From owner-p4-projects@FreeBSD.ORG Fri Oct 12 18:51:26 2007 Return-Path: Delivered-To: p4-projects@freebsd.org Received: by hub.freebsd.org (Postfix, from userid 32767) id D4A0A16A420; Fri, 12 Oct 2007 18:51:25 +0000 (UTC) Delivered-To: perforce@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6250916A41A for ; Fri, 12 Oct 2007 18:51:25 +0000 (UTC) (envelope-from kmacy@freebsd.org) Received: from repoman.freebsd.org (repoman.freebsd.org [IPv6:2001:4f8:fff6::29]) by mx1.freebsd.org (Postfix) with ESMTP id 5993F13C468 for ; Fri, 12 Oct 2007 18:51:25 +0000 (UTC) (envelope-from kmacy@freebsd.org) Received: from repoman.freebsd.org (localhost [127.0.0.1]) by repoman.freebsd.org (8.14.1/8.14.1) with ESMTP id l9CIpPcF083654 for ; Fri, 12 Oct 2007 18:51:25 GMT (envelope-from kmacy@freebsd.org) Received: (from perforce@localhost) by repoman.freebsd.org (8.14.1/8.14.1/Submit) id l9CIpPvK083651 for perforce@freebsd.org; Fri, 12 Oct 2007 18:51:25 GMT (envelope-from kmacy@freebsd.org) Date: Fri, 12 Oct 2007 18:51:25 GMT Message-Id: <200710121851.l9CIpPvK083651@repoman.freebsd.org> X-Authentication-Warning: repoman.freebsd.org: perforce set sender to kmacy@freebsd.org using -f From: Kip Macy To: Perforce Change Reviews Cc: Subject: PERFORCE change 127448 for review X-BeenThere: p4-projects@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: p4 projects tree changes List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 12 Oct 2007 18:51:26 -0000 http://perforce.freebsd.org/chv.cgi?CH=127448 Change 127448 by kmacy@kmacy_home:ethng on 2007/10/12 18:50:38 disable larger than page size allocations in m_getm2 until an apparent memory leak is tracked down Affected files ... .. //depot/projects/ethng/src/sys/kern/uipc_mbuf.c#5 edit Differences ... ==== //depot/projects/ethng/src/sys/kern/uipc_mbuf.c#5 (text+ko) ==== @@ -110,14 +110,19 @@ /* Loop and append maximum sized mbufs to the chain tail. */ while (len > 0) { int clsize = MJUMPAGESIZE; - +#ifdef notyet + /* + * XXX seeing what appears to be a memory leak on blast + * overload conditions - turning this off won't fix + * but it will delay it + */ if (jumbo_phys_contig) { if (len >= MJUM9BYTES) clsize = MJUM16BYTES; else if (len >= MJUMPAGESIZE) clsize = MJUM9BYTES; } - +#endif if (len > MCLBYTES) mb = m_getjcl(how, type, (flags & M_PKTHDR), clsize);