Re: OpenBSD 6.6 amd64 iavf(4) iavf / SR-iov 40G NIC lots of Jitter
Hi Joseph Thanks for your email and suggestion Basically the vm is running 2 cores of a 20 core server with only one other 2 cote vm running My experience would expect jitter of no more than 2 -4ms in running openbsd on kvm where contention on cores is minimal The virtio setup... using the hosts bridge / network stack Has less jitter and higer performance (2x) Also the scale of the jitter is a concern... being over 100ms Compared with the "normal latency of a few hundred micro seconds any pointers for tests that would help me identify the source of the latency would be helpful Thanks On Sunday, 20 October 2019, Joseph Mayer wrote: > Tom, is not the jitter you are experiencing totally normal overhead for > a hypervisor. > > Someone would need to correct me on this one but I'm surprised that you > are surprised about the jitter, considering it's a VM. > > Please run OpenBSD on bare metal?? > > Joseph > > ‐‐‐ Original Message ‐‐‐ > On Sunday, 20 October 2019 07:51, Tom Smyth > wrote: > > > just to say when testing this > > I was running the openbsd6.6vm with one other vm as a guest on a > > proxmox 6.0 / KVM Host, > > with 2x Intel 10 Core Xeon E5 v2 Xeons, with no hyperthreading on the > > host. > > what other tests can I run to help identify the source / cause of the > > jitter > > > > Thanks > > > > Tom Smyth > > > > On Sun, 20 Oct 2019 at 00:49, Tom Smyth tom.sm...@wirelessconnect.eu > > wrote: > > > > > Hello, > > > Thanks to Jonathan Matthew and DLG for their work on ixl and iavf > drivers > > > and everyone else who worked on it.. > > > One thing I have noticed in trying out this driver on 6.5+ current and > > > 6.6 release is that while the latency is low... there is quite > > > considerable Jitter during simple ping testing > > > I have included full Ping output below the dmesg for your information > > > the summary of the ping tests are below > > > > > > --- 10.11.100.1 ping statistics --- > > > 1000 packets transmitted, 1000 packets received, 0.0% packet loss > > > round-trip min/avg/max/std-dev = 0.116/74.187/1000.389/174.442 ms > > > > > > > > > > > > > > I have included below > > > the output of > > > pcidump, pcidump - and dmesg > > > is there anything else I can do to diagnose the issue > > > > > > output of pcidump > > > openbsd66# pcidump > > > Domain /dev/pci0: > > > 0:0:0: Intel 82G33 Host > > > 0:1:0: Bochs VGA > > > 0:26:0: Intel 82801I USB > > > 0:26:1: Intel 82801I USB > > > 0:26:2: Intel 82801I USB > > > 0:26:7: Intel 82801I USB > > > 0:27:0: Intel 82801I HD Audio > > > 0:28:0: Red Hat unknown > > > 0:28:1: Red Hat unknown > > > 0:28:2: Red Hat unknown > > > 0:28:3: Red Hat unknown > > > 0:29:0: Intel 82801I USB > > > 0:29:1: Intel 82801I USB > > > 0:29:2: Intel 82801I USB > > > 0:29:7: Intel 82801I USB > > > 0:30:0: Intel 82801BA Hub-to-PCI > > > 0:31:0: Intel 82801IB LPC > > > 0:31:2: Intel 82801I AHCI > > > 0:31:3: Intel 82801I SMBus > > > 1:0:0: Intel XL710/X710 VF > > > 5:1:0: Red Hat Qemu PCI-PCI > > > 5:2:0: Red Hat Qemu PCI-PCI > > > 5:3:0: Red Hat Qemu PCI-PCI > > > 5:4:0: Red Hat Qemu PCI-PCI > > > 6:7:0: Intel 82801I AHCI > > > > > > > > > > > > > > > > > -- > > > > > > pcidump - > > > Domain /dev/pci0: > > > 0:0:0: Intel 82G33 Host > > > 0x: Vendor ID: 8086, Product ID: 29c0 > > > 0x0004: Command: 0103, Status: > > > 0x0008: Class: 06 Bridge, Subclass: 00 Host, > > > Interface: 00, Revision: 00 > > > 0x000c: BIST: 00, Header Type: 00, Latency Timer: 00, > > > Cache Line Size: 00 > > > 0x0010: BAR empty () > > > 0x0014: BAR empty () > > > 0x0018: BAR empty () > > > 0x001c: BAR empty () > > > 0x0020: BAR empty () > > > 0x0024: BAR empty () > > > 0x0028: Cardbus CIS: > > > 0x002c: Subsystem Vendor ID: 1af4 Product ID: 1100 > > > 0x0030: Expansion ROM Base Address: > > > 0x0038: > > > 0x003c: Interrupt Pin: 00 Line: 00 Min Gnt: 00 Max Lat: 00 > > > 0:1:0: Bochs VGA > > > 0x: Vendor ID: 1234, Product ID: > > > 0x0004: Command: 0107, Status: > > > 0x0008: Class: 03 Display, Subclass:
