similar to: [PATCH 0/2] Runtime configuration of HTB''s HYSTERESIS option

The HTB qdisc has a compile time option, HTB_HYSTERESIS, that trades accuracy of traffic classification for CPU time. These patches change hysteresis to be a runtime option under the control of "tc". The effects of HYSTERESIS on HTB''s accuracy are significant (see chapter 7, section 7.3.1, pp 69-70 in Jesper Brouer''s thesis: http://www.adsl-optimizer.dk/thesis/ ),

The HTB qdisc has a compile time option, HTB_HYSTERESIS, that trades accuracy of traffic classification for CPU time. These patches change hysteresis to be a runtime option under the control of "tc". The effects of HYSTERESIS on HTB''s accuracy are significant (see chapter 7, section 7.3.1, pp 69-70 in Jesper Brouer''s thesis: http://www.adsl-optimizer.dk/thesis/ ),

I posted earlier when I noticed that htb was releasing packets in pairs, even though my burst/quantums were 1 pkt. To fix I set HTB_HYSTERESIS 0 in net/sched/sch_htb.c . This gives a noticable gain in upstream worst case latency, for me with 256kbit/s up I used to see +90 sometimes, now it''s +45. For the many who have 128 up it should limit them to +90 rather than +180. Andy.

Can anyone suggest a package or code for modeling a hysteresis process in R? I'm currently modeling a certain dataset with a GAM using mgcv, something like gam(y~ s(x, by=z) + z, family = Gamma(link=log),data=data) and getting fits with about 9 estimated degrees of freedom in the smooth for each value of z. FWIW, z is a treatment applied to a system which should have made an improvement,

We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we can receive partial csumed packets with metadata kept in the vnet_hdr. This may have several side effects: - It could be overridden by header adjustment, thus is might be not correct after XDP processing. - There's no way to pass such metadata information through XDP_REDIRECT to another driver. - XDP does not

We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we can receive partial csumed packets with metadata kept in the vnet_hdr. This may have several side effects: - It could be overridden by header adjustment, thus is might be not correct after XDP processing. - There's no way to pass such metadata information through XDP_REDIRECT to another driver. - XDP does not

Hello, i have a htb setup where the root and (nearly) all child classes has a ceil rate with max up from my adsl line. But the root class don''t reach the ceil value but some childs are get a huge backlog. My setup: (tc -d class show dev ppp0) [cleaned a bit] ******************************************************** class htb 1:1 root rate 576000bit ceil 576000bit burst 30Kb/8 cburst

On Thu, 1 Mar 2018 21:15:36 +0800 Jason Wang <jasowang at redhat.com> wrote: > On 2018?03?01? 18:35, Jesper Dangaard Brouer wrote: > > On Thu, 1 Mar 2018 17:23:37 +0800 > > Jason Wang <jasowang at redhat.com> wrote: > > > >> On 2018?03?01? 17:10, Jesper Dangaard Brouer wrote: > >>> On Thu, 1 Mar 2018 11:19:03 +0800 > >>> Jason

hi i ve seen one of your replies here and i saw that you receomend 2 modifications in the kernel files in order to improve htb. first in pkt_sched.h, changing PSCHED_JIFFIES to PSCHED_CPU. and then, sch_htb.c, changing HYSTERESIS from 1 to 0. is it that simple? i mean i just change these here variables and i get better results? i ve done a search and found the first file in 3 locations. where

On Sat, 2 Feb 2019 14:27:26 -0700 David Ahern <dsahern at gmail.com> wrote: > On 1/31/19 1:15 PM, Jesper Dangaard Brouer wrote: > >> > >> David, Jesper, care to chime in where we ended up in that last thread > >> discussion this? > > > > IHMO packets RX and TX on a device need to be accounted, in standard > > counters, regardless of XDP.

On Fri, 2 Mar 2018 17:29:14 +0800 Jason Wang <jasowang at redhat.com> wrote: > XDP_REDIRECT support for mergeable buffer was removed since commit > 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable() > case"). This is because we don't reserve enough tailroom for struct > skb_shared_info which breaks XDP assumption. So this patch fixes this >

We don't support partial csumed packet since its metadata will be lost or incorrect during XDP processing. So fail the XDP set if guest_csum feature is negotiated. Fixes: f600b6905015 ("virtio_net: Add XDP support") Reported-by: Jesper Dangaard Brouer <brouer at redhat.com> Cc: Jesper Dangaard Brouer <brouer at redhat.com> Cc: Pavel Popa <pashinho1990 at gmail.com>

From: Jason Wang <jasowang at redhat.com> Date: Thu, 22 Nov 2018 14:36:30 +0800 > We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we > can receive partial csumed packets with metadata kept in the > vnet_hdr. This may have several side effects: > > - It could be overridden by header adjustment, thus is might be not > correct after XDP processing.

On Wed, 6 May 2020 14:16:32 +0800 Jason Wang <jasowang at redhat.com> wrote: > We tried to reserve space for vnet header before > xdp.data_hard_start. But this is useless since the packet could be > modified by XDP which may invalidate the information stored in the > header and IMHO above statements are wrong. XDP cannot access memory before xdp.data_hard_start. Thus, it is

On Thu, 1 Mar 2018 17:23:37 +0800 Jason Wang <jasowang at redhat.com> wrote: > On 2018?03?01? 17:10, Jesper Dangaard Brouer wrote: > > On Thu, 1 Mar 2018 11:19:03 +0800 > > Jason Wang <jasowang at redhat.com> wrote: > > > >> This series tries to re-enable XDP_REDIRECT for mergeable buffer which > >> was removed since commit 7324f5399b06

On Thu, 1 Mar 2018 11:19:04 +0800 Jason Wang <jasowang at redhat.com> wrote: > XDP_REDIRECT support for mergeable buffer was removed since commit > 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable() > case"). This is because we don't reserve enough tailroom for struct > skb_shared_info which breaks XDP assumption. Other complaints are, the >

The virtio_net driver doesn't dynamically change the RX-ring queue layout and backing pages, but instead reject XDP setup if all the conditions for XDP is not meet. Thus, the xdp_rxq_info also remains fairly static. This allow us to simply add the reg/unreg to net_device open/close functions. Driver hook points for xdp_rxq_info: * reg : virtnet_open * unreg: virtnet_close Cc:

On Wed, May 06, 2020 at 04:34:36PM +0800, Jason Wang wrote: > > On 2020/5/6 ??4:21, Jesper Dangaard Brouer wrote: > > On Wed, 6 May 2020 14:16:32 +0800 > > Jason Wang <jasowang at redhat.com> wrote: > > > > > We tried to reserve space for vnet header before > > > xdp.data_hard_start. But this is useless since the packet could be > > >

On 2020/5/6 ??4:21, Jesper Dangaard Brouer wrote: > On Wed, 6 May 2020 14:16:32 +0800 > Jason Wang <jasowang at redhat.com> wrote: > >> We tried to reserve space for vnet header before >> xdp.data_hard_start. But this is useless since the packet could be >> modified by XDP which may invalidate the information stored in the >> header and > IMHO above

On 2020/5/6 ??4:21, Jesper Dangaard Brouer wrote: > On Wed, 6 May 2020 14:16:32 +0800 > Jason Wang <jasowang at redhat.com> wrote: > >> We tried to reserve space for vnet header before >> xdp.data_hard_start. But this is useless since the packet could be >> modified by XDP which may invalidate the information stored in the >> header and > IMHO above