Re: ipfw layer2+3 firewalling question

Hi Ronald, thank you for your reply. On Sun, Mar 23, 2025 at 08:21:21PM +0100, Ronald Klop wrote: I assume that in your setup igb0 is the host interface as well as bridge member. That's correct. That makes the setup a bit hard to reason about. IMHO you now have a virtual setup which you wo

Re: ipfw layer2+3 firewalling question

ir0a="up" ifconfig_epair0b="SYNCDHCP" # or some other inet config NB: this https://wiki.freebsd.org/SummerOfCodeIdeas#Implement_a_new_VLAN_filtering_software_bridge also explains about the problem of having members with configured IP addresses in bridges. I might have mis

ipfw layer2+3 firewalling question

Hi, (originally posted on the forums) My objective is to protect services on a bhyve host, while allowing traffic to the bhyve guests to pass to and from them unprocessed, as these each have pf and their own firewall policies. The host running recent -current. I know ipfw can process both la

Question: Status of Multipath TCP

Hello! I know there has been some efforts in the past to implement Multipath TCP (MPTCP) on FreeBSD but apparently abandoned. I wanted to see if there are any plans to bring MPTCP to FreeBSD in the future, and if this is something that worths the effort. Kind regards, MJ Pooladkhay

Question: Status of Multipath TCP

Hello! I know there has been some efforts in the past to implement Multipath TCP (MPTCP) on FreeBSD but apparently abandoned. I wanted to see if there are any plans to bring MPTCP to FreeBSD in the future, and if this is something that worths the effort. Kind regards, MJ Pooladkhay

Re: Question about netinet6/in6.h

On 26 Apr 2024, at 23:02, Bakul Shah wrote: > On Apr 26, 2024, at 8:41 PM, Warner Losh wrote: >> >> >> >> On Fri, Apr 26, 2024, 9:33 PM Bakul Shah wrote: >> >> >>> On Apr 26, 2024, at 5:02 PM, Mike Karels wrote: >>> >>> On 26 Apr 2024, at 18:06, Warner Losh wrote: >>> On Fri, Apr 26, 2024

Re: Question about netinet6/in6.h

On Apr 26, 2024, at 8:41 PM, Warner Losh wrote: > > > > On Fri, Apr 26, 2024, 9:33 PM Bakul Shah wrote: > > > > On Apr 26, 2024, at 5:02 PM, Mike Karels wrote: > > > > On 26 Apr 2024, at 18:06, Warner Losh wrote: > > > >> On Fri, Apr 26, 2024 at 4:21 PM Mike Karels wrote: > >> > >>> On

Re: Question about netinet6/in6.h

On Fri, Apr 26, 2024, 9:33 PM Bakul Shah wrote: > > > > On Apr 26, 2024, at 5:02 PM, Mike Karels wrote: > > > > On 26 Apr 2024, at 18:06, Warner Losh wrote: > > > >> On Fri, Apr 26, 2024 at 4:21 PM Mike Karels wrote: > >> > >>> On 26 Apr 2024, at 15:49, Mike Karels wrote: > >>> > On 26 Apr

Re: Question about netinet6/in6.h

> On Apr 26, 2024, at 5:02 PM, Mike Karels wrote: > > On 26 Apr 2024, at 18:06, Warner Losh wrote: > >> On Fri, Apr 26, 2024 at 4:21 PM Mike Karels wrote: >> >>> On 26 Apr 2024, at 15:49, Mike Karels wrote: >>> On 26 Apr 2024, at 15:01, Warner Losh wrote: > This has to be a

Re: Question about netinet6/in6.h

On 26 Apr 2024, at 18:06, Warner Losh wrote: > On Fri, Apr 26, 2024 at 4:21 PM Mike Karels wrote: > >> On 26 Apr 2024, at 15:49, Mike Karels wrote: >> >>> On 26 Apr 2024, at 15:01, Warner Losh wrote: >>> This has to be a FAQ I'm porting a program from Linux, I often see an error li

