Re: [PATCH] xen-netback: fix compile errors introduced by r254804 and r254807

2013-08-26 Thread Andre Oppermann
On 26.08.2013 13:02, Roger Pau Monne wrote: r254804 and r254807 changed the types of some of the members of the mbuf struct, and introduced some compile time errors in netback debug messages that prevented compiling a XENHVM kernel. Thanks, I fixed the printf's with r254910 in a slightly

Re: [PATCH] xen-netback: fix compile errors introduced by r254804 and r254807

2013-08-26 Thread Andre Oppermann
On 26.08.2013 15:43, Roger Pau Monné wrote: On 26/08/13 15:22, Andre Oppermann wrote: On 26.08.2013 13:02, Roger Pau Monne wrote: r254804 and r254807 changed the types of some of the members of the mbuf struct, and introduced some compile time errors in netback debug messages that prevented

Further mbuf adjustments and changes

2013-08-21 Thread Andre Oppermann
I want to put these mbuf changes/updates/adjustments up for objections, if any, before committing them. This is a moderate overhaul of the mbuf headers and fields to take us into the next 5 years and two releases. The mbuf headers, in particular the pkthdr, have seen a number of new uses and

Re: [net] protecting interfaces from races between control and data ?

2013-08-07 Thread Andre Oppermann
On 07.08.2013 09:18, Luigi Rizzo wrote: On Wed, Aug 7, 2013 at 5:26 AM, Mike Karels m...@karels.net mailto:m...@karels.net wrote: Jumping to (near) the end of the thread, I like most of Andre's proposal. Running with minimal locks at this layer is an admirable goal, and I agree with

Re: [net] protecting interfaces from races between control and data ?

2013-08-06 Thread Andre Oppermann
On 05.08.2013 23:53, Luigi Rizzo wrote: On Mon, Aug 05, 2013 at 11:04:44PM +0200, Andre Oppermann wrote: On 05.08.2013 19:36, Luigi Rizzo wrote: ... [picking a post at random to reply in this thread] tell whether or not we should bail out). Ideally we don't want to have any locks

Re: [net] protecting interfaces from races between control and data ?

2013-08-05 Thread Andre Oppermann
On 05.08.2013 16:59, Bryan Venteicher wrote: - Original Message - i am slightly unclear of what mechanisms we use to prevent races between interface being reconfigured (up/down/multicast setting, etc, all causing reinitialization of the rx and tx rings) and i) packets from the host

Re: [net] protecting interfaces from races between control and data ?

2013-08-05 Thread Andre Oppermann
On 05.08.2013 19:36, Luigi Rizzo wrote: On Mon, Aug 5, 2013 at 7:17 PM, Adrian Chadd adr...@freebsd.org wrote: I'm travelling back to San Jose today; poke me tomorrow and I'll brain dump what I did in ath(4) and the lessons learnt. The TL;DR version - you don't want to grab an extra lock in

Re: IPSEC crashes after r253088

2013-07-23 Thread Andre Oppermann
On 23.07.2013 09:28, Andrey V. Elsukov wrote: On 21.07.2013 00:43, Taku YAMAMOTO wrote: After r253088, systems with IPSEC and KSTACK_PAGES 4 crashes on booting into multi-user mode. The crash is due to sysctl -a in /etc/rc.d/initrandom ended up with kernel stack overflow. where type is

Re: Improved SYN Cookies: Looking for testers

2013-07-12 Thread Andre Oppermann
On 12.07.2013 12:56, Fabian Keil wrote: Andre Oppermann an...@freebsd.org wrote: On 10.07.2013 15:18, Fabian Keil wrote: Andre Oppermann an...@freebsd.org wrote: We have a SYN cookie implementation for quite some time now but it has some limitations with current realities for window scaling

Re: Improved SYN Cookies: Looking for testers

2013-07-11 Thread Andre Oppermann
On 10.07.2013 15:18, Fabian Keil wrote: Andre Oppermann an...@freebsd.org wrote: We have a SYN cookie implementation for quite some time now but it has some limitations with current realities for window scaling and SACK encoding the in the few available bits. This patch updates and improves

