Re: acpiec on acer aspire S7 with CURRENT

On Mon, Oct 24, 2016 at 3:01 PM, Mark Kettenis wrote: >> Date: Mon, 24 Oct 2016 23:01:22 +0300 >> From: Paul Irofti >> >> On Mon, Oct 24, 2016 at 10:50:00PM +0300, Paul Irofti wrote: >> > On Mon, Oct 24, 2016 at 07:46:33PM +0200, Mark Kettenis wrote: >>

Re: per-cpu caches for pools

On Mon, Oct 24, 2016 at 04:24:13PM +1000, David Gwynne wrote: > ive posted this before as part of a much bigger diff, but smaller > is better. > > it basically lets things ask for per-cpu item caches to be enabled > on pools. the most obvious use case for this is the mbuf pools. > > the caches

Re: network performance fun

On Tue, Oct 25, 2016 at 12:50:50AM +0200, Mike Belopuhov wrote: > On Tue, Oct 25, 2016 at 00:22 +0200, Hrvoje Popovski wrote: > > On 24.10.2016. 23:36, Mike Belopuhov wrote: > > > On Mon, Oct 24, 2016 at 19:04 +0200, Hrvoje Popovski wrote: > > >> Hi all, > > >> > > >> OpenBSD box acts as transit

Re: (re)name cpumem_realloc to cpumem_malloc_ncpus

thank you for looking at this. ive committed it with tweaks based on your suggestions. > On 24 Oct 2016, at 22:15, Alexander Bluhm wrote: > > On Mon, Oct 24, 2016 at 02:48:03PM +1000, David Gwynne wrote: >> cos its not resizing the allocation, its allocating them for

[PATCH] faq/current.html - small correction

Hi all, Recent commit[1] set the font on the rest of the faq/current.html[1] page (i.e. the footer) to boldface. Remove redundant 'rm' while there. [0] http://cvsweb.openbsd.org/cgi-bin/cvsweb/www/faq/current.html.diff?r1=1.741=1.742 [1] http://www.openbsd.org/faq/current.html Cheers, Raf

Re: network performance fun

On Tue, Oct 25, 2016 at 00:22 +0200, Hrvoje Popovski wrote: > On 24.10.2016. 23:36, Mike Belopuhov wrote: > > On Mon, Oct 24, 2016 at 19:04 +0200, Hrvoje Popovski wrote: > >> Hi all, > >> > >> OpenBSD box acts as transit router for /8 networks without pf and with > >> this sysctls > >> > >>

Re: network performance fun

On 25.10.2016. 0:22, Hrvoje Popovski wrote: > On 24.10.2016. 23:36, Mike Belopuhov wrote: >> On Mon, Oct 24, 2016 at 19:04 +0200, Hrvoje Popovski wrote: >>> Hi all, >>> >>> OpenBSD box acts as transit router for /8 networks without pf and with >>> this sysctls >>> >>> ddb.console=1 >>>

Re: network performance fun

On 24.10.2016. 23:36, Mike Belopuhov wrote: > On Mon, Oct 24, 2016 at 19:04 +0200, Hrvoje Popovski wrote: >> Hi all, >> >> OpenBSD box acts as transit router for /8 networks without pf and with >> this sysctls >> >> ddb.console=1 >> kern.pool_debug=0 >> net.inet.ip.forwarding=1 >>

Re: acpiec on acer aspire S7 with CURRENT

> Date: Mon, 24 Oct 2016 23:01:22 +0300 > From: Paul Irofti > > On Mon, Oct 24, 2016 at 10:50:00PM +0300, Paul Irofti wrote: > > On Mon, Oct 24, 2016 at 07:46:33PM +0200, Mark Kettenis wrote: > > > > From: Paul Irofti > > > > Date: Mon, 24 Oct 2016 17:12:01

Re: network performance fun

On Mon, Oct 24, 2016 at 19:04 +0200, Hrvoje Popovski wrote: > Hi all, > > OpenBSD box acts as transit router for /8 networks without pf and with > this sysctls > > ddb.console=1 > kern.pool_debug=0 > net.inet.ip.forwarding=1 > net.inet.ip.ifq.maxlen=8192 > > netstat > 11/8

Re: acpiec on acer aspire S7 with CURRENT

On Mon, Oct 24, 2016 at 10:50:00PM +0300, Paul Irofti wrote: > On Mon, Oct 24, 2016 at 07:46:33PM +0200, Mark Kettenis wrote: > > > From: Paul Irofti > > > Date: Mon, 24 Oct 2016 17:12:01 +0300 > > > > > > Any thoughts on this? > > > > Sorry, yes. Adding the crs "index" as the

Re: acpiec on acer aspire S7 with CURRENT

On Mon, Oct 24, 2016 at 07:46:33PM +0200, Mark Kettenis wrote: > > From: Paul Irofti > > Date: Mon, 24 Oct 2016 17:12:01 +0300 > > > > Any thoughts on this? > > Sorry, yes. Adding the crs "index" as the last argument of the > callback function seems a bit non-intuitive to me.

