From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sowmini Varadhan Subject: Re: [PATCH net-next 0/9] net: Kernel side filtering for route dumps Date: Thu, 11 Oct 2018 12:10:23 -0400 Message-ID: <20181011161023.GA11906@oracle.com> References: <20181011150627.4010-1-dsahern@kernel.org> <20181011082637.3e7833c9@xeon-e3> <02e2a1eb-07be-5a13-c9fc-e0a47287fdbf@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Stephen Hemminger , David Ahern , netdev@vger.kernel.org, davem@davemloft.net To: David Ahern Return-path: Received: from userp2130.oracle.com ([156.151.31.86]:36716 "EHLO userp2130.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726700AbeJKXi0 (ORCPT ); Thu, 11 Oct 2018 19:38:26 -0400 Content-Disposition: inline In-Reply-To: <02e2a1eb-07be-5a13-c9fc-e0a47287fdbf@gmail.com> Sender: netdev-owner@vger.kernel.org List-ID: On (10/11/18 09:32), David Ahern wrote: > > Route dumps are done for the entire FIB for each address family. As we > approach internet routing tables (700k+ routes for IPv4, currently > around 55k for IPv6) with many VRFs dumping the entire table is grossly > inefficient when for example only a single VRF table is wanted. I think someone mentioned a long time ago that a VRF is not an interface/driver/net_device but rather a separate routing table with a dedicated set of interfaces, iirc :-) :-) In the latter model, if you wanted to dump a VRF table, you'd only lock that table, and walk it, instead of holding up other VRFS sorry, could not resist my i-told-you-so moment :-P --Sowmini