lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
Open Source and information security mailing list archives
| ||
|
Message-ID: <1464100646.5939.50.camel@edumazet-glaptop3.roam.corp.google.com> Date: Tue, 24 May 2016 07:37:26 -0700 From: Eric Dumazet <eric.dumazet@...il.com> To: David Laight <David.Laight@...LAB.COM> Cc: 'Jesper Dangaard Brouer' <brouer@...hat.com>, Alexander Duyck <alexander.duyck@...il.com>, netdev <netdev@...r.kernel.org>, Alexander Duyck <aduyck@...antis.com>, John Fastabend <john.r.fastabend@...el.com>, Jamal Hadi Salim <jhs@...atatu.com> Subject: Re: [RFC] net: remove busylock On Tue, 2016-05-24 at 13:50 +0000, David Laight wrote: > From: Jesper Dangaard Brouer > > Sent: 20 May 2016 18:50 > ... > > If would be cool if you could run a test with removed busylock and > > allow HTB to bulk dequeue. > > (Without having looked ....) > Could you have two queues and separate queue and dequeue locks. > > The enqueue code would acquire the enqueue lock and add the packet > to the first queue. > > The dequeue code would acquire the dequeue lock and try to remove > a packet from the 2nd queue, if nothing present it would acquire > the enqueue lock and move the entire 1st queue to the 2nd queue. > > The obvious downside is two lock/unlocks for single packet dequeue. > If you can guarantee a single dequeue thread the 2nd lock isn't needed. > Not with HTB or any 'complex' qdisc hierarchy, where we have many 'queues' and strict limits (packets per qdisc)
Powered by blists - more mailing lists