Re: acpiec on acer aspire S7 with CURRENT

> From: Paul Irofti > Date: Mon, 24 Oct 2016 17:12:01 +0300 > > Any thoughts on this? Sorry, yes. Adding the crs "index" as the last argument of the callback function seems a bit non-intuitive to me. I'd say the void * argument should remain the last argument, and the crs

Re: switchd(8): add flow_mod validation

On Wed, Oct 12, 2016 at 05:39:17PM +0200, Rafael Zalamena wrote: > This diff teaches switchd(8) how to validate flow_mod messages, more > specifically the flow instructions and actions. The oxm validations > were already implemented so we get them for free here. I've updated the flow_mod diff to

network performance fun

Hi all, OpenBSD box acts as transit router for /8 networks without pf and with this sysctls ddb.console=1 kern.pool_debug=0 net.inet.ip.forwarding=1 net.inet.ip.ifq.maxlen=8192 netstat 11/8 192.168.11.2 UGS0 114466419 - 8 ix0 12/8 192.168.12.2

Re: fix carp "carppeer" + "real mac-address"

On Mon, Oct 24, 2016 at 12:04:37PM +0900, YASUOKA Masahiko wrote: > FYI. I just commited regress tests on regress/netinet/carp/ . > carp_4.sh demostrates the problem which the diff fixes. root@ot1:.../carp# make ksh /usr/src/regress/sys/netinet/carp/carp_1.sh -R "11 12" -I "11 12" ksh

Re: acpiec on acer aspire S7 with CURRENT

Any thoughts on this? -Mesaj original- De la: "Paul Irofti" Trimis: ‎22.‎10.‎2016 15:34 Către: "Mark Kettenis" Cc: "guent...@gmail.com" ; "tech@openbsd.org" Subiect: Re: acpiec on acer aspire S7 with

Re: (re)name cpumem_realloc to cpumem_malloc_ncpus

On Mon, Oct 24, 2016 at 02:48:03PM +1000, David Gwynne wrote: > cos its not resizing the allocation, its allocating them for new cpus. realloc is not a good name, so yes to renaming. > the same goes for counters_realloc being named counters_alloc_ncpus. Does the n mean new? This is never

Re: Quirks for pkcbc?

On Sun, Oct 23, 2016 at 03:42:59PM -0600, Theo de Raadt wrote: > [...] > I ask you to figure out logical conditions under which this should > happen, or if some interaction is wrong. > [...] Understood. I'll try tracking down the exact circumstances of the issue and come back with a better diff.

iwn: stop forcing RTS for all frames in 11n mode

This is similar to a recent change in iwm, but it only affects 11n mode in this driver. The condition being removed below was added by me before the RTS threshold was enabled in net80211. So now we should not need it anymore and removing it might actually improve things by removing RTS overhead

Re: tun(4)/tap(4): fix mbuf header space check

On Mon, Oct 24, 2016 at 09:56:13AM +0200, Rafael Zalamena wrote: > tun(4)/tap(4) function tun_dev_write() is checking for the wrong size for > the mbuf packet header. We must check against MHLEN (the mbuf header data > storage size) and not MINCLSIZE (smallest amount of data of a cluster). > >

Re: (re)name cpumem_realloc to cpumem_malloc_ncpus

David Gwynne wrote: > cos its not resizing the allocation, its allocating them for new cpus. > > the same goes for counters_realloc being named counters_alloc_ncpus. > > this adds doco for them too. Hi, FWIW it makes sense to me, for when I was looking at the per-cpu mbstat diff, I blocked a

tun(4)/tap(4): fix mbuf header space check

tun(4)/tap(4) function tun_dev_write() is checking for the wrong size for the mbuf packet header. We must check against MHLEN (the mbuf header data storage size) and not MINCLSIZE (smallest amount of data of a cluster). For the curious: MGETHDR() calls m_gethdr() which uses mbpool to get the mbuf

per-cpu caches for pools

ive posted this before as part of a much bigger diff, but smaller is better. it basically lets things ask for per-cpu item caches to be enabled on pools. the most obvious use case for this is the mbuf pools. the caches are modelled on whats described in the "Magazines and Vmem: Extending the