Re: Companies using openbsd
My company hosts its websites on Linux but almost all developers use OpenBSD. When VP of IT visited I asked him why he choice OpenBSD and he said, "It just works". On Sun, Oct 20, 2019 at 6:37 PM Aaron Mason wrote: > Not our own product, but we run Request Tracker on OpenBSD - after > using ManageEngine ServiceDesk Plus on Windaz, requiring 2GB RAM > minimum. Our RT server has 512mb RAM and it's all it has ever needed. > > On Mon, Oct 21, 2019 at 8:10 AM List wrote: > > > > Hi, > > > > are there companies known to you who use openbsd for their products ? > > > > For building let's say their own OS based upon OpenBSD ? > > > > Thanks for your time. > > > > Regards, > > > > Stephan > > > > > -- > Aaron Mason - Programmer, open source addict > I've taken my software vows - for beta or for worse > >
Re: Nobody said it yet...
On Fri, Oct 18, 2019 at 08:03:04PM -0400, STeve Andre' wrote: > Happy birthday to OpenBSD! >Happy Birthday !
Re: Companies using openbsd
Not our own product, but we run Request Tracker on OpenBSD - after using ManageEngine ServiceDesk Plus on Windaz, requiring 2GB RAM minimum. Our RT server has 512mb RAM and it's all it has ever needed. On Mon, Oct 21, 2019 at 8:10 AM List wrote: > > Hi, > > are there companies known to you who use openbsd for their products ? > > For building let's say their own OS based upon OpenBSD ? > > Thanks for your time. > > Regards, > > Stephan > -- Aaron Mason - Programmer, open source addict I've taken my software vows - for beta or for worse
Re: Companies using openbsd
Our company has developed several devices that run OpenBSD under the hood, including a milk expending machine and a multichannel RoIP device. Curiosly, network features have no relevance for us: stability and a solid and consistent audio interface make OpenBSD a winner for us. Regards! El dom., 20 oct. 2019 a las 23:18, Christopher Turkel (< turkel.christop...@gmail.com>) escribió: > The company I work for uses OpenBSD for development. > > On Sun, Oct 20, 2019 at 5:12 PM List wrote: > > > Hi, > > > > are there companies known to you who use openbsd for their products ? > > > > For building let's say their own OS based upon OpenBSD ? > > > > Thanks for your time. > > > > Regards, > > > > Stephan > > > > >
Re: Companies using openbsd
The company I work for uses OpenBSD for development. On Sun, Oct 20, 2019 at 5:12 PM List wrote: > Hi, > > are there companies known to you who use openbsd for their products ? > > For building let's say their own OS based upon OpenBSD ? > > Thanks for your time. > > Regards, > > Stephan > >
Companies using openbsd
Hi, are there companies known to you who use openbsd for their products ? For building let's say their own OS based upon OpenBSD ? Thanks for your time. Regards, Stephan
Can KDE's Kate e Juk coexists? (KF5 and KDE4)
I have just upgraded my desktop PC to OpenBSD amd64 6.6. I already installed Kate (kate-18.12.0p0, witch uses KF5). I'd like to use Juk too (witch uses KDE4), but I get these errors: casa:/home/giannici# pkg_add juk quirks-3.182 signed on 2019-10-12T12:14:24Z Can't install baloo-4.14.3p7 because of conflicts (kf5-icons-baloo-5.54.0) Can't install nepomuk-core-4.14.3p3: can't resolve baloo-4.14.3p7 Can't install kactivities-4.13.3p1: can't resolve nepomuk-core-4.14.3p3 Can't install kde-runtime-4.14.3p15: can't resolve nepomuk-core-4.14.3p3,kactivities-4.13.3p1 Can't install juk-4.14.3p5: can't resolve kde-runtime-4.14.3p15 --- baloo-4.14.3p7 --- Can't install baloo-4.14.3p7: conflicts Couldn't install baloo-4.14.3p7 juk-4.14.3p5 kactivities-4.13.3p1 kde-runtime-4.14.3p15 nepomuk-core-4.14.3p3 It seems that Juk uses baloo-4.14.3p7 from KDE4, but in the system is already installed kf5-icons-baloo-5.54.0 from KF5. And they seems to conflict! Are KDE4 and KF5 packages supposed to coexists? How can use both Kate and Juk? Thanks.
