes an official RFC soon the sysctl will be changed to the RFC number and moved to net.inet.tcp. This implementation differs from the RFC draft in that it is a bit more conservative in the case of packet loss on SYN or SYN|ACK because we haven't reduced the default RTO to 1 second yet. Also the restart window isn't yet increased as allowed. Both will be adjusted with upcoming changes. Is is enabled by default. In Linux it is enabled since kernel 3.0. After the commit, there was a small discussion thread on svn-src-head@ about the possible problems with the approach. Maybe you are experiencing those? As the commit message says, you should be able to turn the feature off using: sysctl net.inet.tcp.experimental.initcwnd10=0 Can you please try that, and see if the problems go away? From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 11:32:08 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id CF503E52 for ; Sun, 4 Nov 2012 11:32:08 +0000 (UTC) (envelope-from andre@freebsd.org) Received: from c00l3r.networx.ch (c00l3r.networx.ch [62.48.2.2]) by mx1.freebsd.org (Postfix) with ESMTP id 30C2D8FC0A for ; Sun, 4 Nov 2012 11:32:07 +0000 (UTC) Received: (qmail 39000 invoked from network); 4 Nov 2012 13:07:57 -0000 Received: from c00l3r.networx.ch (HELO [127.0.0.1]) ([62.48.2.2]) (envelope-sender ) by c00l3r.networx.ch (qmail-ldap-1.03) with SMTP for ; 4 Nov 2012 13:07:57 -0000 Message-ID: <50965236.6040009@freebsd.org> Date: Sun, 04 Nov 2012 12:32:06 +0100 From: Andre Oppermann User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:16.0) Gecko/20121010 Thunderbird/16.0.1 MIME-Version: 1.0 To: Manfred Antar Subject: Re: weird network problems on current since 10/28/2012 References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> In-Reply-To: <201211040113.qA41DfLn001577@pozo.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Adrian Chadd , freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 11:32:09 -0000 On 04.11.2012 02:13, Manfred Antar wrote: > At 03:29 PM 11/3/2012, Adrian Chadd wrote: >> On 3 November 2012 10:40, Manfred Antar wrote: >>> i have problem connecting to freebsd box on local network since last sunday. >>> the last kernel that works: >>> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >>> anything after that, sometimes i can connect, other times just hangs. >>> any network connection hangs ===== pop httpd ssh etc etc. >>> anyone have any ideas ? >>> i can checkout different sources and see if i can locate the changes that cause this. >> >> Please do! >> >> >> >> adrian > > OK > Here is what I found doing : > setenv CVSROOT /usr/home/ncvs > > cvs co -D"October 28, 2012 12:14:38 PDT" sys > > A kernel from that time works fine. > > doing: > > cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later > the following files were changed: > sys/netinet/tcp_input.c > sys/netinet/tcp_timer.c > sys/netinet/tcp_var.h > > Building a kernel from these new files is when the problem starts. Can you please provide one or more tcpdump from a failing kernel? Also please enable sysctl net.inet.tcp.logdebug=1 and capture LOG_DEBUG output from syslogd. That may give some important information as well. -- Andre From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 11:47:15 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 98BDB2ED; Sun, 4 Nov 2012 11:47:15 +0000 (UTC) (envelope-from yerenkow@gmail.com) Received: from mail-oa0-f54.google.com (mail-oa0-f54.google.com [209.85.219.54]) by mx1.freebsd.org (Postfix) with ESMTP id 3484F8FC12; Sun, 4 Nov 2012 11:47:15 +0000 (UTC) Received: by mail-oa0-f54.google.com with SMTP id n9so6193902oag.13 for ; Sun, 04 Nov 2012 03:47:14 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=v0uEJooRv/gVSe1yoBPnWtvUlftIgnGiuDBqw9kX6hY=; b=VZKSQFSfnJ9eYvzzwyP28zUeI2jhsBOxuLB0DEE4HMrpcvsxk6IP3DWPZmKSG+dJIh Fo8JkYfKV8o3n5VyskHP9SjIcw0kE84e91LmOX2y3hC+t3L3iwR96hDrHlckRIMhzqQc NNBaK28hItv1IPwamSu/easOu0Jvx3jVuU/aS242/4Hjsw7F7GEUccTEOhvCAs5z4GYB N0IKtJlXftYzA+ZY9qMVkDEatSfzOruJZwSIlsurBG9/UPZmAO1M79oSqMqkRUSuMImc 1ruDmmZEfbHwCAX2BGX0N2xqVRgxFB9R4KdtXwqQ/ricFscRRb9xl/c4UvEU6A9YyZn5 pb4A== MIME-Version: 1.0 Received: by 10.182.145.35 with SMTP id sr3mr5377963obb.98.1352029634259; Sun, 04 Nov 2012 03:47:14 -0800 (PST) Received: by 10.60.58.165 with HTTP; Sun, 4 Nov 2012 03:47:14 -0800 (PST) In-Reply-To: <50965236.6040009@freebsd.org> References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50965236.6040009@freebsd.org> Date: Sun, 4 Nov 2012 13:47:14 +0200 Message-ID: Subject: Re: weird network problems on current since 10/28/2012 From: Alexander Yerenkow To: Andre Oppermann Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: Adrian Chadd , freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 11:47:15 -0000 Could this be same problem - PR/173309 ? -- Regards, Alexander Yerenkow From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 12:13:44 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7F24693C; Sun, 4 Nov 2012 12:13:44 +0000 (UTC) (envelope-from hatanou@infolab.ne.jp) Received: from moon.infolab.ne.jp (unknown [IPv6:2001:3e0:90c::1]) by mx1.freebsd.org (Postfix) with ESMTP id DCEE48FC0A; Sun, 4 Nov 2012 12:13:40 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by moon.infolab.ne.jp (8.14.5/8.14.5) with ESMTP id qA4CDb0X035948; Sun, 4 Nov 2012 21:13:37 +0900 (JST) (envelope-from hatanou@infolab.ne.jp) Date: Sun, 04 Nov 2012 21:13:36 +0900 (JST) Message-Id: <20121104.211336.244701604.hatanou@infolab.ne.jp> To: freebsd-stable@freebsd.org Subject: Re: SU+J on 9.1-RC2 ISO From: HATANO Tomomi In-Reply-To: <5095B89F.4070705@freebsd.org> References: <20121103190930.GA23145@icarus.home.lan> <5095B89F.4070705@freebsd.org> Mime-Version: 1.0 Content-Type: Multipart/Mixed; boundary="--Next_Part(Sun_Nov__4_21_13_36_2012_719)--" Content-Transfer-Encoding: 7bit Cc: jdc@koitsu.org, b.smeelen@ose.nl, fnwhitehorn@freebsd.org, freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 12:13:44 -0000 ----Next_Part(Sun_Nov__4_21_13_36_2012_719)-- Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Hi all. The point is: There is completely no way to take a snapshot of SU+J partition unless modify one's kernel. Whether some issue still exist or not, how about enabling snapshoting SU+J partition through sysctl variable? Would you mind to see patch attached? 1. Taking a snapshot of SU+J partition is controlled through sysctl variable. 2. Default to disable. One who want to enable it should set the variable manually. 3. The default value in bsdinstall(8) may be left as is. -- HATANO Tomomi. ----Next_Part(Sun_Nov__4_21_13_36_2012_719)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="snapsuj.patch" --- src/sys/ufs/ffs/ffs_snapshot.c.orig 2012-11-04 11:01:58.000000000 +0900 +++ src/sys/ufs/ffs/ffs_snapshot.c 2012-11-04 11:13:32.000000000 +0900 @@ -182,8 +182,10 @@ */ int dopersistence = 0; -#ifdef DEBUG #include +int snapsuj = 0; +SYSCTL_INT(_debug, OID_AUTO, snapsuj, CTLFLAG_RW, &snapsuj, 0, ""); +#ifdef DEBUG SYSCTL_INT(_debug, OID_AUTO, dopersistence, CTLFLAG_RW, &dopersistence, 0, ""); static int snapdebug = 0; SYSCTL_INT(_debug, OID_AUTO, snapdebug, CTLFLAG_RW, &snapdebug, 0, ""); @@ -230,7 +232,7 @@ * At the moment, journaled soft updates cannot support * taking snapshots. */ - if (MOUNTEDSUJ(mp)) { + if (MOUNTEDSUJ(mp) && (snapsuj == 0)) { vfs_mount_error(mp, "%s: Snapshots are not yet supported when " "running with journaled soft updates", fs->fs_fsmnt); return (EOPNOTSUPP); ----Next_Part(Sun_Nov__4_21_13_36_2012_719)---- From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 12:16:01 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D176EB7C; Sun, 4 Nov 2012 12:16:01 +0000 (UTC) (envelope-from w8hdkim@gmail.com) Received: from mail-vc0-f182.google.com (mail-vc0-f182.google.com [209.85.220.182]) by mx1.freebsd.org (Postfix) with ESMTP id 59CA78FC0A; Sun, 4 Nov 2012 12:16:01 +0000 (UTC) Received: by mail-vc0-f182.google.com with SMTP id fw7so6674439vcb.13 for ; Sun, 04 Nov 2012 04:16:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:date:message-id:subject:from:to:cc:content-type; bh=qblL1B5AQsZj5ioS+a0waQ85TYKIqibksI6+34EOsNg=; b=IXa57ApSO7PlbzdE8mJUpctbLNzam19+RTvDKiAGBHRz9JLc6Gfg+t1rhEx09FS8Es se4BmEayPdkepxgBgpGFjJVZ4iMDbKJlulcC4bHrAKUupNinxEF0Fb9c3qQQOv2sh3uU dLfKf5muMZ50ctsYN8K9lRmV1CeeS3JT6TzSwn+bDclpi4rZQATxll2biR3VD8GOdxDe VoQ7i/jleOT422wCKoSmi8X/koVGAn6GP+oG/w4wT4vNJxdrUwtQAyT2pN40V33NLvwn xZcGcqcWz/wB6GOI+FA1C1/Ng10UVi9aljGFyAfX9NbgXPpRZMim2XNwVhPF+vpGFkft YP/Q== MIME-Version: 1.0 Received: by 10.58.155.169 with SMTP id vx9mr6938122veb.45.1352031361131; Sun, 04 Nov 2012 04:16:01 -0800 (PST) Received: by 10.58.226.163 with HTTP; Sun, 4 Nov 2012 04:16:01 -0800 (PST) Date: Sun, 4 Nov 2012 07:16:01 -0500 Message-ID: Subject: Re: weird network problems on current since 10/28/2012 From: Kim Culhan To: Dimitry Andric Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: Adrian Chadd , freebsd-current@freebsd.org, Andre Oppermann X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 12:16:02 -0000 On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: > On 2012-11-04 02:13, Manfred Antar wrote: >> At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>> On 3 November 2012 10:40, Manfred Antar wrote: >>>> i have problem connecting to freebsd box on local network since last sunday. >>>> the last kernel that works: >>>> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >>>> anything after that, sometimes i can connect, other times just hangs. >>>> any network connection hangs ===== pop httpd ssh etc etc. >>>> anyone have any ideas ? >>>> i can checkout different sources and see if i can locate the changes that cause >>>> this. >>> >>> Please do! > ... >> Here is what I found doing : >> setenv CVSROOT /usr/home/ncvs >> >> cvs co -D"October 28, 2012 12:14:38 PDT" sys >> >> A kernel from that time works fine. >> >> doing: >> >> cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later >> the following files were changed: >> sys/netinet/tcp_input.c >> sys/netinet/tcp_timer.c >> sys/netinet/tcp_var.h >> >> Building a kernel from these new files is when the problem starts. > > So, your problems seem to have been introduced by this commit by Andre: > > http://svn.freebsd.org/changeset/base/242266 > > Increase the initial CWND to 10 segments as defined in IETF TCPM > draft-ietf-tcpm-initcwnd-05. It explains why the increased initial > window improves the overall performance of many web services without > risking congestion collapse. > > As long as it remains a draft it is placed under a sysctl marking it > as experimental: > net.inet.tcp.experimental.initcwnd10 = 1 > When it becomes an official RFC soon the sysctl will be changed to > the RFC number and moved to net.inet.tcp. > > This implementation differs from the RFC draft in that it is a bit > more conservative in the case of packet loss on SYN or SYN|ACK because > we haven't reduced the default RTO to 1 second yet. Also the restart > window isn't yet increased as allowed. Both will be adjusted with > upcoming changes. > > Is is enabled by default. In Linux it is enabled since kernel 3.0. > > After the commit, there was a small discussion thread on svn-src-head@ > about the possible problems with the approach. Maybe you are > experiencing those? > > As the commit message says, you should be able to turn the feature off > using: > > sysctl net.inet.tcp.experimental.initcwnd10=0 > > Can you please try that, and see if the problems go away? FWIW this did not make the problem go away here. thanks -kim -- From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 12:42:29 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E104BFBD; Sun, 4 Nov 2012 12:42:29 +0000 (UTC) (envelope-from naylor.b.david@gmail.com) Received: from mail-we0-f182.google.com (mail-we0-f182.google.com [74.125.82.182]) by mx1.freebsd.org (Postfix) with ESMTP id 0D5998FC0C; Sun, 4 Nov 2012 12:42:28 +0000 (UTC) Received: by mail-we0-f182.google.com with SMTP id x43so2753960wey.13 for ; Sun, 04 Nov 2012 04:42:22 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=from:to:subject:date:user-agent:cc:references:in-reply-to :mime-version:content-type:content-transfer-encoding:message-id; bh=zyg6aJ6WgoRP4/qHIiHk4W2pwOl+XIJMN7Etktm0Q/U=; b=hHanh9ywabyrWbU6jQYPeV1Uf1FEwT2qe/dnwZP4o9laLSuWIRKr2s0Oh1s1JZ+3V/ cPLz66hmb/sOvnw7p+a5RmurxSod2ABt/dAlVjmah/WQTN/WaQp9OwdEo2wKAsTJ+zdD igm0wJN5iYNKgSQHRyZuxYhLAbwU9Xwq6A8jSFHZKH4/v8ZMrcR0A5bTpobitZKU2mYN Yh5I7+fPGsGon6v9eVIcx7nELzjt+HKVY1/ATjuhp+W5ZubG+f98kWy/bfEEnMhkMB0z 59uUPgOo9kR+v5h55TJ0Z4y+JLldp//8bGhjPh+ur+jM51EzWcMRSHMlL3d5VBbRFXR4 /2PA== Received: by 10.216.137.94 with SMTP id x72mr2234022wei.187.1352032942367; Sun, 04 Nov 2012 04:42:22 -0800 (PST) Received: from dragon.dg (41-132-211-149.dsl.mweb.co.za. [41.132.211.149]) by mx.google.com with ESMTPS id j8sm6088405wiy.9.2012.11.04.04.42.19 (version=TLSv1/SSLv3 cipher=OTHER); Sun, 04 Nov 2012 04:42:21 -0800 (PST) From: David Naylor To: Jan Beich Subject: Re: November 5th is Clang-Day Date: Sun, 4 Nov 2012 14:42:13 +0200 User-Agent: KMail/1.13.7 (FreeBSD/9.1-PRERELEASE; KDE/4.9.1; amd64; ; ) References: <20121102032945.GF65074@lor.one-eyed-alien.net> <201211030948.43530.naylor.b.david@gmail.com> <1TUlad-0008bB-OF@internal.tormail.org> In-Reply-To: <1TUlad-0008bB-OF@internal.tormail.org> MIME-Version: 1.0 Content-Type: multipart/signed; boundary="nextPart5521153.u17xfddALF"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit Message-Id: <201211041442.16620.naylor.b.david@gmail.com> Cc: David Chisnall , freebsd-current@freebsd.org, Brooks Davis X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 12:42:30 -0000 --nextPart5521153.u17xfddALF Content-Type: Text/Plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable On Saturday, 3 November 2012 23:47:54 Jan Beich wrote: > David Naylor writes: > > There are two issues here: 1) wine compiled with clang, and 2) wine > > (compiled with gcc) running on clang compiled base. > >=20 > > Regarding 1), according to the wiki [1], wine does have stack alignment > > issues and some wine programs do not run when compiled with clang [2][3] > > and other bugs with clang cause freezing within wine [4][5]. The > > impression I get is that, using the work-a-round of stack realignment, > > wine does work to some extent when compiled by clang. >=20 > Took me some time but now I can confirm that clang-built wine-1.5.16 > works fine for me with gcc-built lib32 (i.e. ld-elf32.so.1 + /usr/lib32). >=20 > > Regarding 2) (which I believe Jan was referring to), when I have a gcc > > built world and just replace lib32 with clang built libraries I have > > winecfg and regedit launching but displaying black screens. Switching > > back to gcc built lib32 I get a working winecfg and regedit. This, to > > me, indicates a clang error somewhere. >=20 > My experience varies between clang-built and gcc-built wine. >=20 > # clang, quick crash >=20 > # gcc, black rectangle >=20 > So, why not switch stack alignment in wine (upstream)? This would make > /stable/9 wine package continue to work on /head. >=20 > Here's my wine package built with and without the patch. >=20 > # sha256: cef5e543a5c534acb7237634224561863122ab3c256df319c6428856266d79fd > http://ompldr.org/vZzR0bw/4byte-clang-wine-fbsd64-1.5.16,1.txz > # sha256: 68e402bf7cb39ea48b9bef7772422cf476e89b214fd3b98ced37e0068f588c6c > http://ompldr.org/vZzR0ZA/16byte-clang-wine-fbsd64-1.5.16,1.txz I tried building (using gcc) wine with your patch and now (at least) winecf= g=20 and regedit work with a clang built lib32. I'll email Gerald (wine's=20 maintainer) about including your patch in wine. =20 regards --nextPart5521153.u17xfddALF Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part. -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) iEYEABECAAYFAlCWYqgACgkQUaaFgP9pFrLPswCfZjFl7/IiwBJnoUB0huOqy8S7 aLYAoIKIrMEch/mjYr7Pr6hWXuJAmJ5Z =Cogn -----END PGP SIGNATURE----- --nextPart5521153.u17xfddALF-- From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 11:07:01 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 728C665E for ; Sun, 4 Nov 2012 11:07:01 +0000 (UTC) (envelope-from levitch@iglou.com) Received: from rdsmtp.iglou.com (rdsmtp.iglou.com [192.107.41.63]) by mx1.freebsd.org (Postfix) with ESMTP id 2386D8FC08 for ; Sun, 4 Nov 2012 11:07:00 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=iglou.com; s=alpha; h=Content-Type:MIME-Version:References:Message-ID:In-Reply-To:Subject:cc:To:From:Date; bh=rN6Fvr2nnv/a8Uv1JivB/fxsieMPbiS1fk0e70IO5as=; b=IUyOLMUjDQj+WlBIP9RW1yPQFra1zVsa7e1MX5uEowTamg8XUyVA+//8W+TTI/GgpSIwDHts21uJbHhibKDcdR10JYvKGLQuIrtxZ8EWiIEbWIOUOrTDzKL/DvaeJI1m65/dzlS1vIRm3UsA+cOg4Tikg7xX6v+mB1DSl3AOPwI=; Received: from iglou1.iglou.com ([192.107.41.3]:35554 helo=mail.iglou.com) by rdsmtp.iglou.com with esmtpa (Exim MTA/8.19.3) (envelope-from ) id 1TUy2d-0000WB-Ue by authid with igloumta_auth for current@freebsd.org; Sun, 04 Nov 2012 06:06:59 -0500 Received: from shell1.iglou.com ([192.107.41.17]:38299 helo=shell1) by mail.iglou.com with esmtps (TLS cipher TLSv1:AES256-SHA:256) (Exim MTA/8.19.3) (envelope-from ) id 1TUy2d-0005Xh-C0; Sun, 04 Nov 2012 06:06:59 -0500 Date: Sun, 4 Nov 2012 06:06:59 -0500 (EST) From: Darrel X-X-Sender: levitch@shell1 To: Garrett Cooper Subject: [solved]: r2421600 amd64 /var/db/pkg In-Reply-To: Message-ID: References: User-Agent: Alpine 2.00 (GSO 1167 2008-08-23) MIME-Version: 1.0 Content-Type: MULTIPART/MIXED; BOUNDARY="-559023410-630072926-1352027219=:24960" X-Originating-IP: 192.107.41.17 X-IgLou-Customer: 3cb6f76205bd20f518810676a67a982b X-Mailman-Approved-At: Sun, 04 Nov 2012 12:47:09 +0000 Cc: Eitan Adler , current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 11:07:01 -0000 This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. ---559023410-630072926-1352027219=:24960 Content-Type: TEXT/PLAIN; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE On Sat, 3 Nov 2012, Garrett Cooper wrote: > On Sat, Nov 3, 2012 at 6:15 PM, Darrel wrote: >=20 > ... > =A0 > Yes, the existing man 8 pkg does not seem to match all of the facts. >=20 >=20 > =A0=A0=A0 What you probably ran into is the common chicken and egg proble= m where > if pkgng is upgraded ports, it blows up when it tries to deinstall the > package, or similarly, when portmaster is upgraded, it doesn't halt the > upgrade and restart it properly. > =A0=A0=A0 It's most likely still a problem; I'm going to doublecheck to m= ake sure > that's the case and file PRs if it is. Thanks, Garrett. For my current problem I am simply going to delete the=20 errant portmaster-3.14 from /var/db/pkg and then run 'portmaster -a -f -D'= =20 with the hope that portmaster-3.14_7 can fix things. If not I will try=20 reinstalling, the are only a few things installed- freeradius, postgresql,= =20 and about a dozen others. Darrel ---559023410-630072926-1352027219=:24960-- From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 13:18:35 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 13EB4D3B; Sun, 4 Nov 2012 13:18:35 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from kib.kiev.ua (kostikbel-1-pt.tunnel.tserv11.ams1.ipv6.he.net [IPv6:2001:470:1f14:13d6::2]) by mx1.freebsd.org (Postfix) with ESMTP id 8AE108FC12; Sun, 4 Nov 2012 13:18:34 +0000 (UTC) Received: from tom.home (localhost [127.0.0.1]) by kib.kiev.ua (8.14.5/8.14.5) with ESMTP id qA4DIU8c027937; Sun, 4 Nov 2012 15:18:30 +0200 (EET) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by tom.home (8.14.5/8.14.5/Submit) id qA4DIUc0027936; Sun, 4 Nov 2012 15:18:30 +0200 (EET) (envelope-from kostikbel@gmail.com) X-Authentication-Warning: tom.home: kostik set sender to kostikbel@gmail.com using -f Date: Sun, 4 Nov 2012 15:18:30 +0200 From: Konstantin Belousov To: David Naylor Subject: Re: November 5th is Clang-Day Message-ID: <20121104131830.GL73505@kib.kiev.ua> References: <20121102032945.GF65074@lor.one-eyed-alien.net> <201211030948.43530.naylor.b.david@gmail.com> <1TUlad-0008bB-OF@internal.tormail.org> <201211041442.16620.naylor.b.david@gmail.