Re: Question about netinet6/in6.h

On Fri, Apr 26, 2024 at 4:21 PM Mike Karels wrote: > On 26 Apr 2024, at 15:49, Mike Karels wrote: > > > On 26 Apr 2024, at 15:01, Warner Losh wrote: > > > >> This has to be a FAQ > >> > >> I'm porting a program from Linux, I often see an error like: > >> ./test/mock-ifaddrs.c:95:19: error: no mem

Re: Question about netinet6/in6.h

On 26 Apr 2024, at 15:49, Mike Karels wrote: > On 26 Apr 2024, at 15:01, Warner Losh wrote: > >> This has to be a FAQ >> >> I'm porting a program from Linux, I often see an error like: >> ./test/mock-ifaddrs.c:95:19: error: no member named 's6_addr32' in 'struct >> in6_addr' >>95 |

Re: Question about netinet6/in6.h

On 26 Apr 2024, at 15:01, Warner Losh wrote: > This has to be a FAQ > > I'm porting a program from Linux, I often see an error like: > ./test/mock-ifaddrs.c:95:19: error: no member named 's6_addr32' in 'struct > in6_addr' >95 | ipv6->sin6_addr.s6_addr32[3] = 0; > |

Question about netinet6/in6.h

This has to be a FAQ I'm porting a program from Linux, I often see an error like: ./test/mock-ifaddrs.c:95:19: error: no member named 's6_addr32' in 'struct in6_addr' 95 | ipv6->sin6_addr.s6_addr32[3] = 0; | ~~~ ^ but yet, we kinda define them,

RE: Network starvation question

UDP, or a misused CC in TCP, but also SCTP, QUIC, RTMP and all others). Best regards, Richard From: owner-freebsd-...@freebsd.org On Behalf Of Cheng Cui Sent: Freitag, 3. November 2023 12:53 To: Yuri Cc: freebsd-net@freebsd.org Subject: Re: Network starvation question Hi Yuri, If I

Re: Network starvation question

On 11/4/23 03:37, Yuri wrote: Router is also involved, and the provider's network as well. But I think that there is a bug in the FreeBSD's network code that it allows a slower TCP connection to be hammered like this, unless there is a good explanation for this observation. Yuri As y

Re: Network starvation question

Re: Network starvation question

Router is also involved, and the provider's network as well. But I think that there is a bug in the FreeBSD's network code that it allows a slower TCP connection to be hammered like this, unless there is a good explanation for this observation. Yuri

Re: Network starvation question

; Then the application B (the RDP TCP connection) attempted to use a much > lower outbound speed, probably < 0.5 MBps, and it got starved. > > Application B (RDP) was super slow as long as the application A kept > running. It was almost impossible to use the RDP connection. > > > My

Network starvation question

starved. Application B (RDP) was super slow as long as the application A kept running. It was almost impossible to use the RDP connection. My question is: shouldn't the system allow less intense streams to also run at a decent speed? Let's say that the outbound bandwidth threshold of the

A question about RSS bytes and Toeplitz hash

Dear subscribers, I have recently enabled and turned on Receive Side Scaling/Steering. The main reason was to use different hashing for the distribution of UDP datagrams over multiple paths. RSS uses 2-tuple hashing for UDP, thus UDP transmission from one host to another takes always the same

Question on Current Status of TCPUTO Socket Option

Hello, I'm working on OpenStack porting stuff recently. I encountered an issue that caused `nova-scheduler` unable to start normally. The `nova- scheduler` needs to build up connections to RabbitMQ with the aid of the RabbitMQ driver in the `oslo.messaging` library. The point is that the driver ne

Re: PF Question

Hi! > Am 21.11.2020 um 23:42 schrieb Saad, Mark : > This is sort of an abstract question. When using pf to only preform nat do I > need to have at least one > rule ? Can I omit the boiler plate "scrub rule " ? Other then allowing > fragments and other fun > stuff t

PF Question

Hi Net This is sort of an abstract question. When using pf to only preform nat do I need to have at least one rule ? Can I omit the boiler plate "scrub rule " ? Other then allowing fragments and other fun stuff to get passed would this have any other implications ? --- Mark S

