From owner-freebsd-bugs@FreeBSD.ORG Thu Feb 12 11:00:12 2009 Return-Path: Delivered-To: freebsd-bugs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D358E106564A for ; Thu, 12 Feb 2009 11:00:12 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id A6D8D8FC08 for ; Thu, 12 Feb 2009 11:00:12 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (gnats@localhost [127.0.0.1]) by freefall.freebsd.org (8.14.3/8.14.3) with ESMTP id n1CB0CD1074824 for ; Thu, 12 Feb 2009 11:00:12 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.3/8.14.3/Submit) id n1CB0Cps074819; Thu, 12 Feb 2009 11:00:12 GMT (envelope-from gnats) Date: Thu, 12 Feb 2009 11:00:12 GMT Message-Id: <200902121100.n1CB0Cps074819@freefall.freebsd.org> To: freebsd-bugs@FreeBSD.org From: Mikolaj Golub Cc: Subject: Re: misc/131597: c++ exceptions very slow on FreeBSD 7.1/amd64 X-BeenThere: freebsd-bugs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Mikolaj Golub List-Id: Bug reports List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 12 Feb 2009 11:00:13 -0000 The following reply was made to PR misc/131597; it has been noted by GNATS. From: Mikolaj Golub To: bug-followup@FreeBSD.org Cc: Guillaume Morin Subject: Re: misc/131597: c++ exceptions very slow on FreeBSD 7.1/amd64 Date: Thu, 12 Feb 2009 12:25:18 +0200 It looks like 6.x is not affected by this problem (or at least the situation is much better here). I have checked on several 6.x hosts and the output looks like this: 0.55 real 0.55 user 0.00 sys 1000 maximum resident set size 4 average shared memory size 33 average unshared data size 133 average unshared stack size 98 page reclaims 0 page faults 0 swaps 0 block input operations 0 block output operations 0 messages sent 0 messages received 0 signals received 1 voluntary context switches 48 involuntary context switches In all cases sys time was zero. While on my 7.1-STABLE i386 (Core(TM)2 CPU 6400 @ 2.13GHz) box : 1.93 real 0.58 user 1.34 sys 1252 maximum resident set size 4 average shared memory size 732 average unshared data size 128 average unshared stack size 115 page reclaims 0 page faults 0 swaps 0 block input operations 0 block output operations 0 messages sent 0 messages received 0 signals received 1 voluntary context switches 32 involuntary context switches or 7.1-RELEASE-p1 amd64 (Xeon(R) CPU E5450 @ 3.00GHz): 3.93 real 3.80 user 0.12 sys 1736 maximum resident set size 4 average shared memory size 1024 average unshared data size 128 average unshared stack size 135 page reclaims 0 page faults 0 swaps 0 block input operations 0 block output operations 0 messages sent 0 messages received 0 signals received 1 voluntary context switches 41 involuntary context switches I have tried g++ both of v3.4 and v4.2 and hasn't noticed significant difference, in my tests 3.4 was a bit faster but it might be influence of external factors (host load). -- Mikolaj Golub