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="dD1ndss832r/QIua" Content-Disposition: inline In-Reply-To: <201211041442.16620.naylor.b.david@gmail.com> User-Agent: Mutt/1.5.21 (2010-09-15) X-Spam-Status: No, score=0.2 required=5.0 tests=ALL_TRUSTED, DKIM_ADSP_CUSTOM_MED,FREEMAIL_FROM,NML_ADSP_CUSTOM_MED autolearn=no version=3.3.2 X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on tom.home Cc: freebsd-current@freebsd.org, David Chisnall , Brooks Davis , Jan Beich X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 13:18:35 -0000 --dD1ndss832r/QIua Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sun, Nov 04, 2012 at 02:42:13PM +0200, David Naylor wrote: > On Saturday, 3 November 2012 23:47:54 Jan Beich wrote: > > David Naylor writes: > > > There are two issues here: 1) wine compiled with clang, and 2) wine > > > (compiled with gcc) running on clang compiled base. > > >=20 > > > Regarding 1), according to the wiki [1], wine does have stack alignme= nt > > > issues and some wine programs do not run when compiled with clang [2]= [3] > > > and other bugs with clang cause freezing within wine [4][5]. The > > > impression I get is that, using the work-a-round of stack realignment, > > > wine does work to some extent when compiled by clang. > >=20 > > Took me some time but now I can confirm that clang-built wine-1.5.16 > > works fine for me with gcc-built lib32 (i.e. ld-elf32.so.1 + /usr/lib32= ). > >=20 > > > Regarding 2) (which I believe Jan was referring to), when I have a gcc > > > built world and just replace lib32 with clang built libraries I have > > > winecfg and regedit launching but displaying black screens. Switching > > > back to gcc built lib32 I get a working winecfg and regedit. This, to > > > me, indicates a clang error somewhere. > >=20 > > My experience varies between clang-built and gcc-built wine. > >=20 > > # clang, quick crash > >=20 > > # gcc, black rectangle > >=20 > > So, why not switch stack alignment in wine (upstream)? This would make > > /stable/9 wine package continue to work on /head. > >=20 > > Here's my wine package built with and without the patch. > >=20 > > # sha256: cef5e543a5c534acb7237634224561863122ab3c256df319c6428856266d7= 9fd > > http://ompldr.org/vZzR0bw/4byte-clang-wine-fbsd64-1.5.16,1.txz > > # sha256: 68e402bf7cb39ea48b9bef7772422cf476e89b214fd3b98ced37e0068f588= c6c > > http://ompldr.org/vZzR0ZA/16byte-clang-wine-fbsd64-1.5.16,1.txz >=20 > I tried building (using gcc) wine with your patch and now (at least) wine= cfg=20 > and regedit work with a clang built lib32. I'll email Gerald (wine's=20 > maintainer) about including your patch in wine. =20 The wine is the wrong place to fix. If system libraries suddenly started requiring 16-byte stack alignment on i386, it is unacceptable breakage of the ABI. I tried to gather the evidence for the case, but apparent submitter of the bug stopped replying to the requests. --dD1ndss832r/QIua Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) iEYEARECAAYFAlCWayUACgkQC3+MBN1Mb4ijHQCgsn6zPVfmb0AVPjncq/QWV41+ PT8AoIZPSpfqb8YAYrNTKmwflW/d0zhq =zpfT -----END PGP SIGNATURE----- --dD1ndss832r/QIua-- From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 13:43:32 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B38D8144 for ; Sun, 4 Nov 2012 13:43:32 +0000 (UTC) (envelope-from olivier@gid0.org) Received: from mail-lb0-f182.google.com (mail-lb0-f182.google.com [209.85.217.182]) by mx1.freebsd.org (Postfix) with ESMTP id 2E3C08FC16 for ; Sun, 4 Nov 2012 13:43:31 +0000 (UTC) Received: by mail-lb0-f182.google.com with SMTP id b5so4497492lbd.13 for ; Sun, 04 Nov 2012 05:43:30 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:x-gm-message-state; bh=nknDB/oXsSKQUfIkgchZeCKvpLLjHQPt6VWGkPEguJU=; b=b8/pv6I/tw3eye186AoYWepvvwayZ5eF4NYr17eJZJWr7Xu4qsT7KeqmCNaC0YGZsO RRHmPn+aZmaccez4WNfo3UMoXEhmXybBiK+5ThIWMnFPiTx1TlrQizRB2R7mqL7rZKJ4 QB/+x8qCCG385Roe6ehKKMUmG4SXGw07vbiWjJZD4i7StIxqLukzh5v7p9tGqmO59UtY kOdma5AANQLoxlFADYmtU+RXInncNZvAKYGMVsmT+3xECJOp0EaVTX039XqUydw6cQVd ignqjTKB2sAQu8cXbBdoSlPmGMrdwrtRWoJ5yBMWl0WROVO22ExgCVMboLqn1iKf7M/5 voow== MIME-Version: 1.0 Received: by 10.112.27.97 with SMTP id s1mr2858142lbg.135.1352036610744; Sun, 04 Nov 2012 05:43:30 -0800 (PST) Received: by 10.112.135.137 with HTTP; Sun, 4 Nov 2012 05:43:30 -0800 (PST) In-Reply-To: References: <20121103232433.00005eee@unknown> Date: Sun, 4 Nov 2012 14:43:30 +0100 Message-ID: Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? From: Olivier Smedts To: Scot Hetzel X-Gm-Message-State: ALoCoQl6a9clrh1Fo42H+QqE7Y9TeP6F6KTVMDiVV175AKQJQsH8faewc8h9o6DMycL8M04LA4eQ Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: Alexander Leidinger , "current@freebsd.org" X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 13:43:32 -0000 Le dimanche 4 novembre 2012, Scot Hetzel a =E9crit : > > When you set CPUTYPE?=3Dnative, bsd.cpu.mk doesn't set MACHINE_CPU to > the correct values for your CPUTYPE. > This comes regularly in the lists. Try setting the correct CPUTYPE for your CPU, and if you want to use "native" somewhere, add "-march=3Dnative" to your CFLAGS. There's another option to use so that *.mk don't add another "-march" with your CPUTYPE automatically. --=20 Olivier Smedts _ ASCII ribbon campaign ( ) e-mail: olivier@gid0.org - against HTML email & vCards X www: http://www.gid0.org - against proprietary attachments / \ "Il y a seulement 10 sortes de gens dans le monde : ceux qui comprennent le binaire, et ceux qui ne le comprennent pas." From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 13:57:42 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7F94B9A4 for ; Sun, 4 Nov 2012 13:57:42 +0000 (UTC) (envelope-from andre@freebsd.org) Received: from c00l3r.networx.ch (c00l3r.networx.ch [62.48.2.2]) by mx1.freebsd.org (Postfix) with ESMTP id BF70C8FC08 for ; Sun, 4 Nov 2012 13:57:40 +0000 (UTC) Received: (qmail 39982 invoked from network); 4 Nov 2012 15:33:29 -0000 Received: from c00l3r.networx.ch (HELO [127.0.0.1]) ([62.48.2.2]) (envelope-sender ) by c00l3r.networx.ch (qmail-ldap-1.03) with SMTP for ; 4 Nov 2012 15:33:29 -0000 Message-ID: <50967453.5090503@freebsd.org> Date: Sun, 04 Nov 2012 14:57:39 +0100 From: Andre Oppermann User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:16.0) Gecko/20121010 Thunderbird/16.0.1 MIME-Version: 1.0 To: Kim Culhan Subject: Re: weird network problems on current since 10/28/2012 References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Dimitry Andric , freebsd-current@freebsd.org, Adrian Chadd X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 13:57:42 -0000 On 04.11.2012 13:11, Kim Culhan wrote: > On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: >> On 2012-11-04 02:13, Manfred Antar wrote: >>> At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>> On 3 November 2012 10:40, Manfred Antar wrote: >>>>> i have problem connecting to freebsd box on local network since last sunday. >>>>> the last kernel that works: >>>>> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >>>>> anything after that, sometimes i can connect, other times just hangs. >>>>> any network connection hangs ===== pop httpd ssh etc etc. >>>>> anyone have any ideas ? >>>>> i can checkout different sources and see if i can locate the changes that cause >>>>> this. >>>> >>>> Please do! >> ... >>> Here is what I found doing : >>> setenv CVSROOT /usr/home/ncvs >>> >>> cvs co -D"October 28, 2012 12:14:38 PDT" sys >>> >>> A kernel from that time works fine. >>> >>> doing: >>> >>> cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later >>> the following files were changed: >>> sys/netinet/tcp_input.c >>> sys/netinet/tcp_timer.c >>> sys/netinet/tcp_var.h >>> >>> Building a kernel from these new files is when the problem starts. >> >> So, your problems seem to have been introduced by this commit by Andre: >> >> http://svn.freebsd.org/changeset/base/242266 >> >> Increase the initial CWND to 10 segments as defined in IETF TCPM >> draft-ietf-tcpm-initcwnd-05. It explains why the increased initial >> window improves the overall performance of many web services without >> risking congestion collapse. >> >> As long as it remains a draft it is placed under a sysctl marking it >> as experimental: >> net.inet.tcp.experimental.initcwnd10 = 1 >> When it becomes an official RFC soon the sysctl will be changed to >> the RFC number and moved to net.inet.tcp. >> >> This implementation differs from the RFC draft in that it is a bit >> more conservative in the case of packet loss on SYN or SYN|ACK because >> we haven't reduced the default RTO to 1 second yet. Also the restart >> window isn't yet increased as allowed. Both will be adjusted with >> upcoming changes. >> >> Is is enabled by default. In Linux it is enabled since kernel 3.0. >> >> After the commit, there was a small discussion thread on svn-src-head@ >> about the possible problems with the approach. Maybe you are >> experiencing those? >> >> As the commit message says, you should be able to turn the feature off >> using: >> >> sysctl net.inet.tcp.experimental.initcwnd10=0 >> >> Can you please try that, and see if the problems go away? > > FWIW this did not make the problem go away on 2 machines. Yes, this very much looks like the same problem as in PR/173309. Please try the attached patch. It fixes the connection hang issue. There may be a second issue I debugging currently base on the feedback from Fabian Keil. -- Andre Index: tcp_input.c =================================================================== --- tcp_input.c (revision 242494) +++ tcp_input.c (working copy) @@ -2650,10 +2652,12 @@ SOCKBUF_LOCK(&so->so_snd); if (acked > so->so_snd.sb_cc) { + tp->snd_wnd -= so->so_snd.sb_cc; sbdrop_locked(&so->so_snd, (int)so->so_snd.sb_cc); ourfinisacked = 1; } else { sbdrop_locked(&so->so_snd, acked); + tp->snd_wnd -= acked; ourfinisacked = 0; } /* NB: sowwakeup_locked() does an implicit unlock. */ From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 14:12:15 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 116B62AD; Sun, 4 Nov 2012 14:12:15 +0000 (UTC) (envelope-from null@pozo.com) Received: from pozo.com (pozo.com [216.101.162.50]) by mx1.freebsd.org (Postfix) with ESMTP id 916E98FC0A; Sun, 4 Nov 2012 14:12:14 +0000 (UTC) Received: from T61p.pozo.com (t61p.pozo.com [192.168.0.4]) (authenticated bits=0) by pozo.com (8.14.5/8.14.5) with ESMTP id qA4EBtab006509 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NOT); Sun, 4 Nov 2012 06:11:56 -0800 (PST) (envelope-from null@pozo.com) Message-Id: <201211041411.qA4EBtab006509@pozo.com> X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Sun, 04 Nov 2012 06:11:50 -0800 To: Dimitry Andric From: Manfred Antar Subject: Re: weird network problems on current since 10/28/2012 In-Reply-To: <50964FBB.4010600@andric.com> References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" X-Spam-Status: No, score=-0.9 required=5.0 tests=ALL_TRUSTED,MISSING_MID autolearn=no version=3.3.2, No X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on pozo.com X-pozocom-MailScanner-Information: Please contact the ISP for more information X-pozocom-MailScanner-ID: qA4EBtab006509 X-pozocom-MailScanner: Found to be clean X-pozocom-MailScanner-From: null@pozo.com Cc: Adrian Chadd , freebsd-current@freebsd.org, Andre Oppermann X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 14:12:15 -0000 At 03:21 AM 11/4/2012, Dimitry Andric wrote: >On 2012-11-04 02:13, Manfred Antar wrote: >>At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>On 3 November 2012 10:40, Manfred Antar wrote: >>>>i have problem connecting to freebsd box on local network since last sunday. >>>>the last kernel that works: >>>> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >>>>anything after that, sometimes i can connect, other times just hangs. >>>>any network connection hangs ===== pop httpd ssh etc etc. >>>>anyone have any ideas ? >>>>i can checkout different sources and see if i can locate the changes that cause this. >>> >>>Please do! >... >>Here is what I found doing : >>setenv CVSROOT /usr/home/ncvs >> >>cvs co -D"October 28, 2012 12:14:38 PDT" sys >> >>A kernel from that time works fine. >> >>doing: >> >>cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later >>the following files were changed: >>sys/netinet/tcp_input.c >>sys/netinet/tcp_timer.c >>sys/netinet/tcp_var.h >> >>Building a kernel from these new files is when the problem starts. > >So, your problems seem to have been introduced by this commit by Andre: > > http://svn.freebsd.org/changeset/base/242266 > > Increase the initial CWND to 10 segments as defined in IETF TCPM > draft-ietf-tcpm-initcwnd-05. It explains why the increased initial > window improves the overall performance of many web services without > risking congestion collapse. > > As long as it remains a draft it is placed under a sysctl marking it > as experimental: > net.inet.tcp.experimental.initcwnd10 = 1 > When it becomes an official RFC soon the sysctl will be changed to > the RFC number and moved to net.inet.tcp. > > This implementation differs from the RFC draft in that it is a bit > more conservative in the case of packet loss on SYN or SYN|ACK because > we haven't reduced the default RTO to 1 second yet. Also the restart > window isn't yet increased as allowed. Both will be adjusted with > upcoming changes. > > Is is enabled by default. In Linux it is enabled since kernel 3.0. > >After the commit, there was a small discussion thread on svn-src-head@ >about the possible problems with the approach. Maybe you are >experiencing those? > >As the commit message says, you should be able to turn the feature off >using: > > sysctl net.inet.tcp.experimental.initcwnd10=0 > >Can you please try that, and see if the problems go away? I read the commit log and tried that. It didn't change. I will try the patch from Andre and enable the debug log. Manfred ======================== || null@pozo.com || || Ph. (415) 681-6235 || ======================== -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 14:29:46 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 02D82AB; Sun, 4 Nov 2012 14:29:45 +0000 (UTC) (envelope-from dim@FreeBSD.org) Received: from tensor.andric.com (cl-327.ede-01.nl.sixxs.net [IPv6:2001:7b8:2ff:146::2]) by mx1.freebsd.org (Postfix) with ESMTP id A6ABE8FC0C; Sun, 4 Nov 2012 14:29:45 +0000 (UTC) Received: from [IPv6:2001:7b8:3a7:0:d48d:da6b:2080:d1e7] (unknown [IPv6:2001:7b8:3a7:0:d48d:da6b:2080:d1e7]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by tensor.andric.com (Postfix) with ESMTPSA id 263F15C59; Sun, 4 Nov 2012 15:29:44 +0100 (CET) Message-ID: <50967BD6.9090806@FreeBSD.org> Date: Sun, 04 Nov 2012 15:29:42 +0100 From: Dimitry Andric Organization: The FreeBSD Project User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:17.0) Gecko/17.0 Thunderbird/17.0 MIME-Version: 1.0 To: Konstantin Belousov Subject: Re: November 5th is Clang-Day References: <20121102032945.GF65074@lor.one-eyed-alien.net> <201211030948.43530.naylor.b.david@gmail.com> <1TUlad-0008bB-OF@internal.tormail.org> <201211041442.16620.naylor.b.david@gmail.com> <20121104131830.GL73505@kib.kiev.ua> In-Reply-To: <20121104131830.GL73505@kib.kiev.ua> Content-Type: multipart/mixed; boundary="------------080601050205030809080704" Cc: David Chisnall , freebsd-current@freebsd.org, David Naylor , Brooks Davis , Jan