Question about net.inet.tcp.minmss

All I was wondering if anyone has a good explication on what net.inet.tcp.minmss's interaction with routing. I can't find any good details. Anyone have any good pointers. --- Mark Saad | mark.s...@lucera.com ___ freebsd-net@freebsd.org mailing list ht

Re: Question about rtadvd

John-Mark Gurney wrote in <20200402211304.gz4...@funkthat.com>: jm> Fernando Gont wrote this message on Tue, Mar 31, 2020 at 22:18 -0300: jm> > Folks, jm> > jm> > I'm playing with rtadvd, and I'm curious about a debug message I'm jm> > getting when specifying Route Information options. jm> > jm

Re: Question about rtadvd

Fernando Gont wrote this message on Tue, Mar 31, 2020 at 22:18 -0300: > Folks, > > I'm playing with rtadvd, and I'm curious about a debug message I'm > getting when specifying Route Information options. > > My config file is this: > - cut here > em0:\ > :addr="fc00:1::":prefixlen=6

Question about rtadvd

Folks, I'm playing with rtadvd, and I'm curious about a debug message I'm getting when specifying Route Information options. My config file is this: - cut here em0:\ :addr="fc00:1::":prefixlen=64\ :rtprefix="fc00:1::":rtplen=64:rtltime=1000 em1:\ :addr="fc00:2::":prefixle

if_vxlan question

Hi, I noticed that my FreeBSD box was dropping vxlan packets with higher VNI's. Looking at the code it seems that the check at line 2548 is not correct: if (vxh->vxlh_flags != htonl(VXLAN_HDR_FLAGS_VALID_VNI) || vxh->vxlh_vni & ~htonl(VXLAN_VNI_MASK)) <- Incorrect?

Re: CARP and NAT question

On Wed, Oct 09, 2019 at 12:50:49PM -0700, Julian Elischer wrote: > On 10/9/19 2:34 AM, Julien Cigar wrote: > > On Tue, Oct 08, 2019 at 01:05:37PM -0700, Julian Elischer wrote: > >> On 10/8/19 8:58 AM, Julien Cigar wrote: > >>> On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: > H

Re: CARP and NAT question

On Wed, Oct 09, 2019 at 01:41:40PM -0500, Matthew Grooms wrote: > On 10/9/2019 4:10 AM, Julien Cigar wrote: > > On Tue, Oct 08, 2019 at 11:22:51AM -0500, Matthew Grooms wrote: > >> On 10/8/2019 10:58 AM, Julien Cigar wrote: > >>> On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: > >>>

Re: CARP and NAT question

There are several ways to do this.. this is just one... The above will assign a dynamic rule for all packets between the  two machines and the table in question will be always used. for that tupple. But you only have a single pipe to the internet, So one wonders how that helps with

Re: CARP and NAT question

source address when using multiple route tables? But you only have a single pipe to the internet, So one wonders how that helps with redundancy? I asked a similar question. He believe he mentioned that he was trying to get around the 1Gbit limit of each interface. WRT redundancy, he probabl

Re: CARP and NAT question

On 10/9/19 2:34 AM, Julien Cigar wrote: On Tue, Oct 08, 2019 at 01:05:37PM -0700, Julian Elischer wrote: On 10/8/19 8:58 AM, Julien Cigar wrote: On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: Hi Julien, Hi Matthew, It's not clear why you are trying to assign multiple carp I

Re: CARP and NAT question

On 10/9/2019 4:10 AM, Julien Cigar wrote: On Tue, Oct 08, 2019 at 11:22:51AM -0500, Matthew Grooms wrote: On 10/8/2019 10:58 AM, Julien Cigar wrote: On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: Hi Julien, Hi Matthew, It's not clear why you are trying to assign multiple ca

Re: CARP and NAT question

On Tue, Oct 08, 2019 at 01:05:37PM -0700, Julian Elischer wrote: > On 10/8/19 8:58 AM, Julien Cigar wrote: > > On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: > >> Hi Julien, > > Hi Matthew, > > > >> It's not clear why you are trying to assign multiple carp IP address to > >> two di