Re: fix for SVN r253208 breaking buildkernel with gcc

2013-07-11 Thread Andre Oppermann
On 11.07.2013 18:09, Michael Butler wrote: On 07/11/13 12:07, Michael Butler wrote: Seems gcc is rather fussy about propagating 'const' and fails to compile /usr/src/sys/crypto/siphash/siphash.c after SVN r253208. I believe the attached patch is correct but please review .. imb grr

Improved SYN Cookies: Looking for testers

2013-07-08 Thread Andre Oppermann
We have a SYN cookie implementation for quite some time now but it has some limitations with current realities for window scaling and SACK encoding the in the few available bits. This patch updates and improves SYN cookies mainly by: a) encoding of MSS, WSCALE (window scaling) and SACK into

Re: Ipfilter pre-Vendor Import Issue

2013-07-08 Thread Andre Oppermann
On 05.07.2013 20:38, Cy Schubert wrote: In message 20130705084649.gc67...@freebsd.org, Gleb Smirnoff writes: What I'd prefer to see is the following: - commit new ipfilter untouched to vendor-sys/ipfilter - nuke sys/contrib/ipfilter - svn copy vendor-sys/ipfilter to sys/netpfil/ipfilter

Re: Panic in tcp_input

2013-06-19 Thread Andre Oppermann
On 19.06.2013 11:10, Ian FREISLICH wrote: Hi I'm seeing this panic quite regularly now. Most recent sighting on r251858. This panic message is not very informative and very hard to extract any meaningful hints. Do you have a core dump and matching debug kernel? -- Andre cpuid = 15 KDB:

Re: Panic in tcp_input

2013-06-19 Thread Andre Oppermann
On 19.06.2013 11:34, Ian FREISLICH wrote: Andre Oppermann wrote: On 19.06.2013 11:10, Ian FREISLICH wrote: Hi I'm seeing this panic quite regularly now. Most recent sighting on r251858. This panic message is not very informative and very hard to extract any meaningful hints. Do you have

make -jN parallel builds is broken

2013-05-31 Thread Andre Oppermann
Any ideas how to fix this? # make -j8 buildworld --- buildworld --- make: illegal option -- J usage: make [-BPSXeiknpqrstv] [-C directory] [-D variable] [-d flags] [-E variable] [-f makefile] [-I directory] [-j max_jobs] [-m directory] [-V variable] [variable=value]

Re: make -jN parallel builds is broken

2013-05-31 Thread Andre Oppermann
On 31.05.2013 12:17, Florent Peterschmitt wrote: Le 31/05/2013 12:13, Andre Oppermann a écrit : Any ideas how to fix this? # make -j8 buildworld --- buildworld --- make: illegal option -- J usage: make [-BPSXeiknpqrstv] [-C directory] [-D variable] [-d flags] [-E variable] [-f

Re: panic in sctp_del_addr_from_vrf() ?

2013-05-08 Thread Andre Oppermann
On 08.05.2013 07:57, Andrey Smagin wrote: I tried by analogy your patch add _padalign in all places where was before r250300, and in stcp. Uptime now 15hours, before - 5min - 3hour max. I waiting for more statistic. my changes: The padalign commit has been backed out in r250300 and we are

Re: forwarding/ipfw/pf evolution (in pps) on -current

2013-04-25 Thread Andre Oppermann
On 25.04.2013 07:40, Olivier Cochard-Labbé wrote: On Wed, Apr 24, 2013 at 1:46 PM, Sami Halabi sodyn...@gmail.com wrote: 3. there some point of improved performance (without fw) that went down again somewhere before Clang got prod. Found it ! It's commit 242402: Rework the known mutexes...