Beich X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 14:29:46 -0000 This is a multi-part message in MIME format. --------------080601050205030809080704 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit On 2012-11-04 14:18, Konstantin Belousov wrote: > On Sun, Nov 04, 2012 at 02:42:13PM +0200, David Naylor wrote: ... >> I tried building (using gcc) wine with your patch and now (at least) winecfg >> and regedit work with a clang built lib32. I'll email Gerald (wine's >> maintainer) about including your patch in wine. > > The wine is the wrong place to fix. If system libraries suddenly started > requiring 16-byte stack alignment on i386, it is unacceptable breakage > of the ABI. So we really must use 4 byte stack alignment on i386 by default? I have attached a diff to llvm for this, but I would like to verify that it is really correct. Apparently Darwin, Linux and Solaris all use 16 byte alignment. The Sys V ABI seems to say only: "The stack is word aligned. Although the architecture does not require any alignment of the stack, software convention and the operating system requires that the stack be aligned on a word boundary". --------------080601050205030809080704 Content-Type: text/x-diff; name="fix-llvm-i386-alignment-1.diff" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="fix-llvm-i386-alignment-1.diff" Index: contrib/llvm/lib/Target/X86/X86Subtarget.cpp =================================================================== --- contrib/llvm/lib/Target/X86/X86Subtarget.cpp (revision 242480) +++ contrib/llvm/lib/Target/X86/X86Subtarget.cpp (working copy) @@ -416,12 +416,12 @@ X86Subtarget::X86Subtarget(const std::string &TT, assert((!In64BitMode || HasX86_64) && "64-bit code requested on a subtarget that doesn't support it!"); - // Stack alignment is 16 bytes on Darwin, FreeBSD, Linux and Solaris (both - // 32 and 64 bit) and for all 64-bit targets. + // Stack alignment is 16 bytes on Darwin, Linux and Solaris (both 32 and 64 + // bit) and for all 64-bit targets. if (StackAlignOverride) - stackAlignment = StackAlignOverride; - else if (isTargetDarwin() || isTargetFreeBSD() || isTargetLinux() || - isTargetSolaris() || In64BitMode) + stackAlignment = StackAlignOverride; + else if (isTargetDarwin() || isTargetLinux() || isTargetSolaris() || + In64BitMode) stackAlignment = 16; } --------------080601050205030809080704-- From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 14:37:03 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7B3893EB; Sun, 4 Nov 2012 14:37:03 +0000 (UTC) (envelope-from kostikbel@gmail.com) Received: from kib.kiev.ua (kostikbel-1-pt.tunnel.tserv11.ams1.ipv6.he.net [IPv6:2001:470:1f14:13d6::2]) by mx1.freebsd.org (Postfix) with ESMTP id C30CF8FC0C; Sun, 4 Nov 2012 14:37:02 +0000 (UTC) Received: from tom.home (localhost [127.0.0.1]) by kib.kiev.ua (8.14.5/8.14.5) with ESMTP id qA4EaxXg035931; Sun, 4 Nov 2012 16:36:59 +0200 (EET) (envelope-from kostikbel@gmail.com) Received: (from kostik@localhost) by tom.home (8.14.5/8.14.5/Submit) id qA4Eaxax035930; Sun, 4 Nov 2012 16:36:59 +0200 (EET) (envelope-from kostikbel@gmail.com) X-Authentication-Warning: tom.home: kostik set sender to kostikbel@gmail.com using -f Date: Sun, 4 Nov 2012 16:36:59 +0200 From: Konstantin Belousov To: Dimitry Andric Subject: Re: November 5th is Clang-Day Message-ID: <20121104143658.GM73505@kib.kiev.ua> References: <20121102032945.GF65074@lor.one-eyed-alien.net> <201211030948.43530.naylor.b.david@gmail.com> <1TUlad-0008bB-OF@internal.tormail.org> <201211041442.16620.naylor.b.david@gmail.com> <20121104131830.GL73505@kib.kiev.ua> <50967BD6.9090806@FreeBSD.org> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="PlDVpzlhHY5RV9ko" Content-Disposition: inline In-Reply-To: <50967BD6.9090806@FreeBSD.org> User-Agent: Mutt/1.5.21 (2010-09-15) X-Spam-Status: No, score=0.2 required=5.0 tests=ALL_TRUSTED, DKIM_ADSP_CUSTOM_MED,FREEMAIL_FROM,NML_ADSP_CUSTOM_MED autolearn=no version=3.3.2 X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on tom.home Cc: David Chisnall , freebsd-current@freebsd.org, David Naylor , Brooks Davis , Jan Beich X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 14:37:03 -0000 --PlDVpzlhHY5RV9ko Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sun, Nov 04, 2012 at 03:29:42PM +0100, Dimitry Andric wrote: > On 2012-11-04 14:18, Konstantin Belousov wrote: > > On Sun, Nov 04, 2012 at 02:42:13PM +0200, David Naylor wrote: > ... > >> I tried building (using gcc) wine with your patch and now (at least) w= inecfg > >> and regedit work with a clang built lib32. I'll email Gerald (wine's > >> maintainer) about including your patch in wine. > > > > The wine is the wrong place to fix. If system libraries suddenly started > > requiring 16-byte stack alignment on i386, it is unacceptable breakage > > of the ABI. >=20 > So we really must use 4 byte stack alignment on i386 by default? I have > attached a diff to llvm for this, but I would like to verify that it is > really correct. Apparently Darwin, Linux and Solaris all use 16 byte > alignment. No, this is a misunderstanding. We must provide libraries that tolerate the 4-byte aligned stack. Also, to be compatible with broken compilers (both older versions of gcc and some versions of clang) we must provide the libraries which preserve the %esp mod 0x10 across the functions entry/leave points. The crt ensures that the stack is 16-byte aligned on entry to main. >=20 > The Sys V ABI seems to say only: "The stack is word aligned. Although > the architecture does not require any alignment of the stack, software > convention and the operating system requires that the stack be aligned > on a word boundary". Right, this is ABI which some binaries follow. There are some other binarie= s, generated by arguably broken compilers, which require 16-byte alignment. The system shall support both. > Index: contrib/llvm/lib/Target/X86/X86Subtarget.cpp > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D > --- contrib/llvm/lib/Target/X86/X86Subtarget.cpp (revision 242480) > +++ contrib/llvm/lib/Target/X86/X86Subtarget.cpp (working copy) > @@ -416,12 +416,12 @@ X86Subtarget::X86Subtarget(const std::string &TT, > assert((!In64BitMode || HasX86_64) && > "64-bit code requested on a subtarget that doesn't support it!"= ); > =20 > - // Stack alignment is 16 bytes on Darwin, FreeBSD, Linux and Solaris (= both > - // 32 and 64 bit) and for all 64-bit targets. > + // Stack alignment is 16 bytes on Darwin, Linux and Solaris (both 32 a= nd 64 > + // bit) and for all 64-bit targets. > if (StackAlignOverride) > - stackAlignment =3D StackAlignOverride; > - else if (isTargetDarwin() || isTargetFreeBSD() || isTargetLinux() || > - isTargetSolaris() || In64BitMode) > + stackAlignment =3D StackAlignOverride; > + else if (isTargetDarwin() || isTargetLinux() || isTargetSolaris() || > + In64BitMode) > stackAlignment =3D 16; > } > =20 --PlDVpzlhHY5RV9ko Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) iEYEARECAAYFAlCWfYoACgkQC3+MBN1Mb4g8SACfXYluKR7qLZ6kHg+aXgYAbc/l GzUAn1u0IfN7lHr+4FS7TpqyXZTq8x5O =crOO -----END PGP SIGNATURE----- --PlDVpzlhHY5RV9ko-- From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 14:40:23 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 42A48697; Sun, 4 Nov 2012 14:40:23 +0000 (UTC) (envelope-from null@pozo.com) Received: from pozo.com (pozo.com [216.101.162.50]) by mx1.freebsd.org (Postfix) with ESMTP id F20808FC08; Sun, 4 Nov 2012 14:40:22 +0000 (UTC) Received: from T61p.pozo.com (t61p.pozo.com [192.168.0.4]) (authenticated bits=0) by pozo.com (8.14.5/8.14.5) with ESMTP id qA4Ee9tF001680 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NOT); Sun, 4 Nov 2012 06:40:15 -0800 (PST) (envelope-from null@pozo.com) Message-Id: <201211041440.qA4Ee9tF001680@pozo.com> X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Sun, 04 Nov 2012 06:40:04 -0800 To: Andre Oppermann From: Manfred Antar Subject: Re: weird network problems on current since 10/28/2012 In-Reply-To: <50967453.5090503@freebsd.org> References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> <50967453.5090503@freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" X-Spam-Status: No, score=-0.9 required=5.0 tests=ALL_TRUSTED,MISSING_MID autolearn=no version=3.3.2, No X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on pozo.com X-pozocom-MailScanner-Information: Please contact the ISP for more information X-pozocom-MailScanner-ID: qA4Ee9tF001680 X-pozocom-MailScanner: Found to be clean X-pozocom-MailScanner-From: null@pozo.com Cc: freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 14:40:23 -0000 At 05:57 AM 11/4/2012, you wrote: >On 04.11.2012 13:11, Kim Culhan wrote: >>On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: >>>On 2012-11-04 02:13, Manfred Antar wrote: >>>>At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>>>On 3 November 2012 10:40, Manfred Antar wrote: >>>>>>i have problem connecting to freebsd box on local network since last sunday. >>>>>>the last kernel that works: >>>>>> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >>>>>>anything after that, sometimes i can connect, other times just hangs. >>>>>>any network connection hangs ===== pop httpd ssh etc etc. >>>>>>anyone have any ideas ? >>>>>>i can checkout different sources and see if i can locate the changes that cause >>>>>>this. >>>>> >>>>>Please do! >>>... >>>>Here is what I found doing : >>>>setenv CVSROOT /usr/home/ncvs >>>> >>>>cvs co -D"October 28, 2012 12:14:38 PDT" sys >>>> >>>>A kernel from that time works fine. >>>> >>>>doing: >>>> >>>>cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later >>>>the following files were changed: >>>>sys/netinet/tcp_input.c >>>>sys/netinet/tcp_timer.c >>>>sys/netinet/tcp_var.h >>>> >>>>Building a kernel from these new files is when the problem starts. >>> >>>So, your problems seem to have been introduced by this commit by Andre: >>> >>> http://svn.freebsd.org/changeset/base/242266 >>> >>> Increase the initial CWND to 10 segments as defined in IETF TCPM >>> draft-ietf-tcpm-initcwnd-05. It explains why the increased initial >>> window improves the overall performance of many web services without >>> risking congestion collapse. >>> >>> As long as it remains a draft it is placed under a sysctl marking it >>> as experimental: >>> net.inet.tcp.experimental.initcwnd10 = 1 >>> When it becomes an official RFC soon the sysctl will be changed to >>> the RFC number and moved to net.inet.tcp. >>> >>> This implementation differs from the RFC draft in that it is a bit >>> more conservative in the case of packet loss on SYN or SYN|ACK because >>> we haven't reduced the default RTO to 1 second yet. Also the restart >>> window isn't yet increased as allowed. Both will be adjusted with >>> upcoming changes. >>> >>> Is is enabled by default. In Linux it is enabled since kernel 3.0. >>> >>>After the commit, there was a small discussion thread on svn-src-head@ >>>about the possible problems with the approach. Maybe you are >>>experiencing those? >>> >>>As the commit message says, you should be able to turn the feature off >>>using: >>> >>> sysctl net.inet.tcp.experimental.initcwnd10=0 >>> >>>Can you please try that, and see if the problems go away? >> >>FWIW this did not make the problem go away on 2 machines. > >Yes, this very much looks like the same problem as in PR/173309. > >Please try the attached patch. It fixes the connection hang issue. >There may be a second issue I debugging currently base on the feedback >from Fabian Keil. > >-- >Andre > >Index: tcp_input.c >=================================================================== >--- tcp_input.c (revision 242494) >+++ tcp_input.c (working copy) >@@ -2650,10 +2652,12 @@ > > SOCKBUF_LOCK(&so->so_snd); > if (acked > so->so_snd.sb_cc) { >+ tp->snd_wnd -= so->so_snd.sb_cc; > sbdrop_locked(&so->so_snd, (int)so->so_snd.sb_cc); > ourfinisacked = 1; > } else { > sbdrop_locked(&so->so_snd, acked); >+ tp->snd_wnd -= acked; > ourfinisacked = 0; > } > /* NB: sowwakeup_locked() does an implicit unlock. */ This patch improves the connection issue, not hanging on trying to connect (ssh pop) It still seems that it is taking longer to connect though. But in the end the connection goes through. I can capture a tcpdump and put it at http://pozo.com/tcpdump/tpdump.txt if that will help. I'll let it run for about 1/2 hour. Manfred -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 13:58:21 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 365C6AFD for ; Sun, 4 Nov 2012 13:58:21 +0000 (UTC) (envelope-from bryan@shatow.net) Received: from secure.xzibition.com (secure.xzibition.com [173.160.118.92]) by mx1.freebsd.org (Postfix) with ESMTP id CA7E18FC1A for ; Sun, 4 Nov 2012 13:58:20 +0000 (UTC) DomainKey-Signature: a=rsa-sha1; c=nofws; d=shatow.net; h=message-id :date:from:mime-version:to:cc:subject:references:in-reply-to :content-type:content-transfer-encoding; q=dns; s=sweb; b=flGonC UMqYJqUqKlyTfjb7fYz29OJN32Xn7EyP4f2cVCm1anvIlmEnckuZRmiItguZXmPj TYDHks7lITLaIRmnHvgaof8wKT1n71GFwF1va7GSsweZF34Eh0QMEnOf+Z0ZVQL1 SRyFUDq86bD68es8K4CadAbEWyryrgdXAHlAw= DKIM-Signature: v=1; a=rsa-sha256; c=simple; d=shatow.net; h=message-id :date:from:mime-version:to:cc:subject:references:in-reply-to :content-type:content-transfer-encoding; s=sweb; bh=xs5ddHGjrTqT 5LxbBGKmCI8aBBTQwuZzYIa/YdI6eOk=; b=I0KBAtvKNm+q71UQEL6dkLRXI6uH k2kVyEcvlu5BUU5sDHvY5BQYHZuGY+dLnJC83OPwU7iDS6Oy0EV+TJhFGvZGgf1c WdKNsS/qPOiXBQhdvr2MHGSjduVaaOhCW4YDTwTtKDD44UNk0SBvANr9l3tMzPzS v2UjkV9ZsUzOab0= Received: (qmail 28302 invoked from network); 4 Nov 2012 07:58:12 -0600 Received: from unknown (HELO ?10.10.0.115?) (bryan@shatow.net@10.10.0.115) by sweb.xzibition.com with ESMTPA; 4 Nov 2012 07:58:12 -0600 Message-ID: <50967473.8080808@shatow.net> Date: Sun, 04 Nov 2012 07:58:11 -0600 From: Bryan Drewery User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:16.0) Gecko/20121026 Thunderbird/16.0.2 MIME-Version: 1.0 To: Darrel Subject: Re: [solved]: r2421600 amd64 /var/db/pkg References: In-Reply-To: X-Enigmail-Version: 1.4.5 OpenPGP: id=3C9B0CF9; url=http://www.shatow.net/bryan/bryan.asc Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sun, 04 Nov 2012 15:12:05 +0000 Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 13:58:21 -0000 On 11/4/2012 5:06 AM, Darrel wrote: > > On Sat, 3 Nov 2012, Garrett Cooper wrote: > >> On Sat, Nov 3, 2012 at 6:15 PM, Darrel wrote: >> >> ... >> >> Yes, the existing man 8 pkg does not seem to match all of the facts. >> >> >> What you probably ran into is the common chicken and egg problem >> where >> if pkgng is upgraded ports, it blows up when it tries to deinstall the >> package, or similarly, when portmaster is upgraded, it doesn't halt the >> upgrade and restart it properly. >> It's most likely still a problem; I'm going to doublecheck to make >> sure >> that's the case and file PRs if it is. > > Thanks, Garrett. For my current problem I am simply going to delete the > errant portmaster-3.14 from /var/db/pkg and then run 'portmaster -a -f > -D' with the hope that portmaster-3.14_7 can fix things. If not I will > try reinstalling, the are only a few things installed- freeradius, > postgresql, and about a dozen others. This is overkill. You either have a pkg_install database or a pkgng database. Determining which will save you time. After you run pkg2ng, pkg_info will no longer work. It will complain about corrupted packages, since all the data is gone, but portmaster has stored additional information there, which confuses pkg_info. Check the output of 'pkg info'. If it lists all your packages, you are done. Nothing more to do. If not, run pkg2ng. Also, you can see any packages that have not converted with: find /var/db/pkg -name +CONTENTS If nothing comes up, they are already all converted. Bryan From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 15:42:08 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id C7DF51BF for ; Sun, 4 Nov 2012 15:42:08 +0000 (UTC) (envelope-from nwhitehorn@freebsd.org) Received: from adsum.doit.wisc.edu (adsum.doit.wisc.edu [144.92.197.210]) by mx1.freebsd.org (Postfix) with ESMTP id 91EA98FC16 for ; Sun, 4 Nov 2012 15:42:08 +0000 (UTC) MIME-version: 1.0 Content-transfer-encoding: 7BIT Content-type: text/plain; CHARSET=US-ASCII; format=flowed Received: from avs-daemon.smtpauth1.wiscmail.wisc.edu by smtpauth1.wiscmail.wisc.edu (Sun Java(tm) System Messaging Server 7u2-7.05 32bit (built Jul 30 2009)) id <0MCY00D00WU16Q00@smtpauth1.wiscmail.wisc.edu> for freebsd-current@freebsd.org; Sun, 04 Nov 2012 08:42:01 -0600 (CST) Received: from comporellon.tachypleus.net (adsl-71-150-249-157.dsl.mdsnwi.sbcglobal.net [71.150.249.157]) by smtpauth1.wiscmail.wisc.edu (Sun Java(tm) System Messaging Server 7u2-7.05 32bit (built Jul 30 2009)) with ESMTPSA id <0MCY00997WU08610@smtpauth1.wiscmail.wisc.edu> for freebsd-current@freebsd.org; Sun, 04 Nov 2012 08:42:01 -0600 (CST) Date: Sun, 04 Nov 2012 08:42:00 -0600 From: Nathan Whitehorn Subject: Re: November 5th is Clang-Day In-reply-to: <50967BD6.9090806@FreeBSD.org> To: freebsd-current@freebsd.org Message-id: <50967EB8.50308@freebsd.org> X-Spam-Report: AuthenticatedSender=yes, SenderIP=71.150.249.157 X-Spam-PmxInfo: Server=avs-13, Version=5.6.1.2065439, Antispam-Engine: 2.7.2.376379, Antispam-Data: 2012.11.4.143317, SenderIP=71.150.249.157 References: <20121102032945.GF65074@lor.one-eyed-alien.net> <201211030948.43530.naylor.b.david@gmail.com> <1TUlad-0008bB-OF@internal.tormail.org> <201211041442.16620.naylor.b.david@gmail.com> <20121104131830.GL73505@kib.kiev.ua> <50967BD6.9090806@FreeBSD.org> User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:16.0) Gecko/20121103 Thunderbird/16.0.2 