Re: CARP and NAT question

On Tue, Oct 08, 2019 at 11:22:51AM -0500, Matthew Grooms wrote: > On 10/8/2019 10:58 AM, Julien Cigar wrote: > > On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: > >> Hi Julien, > > Hi Matthew, > > > >> It's not clear why you are trying to assign multiple carp IP address to > >> two

Re: CARP and NAT question

On 10/8/19 8:58 AM, Julien Cigar wrote: On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: Hi Julien, Hi Matthew, It's not clear why you are trying to assign multiple carp IP address to two different interfaces from within the same IP subnet. Are you trying to fail over a 2nd car

Re: CARP and NAT question

On 10/8/2019 10:58 AM, Julien Cigar wrote: On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: Hi Julien, Hi Matthew, It's not clear why you are trying to assign multiple carp IP address to two different interfaces from within the same IP subnet. Are you trying to fail over a 2nd

Re: CARP and NAT question

On Tue, Oct 08, 2019 at 10:20:34AM -0500, Matthew Grooms wrote: > Hi Julien, Hi Matthew, > > It's not clear why you are trying to assign multiple carp IP address to > two different interfaces from within the same IP subnet. Are you trying > to fail over a 2nd carp address or are you trying to

Re: CARP and NAT question

Hi Julien, It's not clear why you are trying to assign multiple carp IP address to two different interfaces from within the same IP subnet. Are you trying to fail over a 2nd carp address or are you trying to improve throughput/redundancy? If you just want to fail over a 2nd carp address, assi

CARP and NAT question

Hello, I'd like to NAT outbound traffic from two different private networks through two different interfaces, with CARP on top. I have 4 public IPS available (193.x.x.89, 193.x.x.90, 193.x.x.91, 193.x.x.92). I have two redundant router/firewall running FreeBSD 12 with CARP and PF with the follo

Re: packets per second tool for CLI - and question about checksum_errs

On Tue, Aug 20, 2019 at 10:34:40PM -0700, Rudy wrote: > > Here is a quick tool so show Packets Per Second on the CLI for all your > interfaces (only tested with ix and igb). > It uses the output of sysctl every second.  If you like it, great! > How about: $ systat -ifstat -pps - [tj] ___

Re: packets per second tool for CLI - and question about checksum_errs

On 8/20/19 10:43 PM, moridin wrote: systat -ifstat -pps Awesome, that was the command I needed for PPS.  Chalk it up to Another re-inventing the wheel! The script does spotlight Checksum Errors on the Intel ethernet ports - should I be concerned with those errors? #sysctl dev.ix. | grep

Re: packets per second tool for CLI - and question about checksum_errs

Rudy wrote: Here is a quick tool so show Packets Per Second on the CLI for all your interfaces (only tested with ix and igb). It uses the output of sysctl every second.  If you like it, great! Quick question, why am I seeing checksum_errs around 1k on a link doing 3Gbps? * **Sample output of

packets per second tool for CLI - and question about checksum_errs

Here is a quick tool so show Packets Per Second on the CLI for all your interfaces (only tested with ix and igb). It uses the output of sysctl every second.  If you like it, great! Quick question, why am I seeing checksum_errs around 1k on a link doing 3Gbps? * **Sample output of script

RE: Some question about DCTCP implementation in FreeBSD

t; 1) || (new < 0)) error = EINVAL; else V_dctcp_slowstart = new; @@ -454,7 +515,7 @@ SYSCTL_NODE(_net_inet_tcp_cc, OID_AUTO, dctcp, CTLFLAG_RW, NULL, SYSCTL_PROC(_net_inet_tcp_cc_dctcp, OID_AUTO, alpha, CTLFLAG_VNET|CTLTYPE_U

Re: Some question about DCTCP implementation in FreeBSD

Hi, glad to see interest in DCTCP! On 2019-6-4, at 11:05, Yu He via freebsd-net wrote: > In line 387 of file cc_tcp.c, the update of alpha is calculated by following > code: > > dctcp_data->alpha = min(alpha_prev - (alpha_prev >> V_dctcp_shift_g) + > (dctcp_data->bytes_ecn << (10 -