Re: Requesting vi tips
marks are fairly useful and easy to define, though traditional vi doesn't keep them when swapping buffers, unfortunately. ... that's one of the main reasons why I've upgraded to vim. That and v, and multiple buffers visible at the same time. Just for the record, to not confuse the OP, vi in Openbsd is nvi. Nvi can display multiple buffers (they are called screens) splitting the screen. Nvi keeps the marks between screens when they are views of the same file. About v, I mark the starting position with ms. Then move around and use `s`` to see what I have. regards, adr
Re: OpenBSD 6.6 amd64 iavf(4) iavf / SR-iov 40G NIC lots of Jitter
Tom, is not the jitter you are experiencing totally normal overhead for a hypervisor. Someone would need to correct me on this one but I'm surprised that you are surprised about the jitter, considering it's a VM. Please run OpenBSD on bare metal?? Joseph ‐‐‐ Original Message ‐‐‐ On Sunday, 20 October 2019 07:51, Tom Smyth wrote: > just to say when testing this > I was running the openbsd6.6vm with one other vm as a guest on a > proxmox 6.0 / KVM Host, > with 2x Intel 10 Core Xeon E5 v2 Xeons, with no hyperthreading on the > host. > what other tests can I run to help identify the source / cause of the > jitter > > Thanks > > Tom Smyth > > On Sun, 20 Oct 2019 at 00:49, Tom Smyth tom.sm...@wirelessconnect.eu > wrote: > > > Hello, > > Thanks to Jonathan Matthew and DLG for their work on ixl and iavf drivers > > and everyone else who worked on it.. > > One thing I have noticed in trying out this driver on 6.5+ current and > > 6.6 release is that while the latency is low... there is quite > > considerable Jitter during simple ping testing > > I have included full Ping output below the dmesg for your information > > the summary of the ping tests are below > > > > --- 10.11.100.1 ping statistics --- > > 1000 packets transmitted, 1000 packets received, 0.0% packet loss > > round-trip min/avg/max/std-dev = 0.116/74.187/1000.389/174.442 ms > > > > > > > > I have included below > > the output of > > pcidump, pcidump - and dmesg > > is there anything else I can do to diagnose the issue > > > > output of pcidump > > openbsd66# pcidump > > Domain /dev/pci0: > > 0:0:0: Intel 82G33 Host > > 0:1:0: Bochs VGA > > 0:26:0: Intel 82801I USB > > 0:26:1: Intel 82801I USB > > 0:26:2: Intel 82801I USB > > 0:26:7: Intel 82801I USB > > 0:27:0: Intel 82801I HD Audio > > 0:28:0: Red Hat unknown > > 0:28:1: Red Hat unknown > > 0:28:2: Red Hat unknown > > 0:28:3: Red Hat unknown > > 0:29:0: Intel 82801I USB > > 0:29:1: Intel 82801I USB > > 0:29:2: Intel 82801I USB > > 0:29:7: Intel 82801I USB > > 0:30:0: Intel 82801BA Hub-to-PCI > > 0:31:0: Intel 82801IB LPC > > 0:31:2: Intel 82801I AHCI > > 0:31:3: Intel 82801I SMBus > > 1:0:0: Intel XL710/X710 VF > > 5:1:0: Red Hat Qemu PCI-PCI > > 5:2:0: Red Hat Qemu PCI-PCI > > 5:3:0: Red Hat Qemu PCI-PCI > > 5:4:0: Red Hat Qemu PCI-PCI > > 6:7:0: Intel 82801I AHCI > > > > -- > > > > pcidump - > > Domain /dev/pci0: > > 0:0:0: Intel 82G33 Host > > 0x: Vendor ID: 8086, Product ID: 29c0 > > 0x0004: Command: 0103, Status: > > 0x0008: Class: 06 Bridge, Subclass: 00 Host, > > Interface: 00, Revision: 00 > > 0x000c: BIST: 00, Header Type: 00, Latency Timer: 00, > > Cache Line Size: 00 > > 0x0010: BAR empty () > > 0x0014: BAR empty () > > 0x0018: BAR empty () > > 0x001c: BAR empty () > > 0x0020: BAR empty () > > 0x0024: BAR empty () > > 0x0028: Cardbus CIS: > > 0x002c: Subsystem Vendor ID: 1af4 Product ID: 1100 > > 0x0030: Expansion ROM Base Address: > > 0x0038: > > 0x003c: Interrupt Pin: 00 Line: 00 Min Gnt: 00 Max Lat: 00 > > 0:1:0: Bochs VGA > > 0x: Vendor ID: 1234, Product ID: > > 0x0004: Command: 0107, Status: > > 0x0008: Class: 03 Display, Subclass: 00 VGA, > > Interface: 00, Revision: 02 > > 0x000c: BIST: 00, Header Type: 00, Latency Timer: 00, > > Cache Line Size: 00 > > 0x0010: BAR mem prefetchable 32bit addr: 0xfb00/0x0100 > > 0x0014: BAR empty () > > 0x0018: BAR mem 32bit addr: 0xfea14000/0x1000 > > 0x001c: BAR empty () > > 0x0020: BAR empty () > > 0x0024: BAR empty () > > 0x0028: Cardbus CIS: > > 0x002c: Subsystem Vendor ID: 1af4 Product ID: 1100 > > 0x0030: Expansion ROM Base Address: fea0 > > 0x0038: > > 0x003c: Interrupt Pin: 00 Line: 00 Min Gnt: 00 Max Lat: 00 > > 0:26:0: Intel 82801I USB > > 0x: Vendor ID: 8086, Product ID: 2937 > > 0x0004: Command: 0107, Status: > > 0x0008: Class: 0c Serial Bus, Subclass: 03 USB, > > Interface: 00, Revision: 03 > > 0x000c: BIST: 00, Header Type: 80, Latency Timer: 00, > > Cache Line Size: 00 > > 0x0010: BAR empty
Re: Requesting vi tips
On Fri, Oct 18, 2019 at 03:45:42PM +0100, cho...@jtan.com wrote:
> Claudio Jeker writes:
> > set wl=72 will limit the line lenght to around 72. Additionally you
> > can use !fmt with movement chars to reformat sections. I use !{fmt
> > or {!}fmt frequently to reformat the paragraph I'm in.
>
> I didn't know [how] ! took movement commands. Thanks. I'll have a play
> with that one.
About everything in vi takes movement commands. That includes !
or > or <, among others.
And there are lots of useful movement commands, % being one of the most
often forgotten.
marks are fairly useful and easy to define, though traditional vi doesn't
keep them when swapping buffers, unfortunately.
... that's one of the main reasons why I've upgraded to vim. That and v,
and multiple buffers visible at the same time.
ppppoe octeon kernel panic .6.6
hi
if i boot my edgerouter with connected dsl modem i get an kernel panic.
reordering libraries:
Trap cause = 2 Frame 0x98004efcb860
Trap PC 0x813cc38c RA 0x8109feac fault 0x0
0x813cc2d8 (1,98000f991b76,1,2) ra 0x8109feac sp
0x98004efcb9b8, sz 0
0x8109fda0 (1,98000f991b76,1,2) ra 0x8109bd34 sp
0x98004efcb9b8, sz 144
0x8109bac0 (1,98000f991b76,1,2) ra 0x81095a04 sp
0x98004efcba48, sz 128
0x81095240 (1,98000f991b76,1,2) ra 0x0 sp
0x98004efcbac8, sz 0
User-level: pid 98161
stopped on non ddb fault
Stopped at 0x813cc38c: lbu v1,0(a0)
ddb{0}> boot reboot
System restart.
in my atom box with 6.5 , the same configuration for the pppoe device ,
the system boot and run well.
this problem at the octeon system i got also with 6.5 .
configs are
at the octeon replace the interface re3 to cnmac3
/etc 23>cat hostname.re3
rdomain 40
mtu 1518
inet 192.168.1.250 255.255.255.0 NONE
up
/etc 25>cat hostname.vlan7
mtu 1508
rdomain 40
parent re3 vnetid 7
up
/etc 26>cat hostname.pppoe0
!echo "add to rdomain 40"
rdomain 40
rtlabel netcologne
!echo "set startup ip"
inet 0.0.0.0 255.255.255.255 NONE mtu 1500 \
pppoedev vlan7 authproto pap \
authname 'x@y' authkey 'abc123' up
dest 0.0.0.1
!echo "enable ipv6"
inet6 autoconf autoconfprivacy
!/sbin/route -n -T 40 add default -ifp pppoe0 0.0.0.1
!/sbin/route -n -T 40 add -inet6 default -ifp pppoe0 fe80::%pppoe0
howto fix this ?
holger