X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 15:42:08 -0000 On 11/04/12 08:29, Dimitry Andric wrote: > On 2012-11-04 14:18, Konstantin Belousov wrote: >> On Sun, Nov 04, 2012 at 02:42:13PM +0200, David Naylor wrote: > ... >>> I tried building (using gcc) wine with your patch and now (at least) >>> winecfg >>> and regedit work with a clang built lib32. I'll email Gerald (wine's >>> maintainer) about including your patch in wine. >> >> The wine is the wrong place to fix. If system libraries suddenly started >> requiring 16-byte stack alignment on i386, it is unacceptable breakage >> of the ABI. > > So we really must use 4 byte stack alignment on i386 by default? I have > attached a diff to llvm for this, but I would like to verify that it is > really correct. Apparently Darwin, Linux and Solaris all use 16 byte > alignment. > > The Sys V ABI seems to say only: "The stack is word aligned. Although > the architecture does not require any alignment of the stack, software > convention and the operating system requires that the stack be aligned > on a word boundary". This is an ugly business. The stack is really 4 bytes aligned on Linux and Solaris too, but GCC decided to unilaterally change the ABI a few years ago (also on FreeBSD). You can find a chunk of the sordid story of this in a number of GCC bugs marked WONTFIX (e.g. http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38496). To pacify the people who were yelling about it, they added some __attribute__(()) foo and compiler flags to change what it uses for specific programs and add magic to realign the stack at boundaries. So much water has passed under the bridge at this point as to reach flood stage, so I think the correct solution here is to add the same __attribute__(()) and flags to clang rather than changing the default alignment back to 4. Changing it only on FreeBSD is especially wrong. -Nathan From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 15:09:45 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 43AB97FE for ; Sun, 4 Nov 2012 15:09:45 +0000 (UTC) (envelope-from levitch@iglou.com) Received: from rdsmtp.iglou.com (rdsmtp.iglou.com [192.107.41.63]) by mx1.freebsd.org (Postfix) with ESMTP id EA9258FC14 for ; Sun, 4 Nov 2012 15:09:44 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=iglou.com; s=alpha; h=Content-Type:MIME-Version:References:Message-ID:In-Reply-To:Subject:cc:To:From:Date; bh=nwcmw50PRbhR4OIiT+uzOPgjhlrIYBysaBrPzBY6+Iw=; b=rsPrttZ/3SAd3TRAE+8DJ0h6MBE53KHeXyE/QK+tZpzxlf+yi4rP/u50WCL+ZKQB5NEeyHMvYHU/4XI25SxWXzr0FLZ/ZPFm5RNHT8dxPiVbujNcAUArJ+QnOiAWTnNcItD2P+hGHP53Tbhe8WLAY2L6ORP9oRsCC93uodiPCi4=; Received: from iglou4.iglou.com ([192.107.41.39]:48509 helo=mail.iglou.com) by rdsmtp.iglou.com with esmtpa (Exim MTA/8.19.3) (envelope-from ) id 1TV1pX-0006U4-D6 by authid with igloumta_auth for current@freebsd.org; Sun, 04 Nov 2012 10:09:43 -0500 Received: from shell1.iglou.com ([192.107.41.17]:38848 helo=shell1) by mail.iglou.com with esmtps (TLS cipher TLSv1:AES256-SHA:256) (Exim MTA/8.19.3) (envelope-from ) id 1TV1pX-0005UT-00; Sun, 04 Nov 2012 10:09:43 -0500 Date: Sun, 4 Nov 2012 10:09:42 -0500 (EST) From: Darrel X-X-Sender: levitch@shell1 To: Bryan Drewery Subject: Re: [solved]: r2421600 amd64 /var/db/pkg In-Reply-To: <50967473.8080808@shatow.net> Message-ID: References: <50967473.8080808@shatow.net> User-Agent: Alpine 2.00 (GSO 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Originating-IP: 192.107.41.17 X-IgLou-Customer: 3cb6f76205bd20f518810676a67a982b X-Mailman-Approved-At: Sun, 04 Nov 2012 16:47:52 +0000 Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 15:09:45 -0000 >>> What you probably ran into is the common chicken and egg problem >>> where >>> if pkgng is upgraded ports, it blows up when it tries to deinstall the >>> package, or similarly, when portmaster is upgraded, it doesn't halt the >>> upgrade and restart it properly. >>> It's most likely still a problem; I'm going to doublecheck to make >>> sure >>> that's the case and file PRs if it is. >> >> Thanks, Garrett. For my current problem I am simply going to delete the >> errant portmaster-3.14 from /var/db/pkg and then run 'portmaster -a -f >> -D' with the hope that portmaster-3.14_7 can fix things. If not I will >> try reinstalling, the are only a few things installed- freeradius, >> postgresql, and about a dozen others. > > This is overkill. You either have a pkg_install database or a pkgng > database. Determining which will save you time. > > After you run pkg2ng, pkg_info will no longer work. It will complain > about corrupted packages, since all the data is gone, but portmaster has > stored additional information there, which confuses pkg_info. > > Check the output of 'pkg info'. If it lists all your packages, you are > done. Nothing more to do. > > If not, run pkg2ng. > > Also, you can see any packages that have not converted with: > find /var/db/pkg -name +CONTENTS > If nothing comes up, they are already all converted. > > Thanks, Bryan. Actually my fbsd10 machine already has portmaster reinstalling, which seems to be running alright. It has less than two dozen packages on it. I am looking at a fbsd9.1 machine right now, and it seems like a strange case considering your advice. If I run 'pkg info' or 'pkg_info' then all of the packages are listed. If I run 'find /var/db/pkg -name +CONTENTS' then all of the packages are found. Yet on that machine in /etc/make.conf exists 'WITH_PKGNG=yes' and I ran pkg2ng on the 15th of October. Darrel From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 19:46:59 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1DEEAF14; Sun, 4 Nov 2012 19:46:59 +0000 (UTC) (envelope-from tinderbox@freebsd.org) Received: from freebsd-current.sentex.ca (freebsd-current.sentex.ca [64.7.128.98]) by mx1.freebsd.org (Postfix) with ESMTP id CC13C8FC12; Sun, 4 Nov 2012 19:46:55 +0000 (UTC) Received: from freebsd-current.sentex.ca (localhost [127.0.0.1]) by freebsd-current.sentex.ca (8.14.5/8.14.5) with ESMTP id qA4Jksn9048232; Sun, 4 Nov 2012 14:46:54 -0500 (EST) (envelope-from tinderbox@freebsd.org) Received: (from tinderbox@localhost) by freebsd-current.sentex.ca (8.14.5/8.14.5/Submit) id qA4JksWQ048228; Sun, 4 Nov 2012 19:46:54 GMT (envelope-from tinderbox@freebsd.org) Date: Sun, 4 Nov 2012 19:46:54 GMT Message-Id: <201211041946.qA4JksWQ048228@freebsd-current.sentex.ca> X-Authentication-Warning: freebsd-current.sentex.ca: tinderbox set sender to FreeBSD Tinderbox using -f Sender: FreeBSD Tinderbox From: FreeBSD Tinderbox To: FreeBSD Tinderbox , , Subject: [head tinderbox] failure on mips64/mips Precedence: bulk X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 19:46:59 -0000 TB --- 2012-11-04 19:40:55 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-11-04 19:40:55 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 des@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-11-04 19:40:55 - starting HEAD tinderbox run for mips64/mips TB --- 2012-11-04 19:40:55 - cleaning the object tree TB --- 2012-11-04 19:40:55 - checking out /src from svn://svn.freebsd.org/base/head TB --- 2012-11-04 19:40:55 - cd /tinderbox/HEAD/mips64/mips TB --- 2012-11-04 19:40:55 - /usr/local/bin/svn cleanup /src TB --- 2012-11-04 19:41:54 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:41:54 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:41:54 - WARNING: sleeping 30 s and retrying... TB --- 2012-11-04 19:42:24 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:42:24 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:42:24 - WARNING: sleeping 60 s and retrying... TB --- 2012-11-04 19:43:24 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:43:24 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:43:24 - WARNING: sleeping 90 s and retrying... TB --- 2012-11-04 19:44:54 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:44:54 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:44:54 - WARNING: sleeping 120 s and retrying... TB --- 2012-11-04 19:46:54 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:46:54 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:46:54 - ERROR: unable to check out the source tree TB --- 2012-11-04 19:46:54 - 2.78 user 4.02 system 359.57 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-mips64-mips.full From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 19:53:03 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9EAC5454; Sun, 4 Nov 2012 19:53:03 +0000 (UTC) (envelope-from tinderbox@freebsd.org) Received: from freebsd-current.sentex.ca (freebsd-current.sentex.ca [64.7.128.98]) by mx1.freebsd.org (Postfix) with ESMTP id 5AE568FC14; Sun, 4 Nov 2012 19:53:03 +0000 (UTC) Received: from freebsd-current.sentex.ca (localhost [127.0.0.1]) by freebsd-current.sentex.ca (8.14.5/8.14.5) with ESMTP id qA4Jr2ep075564; Sun, 4 Nov 2012 14:53:02 -0500 (EST) (envelope-from tinderbox@freebsd.org) Received: (from tinderbox@localhost) by freebsd-current.sentex.ca (8.14.5/8.14.5/Submit) id qA4Jr2l2075563; Sun, 4 Nov 2012 19:53:02 GMT (envelope-from tinderbox@freebsd.org) Date: Sun, 4 Nov 2012 19:53:02 GMT Message-Id: <201211041953.qA4Jr2l2075563@freebsd-current.sentex.ca> X-Authentication-Warning: freebsd-current.sentex.ca: tinderbox set sender to FreeBSD Tinderbox using -f Sender: FreeBSD Tinderbox From: FreeBSD Tinderbox To: FreeBSD Tinderbox , , Subject: [head tinderbox] failure on powerpc/powerpc Precedence: bulk X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 19:53:03 -0000 TB --- 2012-11-04 19:46:54 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-11-04 19:46:54 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 des@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-11-04 19:46:54 - starting HEAD tinderbox run for powerpc/powerpc TB --- 2012-11-04 19:46:54 - cleaning the object tree TB --- 2012-11-04 19:46:54 - checking out /src from svn://svn.freebsd.org/base/head TB --- 2012-11-04 19:46:54 - cd /tinderbox/HEAD/powerpc/powerpc TB --- 2012-11-04 19:46:54 - /usr/local/bin/svn cleanup /src TB --- 2012-11-04 19:48:02 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:48:02 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:48:02 - WARNING: sleeping 30 s and retrying... TB --- 2012-11-04 19:48:32 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:48:32 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:48:32 - WARNING: sleeping 60 s and retrying... TB --- 2012-11-04 19:49:32 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:49:32 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:49:32 - WARNING: sleeping 90 s and retrying... TB --- 2012-11-04 19:51:02 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:51:02 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:51:02 - WARNING: sleeping 120 s and retrying... TB --- 2012-11-04 19:53:02 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:53:02 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:53:02 - ERROR: unable to check out the source tree TB --- 2012-11-04 19:53:02 - 2.84 user 3.88 system 367.87 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-powerpc-powerpc.full From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 19:53:05 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6319A457 for ; Sun, 4 Nov 2012 19:53:05 +0000 (UTC) (envelope-from andre@freebsd.org) Received: from c00l3r.networx.ch (c00l3r.networx.ch [62.48.2.2]) by mx1.freebsd.org (Postfix) with ESMTP id E85718FC0A for ; Sun, 4 Nov 2012 19:53:04 +0000 (UTC) Received: (qmail 42186 invoked from network); 4 Nov 2012 21:28:51 -0000 Received: from c00l3r.networx.ch (HELO [127.0.0.1]) ([62.48.2.2]) (envelope-sender ) by c00l3r.networx.ch (qmail-ldap-1.03) with SMTP for ; 4 Nov 2012 21:28:51 -0000 Message-ID: <5096C79E.6020400@freebsd.org> Date: Sun, 04 Nov 2012 20:53:02 +0100 From: Andre Oppermann User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:16.0) Gecko/20121010 Thunderbird/16.0.1 MIME-Version: 1.0 To: John Baldwin Subject: Re: kernel module parallel build? References: <5083D84E.50903@freebsd.org> <201210220928.52778.jhb@freebsd.org> In-Reply-To: <201210220928.52778.jhb@freebsd.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-hackers@freebsd.org, freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 19:53:05 -0000 On 22.10.2012 15:28, John Baldwin wrote: > On Sunday, October 21, 2012 7:11:10 am Andre Oppermann wrote: >> What's keeping kernel modules from building in parallel with >> "make -j8"? > > They don't for you? They do for me either via 'make buildkernel' > or the old method. They do, but only partially. Within a module the files are built in parallel. However the module directories seem to be serialized. I'm a Makefile noob though. -- Andre From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 19:58:47 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 656CA8CA; Sun, 4 Nov 2012 19:58:47 +0000 (UTC) (envelope-from tinderbox@freebsd.org) Received: from freebsd-current.sentex.ca (freebsd-current.sentex.ca [64.7.128.98]) by mx1.freebsd.org (Postfix) with ESMTP id 200E08FC0C; Sun, 4 Nov 2012 19:58:47 +0000 (UTC) Received: from freebsd-current.sentex.ca (localhost [127.0.0.1]) by freebsd-current.sentex.ca (8.14.5/8.14.5) with ESMTP id qA4JwkgY019324; Sun, 4 Nov 2012 14:58:46 -0500 (EST) (envelope-from tinderbox@freebsd.org) Received: (from tinderbox@localhost) by freebsd-current.sentex.ca (8.14.5/8.14.5/Submit) id qA4Jwkhq019323; Sun, 4 Nov 2012 19:58:46 GMT (envelope-from tinderbox@freebsd.org) Date: Sun, 4 Nov 2012 19:58:46 GMT Message-Id: <201211041958.qA4Jwkhq019323@freebsd-current.sentex.ca> X-Authentication-Warning: freebsd-current.sentex.ca: tinderbox set sender to FreeBSD Tinderbox using -f Sender: FreeBSD Tinderbox From: FreeBSD Tinderbox To: FreeBSD Tinderbox , , Subject: [head tinderbox] failure on powerpc64/powerpc Precedence: bulk X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 19:58:47 -0000 TB --- 2012-11-04 19:53:02 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-11-04 19:53:02 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 des@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-11-04 19:53:02 - starting HEAD tinderbox run for powerpc64/powerpc TB --- 2012-11-04 19:53:02 - cleaning the object tree TB --- 2012-11-04 19:53:02 - checking out /src from svn://svn.freebsd.org/base/head TB --- 2012-11-04 19:53:02 - cd /tinderbox/HEAD/powerpc64/powerpc TB --- 2012-11-04 19:53:02 - /usr/local/bin/svn cleanup /src TB --- 2012-11-04 19:53:46 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:53:46 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:53:46 - WARNING: sleeping 30 s and retrying... TB --- 2012-11-04 19:54:16 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:54:16 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:54:16 - WARNING: sleeping 60 s and retrying... TB --- 2012-11-04 19:55:16 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:55:16 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:55:16 - WARNING: sleeping 90 s and retrying... TB --- 2012-11-04 19:56:46 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:56:46 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:56:46 - WARNING: sleeping 120 s and retrying... TB --- 2012-11-04 19:58:46 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:58:46 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:58:46 - ERROR: unable to check out the source tree TB --- 2012-11-04 19:58:46 - 3.01 user 3.77 system 343.60 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-powerpc64-powerpc.full From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 20:04:15 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7FA3BD1A; Sun, 4 Nov 2012 20:04:15 +0000 (UTC) (envelope-from tinderbox@freebsd.org) Received: from freebsd-current.sentex.ca (freebsd-current.sentex.ca [64.7.128.98]) by mx1.freebsd.org (Postfix) with ESMTP id 3D4408FC0C; Sun, 4 Nov 2012 20:04:14 +0000 (UTC) Received: from freebsd-current.sentex.ca (localhost [127.0.0.1]) by freebsd-current.sentex.ca (8.14.5/8.14.5) with ESMTP id qA4K4EOj030711; Sun, 4 Nov 2012 15:04:14 -0500 (EST) (envelope-from tinderbox@freebsd.org) Received: (from tinderbox@localhost) by freebsd-current.sentex.ca (8.14.5/8.14.5/Submit) id qA4K4Eow030707; Sun, 4 Nov 2012 20:04:14 GMT (envelope-from tinderbox@freebsd.org) Date: Sun, 4 Nov 2012 20:04:14 GMT Message-Id: <201211042004.qA4K4Eow030707@freebsd-current.sentex.ca> X-Authentication-Warning: freebsd-current.sentex.ca: tinderbox set sender to FreeBSD Tinderbox using -f Sender: FreeBSD Tinderbox From: FreeBSD Tinderbox To: FreeBSD Tinderbox , , Subject: [head tinderbox] failure on sparc64/sparc64 Precedence: bulk X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 20:04:15 -0000 TB --- 2012-11-04 19:58:46 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-11-04 19:58:46 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 des@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-11-04 19:58:46 - starting HEAD tinderbox run for sparc64/sparc64 TB --- 2012-11-04 19:58:46 - cleaning the object tree TB --- 2012-11-04 19:58:46 - checking out /src from svn://svn.freebsd.org/base/head TB --- 2012-11-04 19:58:46 - cd /tinderbox/HEAD/sparc64/sparc64 TB --- 2012-11-04 19:58:46 - /usr/local/bin/svn cleanup /src TB --- 2012-11-04 19:59:14 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:59:14 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:59:14 - WARNING: sleeping 30 s and retrying... TB --- 2012-11-04 19:59:44 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:59:44 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:59:44 - WARNING: sleeping 60 s and retrying... TB --- 2012-11-04 20:00:44 - /usr/local/bin/svn update /src TB --- 2012-11-04 