Some question about DCTCP implementation in FreeBSD

Greetings! I’m a graduate student from Carnegie Mellon University, and currently an intern in VMware. I’m now working on some internal project about implementing DCTCP algorithm and coming across the implementation in https://reviews.freebsd.org/rS277054. There is one thing I’m quite curious a

Trivia question: Limiting per user networking usage

Sorry. I really should go off and RTFM on this, but I'm kind of pressed for time, so I'll just ask. I've gotten myself into a minor verbal altercation with another fellow, over email, and one of the issues that came up was how to prevent one user from hogging all of the outbound IPv4 port numbe

Re: ib_unregister_device - OFED related question

On 07/07/18 02:49, Somayajulu, David wrote: We see that module_unload() grabs the Gaint Lock prior to invoking UNLOAD. Isn't this a problem with cma_process_remove() or am I missing something? Hi, The LinuxKPI should DROP_GIANT and PICKUP_GIANT when sleeping. I haven't checked FreeBSD 10 rec

ib_unregister_device - OFED related question

Hi All, ib_unregister_device() is typically called as part of the rdma driver module unload for a given device. As part of execution of this function it loops through the following code: ofed/drivers/inifiniband/core/device.

accf_http question

In my application I set SO_RECVTIMEO to 1.5 seconds, then enable SO_ACCEPTFILTER (httpready). accf_http module is loaded in the kernel. The problem is that if I connect to the socket but don’t send any data, the connection remains open indefinitely. The application of course won’t see a connec

Re: Question on SRIOV vf -> pf mapping

This isn't possible in general. When PCI Passthrough is in use, the VF driver will run in the context of the VM's kernel and there is no device_t corresponding to the PF at all. If you're looking to pass information from the PF down to the VF, then you need to establish some kind of device-mediat

Question on SRIOV vf -> pf mapping

Hi, Given "device_t dev" of a VF is there a way to retrieve the "device_t dev" of its PF ? In other words when device_attach is invoked for VF, is there a way to get to the "struct device" of its PF ? Thanks David S. (davi...@freebsd.org) ___ freebsd-

A Quick Question

Good morning, Since resources you provide intrigued me, I would like to ask you a quick question related to your website. Are you the correct person to speak about it? Thank you and have a nice day! -- Linda ___ freebsd-net@freebsd.org mailing list

Re: Question on taskqueue_drain

On 04/19/17 19:36, Somayajulu, David wrote: Hans, Thanks for the info. No sleeping functions like taskqueue_drain() can be called when the MTX_DEF lock is grabbed. I am guessing this is true irrespective of whether the taskqueue is "fast" or not. Thanks Yes, that is correct. --HPS ___

RE: Question on taskqueue_drain

elasky [mailto:h...@selasky.org] Sent: Tuesday, April 18, 2017 9:22 PM To: Sepherosa Ziehau ; Somayajulu, David Cc: freebsd-net@freebsd.org Subject: Re: Question on taskqueue_drain On 04/19/17 05:37, Sepherosa Ziehau wrote: > On Wed, Apr 19, 2017 at 10:39 AM, Somayajulu, David > wrote: >> S

Re: Question on taskqueue_drain

On 04/19/17 05:37, Sepherosa Ziehau wrote: On Wed, Apr 19, 2017 at 10:39 AM, Somayajulu, David wrote: Sorry what I meant to ask was, whether it is O.K to call taskqueue_drain(), when an MTX_DEF lock is grabbed prior to calling taskqueue_drain(). You will hit WITNESS, if the drain needs to w

Re: Question on taskqueue_drain

On Wed, Apr 19, 2017 at 10:39 AM, Somayajulu, David wrote: > Sorry what I meant to ask was, whether it is O.K to call taskqueue_drain(), > when an MTX_DEF lock is grabbed prior to calling taskqueue_drain(). > You will hit WITNESS, if the drain needs to wait; that's probably the best case. If th

