Return-path: Received: from mail-iy0-f174.google.com ([209.85.210.174]:55651 "EHLO mail-iy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754672Ab2HXOKC (ORCPT ); Fri, 24 Aug 2012 10:10:02 -0400 Message-ID: <50378B35.80307@lwfinger.net> (sfid-20120824_161010_092005_64FABB14) Date: Fri, 24 Aug 2012 09:09:57 -0500 From: Larry Finger MIME-Version: 1.0 To: Eric Dumazet CC: Neal Cardwell , "David S. Miller" , John W Linville , linux-wireless , LKML Subject: Re: Regression associated with commit c8628155ece3 - "tcp: reduce out_of_order memory use" References: <50345B12.1050600@lwfinger.net> <1345612503.5158.566.camel@edumazet-glaptop> <50355021.7000408@lwfinger.net> <1345694593.5904.87.camel@edumazet-glaptop> <50369925.3050705@lwfinger.net> <1345757200.5904.1890.camel@edumazet-glaptop> In-Reply-To: <1345757200.5904.1890.camel@edumazet-glaptop> Content-Type: text/plain; charset=UTF-8; format=flowed Sender: linux-wireless-owner@vger.kernel.org List-ID: On 08/23/2012 04:26 PM, Eric Dumazet wrote: > > skb->truesize is adjusted when a frag is added to one skb, or when > skb->head is re-allocated. > > Are you sure you dont have another problem, because as I said commit > c8628155ece3 had a bug, so a bisect is not very useful. > > How many reloads are needed to trigger the bug, do you have a script to > reproduce it ? I was doing the tests with a browser; however, it seems that a wget of that same page is much more effective at triggering the problem. Now I have a script that tries 60 passes of wget https://bugzilla.redhat.com/show_bug.cgi?id=847525 I usually get failures on the first or second try. A kernel built from "git checkout c862815" gets the following wget output: ============================================================================ --2012-08-23 21:50:32-- https://bugzilla.redhat.com/show_bug.cgi?id=847525 Resolving bugzilla.redhat.com (bugzilla.redhat.com)... 209.132.183.69 Connecting to bugzilla.redhat.com (bugzilla.redhat.com)|209.132.183.69|:443... connected. OpenSSL: error:0D0680A8:asn1 encoding routines:ASN1_CHECK_TLEN:wrong tag OpenSSL: error:0D07803A:asn1 encoding routines:ASN1_ITEM_EX_D2I:nested asn1 error OpenSSL: error:0D08303A:asn1 encoding routines:ASN1_TEMPLATE_NOEXP_D2I:nested asn1 error OpenSSL: error:0D08303A:asn1 encoding routines:ASN1_TEMPLATE_NOEXP_D2I:nested asn1 error OpenSSL: error:1409000D:SSL routines:SSL3_GET_SERVER_CERTIFICATE:ASN1 lib Unable to establish SSL connection. ============================================================================ With kernel 3.6-rc2, the error changes to the following: ============================================================================ --2012-08-24 08:26:42-- https://bugzilla.redhat.com/show_bug.cgi?id=847525 Resolving bugzilla.redhat.com (bugzilla.redhat.com)... 209.132.183.69 Connecting to bugzilla.redhat.com (bugzilla.redhat.com)|209.132.183.69|:443... connected. HTTP request sent, awaiting response... 200 OK Length: unspecified [text/html] Saving to: `show_bug.cgi?id=847525.3' [ <=> ] 0 --.-K/s in 0s 2012-08-24 08:26:45 (0.00 B/s) - Read error at byte 0 (error:1408F119:SSL routines:SSL3_GET_RECORD:decryption failed or bad record mac).Retrying. ============================================================================ > Could it be a PMTU problem ? (check > http://git.kernel.org/?p=linux/kernel/git/davem/net.git;a=commit;h=9b04f350057863d1fad1ba071e09362a1da3503e ) I added the PMTU patch to kernel 3.6-rc2 - nothing changed. Anything else to try? Thanks, Larry