20:00:44 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 20:00:44 - WARNING: sleeping 90 s and retrying... TB --- 2012-11-04 20:02:14 - /usr/local/bin/svn update /src TB --- 2012-11-04 20:02:14 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 20:02:14 - WARNING: sleeping 120 s and retrying... TB --- 2012-11-04 20:04:14 - /usr/local/bin/svn update /src TB --- 2012-11-04 20:04:14 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 20:04:14 - ERROR: unable to check out the source tree TB --- 2012-11-04 20:04:14 - 2.79 user 3.84 system 327.79 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-sparc64-sparc64.full From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 20:06:35 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 8A342FE0; Sun, 4 Nov 2012 20:06:35 +0000 (UTC) (envelope-from tinderbox@freebsd.org) Received: from freebsd-current.sentex.ca (freebsd-current.sentex.ca [64.7.128.98]) by mx1.freebsd.org (Postfix) with ESMTP id 3E2798FC14; Sun, 4 Nov 2012 20:06:34 +0000 (UTC) Received: from freebsd-current.sentex.ca (localhost [127.0.0.1]) by freebsd-current.sentex.ca (8.14.5/8.14.5) with ESMTP id qA4JesWV028215; Sun, 4 Nov 2012 14:40:54 -0500 (EST) (envelope-from tinderbox@freebsd.org) Received: (from tinderbox@localhost) by freebsd-current.sentex.ca (8.14.5/8.14.5/Submit) id qA4Jesx7028211; Sun, 4 Nov 2012 19:40:54 GMT (envelope-from tinderbox@freebsd.org) Date: Sun, 4 Nov 2012 19:40:54 GMT Message-Id: <201211041940.qA4Jesx7028211@freebsd-current.sentex.ca> X-Authentication-Warning: freebsd-current.sentex.ca: tinderbox set sender to FreeBSD Tinderbox using -f Sender: FreeBSD Tinderbox From: FreeBSD Tinderbox To: FreeBSD Tinderbox , , Subject: [head tinderbox] failure on mips/mips Precedence: bulk X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 20:06:35 -0000 TB --- 2012-11-04 19:35:19 - tinderbox 2.9 running on freebsd-current.sentex.ca TB --- 2012-11-04 19:35:19 - FreeBSD freebsd-current.sentex.ca 8.3-PRERELEASE FreeBSD 8.3-PRERELEASE #0: Mon Mar 26 13:54:12 EDT 2012 des@freebsd-current.sentex.ca:/usr/obj/usr/src/sys/GENERIC amd64 TB --- 2012-11-04 19:35:19 - starting HEAD tinderbox run for mips/mips TB --- 2012-11-04 19:35:19 - cleaning the object tree TB --- 2012-11-04 19:35:19 - checking out /src from svn://svn.freebsd.org/base/head TB --- 2012-11-04 19:35:19 - cd /tinderbox/HEAD/mips/mips TB --- 2012-11-04 19:35:19 - /usr/local/bin/svn cleanup /src TB --- 2012-11-04 19:35:54 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:35:54 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:35:54 - WARNING: sleeping 30 s and retrying... TB --- 2012-11-04 19:36:24 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:36:24 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:36:24 - WARNING: sleeping 60 s and retrying... TB --- 2012-11-04 19:37:24 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:37:24 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:37:24 - WARNING: sleeping 90 s and retrying... TB --- 2012-11-04 19:38:54 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:38:54 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:38:54 - WARNING: sleeping 120 s and retrying... TB --- 2012-11-04 19:40:54 - /usr/local/bin/svn update /src TB --- 2012-11-04 19:40:54 - WARNING: /usr/local/bin/svn returned exit code 1 TB --- 2012-11-04 19:40:54 - ERROR: unable to check out the source tree TB --- 2012-11-04 19:40:54 - 2.95 user 3.45 system 335.25 real http://tinderbox.freebsd.org/tinderbox-head-HEAD-mips-mips.full From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 20:41:18 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4C488C34; Sun, 4 Nov 2012 20:41:18 +0000 (UTC) (envelope-from andreast-list@fgznet.ch) Received: from smtp.fgznet.ch (mail.fgznet.ch [81.92.96.47]) by mx1.freebsd.org (Postfix) with ESMTP id E4A858FC0A; Sun, 4 Nov 2012 20:41:17 +0000 (UTC) Received: from deuterium.andreas.nets (dhclient-91-190-14-19.flashcable.ch [91.190.14.19]) by smtp.fgznet.ch (8.13.8/8.13.8/Submit_SMTPAUTH) with ESMTP id qA4KFQiE091552; Sun, 4 Nov 2012 21:15:27 +0100 (CET) (envelope-from andreast-list@fgznet.ch) Message-ID: <5096CCDE.7090305@fgznet.ch> Date: Sun, 04 Nov 2012 21:15:26 +0100 From: Andreas Tobler User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.5; rv:16.0) Gecko/20121026 Thunderbird/16.0.2 MIME-Version: 1.0 To: Andre Oppermann Subject: Re: weird network problems on current since 10/28/2012 References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> <50967453.5090503@freebsd.org> In-Reply-To: <50967453.5090503@freebsd.org> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.64 on 81.92.96.47 Cc: Kim Culhan , Dimitry Andric , freebsd-current@freebsd.org, Adrian Chadd X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 20:41:18 -0000 On 04.11.12 14:57, Andre Oppermann wrote: > On 04.11.2012 13:11, Kim Culhan wrote: >> On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: >>> On 2012-11-04 02:13, Manfred Antar wrote: >>>> At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>>> On 3 November 2012 10:40, Manfred Antar wrote: >>>>>> i have problem connecting to freebsd box on local network since last sunday. >>>>>> the last kernel that works: >>>>>> FreeBSD 10.0-CURRENT #0: Sun Oct 28 12:14:38 PDT 2012 >>>>>> anything after that, sometimes i can connect, other times just hangs. >>>>>> any network connection hangs ===== pop httpd ssh etc etc. >>>>>> anyone have any ideas ? >>>>>> i can checkout different sources and see if i can locate the changes that cause >>>>>> this. >>>>> >>>>> Please do! >>> ... >>>> Here is what I found doing : >>>> setenv CVSROOT /usr/home/ncvs >>>> >>>> cvs co -D"October 28, 2012 12:14:38 PDT" sys >>>> >>>> A kernel from that time works fine. >>>> >>>> doing: >>>> >>>> cvs up -D"October 28, 2012 13:14:38 PDT" sys 1 hour later >>>> the following files were changed: >>>> sys/netinet/tcp_input.c >>>> sys/netinet/tcp_timer.c >>>> sys/netinet/tcp_var.h >>>> >>>> Building a kernel from these new files is when the problem starts. >>> >>> So, your problems seem to have been introduced by this commit by Andre: >>> >>> http://svn.freebsd.org/changeset/base/242266 >>> >>> Increase the initial CWND to 10 segments as defined in IETF TCPM >>> draft-ietf-tcpm-initcwnd-05. It explains why the increased initial >>> window improves the overall performance of many web services without >>> risking congestion collapse. >>> >>> As long as it remains a draft it is placed under a sysctl marking it >>> as experimental: >>> net.inet.tcp.experimental.initcwnd10 = 1 >>> When it becomes an official RFC soon the sysctl will be changed to >>> the RFC number and moved to net.inet.tcp. >>> >>> This implementation differs from the RFC draft in that it is a bit >>> more conservative in the case of packet loss on SYN or SYN|ACK because >>> we haven't reduced the default RTO to 1 second yet. Also the restart >>> window isn't yet increased as allowed. Both will be adjusted with >>> upcoming changes. >>> >>> Is is enabled by default. In Linux it is enabled since kernel 3.0. >>> >>> After the commit, there was a small discussion thread on svn-src-head@ >>> about the possible problems with the approach. Maybe you are >>> experiencing those? >>> >>> As the commit message says, you should be able to turn the feature off >>> using: >>> >>> sysctl net.inet.tcp.experimental.initcwnd10=0 >>> >>> Can you please try that, and see if the problems go away? >> >> FWIW this did not make the problem go away on 2 machines. > > Yes, this very much looks like the same problem as in PR/173309. > > Please try the attached patch. It fixes the connection hang issue. > There may be a second issue I debugging currently base on the feedback > from Fabian Keil. I jump into this thread since I have a similar network issue. My scenario: 'make installkernel DESTDIR=/netboot/test' to a nfs mounted drive. The nfs drive on the server is an ufs fs. No zfs. Up to r242261 I can install the kernel (or world) in a fluent way to the nfs destination. >From r242262 it doesn't work smooth. I have stalls, sometimes my patience is not enough and I kill the process. I tried 242266 with the above mentioned patch. No real success. How can I help/test? TIA, Andreas From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 21:50:14 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7BB995BB for ; Sun, 4 Nov 2012 21:50:14 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id 2332B8FC0A for ; Sun, 4 Nov 2012 21:50:13 +0000 (UTC) Received: from outgoing.leidinger.net (p5DD4596B.dip.t-dialin.net [93.212.89.107]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id 6B8A3844096; Sun, 4 Nov 2012 22:50:10 +0100 (CET) Received: from unknown (IO.Leidinger.net [192.168.1.12]) by outgoing.leidinger.net (Postfix) with ESMTPS id EAC78218C; Sun, 4 Nov 2012 22:50:07 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=leidinger.net; s=outgoing-alex; t=1352065807; bh=wHwjIhxQvEcBlDGvOAODUT3x6oWsbQ4Up7IghIpufQY=; h=Date:From:To:Cc:Subject:In-Reply-To:References; b=Lj7AkUhU/oF/iK9nMq8Riwatm20C3mQHxOGjoq1xQBrJqiw7MblYzQQ2ULMACRLL9 ZYzvw370ofazybIoxhlS45cql0dkZgUTdljAp3Ox+pHXZfXkSNvz0v5gM/pyHM0i15 U57pDWAPLVF+5mNVRnATOlzOCtTLF541wgxU5WMrtxLB2MVs8PONS4MwmcHpNeIZgD 53OVWzB7/SijuQaXUwpmv1z7uQGmhtOStFv2fRIkyySeinxgHeIUEhGBLO6zRCGz6E RkvXtU5rtS5hsQPVvgqeSJ37LPJr5z9edvMyc+P+3EqEAs415t0wNPJhNWWKMzE18d NMPygu9Tzq6mQ== Date: Sun, 4 Nov 2012 22:50:10 +0100 From: Alexander Leidinger To: d@delphij.net Subject: Re: watchdogd coredump Message-ID: <20121104225010.00000560@unknown> In-Reply-To: <50959F0B.7010505@delphij.net> References: <20121103225542.00001118@unknown> <20121103220843.GI73505@kib.kiev.ua> <20121103233426.0000371d@unknown> <50959F0B.7010505@delphij.net> X-Mailer: Claws Mail 3.8.0cvs30 (GTK+ 2.24.10; i586-pc-mingw32msvc) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: 6B8A3844096.AEFC2 X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=-1.259, required 6, autolearn=disabled, ALL_TRUSTED -1.00, AWL -1.11, DKIM_SIGNED 0.10, J_CHICKENPOX_65 0.60, TW_SV 0.08, TW_VN 0.08, T_DKIM_INVALID 0.01, T_RP_MATCHES_RCVD -0.01) X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1352670610.61308@UrAGxZe/x4iloCt7UlrQBA X-EBL-Spam-Status: No Cc: freebsd-current@freebsd.org, delphij@delphij.net X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 21:50:14 -0000 On Sat, 03 Nov 2012 15:47:39 -0700 Xin Li wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA256 > > On 11/3/12 3:34 PM, Alexander Leidinger wrote: > > On Sun, 4 Nov 2012 00:08:43 +0200 Konstantin Belousov > > wrote: > > > >> Are you sure that your kernel is at r242511 ? > >> > >> The issue should have been fixed by r242011. > > > > # svnversion 242511M > > > > # svn status M contrib/bind9/bin/named/interfacemgr.c M > > etc/defaults/rc.conf M etc/rc.d/jail M > > sys/dev/ata/ata-all.c M sys/dev/drm/drmP.h M > > sys/dev/usb/serial/ulpt.c M sys/kern/kern_jail.c M > > sys/sys/jail.h M sys/sys/priv.h M sys/vm/uma_core.c > > > > The uma_core patch is the one floating around which shall prevent > > memory fragmentation, the others are mostly my X-in-jail and some > > minor default values (ata, ulpt) changes. > > > > Currently I'm back to the previous kernel+world, but I still have > > the r242511M boot environment available (I have no time to > > investigate the problem this evening, and I want to have a stable > > system until I get time to have a deeper look at this). > > What was 'strings /boot/kernel.bad/kernel | tail' saying? I verified at boot that the kernel was booting the right kernel: ---snip--- # strings /rpool/ROOT/r242511M/boot/kernel/kernel | tail [...] @(#)FreeBSD 10.0-CURRENT #10 r242511M: Sat Nov 3 17:49:09 CET 2012 FreeBSD 10.0-CURRENT #10 r242511M: Sat Nov 3 17:49:09 CET 2012 root@Andromeda.Leidinger.net:/usr/obj/space/system/usr_src/sys/ANDROMEDA [...] ---snip--- Anything special you want me to investigate? Bye, Alexander. -- http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID = B0063FE7 http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID = 72077137 From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 21:55:32 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9EFDE707; Sun, 4 Nov 2012 21:55:32 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id 484858FC12; Sun, 4 Nov 2012 21:55:32 +0000 (UTC) Received: from outgoing.leidinger.net (p5DD4596B.dip.t-dialin.net [93.212.89.107]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id 4143E844096; Sun, 4 Nov 2012 22:55:29 +0100 (CET) Received: from unknown (IO.Leidinger.net [192.168.1.12]) by outgoing.leidinger.net (Postfix) with ESMTPS id B2D16218E; Sun, 4 Nov 2012 22:55:26 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=leidinger.net; s=outgoing-alex; t=1352066126; bh=GJh/k4Bbq3KfdIBkt9mYJ8ZCOzXtaU9ZCGdCeoNFBIo=; h=Date:From:To:Cc:Subject:In-Reply-To:References; b=jZS9/e6Fr9a1yuihitC+pGSEzR734nWREIEinvwN2OiiJTqOk/gRZDn+KZbbnocJF e9xGCOXbpPz3RnQoomd4i3DqJ/lON9XMMol3GzvyzLERayaC1ROSiVJqAB9OiGo/uX kR5Ys9+JF/tvmDp9NV5ZO/ke6zcGHg49iUff78zsN4pSp1zAaHci2njcySQLwKngtk QJSe7YcmCf7w83z8YtNO0Yn9Q3KiV/Jtag914Nx4NW2SM10pl089JlDPKofb3xNfNr Igh8jpJn2TR+fC0ocMnf03tLlXSBruGj/S1+BFhiOtLdnP8ICeYUVIAqj2Vxq0Kn7D OrJw61ljcHM7w== Date: Sun, 4 Nov 2012 22:55:29 +0100 From: Alexander Leidinger To: Dimitry Andric Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? Message-ID: <20121104225529.000028a9@unknown> In-Reply-To: <5095ACC7.1050002@FreeBSD.org> References: <20121103232433.00005eee@unknown> <5095ACC7.1050002@FreeBSD.org> X-Mailer: Claws Mail 3.8.0cvs30 (GTK+ 2.24.10; i586-pc-mingw32msvc) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: 4143E844096.ADB97 X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=-1.627, required 6, autolearn=disabled, ALL_TRUSTED -1.00, AWL -0.73, DKIM_SIGNED 0.10, T_DKIM_INVALID 0.01, T_RP_MATCHES_RCVD -0.01) X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1352670929.40752@Jg34r9xaffkAthVY0yLomg X-EBL-Spam-Status: No Cc: current@FreeBSD.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 21:55:32 -0000 On Sun, 04 Nov 2012 00:46:15 +0100 Dimitry Andric wrote: > On 2012-11-03 23:24, Alexander Leidinger wrote: > > while trying to update from r239708 to r242511 (amd64 arch) I tried > > to compile the world with "make -j8". After a short while I got an > > internal error in the clang compile (this is a gcc-compiled system, > > I don't use clang). The CFLAGS/COPTFLAGS are -O2 -pipe. > > > > Without the -j8 it compiles just fine. > > Without the CPUTYPE?=native it compiles even with -j8. > > Hm, at first I thought you might be running out of RAM, but apparently > that is not the case then. :) The machine has 12 MB RAM (no swap configured), after nearly a day uptime it looks like this: ---snip--- Mem: 348M Active, 599M Inact, 9281M Wired, 264K Cache, 1548M Free ARC: 7117M Total, 1607M MRU, 3996M MFU, 934K Anon, 208M Header, 1307M Other ---snip--- I would not expect an internal compiler error when I run out of RAM. > > The CPU is an Intel(R) Xeon(R) CPU (L5630) with ECC ram. > > What does gcc detect for this CPU with -march=native? You can do: > > gcc -march=native -v -c -x c /dev/null 2>&1 | grep -- -march > > to see what it passes to the second stage. ---snip--- # gcc -march=native -v -c -x c /dev/null 2>&1 | grep -- -march /usr/libexec/cc1 -quiet -v -D_LONGLONG /dev/null -march=core2 -mtune=generic -quiet -dumpbase null -auxbase null -version -o /tmp//cc7kc0JI.s ---snip--- Bye, Alexander. -- http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID = B0063FE7 http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID = 72077137 From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 21:57:43 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id BA63D9E4 for ; Sun, 4 Nov 2012 21:57:43 +0000 (UTC) (envelope-from andre@freebsd.org) Received: from c00l3r.networx.ch (c00l3r.networx.ch [62.48.2.2]) by mx1.freebsd.org (Postfix) with ESMTP id 1B0AE8FC0C for ; Sun, 4 Nov 2012 21:57:42 +0000 (UTC) Received: (qmail 43055 invoked from network); 4 Nov 2012 23:33:28 -0000 Received: from c00l3r.networx.ch (HELO [127.0.0.1]) ([62.48.2.2]) (envelope-sender ) by c00l3r.networx.ch (qmail-ldap-1.03) with SMTP for ; 4 Nov 2012 23:33:28 -0000 Message-ID: <5096E4D4.6000000@freebsd.org> Date: Sun, 04 Nov 2012 22:57:40 +0100 From: Andre Oppermann User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:16.0) Gecko/20121010 Thunderbird/16.0.1 MIME-Version: 1.0 To: Andreas Tobler Subject: Re: weird network problems on current since 10/28/2012 References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> <50967453.5090503@freebsd.org> <5096CCDE.7090305@fgznet.ch> In-Reply-To: <5096CCDE.7090305@fgznet.ch> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Kim Culhan , Dimitry Andric , freebsd-current@freebsd.org, Adrian Chadd X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 21:57:43 -0000 On 04.11.2012 21:15, Andreas Tobler wrote: > On 04.11.12 14:57, Andre Oppermann wrote: >> On 04.11.2012 13:11, Kim Culhan wrote: >>> On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: >>>> On 2012-11-04 02:13, Manfred Antar wrote: >>>>> At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>> After the commit, there was a small discussion thread on svn-src-head@ >>>> about the possible problems with the approach. Maybe you are >>>> experiencing those? >>>> >>>> As the commit message says, you should be able to turn the feature off >>>> using: >>>> >>>> sysctl net.inet.tcp.experimental.initcwnd10=0 >>>> >>>> Can you please try that, and see if the problems go away? >>> >>> FWIW this did not make the problem go away on 2 machines. >> >> Yes, this very much looks like the same problem as in PR/173309. >> >> Please try