RE: Question on taskqueue_drain

Sorry what I meant to ask was, whether it is O.K to call taskqueue_drain(), when an MTX_DEF lock is grabbed prior to calling taskqueue_drain(). Thanks David S. (davi...@freebsd.org) ___ freebsd-net@freebsd.org mailing list https://lists.freebsd.org/ma

Question on taskqueue_drain

Hi, Is it ok to call taskqueue_drain() when the MTX_DEF lock is held ? Thanks David S. ___ freebsd-net@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to "freebsd-net-unsubscr...@freebsd.org"

Re: Small socket programming question

On 4/16/2017 22:01, Ronald F. Guilmette wrote: > Sorry, I -think- I know that answer to this question, but > I'd prefer to ask and make sure, in case I have misunderstood > things. > > I am aware that for any open socket, the kernel sets aside > some amount of buffer space

Small socket programming question

Sorry, I -think- I know that answer to this question, but I'd prefer to ask and make sure, in case I have misunderstood things. I am aware that for any open socket, the kernel sets aside some amount of buffer space for that socket. (And yes, I *do* also know that the specific amount set

Re: Question on contrib/ofed

On 02/14/17 00:26, Somayajulu, David wrote: Hi All, I have been trying building the OFED user mode libraries/apps in FreeBSD11 and have not been successful (please see below). Are there any configure/set up commands that need to be run ? I would appreciate any help. Try to add: WITH_OFED=Y

Question on contrib/ofed

Hi All, I have been trying building the OFED user mode libraries/apps in FreeBSD11 and have not been successful (please see below). Are there any configure/set up commands that need to be run ? I would appreciate any help. Thanks David S. (davi...@freebsd.org)

Ask a question

Hi, My name is Stephen Joseph, the Business Development Manager at one of the leading email database providing companies. Our area of expertise lies specifically in the major industrial lists like: Agriculture, Business Services, Chambers of Commerce, Cities, Towns & Municipalities, Construction

General question about 1GB vs 10GB NIC's

I want to build a router that has 2 x 500mb/s radio ISP facing, 2 x 500mb/s radio's facing another site, plus a 1gb/s link to the LAN. I plan to plug everything into a switch so I can have redundant routers. So my question is should I go with 5 x 1GB NIC's or 2x10GB NIC's on

Re: question about fopen fd limit

adfn)(void *, char *, int), int (*writefn)(void *, const char *, int), fpos_t (*seekfn)(void *, fpos_t, int), int (*closefn)(void *)); If you need more help please make sure to email me directly so I can see your question. -Alfred On 12/23/16 12:48 AM, 盛慧华 wrote: hi all,

RE: RE: question about fopen fd limit

...@corp.netease.com] Sent: Friday, December 23, 2016 11:02 AM To: Hongjiang Zhang ; freebsd-net Subject: Re: RE: question about fopen fd limit hi all, not map TCP to FILE, you misunderstanding my meaning~ for example, if my server tcp already holds 32000 connection fopen only has 767 fd to

Re: RE: question about fopen fd limit

Zhang ? nice to meet you ! winson sheng winson sheng From: Hongjiang Zhang Date: 2016-12-23 11:44 To: 盛慧华; freebsd-net Subject: RE: RE: question about fopen fd limit Ok. I know. There are two pos

RE: question about fopen fd limit

: Thursday, December 22, 2016 11:57 PM To: freebsd-net Subject: question about fopen fd limit hi all, hi~ we are from Chinese Game Develop Corp, Netease. and One of our product using FreeBsd as its OS platform. This Game has Millions of players online , and Each Server may holds 25000+ tcp

Re: RE: question about fopen fd limit

ugh for me, and i don't wanna change a lot of FILE function that take FILE * as its argument ~ Thank you ~~~ winson sheng winson sheng From: Hongjiang Zhang Date: 2016-12-23 10:17 To: 盛慧华; freebsd-net Subject: RE: question about fopen fd limi

Re: question about fopen fd limit

On 12/22/16 10:57, 盛慧华 wrote: and even in BSD 10 , it seems this short limit still there , but other OS as debian , FILE strucnt's fileno is a int . * Certain members of __sFILE are accessed directly via macros or * inline functions. To preserve ABI compat, these members must not * be di

question about fopen fd limit

hi all, hi~ we are from Chinese Game Develop Corp, Netease. and One of our product using FreeBsd as its OS platform. This Game has Millions of players online , and Each Server may holds 25000+ tcp connection at the same time.Thanks to BSD and kqueue :) for example, it's one of our

quick question on carp(4)

I was reading on OpenBSD carp, where it has load-balancing capabilities versus failover. >From a cursory inspection, in the FreeBSD handbook, carp(4), or ifconfig(8) -- I didn't immediately see similar capabilities. Does FreeBSD carp support active/active load-balanced configurations? ___

Re: NETMAP application architecture question

On Fri, Sep 16, 2016 at 05:05:33PM +0200, Luigi Rizzo wrote: > Hi, > I don't think there is any hard limitation on the total number > of pipes, very likely the number (64) is just some arbitrary > limit that we set, and can be increased through a sysctl or > worst case a compile time constant. >

Re: NETMAP application architecture question

I am "VERY WILLING" to test out a specific branch of FreeBSD current with this code merged. There are wonderful features such as the new LB app in the new code that I would greatly desire to be included in FreeBSD. I tried to do a simple merge and it was more involved. I was hoping to have some ti

Re: NETMAP application architecture question

On Fri, Sep 16, 2016 at 5:14 PM, Slawa Olhovchenkov wrote: > On Fri, Sep 16, 2016 at 05:05:33PM +0200, Luigi Rizzo wrote: > > >> Please have a look at the source code if you can find where >> you are hitting the limit, and which parameters are involved. >> In case you don't find it, get back to u

Re: NETMAP application architecture question

On Fri, Sep 16, 2016 at 05:05:33PM +0200, Luigi Rizzo wrote: > Hi, > I don't think there is any hard limitation on the total number > of pipes, very likely the number (64) is just some arbitrary > limit that we set, and can be increased through a sysctl or > worst case a compile time constant. I

Re: NETMAP application architecture question

Hi, I don't think there is any hard limitation on the total number of pipes, very likely the number (64) is just some arbitrary limit that we set, and can be increased through a sysctl or worst case a compile time constant. Please have a look at the source code if you can find where you are hittin

NETMAP application architecture question

I am wrote NETMAP application and meet some limitation. I am use server 16-core server. Workers thread run mostly independend, with minimal interworking. I am use balancer threads for distributing packet flow between worker threads. I am using two NETMAP pipes between balancer and workers. As resul

Re: question about if a recent Linux patch on window scaling is required in FreeBSD

Add freebsd-net to increase the size of audience. Thanks, --Cheng Cui NetApp Scale Out Networking On 8/30/16, 10:19 AM, "Cui, Cheng" wrote: Refresh this question. Can anyone make a comment? Thanks, --Cheng Cui NetApp Scale Out Networking On 8/25/1

Re: Question about em_irq_fast

On 08/08/16 15:40, Sreekanth Rupavatharam wrote: > Quite possibly, but my question remains. If the register doesn’t have any > specific value for just a received packet(no other events), how is a value of > 0 considered to be wrong? Or to flip the question around, what should be the

Re: Question about em_irq_fast

Quite possibly, but my question remains. If the register doesn’t have any specific value for just a received packet(no other events), how is a value of 0 considered to be wrong? Or to flip the question around, what should be the value of the register for just receive of a packet? Thanks

Re: Question about em_irq_fast

On 08/08/16 13:14, Sreekanth Rupavatharam wrote: > > > Thanks, > > -Sreekanth > >> On Aug 8, 2016, at 12:09 PM, Sean Bruno wrote: >> >> Is this with the "lem" driver or the "em" driver under QEMU? >> > It's for lem dri

Re: Question about em_irq_fast

Thanks, -Sreekanth > On Aug 8, 2016, at 12:09 PM, Sean Bruno wrote: > > Is this with the "lem" driver or the "em" driver under QEMU? > It's for lem driver under qemu. My question is mainly about there being no specific bit for a packet received in th