the attached patch. It fixes the connection hang issue. >> There may be a second issue I debugging currently base on the feedback >> from Fabian Keil. > > I jump into this thread since I have a similar network issue. > > My scenario: > > 'make installkernel DESTDIR=/netboot/test' to a nfs mounted drive. > The nfs drive on the server is an ufs fs. No zfs. > > Up to r242261 I can install the kernel (or world) in a fluent way to the > nfs destination. > >>From r242262 it doesn't work smooth. I have stalls, sometimes my > patience is not enough and I kill the process. > > I tried 242266 with the above mentioned patch. No real success. > > How can I help/test? Please try the attach patch instead of the above mentioned one. -- Andre Index: netinet/tcp_output.c =================================================================== --- netinet/tcp_output.c (revision 242577) +++ netinet/tcp_output.c (working copy) @@ -228,7 +228,7 @@ tso = 0; mtu = 0; off = tp->snd_nxt - tp->snd_una; - sendwin = min(tp->snd_wnd, tp->snd_cwnd); + sendwin = ulmax(ulmin(tp->snd_wnd - off, tp->snd_cwnd), 0); flags = tcp_outflags[tp->t_state]; /* @@ -249,7 +249,7 @@ (p = tcp_sack_output(tp, &sack_bytes_rxmt))) { long cwin; - cwin = min(tp->snd_wnd, tp->snd_cwnd) - sack_bytes_rxmt; + cwin = ulmin(tp->snd_wnd - off, tp->snd_cwnd) - sack_bytes_rxmt; if (cwin < 0) cwin = 0; /* Do not retransmit SACK segments beyond snd_recover */ @@ -355,7 +355,7 @@ * sending new data, having retransmitted all the * data possible in the scoreboard. */ - len = ((long)ulmin(so->so_snd.sb_cc, tp->snd_wnd) + len = ((long)ulmin(so->so_snd.sb_cc, tp->snd_wnd - off) - off); /* * Don't remove this (len > 0) check ! From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 22:01:03 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E9057CD0 for ; Sun, 4 Nov 2012 22:01:03 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id 8FA368FC1A for ; Sun, 4 Nov 2012 22:01:03 +0000 (UTC) Received: from outgoing.leidinger.net (p5DD4596B.dip.t-dialin.net [93.212.89.107]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id 9D37E844096; Sun, 4 Nov 2012 23:00:53 +0100 (CET) Received: from unknown (IO.Leidinger.net [192.168.1.12]) by outgoing.leidinger.net (Postfix) with ESMTPS id 1F82D2190; Sun, 4 Nov 2012 23:00:51 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=leidinger.net; s=outgoing-alex; t=1352066451; bh=0G0pqjMesrg1gf/Z35wgRpNctOHXWukgGmlA8++I9ko=; h=Date:From:To:Cc:Subject:In-Reply-To:References; b=FYNxj6ZyMkQoSjCfkiYvSkNtZWum5OGxtYXc41clcvtrpJ8K4pdZoLo3JJSJNT4J1 gUI5nMsLx31fWZ9YuZ+Z8hPLaAuHv3YzYlWc7qyEAhW6G/xF8qa5wqZpj2rBbZgMKP 3nBhuT7rzqhXF8YOG7Jfn5DDBpATPut95HIhRUCnDKpjpPQ7w9HCnXb+QzTLZ2FluH pdCUDUcgKUK7KG8RZCc6IzjeVZkxX7YpTqquk3s1g6QXM6fG4QialBeePD/fWSCHSK 3TgvW9QTq5eFMWvsTgAULDI6A8CgJaPOllkV0IBJLRJDI8VXcALmFEq5LnoPCz6AoQ +8dNKL6BiQ7OQ== Date: Sun, 4 Nov 2012 23:00:53 +0100 From: Alexander Leidinger To: Olivier Smedts Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? Message-ID: <20121104230053.00006cd6@unknown> In-Reply-To: References: <20121103232433.00005eee@unknown> X-Mailer: Claws Mail 3.8.0cvs30 (GTK+ 2.24.10; i586-pc-mingw32msvc) Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: 9D37E844096.A00DA X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=-1.646, required 6, autolearn=disabled, ALL_TRUSTED -1.00, AWL -0.75, DKIM_SIGNED 0.10, T_DKIM_INVALID 0.01, T_RP_MATCHES_RCVD -0.01) X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1352671255.45265@bwHW1j4rKCzlHq+yjnJ9dg X-EBL-Spam-Status: No Cc: Scot Hetzel , "current@freebsd.org" X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 22:01:04 -0000 On Sun, 4 Nov 2012 14:43:30 +0100 Olivier Smedts wrote: > Le dimanche 4 novembre 2012, Scot Hetzel a =E9crit : > > > > When you set CPUTYPE?=3Dnative, bsd.cpu.mk doesn't set MACHINE_CPU to > > the correct values for your CPUTYPE. > > >=20 > This comes regularly in the lists. This basically means we need to do something about it. > Try setting the correct CPUTYPE for your CPU, and if you want to use > "native" somewhere, add "-march=3Dnative" to your CFLAGS. There's > another option to use so that *.mk don't add another "-march" with > your CPUTYPE automatically. We either should bail out if someone uses native as CPUTYPE, or we should make it just work. Personally I don't have a preference for one or the other, important is that the user gets a behavior he can count on. Bye, Alexander. --=20 http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID =3D B0063FE7 http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID =3D 72077137 From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 22:02:48 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 079FADFA for ; Sun, 4 Nov 2012 22:02:48 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id A52CD8FC0C for ; Sun, 4 Nov 2012 22:02:47 +0000 (UTC) Received: from outgoing.leidinger.net (p5DD4596B.dip.t-dialin.net [93.212.89.107]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id 5F618844096; Sun, 4 Nov 2012 23:02:45 +0100 (CET) Received: from unknown (IO.Leidinger.net [192.168.1.12]) by outgoing.leidinger.net (Postfix) with ESMTPS id D6A202191; Sun, 4 Nov 2012 23:02:42 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=leidinger.net; s=outgoing-alex; t=1352066562; bh=esLr5BkgEP3ZznVJWuEzZy3kqI8XKeHBbMtf7F1o5r4=; h=Date:From:To:Cc:Subject:In-Reply-To:References; b=i/P1WqtGGDXgevhVyYF4sg0+tIQU87MZ8bWTecACy3Yld8h6p33x2pFe45ye8CvST FPfS6MEfyCFc3afviovPbiVVQGhcKM75M+GKATRYSI0vlYi/E1VU5nVeHx49HvyW/e iUb+717Ey0423mx/IXnmZDlCqDNnFIn25eV/g+gdSu8jbUydN+7j9DSzx9GXn+nKzV U33OWaKKCZSzg8q/iHBcERlMh5qKIglCu10RE59pQSFpLYMqTui1PsEjY1NZ+1R8gW LrsBDJqyn056WlVdIpDFz0geqZCau+9XSkGS1VLS6Y8fVkwZNg1auqgolHo58BA1Gk hiJmmXeFTVOVA== Date: Sun, 4 Nov 2012 23:02:45 +0100 From: Alexander Leidinger To: Scot Hetzel Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? Message-ID: <20121104230245.00007139@unknown> In-Reply-To: References: <20121103232433.00005eee@unknown> X-Mailer: Claws Mail 3.8.0cvs30 (GTK+ 2.24.10; i586-pc-mingw32msvc) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: 5F618844096.A011A X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=-1.663, required 6, autolearn=disabled, ALL_TRUSTED -1.00, AWL -0.76, DKIM_SIGNED 0.10, T_DKIM_INVALID 0.01, T_RP_MATCHES_RCVD -0.01) X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1352671365.781@SZkZFaFmj2j4MghsVltgQA X-EBL-Spam-Status: No Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 22:02:48 -0000 On Sun, 4 Nov 2012 03:43:13 -0600 Scot Hetzel wrote: > Not sure if your hitting the same bug, that was found in PR 112997. > > When you set CPUTYPE?=native, bsd.cpu.mk doesn't set MACHINE_CPU to > the correct values for your CPUTYPE. > > See http://www.freebsd.org/cgi/query-pr.cgi?pr=conf/112997 for a patch > to bsd.cpu.mk. I try to get a look at it this week. > Does your system compile correctly, if you specify the CPUTYPE? I haven't tried it yet. I will give it a try later. Bye, Alexander. -- http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID = B0063FE7 http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID = 72077137 From owner-freebsd-current@FreeBSD.ORG Sun Nov 4 23:28:11 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D18E92D0; Sun, 4 Nov 2012 23:28:11 +0000 (UTC) (envelope-from andreast-list@fgznet.ch) Received: from smtp.fgznet.ch (mail.fgznet.ch [81.92.96.47]) by mx1.freebsd.org (Postfix) with ESMTP id 42D5D8FC14; Sun, 4 Nov 2012 23:28:08 +0000 (UTC) Received: from deuterium.andreas.nets (dhclient-91-190-14-19.flashcable.ch [91.190.14.19]) by smtp.fgznet.ch (8.13.8/8.13.8/Submit_SMTPAUTH) with ESMTP id qA4NS3rc011366; Mon, 5 Nov 2012 00:28:07 +0100 (CET) (envelope-from andreast-list@fgznet.ch) Message-ID: <5096FA03.9010509@fgznet.ch> Date: Mon, 05 Nov 2012 00:28:03 +0100 From: Andreas Tobler User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.5; rv:16.0) Gecko/20121026 Thunderbird/16.0.2 MIME-Version: 1.0 To: Andre Oppermann Subject: Re: weird network problems on current since 10/28/2012 References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> <50967453.5090503@freebsd.org> <5096CCDE.7090305@fgznet.ch> <5096E4D4.6000000@freebsd.org> In-Reply-To: <5096E4D4.6000000@freebsd.org> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.64 on 81.92.96.47 Cc: freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 04 Nov 2012 23:28:11 -0000 On 04.11.12 22:57, Andre Oppermann wrote: > On 04.11.2012 21:15, Andreas Tobler wrote: >> On 04.11.12 14:57, Andre Oppermann wrote: >>> On 04.11.2012 13:11, Kim Culhan wrote: >>>> On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: >>>>> On 2012-11-04 02:13, Manfred Antar wrote: >>>>>> At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>>> After the commit, there was a small discussion thread on svn-src-head@ >>>>> about the possible problems with the approach. Maybe you are >>>>> experiencing those? >>>>> >>>>> As the commit message says, you should be able to turn the feature off >>>>> using: >>>>> >>>>> sysctl net.inet.tcp.experimental.initcwnd10=0 >>>>> >>>>> Can you please try that, and see if the problems go away? >>>> >>>> FWIW this did not make the problem go away on 2 machines. >>> >>> Yes, this very much looks like the same problem as in PR/173309. >>> >>> Please try the attached patch. It fixes the connection hang issue. >>> There may be a second issue I debugging currently base on the feedback >>> from Fabian Keil. >> >> I jump into this thread since I have a similar network issue. >> >> My scenario: >> >> 'make installkernel DESTDIR=/netboot/test' to a nfs mounted drive. >> The nfs drive on the server is an ufs fs. No zfs. >> >> Up to r242261 I can install the kernel (or world) in a fluent way to the >> nfs destination. >> >> >From r242262 it doesn't work smooth. I have stalls, sometimes my >> patience is not enough and I kill the process. >> >> I tried 242266 with the above mentioned patch. No real success. >> >> How can I help/test? > > Please try the attach patch instead of the above mentioned one. Test run based on 242266. It starts much smoother. But it stalls later on. Continues, stalls for several seconds, cont..... thx so far. Andreas 1391 0 D+ 0:00.00 install -o root -g wheel -m 555 crypto.ko /netboot/test_install procstat -kk 1391 PID TID COMM TDNAME KSTACK 1391 100099 install - mi_switch+0x186 sleepq_timedwait+0x42 _sleep+0x1c9 clnt_vc_call+0x763 clnt_reconnect_call+0xfb newnfs_request+0xadb nfscl_request+0x72 nfsrpc_setattr+0x28f nfs_setattr+0x2b0 VOP_SETATTR_APV+0x31 setfmode+0x101 vn_chmod+0x8a sys_fchmod+0x8b amd64_syscall+0x55f Xfast_syscall+0xf7 From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 01:49:05 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id B49DAD83; Mon, 5 Nov 2012 01:49:05 +0000 (UTC) (envelope-from null@pozo.com) Received: from pozo.com (pozo.com [216.101.162.50]) by mx1.freebsd.org (Postfix) with ESMTP id 743A88FC0C; Mon, 5 Nov 2012 01:49:05 +0000 (UTC) Received: from T61p.pozo.com (t61p.pozo.com [192.168.0.4]) (authenticated bits=0) by pozo.com (8.14.5/8.14.5) with ESMTP id qA51daHj019870 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NOT); Sun, 4 Nov 2012 17:39:42 -0800 (PST) (envelope-from null@pozo.com) Message-Id: <201211050139.qA51daHj019870@pozo.com> X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Sun, 04 Nov 2012 17:39:10 -0800 To: Andre Oppermann From: Manfred Antar Subject: Re: weird network problems on current since 10/28/2012 In-Reply-To: <5096E4D4.6000000@freebsd.org> References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> <50967453.5090503@freebsd.org> <5096CCDE.7090305@fgznet.ch> <5096E4D4.6000000@freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" X-Spam-Status: No, score=-0.9 required=5.0 tests=ALL_TRUSTED,MISSING_MID autolearn=no version=3.3.2, No X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on pozo.com X-pozocom-MailScanner-Information: Please contact the ISP for more information X-pozocom-MailScanner-ID: qA51daHj019870 X-pozocom-MailScanner: Found to be clean X-pozocom-MailScanner-From: null@pozo.com Cc: freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 01:49:05 -0000 At 01:57 PM 11/4/2012, you wrote: >On 04.11.2012 21:15, Andreas Tobler wrote: >>On 04.11.12 14:57, Andre Oppermann wrote: >>>On 04.11.2012 13:11, Kim Culhan wrote: >>>>On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: >>>>>On 2012-11-04 02:13, Manfred Antar wrote: >>>>>>At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>>>After the commit, there was a small discussion thread on svn-src-head@ >>>>>about the possible problems with the approach. Maybe you are >>>>>experiencing those? >>>>> >>>>>As the commit message says, you should be able to turn the feature off >>>>>using: >>>>> >>>>> sysctl net.inet.tcp.experimental.initcwnd10=0 >>>>> >>>>>Can you please try that, and see if the problems go away? >>>> >>>>FWIW this did not make the problem go away on 2 machines. >>> >>>Yes, this very much looks like the same problem as in PR/173309. >>> >>>Please try the attached patch. It fixes the connection hang issue. >>>There may be a second issue I debugging currently base on the feedback >>>from Fabian Keil. >> >>I jump into this thread since I have a similar network issue. >> >>My scenario: >> >>'make installkernel DESTDIR=/netboot/test' to a nfs mounted drive. >>The nfs drive on the server is an ufs fs. No zfs. >> >>Up to r242261 I can install the kernel (or world) in a fluent way to the >>nfs destination. >> >>>From r242262 it doesn't work smooth. I have stalls, sometimes my >>patience is not enough and I kill the process. >> >>I tried 242266 with the above mentioned patch. No real success. >> >>How can I help/test? > >Please try the attach patch instead of the above mentioned one. > >-- >Andre > >Index: netinet/tcp_output.c >=================================================================== >--- netinet/tcp_output.c (revision 242577) >+++ netinet/tcp_output.c (working copy) >@@ -228,7 +228,7 @@ > tso = 0; > mtu = 0; > off = tp->snd_nxt - tp->snd_una; >- sendwin = min(tp->snd_wnd, tp->snd_cwnd); >+ sendwin = ulmax(ulmin(tp->snd_wnd - off, tp->snd_cwnd), 0); > > flags = tcp_outflags[tp->t_state]; > /* >@@ -249,7 +249,7 @@ > (p = tcp_sack_output(tp, &sack_bytes_rxmt))) { > long cwin; > >- cwin = min(tp->snd_wnd, tp->snd_cwnd) - sack_bytes_rxmt; >+ cwin = ulmin(tp->snd_wnd - off, tp->snd_cwnd) - sack_bytes_rxmt; > if (cwin < 0) > cwin = 0; > /* Do not retransmit SACK segments beyond snd_recover */ >@@ -355,7 +355,7 @@ > * sending new data, having retransmitted all the > * data possible in the scoreboard. > */ >- len = ((long)ulmin(so->so_snd.sb_cc, tp->snd_wnd) >+ len = ((long)ulmin(so->so_snd.sb_cc, tp->snd_wnd - off) > - off); > /* > * Don't remove this (len > 0) check ! This doesn't seem to make a difference. I have a ssh window thats been trying to connect for the past 5 minutes. This is on a local network 192.168.0.4 >===========SSH==============> 192.168.0.5 Also pop from the same machines endless trying to connect. Hopefully this mail will get thru , otherwise i will need to reboot to old kernel Manfred ======================== || null@pozo.com || || Ph. (415) 681-6235 || ======================== -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 02:40:59 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E4E70F61 for ; Mon, 5 Nov 2012 02:40:59 +0000 (UTC) (envelope-from davidxu@freebsd.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:1900:2254:206c::16:87]) by mx1.freebsd.org (Postfix) with ESMTP id B09BC8FC0A; Mon, 5 Nov 2012 02:40:59 +0000 (UTC) Received: from xyf.my.dom (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.5/8.14.5) with ESMTP id qA52ewj7056993; Mon, 5 Nov 2012 02:40:59 GMT (envelope-from davidxu@freebsd.org) Message-ID: <50972740.7000703@freebsd.org> Date: Mon, 05 Nov 2012 10:41:04 +0800 From: David Xu User-Agent: Mozilla/5.0 (X11; FreeBSD i386; rv:14.0) Gecko/20120822 Thunderbird/14.0 MIME-Version: 1.0 To: Jeff Roberson Subject: Re: ULE patch, call for testers References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 02:41:00 -0000 On 2012/11/03 02:26, Jeff Roberson wrote: > I have a small patch to the ULE scheduler that makes a fairly large > change to the way timeshare threads are handled. > > http://people.freebsd.org/~jeff/schedslice.diff > > Previously ULE used a fixed slice size for all timeshare threads. Now > it scales the slice size down based on load. This should reduce latency > for timeshare threads as load increases. It is important to note that > this does not impact interactive threads. But when a thread transitions > to interactive from timeshare it should see some improvement. This > happens when something like Xorg chews up a lot of CPU. > > If anyone has perf tests they'd like to run please report back. I have > done a handful of validation. > > Thanks, > Jeff Another problem I remembered is that a thread on runqueue may be starved because ULE treats a sleeping thread and a thread waiting on runqueue differently. If a thread has slept for a while, after it is woken up, its priority is boosted, but for a thread on runqueue, its priority will never be boosted. In essential, they should be same becase both of them are waiting for cpu. If I am a thread, I'd like to wait on sleep queue rather than on runqueue, since in former case, I will get bonus, while in later case, I'll get nothing. Under heavy load, there are many runnable threads, this unfair can cause a very low priority thread on runqueue to be starved. 