Re: Question about em_irq_fast

On 08/05/16 12:01, Sreekanth Rupavatharam wrote: > We have this code snippet in em_irq_fast > > ifp = > adapter->ifp; > > > > > reg_icr = E100

Question about em_irq_fast

We have this code snippet in em_irq_fast ifp = adapter->ifp; reg_icr = E1000_READ_REG(&adapter->hw, E1000_ICR); /* Hot eject? */ if (reg_icr == 0x) return FILTER_STRAY; /* Definitely not our interrupt. */ if (reg

netmap question

Hello Luigi, first of all i have to say you have done great work. I had some fun with netmap but i have a question: How can we fill in the transmit ring buffers of a network card from different CPUs/threads? Or to clarify i am able to fill the send ring on the thread that does the poll, but

Re: Question on sysctl tree handling

On Mon, Apr 11, 2016 at 3:01 PM, Jack Vogel wrote: > Why should init have to be rerun just because TSO or CSUM is turned off or > on, > its a flag that is checked in the TX routines? I actually haven't looked in to it yet. But it does annoy the heck out of me. Nonetheless, it is the current state

Re: Question on sysctl tree handling

Hmmm, after so many years of unloading and reloading drivers, it just seemed like such a convenience :) But, instability isn't fun either, I've looked at bxe a little, such a monstrous driver :) I'll give it some thought, and maybe discuss it with David. Thanks. Cheers, Jack On Mon, Apr 11,

Re: Question on sysctl tree handling

Expanding on what mmacy said... I don't think the benefits of "easy reconfiguration" are worth the headaches you're going to potentially run into in production. bxe(4) used to do this, and it caused us a lot of problems (i.e. panics) at $DAY_JOB. For example, if a lagg was on top of bxe and then y

Re: Question on sysctl tree handling

Why should init have to be rerun just because TSO or CSUM is turned off or on, its a flag that is checked in the TX routines? I am controlling some cases in the ioctl routine so it does the necessary things, but does not rerun all of init. If its a long running system that means its unlikely be g

Re: Question on sysctl tree handling

You do understand that init needs to be run every time interface settings are changed (TSO / PROMISC / CSUM/ etc)? Reallocating queues and interrupts every time is fragile (long running systems can run low on contiguous memory) and, in the common case that you're not actually changing the number, g

Re: Question on sysctl tree handling

LOL, why does it seem that as soon as I ask the answer hits me in the nose :) I found the sysctl_ctx_free call, sorry for the noise Jack On Fri, Apr 8, 2016 at 2:51 PM, Jack Vogel wrote: > > I have a driver design where the queue/ring/irq layout is done in init > rather > than in attach,

Question on sysctl tree handling

I have a driver design where the queue/ring/irq layout is done in init rather than in attach, allowing easy reconfiguration. What I'm not sure about is how to handle the sysctl tree during a reinit, I don't see a procedure to free up things so I can restructure :( Am I missing something, any point

Re: gateway machine port redirect question

On Mon, 22 Feb 2016, Julian Elischer wrote: I Believe the problem is as follows: there are two machines inside the NAT'd lan, A and B, (local addresses) . The NAT machine is X on the outside and Y on the inside. B is also visible to the outside world as the Nat'd address C (which may or may n

Re: gateway machine port redirect question

On 21/02/2016 4:48 PM, Gary Corcoran wrote: On 2/20/2016 9:22 PM, Valeri Galtsev wrote: Dear Experts, I'm one of Linux refugees who several years ago migrated majority of servers from Linux to FreeBSD and is happy since. When recently I needed to set up gateway (Firewall + NAT) machine, I set

Re: gateway machine port redirect question

On 22/02/2016 4:03 AM, Ian Smith wrote: On Sun, 21 Feb 2016 16:32:53 -0800, Julian Elischer wrote: > On 20/02/2016 6:22 PM, Valeri Galtsev wrote: > > Dear Experts, > > > > I'm one of Linux refugees who several years ago migrated majority of > > servers from Linux to FreeBSD and is happy

  1   2   3   4   5   6   7   8   9   10   >