4BSD seems not suffer from this problem, because it also decay cpu time of thread on runqueue. I think ULE needs some anti-starvation code to give thread a shot if it is waiting on runqueue too long time. Regards, David Xu From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 06:12:23 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 22970FB5 for ; Mon, 5 Nov 2012 06:12:23 +0000 (UTC) (envelope-from lists@rewt.org.uk) Received: from abby.lhr1.as41113.net (unknown [IPv6:2001:b70:201:2::22]) by mx1.freebsd.org (Postfix) with ESMTP id DAD448FC0C for ; Mon, 5 Nov 2012 06:12:22 +0000 (UTC) Received: from [172.16.11.21] (bella.stf.rewt.org.uk [91.208.177.62]) (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by abby.lhr1.as41113.net (Postfix) with ESMTPS id 3Xw3St41J9z13P0 for ; Mon, 5 Nov 2012 06:12:14 +0000 (GMT) Message-ID: <509758B8.1000409@rewt.org.uk> Date: Mon, 05 Nov 2012 06:12:08 +0000 From: Joe Holden User-Agent: Thunderbird 2.0.0.24 (Windows/20100228) MIME-Version: 1.0 To: current@freebsd.org Subject: Dynamic Ticks/HZ Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 06:12:23 -0000 Hi guys, Has some default changed between 9.1-RC2 and HEAD? On identical machines, one with 9.1-RC2 and one with HEAD from yesterday (GENERIC) I see the following in systat -v: 9.1: 65 cpu0:timer 10 cpu1:timer HEAD: 1127 cpu0:timer 22 cpu1:timer These are Supermicro i3 boxes and as far as I can see they have matching BIOS config. Thanks, J From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 06:29:32 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 70382253 for ; Mon, 5 Nov 2012 06:29:32 +0000 (UTC) (envelope-from davide.italiano@gmail.com) Received: from mail-vb0-f54.google.com (mail-vb0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id 1F9388FC08 for ; Mon, 5 Nov 2012 06:29:31 +0000 (UTC) Received: by mail-vb0-f54.google.com with SMTP id l1so7221997vba.13 for ; Sun, 04 Nov 2012 22:29:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=UPyjbEw+h9N77ILrpJwMbzWWpWlFxqfhF7aEuSp3A6Q=; b=xUOeRhJFdyD4PgZw6xFjfQZqjExGsAkUAzapFCgC3LAjjZVrfuN7ydnqb+6/JC1dAG Ckqe2ZhbRUzAWL+Et8S9nw+diUQUzw9rQ8FtYUqFC8aOY+dpb+ODO4QrlMNjESKJXkax NNOf0AOCAuMsDkI7fCjXIzldfZrPeWgmrAK0idj78hf7DkE/SstIuJu7uqUwIBob20+J Xv1Rvuzfwr5zGWyuQhUikF4l4LuQsiqgyoQMEHirVSTAxe9ayvS+bi6FOtk3pAt7O0jm 4C/HPCAqI5ho+ItMjG4h0k7GgUd8LJ8TEE+laG7HxnGI6W7MB9TqrRvm5HqNE8dLQhPk MhSg== MIME-Version: 1.0 Received: by 10.58.133.3 with SMTP id oy3mr8920526veb.15.1352096971308; Sun, 04 Nov 2012 22:29:31 -0800 (PST) Sender: davide.italiano@gmail.com Received: by 10.58.247.132 with HTTP; Sun, 4 Nov 2012 22:29:31 -0800 (PST) In-Reply-To: <509758B8.1000409@rewt.org.uk> References: <509758B8.1000409@rewt.org.uk> Date: Mon, 5 Nov 2012 07:29:31 +0100 X-Google-Sender-Auth: uFTZM0IPOKcZuKDGR8lzmknRjnM Message-ID: Subject: Re: Dynamic Ticks/HZ From: Davide Italiano To: Joe Holden Content-Type: text/plain; charset=ISO-8859-1 Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 06:29:32 -0000 On Mon, Nov 5, 2012 at 7:12 AM, Joe Holden wrote: > Hi guys, > > Has some default changed between 9.1-RC2 and HEAD? > > On identical machines, one with 9.1-RC2 and one with HEAD from yesterday > (GENERIC) I see the following in systat -v: > > 9.1: > 65 cpu0:timer > 10 cpu1:timer > > HEAD: > 1127 cpu0:timer > 22 cpu1:timer > > These are Supermicro i3 boxes and as far as I can see they have matching > BIOS config. > > Thanks, > J > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" Which is your refresh rate for systat? I generally measure sampling every one second (i.e. systat -vm 1). Also, are you making your measurements when the system is idle? In order to trace the source(s) of these interrupts you might consider to collect data via KTR. -- Davide From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 06:40:55 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6DB44506; Mon, 5 Nov 2012 06:40:55 +0000 (UTC) (envelope-from lists@rewt.org.uk) Received: from abby.lhr1.as41113.net (abby.lhr1.as41113.net [91.208.177.20]) by mx1.freebsd.org (Postfix) with ESMTP id 2C7108FC0A; Mon, 5 Nov 2012 06:40:54 +0000 (UTC) Received: from [172.16.11.21] (bella.stf.rewt.org.uk [91.208.177.62]) (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by abby.lhr1.as41113.net (Postfix) with ESMTPS id 3Xw45x32KFz13P0; Mon, 5 Nov 2012 06:40:53 +0000 (GMT) Message-ID: <50975F6F.6010907@rewt.org.uk> Date: Mon, 05 Nov 2012 06:40:47 +0000 From: Joe Holden User-Agent: Thunderbird 2.0.0.24 (Windows/20100228) MIME-Version: 1.0 To: Davide Italiano Subject: Re: Dynamic Ticks/HZ References: <509758B8.1000409@rewt.org.uk> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 06:40:55 -0000 Davide Italiano wrote: > On Mon, Nov 5, 2012 at 7:12 AM, Joe Holden wrote: >> Hi guys, >> >> Has some default changed between 9.1-RC2 and HEAD? >> >> On identical machines, one with 9.1-RC2 and one with HEAD from yesterday >> (GENERIC) I see the following in systat -v: >> >> 9.1: >> 65 cpu0:timer >> 10 cpu1:timer >> >> HEAD: >> 1127 cpu0:timer >> 22 cpu1:timer >> >> These are Supermicro i3 boxes and as far as I can see they have matching >> BIOS config. >> >> Thanks, >> J >> _______________________________________________ >> freebsd-current@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-current >> To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" > > Which is your refresh rate for systat? > I generally measure sampling every one second (i.e. systat -vm 1). > Also, are you making your measurements when the system is idle? > In order to trace the source(s) of these interrupts you might consider > to collect data via KTR. > I'm also using a one second refresh rate, the system is entirely idle and the interupt rate is almost entirely static at 1127, occasionally it will drop to 1119. From what I understand the timer is hz/ticks which became dynamic in 9.0, although that behaviour doesn't appear to be in HEAD anymore, at least on this hardware. Thanks, J From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 06:52:57 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9638A793 for ; Mon, 5 Nov 2012 06:52:57 +0000 (UTC) (envelope-from davide.italiano@gmail.com) Received: from mail-vb0-f54.google.com (mail-vb0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id 3D5448FC0C for ; Mon, 5 Nov 2012 06:52:57 +0000 (UTC) Received: by mail-vb0-f54.google.com with SMTP id l1so7238429vba.13 for ; Sun, 04 Nov 2012 22:52:56 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=cvncGtNGHsgdK/HVx07zEVImENQQ4RZ7PqSgBgofKhA=; b=kDynITC7wkwg0UAwAJ1MwDHEjE3BR0V1yImwEWBx8MpNBu9eTipPP5r2umVRzI8Oha IK/gRtwAn6RsbKAhNiGVI/qebSPUkTNhf8aVtFMblipEvfyi0JwJwHL693GcY1yab592 gES0q3a+V2UUSt7z5X15la9F1qMJALtboDvIR7EY1ip56PwViKay9S+v9q7Ca7OPzftT YAsb3ieP62YX+2skjYGbIL/HEn3NGREbuVAOSzbA+X+t+5GCEUv/Cvhuo7radGTnU9On zttLg/rro/f0MSLR2b33MHfPm6A1aPSXnk8IO0tSg8f0hFJduxInP/ZdrSE1SgKcx3o9 yovw== MIME-Version: 1.0 Received: by 10.52.99.103 with SMTP id ep7mr7759950vdb.17.1352098376512; Sun, 04 Nov 2012 22:52:56 -0800 (PST) Sender: davide.italiano@gmail.com Received: by 10.58.247.132 with HTTP; Sun, 4 Nov 2012 22:52:56 -0800 (PST) Received: by 10.58.247.132 with HTTP; Sun, 4 Nov 2012 22:52:56 -0800 (PST) In-Reply-To: <50975F6F.6010907@rewt.org.uk> References: <509758B8.1000409@rewt.org.uk> <50975F6F.6010907@rewt.org.uk> Date: Mon, 5 Nov 2012 07:52:56 +0100 X-Google-Sender-Auth: 6BscRDXse5orZtrlBHOqETnKkpQ Message-ID: Subject: Re: Dynamic Ticks/HZ From: Davide Italiano To: Joe Holden Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 06:52:57 -0000 On Nov 4, 2012 10:40 PM, "Joe Holden" wrote: > > Davide Italiano wrote: >> >> On Mon, Nov 5, 2012 at 7:12 AM, Joe Holden wrote: >>> >>> Hi guys, >>> >>> Has some default changed between 9.1-RC2 and HEAD? >>> >>> On identical machines, one with 9.1-RC2 and one with HEAD from yesterday >>> (GENERIC) I see the following in systat -v: >>> >>> 9.1: >>> 65 cpu0:timer >>> 10 cpu1:timer >>> >>> HEAD: >>> 1127 cpu0:timer >>> 22 cpu1:timer >>> >>> These are Supermicro i3 boxes and as far as I can see they have matching >>> BIOS config. >>> >>> Thanks, >>> J >>> _______________________________________________ >>> freebsd-current@freebsd.org mailing list >>> http://lists.freebsd.org/mailman/listinfo/freebsd-current >>> To unsubscribe, send any mail to " freebsd-current-unsubscribe@freebsd.org" >> >> >> Which is your refresh rate for systat? >> I generally measure sampling every one second (i.e. systat -vm 1). >> Also, are you making your measurements when the system is idle? >> In order to trace the source(s) of these interrupts you might consider >> to collect data via KTR. >> > > I'm also using a one second refresh rate, the system is entirely idle and the interupt rate is almost entirely static at 1127, occasionally it will drop to 1119. > > From what I understand the timer is hz/ticks which became dynamic in 9.0, although that behaviour doesn't appear to be in HEAD anymore, at least on this hardware. > > Thanks, > J It should be available, AFAIK. As I can see from your previous post you get about 20 interrupts on cpu1. This number is about 1/100 of the value you get on a !tickless kernel. If you provide the required ktr infos, probably someone will take a look. From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 09:14:01 2012 Return-Path: Delivered-To: current@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 56224916; Mon, 5 Nov 2012 09:14:01 +0000 (UTC) (envelope-from avg@FreeBSD.org) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 4ED6B8FC15; Mon, 5 Nov 2012 09:13:59 +0000 (UTC) Received: from porto.starpoint.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id LAA26846; Mon, 05 Nov 2012 11:13:58 +0200 (EET) (envelope-from avg@FreeBSD.org) Received: from localhost ([127.0.0.1]) by porto.starpoint.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1TVIkn-0004F0-P0; Mon, 05 Nov 2012 11:13:57 +0200 Message-ID: <50978353.7090204@FreeBSD.org> Date: Mon, 05 Nov 2012 11:13:55 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:16.0) Gecko/20121030 Thunderbird/16.0.2 MIME-Version: 1.0 To: David Xu , Jeff Roberson Subject: Re: ULE patch, call for testers References: <50972740.7000703@freebsd.org> In-Reply-To: <50972740.7000703@freebsd.org> X-Enigmail-Version: 1.4.5 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: current@FreeBSD.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 09:14:01 -0000 on 05/11/2012 04:41 David Xu said the following: > Another problem I remembered is that a thread on runqueue may be starved > because ULE treats a sleeping thread and a thread waiting on runqueue > differently. If a thread has slept for a while, after it is woken up, > its priority is boosted, but for a thread on runqueue, its priority > will never be boosted. In essential, they should be same becase both of > them are waiting for cpu. If I am a thread, I'd like to wait on sleep > queue rather than on runqueue, since in former case, I will get > bonus, while in later case, I'll get nothing. Under heavy load, > there are many runnable threads, this unfair can cause a very low priority > thread on runqueue to be starved. 4BSD seems not suffer from > this problem, because it also decay cpu time of thread on runqueue. > I think ULE needs some anti-starvation code to give thread a shot > if it is waiting on runqueue too long time. I also noticed this issue and I've been playing with the following patch. Two points: o I am not sure if it is ideologically correct o it didn't improve much the behavior of my workloads In any case, here it is: - extend accounted interactive sleep time to a point where a thread runs (as opposed to be added to runq) --- a/sys/kern/sched_ule.c +++ b/sys/kern/sched_ule.c @@ -1898,8 +1899,21 @@ sched_switch(struct thread *td, struct thread *newtd, int flags) SDT_PROBE2(sched, , , off_cpu, td, td->td_proc); lock_profile_release_lock(&TDQ_LOCKPTR(tdq)->lock_object); TDQ_LOCKPTR(tdq)->mtx_lock = (uintptr_t)newtd; +#if 1 + /* + * If we slept for more than a tick update our interactivity and + * priority. + */ + int slptick; + slptick = newtd->td_slptick; + newtd->td_slptick = 0; + if (slptick && slptick != ticks) { + newtd->td_sched->ts_slptime += + (ticks - slptick) << SCHED_TICK_SHIFT; + sched_interact_update(newtd); + } +#endif sched_pctcpu_update(newtd->td_sched, 0); - #ifdef KDTRACE_HOOKS /* * If DTrace has set the active vtime enum to anything @@ -1990,6 +2004,7 @@ sched_wakeup(struct thread *td) THREAD_LOCK_ASSERT(td, MA_OWNED); ts = td->td_sched; td->td_flags &= ~TDF_CANSWAP; +#if 0 /* * If we slept for more than a tick update our interactivity and * priority. @@ -2001,6 +2016,7 @@ sched_wakeup(struct thread *td) sched_interact_update(td); sched_pctcpu_update(ts, 0); } +#endif /* Reset the slice value after we sleep. */ ts->ts_slice = sched_slice; sched_add(td, SRQ_BORING); -- Andriy Gapon From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 09:19:26 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id A00C3BF9 for ; Mon, 5 Nov 2012 09:19:26 +0000 (UTC) (envelope-from andre@freebsd.org) Received: from c00l3r.networx.ch (c00l3r.networx.ch [62.48.2.2]) by mx1.freebsd.org (Postfix) with ESMTP id 07D0F8FC12 for ; Mon, 5 Nov 2012 09:19:25 +0000 (UTC) Received: (qmail 80245 invoked from network); 5 Nov 2012 10:55:06 -0000 Received: from c00l3r.networx.ch (HELO [127.0.0.1]) ([62.48.2.2]) (envelope-sender ) by c00l3r.networx.ch (qmail-ldap-1.03) with SMTP for ; 5 Nov 2012 10:55:06 -0000 Message-ID: <5097849A.30603@freebsd.org> Date: Mon, 05 Nov 2012 10:19:22 +0100 From: Andre Oppermann User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:16.0) Gecko/20121010 Thunderbird/16.0.1 MIME-Version: 1.0 To: Manfred Antar Subject: Re: weird network problems on current since 10/28/2012 References: <201211031740.qA3HeqVX001622@pozo.com> <201211040113.qA41DfLn001577@pozo.com> <50964FBB.4010600@andric.com> <50967453.5090503@freebsd.org> <5096CCDE.7090305@fgznet.ch> <5096E4D4.6000000@freebsd.org> <201211050139.qA51daHj019870@pozo.com> In-Reply-To: <201211050139.qA51daHj019870@pozo.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 09:19:26 -0000 On 05.11.2012 02:39, Manfred Antar wrote: > At 01:57 PM 11/4/2012, you wrote: >> On 04.11.2012 21:15, Andreas Tobler wrote: >>> On 04.11.12 14:57, Andre Oppermann wrote: >>>> On 04.11.2012 13:11, Kim Culhan wrote: >>>>> On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: >>>>>> On 2012-11-04 02:13, Manfred Antar wrote: >>>>>>> At 03:29 PM 11/3/2012, Adrian Chadd wrote: >>>>>> After the commit, there was a small discussion thread on svn-src-head@ >>>>>> about the possible problems with the approach. Maybe you are >>>>>> experiencing those? >>>>>> >>>>>> As the commit message says, you should be able to turn the feature off >>>>>> using: >>>>>> >>>>>> sysctl net.inet.tcp.experimental.initcwnd10=0 >>>>>> >>>>>> Can you please try that, and see if the problems go away? >>>>> >>>>> FWIW this did not make the problem go away on 2 machines. >>>> >>>> Yes, this very much looks like the same problem as in PR/173309. >>>> >>>> Please try the attached patch. It fixes the connection hang issue. >>>> There may be a second issue I debugging currently base on the feedback >>> >from Fabian Keil. >>> >>> I jump into this thread since I have a similar network issue. >>> >>> My scenario: >>> >>> 'make installkernel DESTDIR=/netboot/test' to a nfs mounted drive. >>> The nfs drive on the server is an ufs fs. No zfs. >>> >>> Up to r242261 I can install the kernel (or world) in a fluent way to the >>> nfs destination. >>> >>> >From r242262 it doesn't work smooth. I have stalls, sometimes my >>> patience is not enough and I kill the process. >>> >>> I tried 242266 with the above mentioned patch. No real success. >>> >>> How can I help/test? >> >> Please try the attach patch instead of the above mentioned one. >> >> -- >> Andre >> >> Index: netinet/tcp_output.c >> =================================================================== >> --- netinet/tcp_output.c (revision 242577) >> +++ netinet/tcp_output.c (working copy) >> @@ -228,7 +228,7 @@ >> tso = 0; >> mtu = 0; >> off = tp->snd_nxt - tp->snd_una; >> - sendwin = min(tp->snd_wnd, tp->snd_cwnd); >> + sendwin = ulmax(ulmin(tp->snd_wnd - off, tp->snd_cwnd), 0); >> >> flags = tcp_outflags[tp->t_state]; >> /* >> @@ -249,7 +249,7 @@ >> (p = tcp_sack_output(tp, &sack_bytes_rxmt))) { >> long cwin; >> >> - cwin = min(tp->snd_wnd, tp->snd_cwnd) - sack_bytes_rxmt; >> + cwin = ulmin(tp->snd_wnd - off, tp->snd_cwnd) - sack_bytes_rxmt; >> if (cwin < 0) >> cwin = 0; >> /* Do not retransmit SACK segments beyond snd_recover */ >> @@ -355,7 +355,7 @@ >> * sending new data, having retransmitted all the >> * data possible in the scoreboard. >> */ >> - len = ((long)ulmin(so->so_snd.sb_cc, tp->snd_wnd) >> + len = ((long)ulmin(so->so_snd.sb_cc, tp->snd_wnd - off) >> - off); >> /* >> * Don't remove this (len > 0) check ! > > This doesn't seem to make a difference. > I have a ssh window thats been trying to connect for the past 5 minutes. > This is on a local network 192.168.0.4 >===========SSH==============> 192.168.0.5 > Also pop from the same machines endless trying to connect. > Hopefully this mail will get thru , otherwise i will need to reboot to old kernel I've backed out the change with r242601 as it exhibits still too many problems. I'll fix these problems in the next days but in the mean time HEAD should be in a working state. I'm sorry for the trouble. -- Andre From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 09:38:03 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 5C8BA76B for ; Mon, 5 Nov 2012 09:38:03 +0000 (UTC) (envelope-from olivier@gid0.org) Received: from mail-la0-f54.google.com (mail-la0-f54.google.com [209.85.215.54]) by mx1.freebsd.org (Postfix) with ESMTP id C84AF8FC19 for ; Mon, 5 Nov 2012 09:38:02 +0000 (UTC) Received: by mail-la0-f54.google.com with SMTP id e12so4960751lag.13 for ; Mon, 05 Nov 2012 01:38:01 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:x-gm-message-state; bh=mbVicoa8gSyTy2an7MoisNJ1m1eDU6q3mcgopyMgx+Q=; b=TQx2oneTHnXNPqWj4an+eZMnDOOGxCo0gTmV2N+st9TGm6FvtrQZQ4yrfe7DUZtB4R q5QfRLnLdm66SrCgOW1cTQgZBSRP6o2CdLUGuj4+Ir5p5UMGSyDfmwGLvrBpqMtI+vhS 1PsDlZRKgHjJQpfblaX1S7i06EppVGhO9avhWMBZTlEMgqyIO5AHcyrkjnW72gZzddXB J6Pmhj4wWBNFME5AfU76cd+h6HuRi41ocv9QyI+kqNsLRclNbLCEAGbDgVvbz3gv1haa CDX9cFLI5zdrwHIXfXIAKRt0EDUbjv50hrLtxCxPSU/XzQ+6MfBr1yJMuFyHwnwwSnw+ cPkg== MIME-Version: 1.0 Received: by 10.112.48.71 with SMTP id j7mr3751317lbn.57.1352108281583; Mon, 05 Nov 2012 01:38:01 -0800 (PST) Received: by 10.112.135.137 with HTTP; Mon, 5 Nov 2012 01:38:01 -0800 (PST) In-Reply-To: <20121104225529.000028a9@unknown> References: <20121103232433.00005eee@unknown> <5095ACC7.1050002@FreeBSD.org> <20121104225529.000028a9@unknown> Date: Mon, 5 Nov 2012 10:38:01 +0100 Message-ID: Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? From: Olivier Smedts To: Alexander Leidinger X-Gm-Message-State: ALoCoQl2Kk9HNxsbnN96+k4bjbyDC+knxYoO664bM8Thu+9/ZONuJG5A6Jat+KevoH/YeBC7XPNH Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: Dimitry Andric , "current@freebsd.org" X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 09:38:03 -0000 Le dimanche 4 novembre 2012, Alexander Leidinger a =E9crit : > > The machine has 12 MB RAM (no swap configured), after nearly a day > uptime it looks like this: > > ---snip--- > Mem: 348M Active, 599M Inact, 9281M Wired, 264K Cache, 1548M Free > ARC: 7117M Total, 1607M MRU, 3996M MFU, 934K Anon, 208M Header, 1307M Oth= er > ---snip--- > > I would not expect an internal compiler error when I run out of RAM. > Not related, but I think you should configure --=20 Olivier Smedts _ ASCII ribbon campaign ( ) e-mail: olivier@gid0.org - against HTML email & vCards X www: http://www.gid0.org - against proprietary attachments / \ "Il y a seulement 10 sortes de gens dans le monde : ceux qui comprennent le binaire, et ceux qui ne le comprennent pas." From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 09:40:36 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1ECD9919; Mon, 5 Nov 2012 09:40:36 +0000 (UTC) (envelope-from lists@rewt.org.uk) Received: from abby.lhr1.as41113.net (abby.lhr1.as41113.net [91.208.177.20]) by mx1.freebsd.org (Postfix) with ESMTP id D0B548FC1B; Mon, 5 Nov 2012 09:40:35 +0000 (UTC) Received: from [172.16.11.21] (bella.stf.rewt.org.uk [91.208.177.62]) (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by abby.lhr1.as41113.net (Postfix) with ESMTPS id 3Xw85G1D0bz13P0; Mon, 5 Nov 2012 09:40:34 +0000 (GMT) Message-ID: <5097898C.9080109@rewt.org.uk> Date: Mon, 05 Nov 2012 09:40:28 +0000 From: Joe Holden User-Agent: Thunderbird 2.0.0.24 (Windows/20100228) MIME-Version: 1.0 To: Davide Italiano Subject: Re: Dynamic Ticks/HZ References: <509758B8.1000409@rewt.org.uk> <50975F6F.6010907@rewt.org.uk> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: current@freebsd.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 09:40:36 -0000 Davide Italiano wrote: > On Nov 4, 2012 10:40 PM, "Joe Holden" wrote: >> Davide Italiano wrote: >>> On Mon, Nov 5, 2012 at 7:12 AM, Joe Holden wrote: >>>> Hi guys, >>>> >>>> Has some default changed between 9.1-RC2 and HEAD? >>>> >>>> On identical machines, one with 9.1-RC2 and one with HEAD from yesterday >>>> (GENERIC) I see the following in systat -v: >>>> >>>> 9.1: >>>> 65 cpu0:timer >>>> 10 cpu1:timer >>>> >>>> HEAD: >>>> 1127 cpu0:timer >>>> 22 cpu1:timer >>>> >>>> These are Supermicro i3 boxes and as far as I can see they have matching >>>> BIOS config. >>>> >>>> Thanks, >>>> J >>>> _______________________________________________ >>>> freebsd-current@freebsd.org mailing list >>>> http://lists.freebsd.org/mailman/listinfo/freebsd-current >>>> To unsubscribe, send any mail to " > freebsd-current-unsubscribe@freebsd.org" >>> >>> Which is your refresh rate for systat? >>> I generally measure sampling every one second (i.e. systat -vm 1). >>> Also, are you making your measurements when the system is idle? >>> In order to trace the source(s) of these interrupts you might consider >>> to collect data via KTR. >>> >> I'm also using a one second refresh rate, the system is entirely idle and > the interupt rate is almost entirely static at 1127, occasionally it will > drop to 1119. >> From what I understand the timer is hz/ticks which became dynamic in 9.0, > although that behaviour doesn't appear to be in HEAD anymore, at least on > this hardware. >> Thanks, >> J > > It should be available, AFAIK. As I can see from your previous post you get > about 20 interrupts on cpu1. This number is about 1/100 of the value you > get on a !tickless kernel. > If you provide the required ktr infos, probably someone will take a look. doh, running kernel wasn't as GENERIC as I thought it was, looks like device polling not only breaks dynamic ticks but also reduces rx ability significantly, exactly 150,000 pps per 1000hz on igb versus 650,000 without Is this a known issue? (and if device polling isn't as useful as it once was, should it be removed?) From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 09:43:47 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id DBF55AB6 for ; Mon, 5 Nov 2012 09:43:47 +0000 (UTC) (envelope-from olivier@gid0.org) Received: from mail-lb0-f182.google.com (mail-lb0-f182.google.com [209.85.217.182]) by mx1.freebsd.org (Postfix) with ESMTP id 4F91F8FC08 for ; Mon, 5 Nov 2012 09:43:46 +0000 (UTC) Received: by mail-lb0-f182.google.com with SMTP id b5so5013480lbd.13 for ; Mon, 05 Nov 2012 01:43:45 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:x-gm-message-state; bh=FqqcuzhwlURxxbAKi3Je51w/aJ0GBCbtHGVw5kZZv1k=; b=RWgbmLyrVy/jxULlwziLHexLBDPnHXS2ZZlh/ChQjMZhPb6LfLfdgzMmHf4QrXlGAD ktZEe1inbyV+PixDogozrTIGq6GkC1ax4as4acqHHiXiq6FXDpOoHIMGSu4eCipRFvlP UYjcm1h+Em2+PpqmO78YYhXgXommFt1zS5UrEYZ3M2rrQZiNnvPuYfo7yQdVzgujN+kF 3qheM3b/eGHy7mPDNo3E++NPwa03kKtJ/5nkNnHHZwTZh9qARC1VCR/w1dPvjNqxCP0A ZT7JyPzb9lZLy0CenU5O/EdDS7OdIDQmDjagML/Qx/nCbzMay39SgTJ1xR4L6CEBtZnx gT9w== MIME-Version: 1.0 Received: by 10.112.23.195 with SMTP id o3mr3801011lbf.6.1352108625742; Mon, 05 Nov 2012 01:43:45 -0800 (PST) Received: by 10.112.135.137 with HTTP; Mon, 5 Nov 2012 01:43:45 -0800 (PST) In-Reply-To: References: <20121103232433.00005eee@unknown> <5095ACC7.1050002@FreeBSD.org> <20121104225529.000028a9@unknown> Date: Mon, 5 Nov 2012 10:43:45 +0100 Message-ID: Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? From: Olivier Smedts To: Alexander Leidinger X-Gm-Message-State: ALoCoQmlVs2OAxx+rwKGFaemhvSrRpD1+IqA7qEWLK81Y2szWNqkG3lVv1SUn1U46OuJYrdNgPnH Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: Dimitry Andric , "current@freebsd.org" X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 09:43:48 -0000 Le lundi 5 novembre 2012, Olivier Smedts a =E9crit : > > Le dimanche 4 novembre 2012, Alexander Leidinger a =E9crit : > > The machine has 12 MB RAM (no swap configured), after nearly a day >> uptime it looks like this: >> >> ---snip--- >> Mem: 348M Active, 599M Inact, 9281M Wired, 264K Cache, 1548M Free >> ARC: 7117M Total, 1607M MRU, 3996M MFU, 934K Anon, 208M Header, 1307M >> Other >> ---snip--- >> >> I would not expect an internal compiler error when I run out of RAM. > > Not related, but I think you should configure > ...at least a little swap (sorry, damn "smart"-phone). When under memory pressure, ZFS sometimes don't have time to evict ARC memory and some MBs are written to swap instead of waiting. No real technical details --=20 Olivier Smedts _ ASCII ribbon campaign ( ) e-mail: olivier@gid0.org - against HTML email & vCards X www: http://www.gid0.org - against proprietary attachments / \ "Il y a seulement 10 sortes de gens dans le monde : ceux qui comprennent le binaire, et ceux qui ne le comprennent pas." From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 09:51:12 2012 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 5265875 for ; Mon, 5 Nov 2012 09:51:12 +0000 (UTC) (envelope-from olivier@gid0.org) Received: from mail-lb0-f182.google.com (mail-lb0-f182.google.com [209.85.217.182]) by mx1.freebsd.org (Postfix) with ESMTP id BD79D8FC08 for ; Mon, 5 Nov 2012 09:51:11 +0000 (UTC) Received: by mail-lb0-f182.google.com with SMTP id b5so5019181lbd.13 for ; Mon, 05 Nov 2012 01:51:10 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:x-gm-message-state; bh=HA4EvP54J9lsbSHh/em1g37xhLII0frrkkH2ytO+S5c=; b=BgGtoz5xkxvNmoRxD7iqWFE4DmwAxyJikhI8WxlXH8gUZda+QopbOc8biwYKQ/uzA3 OXX/5BIT9zXFx5Y3YieII5whSIMOk68+soQ8SvUmM9bg9Knj1Jp5yc1UlQ/Qut6pbo5e VHLCjFyqIl9D51V1dfyd7XaF3AxPnhtmxuSVPHjqf2bLTeD39F+xiBFU604NY42hgbUP ocQL6dPZVf/ewuVEP+UOxW3ZFnBEDFinbxwRQaZuVT44X49DxRyIr3fJ/StKoA1xsD9x Egh4GK9iumN6ZL2aGb+qtz0ORnXrauyg8R3phMpZoPY6Mxe5pv1fsgr3I8hWth7dIS9J vO2w== MIME-Version: 1.0 Received: by 10.112.47.228 with SMTP id g4mr3536389lbn.21.1352109070511; Mon, 05 Nov 2012 01:51:10 -0800 (PST) Received: by 10.112.135.137 with HTTP; Mon, 5 Nov 2012 01:51:10 -0800 (PST) In-Reply-To: References: <20121103232433.00005eee@unknown> <5095ACC7.1050002@FreeBSD.org> <20121104225529.000028a9@unknown> Date: Mon, 5 Nov 2012 10:51:10 +0100 Message-ID: Subject: Re: Do we have a CPUTYPE=native and/or generic stability problem? From: Olivier Smedts To: Alexander Leidinger X-Gm-Message-State: ALoCoQlsIe3jf7qbQV3Z7zozTC9iVvIGPO7fbvj6CQ0shzGu4iKU6D91F4dXd0ZeaL2jaiR9oPlv Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: Dimitry Andric , "current@freebsd.org" X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 09:51:12 -0000 Le lundi 5 novembre 2012, Olivier Smedts a =E9crit : > > Le lundi 5 novembre 2012, Olivier Smedts a =E9crit : > >> >> Le dimanche 4 novembre 2012, Alexander Leidinger a =E9crit : > > >> >> The machine has 12 MB RAM (no swap configured), after nearly a day >>> uptime it looks like this: >>> >>> ---snip--- >>> Mem: 348M Active, 599M Inact, 9281M Wired, 264K Cache, 1548M Free >>> ARC: 7117M Total, 1607M MRU, 3996M MFU, 934K Anon, 208M Header, 1307M >>> Other >>> ---snip--- >>> >>> I would not expect an internal compiler error when I run out of RAM. >> >> Not related, but I think you should configure >> > ...at least a little swap (sorry, damn "smart"-phone). When under memory > pressure, ZFS sometimes don't have time to evict ARC memory and some MBs > are written to swap instead of waiting. No real technical details > ...here, I'll leave it to ZFS or VM gurus, but I always have few dozens of MBs of my swap used even if I have lots of memory. And I promise my next reply will be made on a real computer, not on a too small touch interface with an editor which tries to replace all your english words by some of your mother tongue words. Sorry for triple posting. --=20 Olivier Smedts _ ASCII ribbon campaign ( ) e-mail: olivier@gid0.org - against HTML email & vCards X www: http://www.gid0.org - against proprietary attachments / \ "Il y a seulement 10 sortes de gens dans le monde : ceux qui comprennent le binaire, et ceux qui ne le comprennent pas." From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 10:26:06 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D46BE88D for ; Mon, 5 Nov 2012 10:26:06 +0000 (UTC) (envelope-from paul-freebsd@fletchermoorland.co.uk) Received: from hercules.mthelicon.com (hercules.mthelicon.com [66.90.118.40]) by mx1.freebsd.org (Postfix) with ESMTP id A8B008FC0A for ; Mon, 5 Nov 2012 10:26:06 +0000 (UTC) Received: from demophon.fletchermoorland.co.uk (hydra.fletchermoorland.co.uk [78.33.209.59] (may be forged)) (authenticated bits=0) by hercules.mthelicon.com (8.14.5/8.14.5) with ESMTP id qA5APxnb054779 for ; Mon, 5 Nov 2012 10:25:59 GMT (envelope-from paul-freebsd@fletchermoorland.co.uk) Message-ID: <50979436.4020907@fletchermoorland.co.uk> Date: Mon, 05 Nov 2012 10:25:58 +0000 From: Paul Wootton User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:12.0) Gecko/20120530 Thunderbird/12.0.1 MIME-Version: 1.0 To: freeBSD-CURRENT Mailing List Subject: ZFS RaidZ-2 problems References: <508F98F9.3040604@fletchermoorland.co.uk> In-Reply-To: <508F98F9.3040604@fletchermoorland.co.uk> X-Forwarded-Message-Id: <508F98F9.3040604@fletchermoorland.co.uk> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 10:26:07 -0000 I've already posted this to freebsd-fs@ but still have no idea as to why the below has happened. On 10/30/12 09:08, Paul Wootton wrote: > Hi, > > I have had lots of bad luck with SATA drives and have had them fail on > me far too often. Started with a 3 drive RAIDZ and lost 2 drives at > the same time. Upgraded to a 6 drive RAIDZ and lost 2 drives with in > hours of each other and finally had a 9 drive RAIDZ (1 parity) and > lost another 2 drives (as luck would happen, this time I had a 90% > backup on another machine so did not loose everything). I finally > decided that I should switch to a RAIDZ2 (my current setup). > Now I have lost 1 drive and the pack is showing as faulted. I have > tried exporting and reimporting, but that did not help either. > Is this normal? Has any one got any ideas as to what has happened and > why? > > The fault this time might be cabling so I might not have lost the > data, but my understanding was that with RAIDZ-2, you could loose 2 > drives and still have a working pack. > I do know the fault could also be the power supply, controller etc. I > can take care of all the hardware. > The issue I have is, I have a 9 RAIDZ-2 pack with only 1 disk showing > as offline and the pack is showing as faulted. > If the power supply was bouncing and a drive was giving bad data, I > would expect ZFS to report that 2 drives were faulted (1 offline and 1 > corrupt) > > Is there a way with ZDB that I can see why the pool is showing as > faulted? Can it tell me which drives it thinks are bad, or has bad data? > > I do still have the 90% backup of the pool and nothing has really > changed since that backup, so if someone wants me to try something and > it blows the pack away, it's not the end of the world. > > > Cheers > Paul > > > pool: storage > state: FAULTED > status: One or more devices could not be opened. There are insufficient > replicas for the pool to continue functioning. > action: Attach the missing device and online it using 'zpool online'. > see: http://illumos.org/msg/ZFS-8000-3C > scan: resilvered 30K in 0h0m with 0 errors on Sun Oct 14 12:52:45 2012 > config: > > NAME STATE READ WRITE CKSUM > storage FAULTED 0 0 1 > raidz2-0 FAULTED 0 0 6 > ada0 ONLINE 0 0 0 > ada1 ONLINE 0 0 0 > ada2 ONLINE 0 0 0 > 17777811927559723424 UNAVAIL 0 0 0 was > /dev/ada3 > ada4 ONLINE 0 0 0 > ada5 ONLINE 0 0 0 > ada6 ONLINE 0 0 0 > ada7 ONLINE 0 0 0 > ada8 ONLINE 0 0 0 > ada10p4 ONLINE 0 0 0 > > root@filekeeper:/storage # zpool export storage > root@filekeeper:/storage # zpool import storage > cannot import 'storage': I/O error > Destroy and re-create the pool from > a backup source. > > root@filekeeper:/usr/home/paul # uname -a > FreeBSD filekeeper.caspersworld.co.uk 10.0-CURRENT FreeBSD > 10.0-CURRENT #0 r240967: Thu Sep 27 08:01:24 UTC 2012 > root@filekeeper.caspersworld.co.uk:/usr/obj/usr/src/sys/GENERIC amd64 From owner-freebsd-current@FreeBSD.ORG Mon Nov 5 10:50:02 2012 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id C66CF62E for ; Mon, 5 Nov 2012 10:50:02 +0000 (UTC) (envelope-from prvs=1656497edf=killing@multiplay.co.uk) Received: from mail1.multiplay.co.uk (mail1.multiplay.co.uk [85.236.96.23]) by mx1.freebsd.org (Postfix) with ESMTP id 545748FC18 for ; Mon, 5 Nov 2012 10:50:01 +0000 (UTC) Received: from r2d2 ([188.220.16.49]) by mail1.multiplay.co.uk (mail1.multiplay.co.uk [85.236.96.23]) (MDaemon PRO v10.0.4) with ESMTP id md50000957641.msg for ; Mon, 05 Nov 2012 10:49:54 +0000 X-Spam-Processed: mail1.multiplay.co.uk, Mon, 05 Nov 2012 10:49:54 +0000 (not processed: message from valid local sender) X-MDRemoteIP: 188.220.16.49 X-Return-Path: prvs=1656497edf=killing@multiplay.co.uk X-Envelope-From: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-current@freebsd.org Message-ID: <749120126EF1493696FA77101C824F09@multiplay.co.uk> From: "Steven Hartland" To: "Paul Wootton" , "freeBSD-CURRENT Mailing List" References: <508F98F9.3040604@fletchermoorland.co.uk> <50979436.4020907@fletchermoorland.co.uk> Subject: Re: ZFS RaidZ-2 problems Date: Mon, 5 Nov 2012 10:49:57 -0000 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.5931 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.6157 X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Nov 2012 10:50:02 -0000 Yes RAIDZ2 should enable a 2 drive failure without the array faulting so something strange is going on there somewhere. Silly question, what size drives and what driver are you using? Regards Steve ----- Original Message ----- From: "Paul Wootton" To: "freeBSD-CURRENT Mailing List" Sent: Monday, November 05, 2012 10:25 AM Subject: ZFS RaidZ-2 problems > I've already posted this to freebsd-fs@ but still have no idea as to why > the below has happened. > > > On 10/30/12 09:08, Paul Wootton wrote: >> Hi, >> >> I have had lots of bad luck with SATA drives and have had them fail on >> me far too often. Started with a 3 drive RAIDZ and lost 2 drives at >> the same time. Upgraded to a 6 drive RAIDZ and lost 2 drives with in >> hours of each other and finally had a 9 drive RAIDZ (1 parity) and >> lost another 2 drives (as luck would happen, this time I had a 90% >> backup on another machine so did not loose everything). I finally >> decided that I should switch to a RAIDZ2 (my current setup). >> Now I have lost 1 drive and the pack is showing as faulted. I have >> tried exporting and reimp