Re: forwarding/ipfw/pf evolution (in pps) on -current

2013-04-24 Thread Andre Oppermann
On 24.04.2013 12:45, Olivier Cochard-Labbé wrote: Hi all, here is the result of my simple-and-dummy bench script regarding forwarding/ipfw/pf performance evolution on -current on a single-core server with one flow only. It's the result of more than 810 bench tests (including reboot between

Re: ipfilter(4) needs maintainer

2013-04-16 Thread Andre Oppermann
On 15.04.2013 19:48, Cy Schubert wrote: I did consider a port but given it would has to touch bits and pieces of the source tree (/usr/src), a port would be messy and the decision was made to work on importing it into base. Actually it shouldn't touch many if any pieces of src/sys. Everything

Re: EuroBSDcon 2013: Call for Proposals, Conference on September 28+29 2013

2013-04-16 Thread Andre Oppermann
On 15.04.2013 05:32, Julian Elischer wrote: On 4/11/13 5:18 PM, Andre Oppermann wrote: Excuse me for being slightly spammy but I've received feedback that we haven't spread this information widely enough outside the inner circles and interested people missed the announcement. EuroBSDcon 2013

EuroBSDcon 2013: Call for Proposals, Conference on September 28+29 2013

2013-04-11 Thread Andre Oppermann
Excuse me for being slightly spammy but I've received feedback that we haven't spread this information widely enough outside the inner circles and interested people missed the announcement. EuroBSDcon 2013: September 28-29 in Malta = EuroBSDcon is the

Re: NewNFS vs. oldNFS for 10.0?

2013-03-18 Thread Andre Oppermann
On 16.03.2013 01:44, Peter Wemm wrote: On Fri, Mar 15, 2013 at 2:03 PM, John Baldwin j...@freebsd.org wrote: On Friday, March 15, 2013 11:24:32 am Andre Oppermann wrote: On 15.03.2013 14:46, John Baldwin wrote: On Friday, March 15, 2013 9:40:56 am Andre Oppermann wrote: Hi Rick, all

Re: NewNFS vs. oldNFS for 10.0?

2013-03-18 Thread Andre Oppermann
On 15.03.2013 15:08, Rick Macklem wrote: Lars Eggert wrote: Hi, this reminds me that I ran into an issue lately with the new NFS and locking for NFSv3 mounts on a client that ran -CURRENT and a server that ran -STABLE. When I ran portmaster -a on the client, which mounted /usr/ports and

NewNFS vs. oldNFS for 10.0?

2013-03-15 Thread Andre Oppermann
Hi Rick, all, is there a plan to decide for one NFS implementation for FreeBSD 10.0, or to keep both around indefinately? I'm talking about: oldNFS in sys/{nfs, nfsclient, nfsserver} NFSv2+NFSv3 newNFS in sys/fs/{nfs, nfsclient, nfsserver} NFSv2+NFSv3+NFSv4 NewNFS supports newer NFS

Re: NewNFS vs. oldNFS for 10.0?

2013-03-15 Thread Andre Oppermann
On 15.03.2013 15:01, Eggert, Lars wrote: Hi, this reminds me that I ran into an issue lately with the new NFS and locking for NFSv3 mounts on a client that ran -CURRENT and a server that ran -STABLE. When I ran portmaster -a on the client, which mounted /usr/ports and /usr/local, as well as

Re: NewNFS vs. oldNFS for 10.0?

2013-03-15 Thread Andre Oppermann
On 15.03.2013 14:46, John Baldwin wrote: On Friday, March 15, 2013 9:40:56 am Andre Oppermann wrote: Hi Rick, all, is there a plan to decide for one NFS implementation for FreeBSD 10.0, or to keep both around indefinately? I'm talking about: oldNFS in sys/{nfs, nfsclient, nfsserver

Re: Cleanup and untangling of kernel VM initialization

2013-03-08 Thread Andre Oppermann
On 08.03.2013 10:16, Konstantin Belousov wrote: On Thu, Mar 07, 2013 at 06:03:51PM +0100, Andre Oppermann wrote: pager_map: is used for pager IO to a storage media (disk). Not pageable. Calculation: MAXPHYS * min(max(nbuf/4, 16), 256). It is more versatile. The space is used for pbufs

Re: Cleanup and untangling of kernel VM initialization

2013-03-07 Thread Andre Oppermann
On 01.02.2013 18:09, Alan Cox wrote: On 02/01/2013 07:25, Andre Oppermann wrote: Rebase auto-sizing of limits on the available KVM/kmem_map instead of physical memory. Depending on the kernel and architecture configuration these two can be very different. Comments and reviews

Re: Trouble with recent auto-tuning changes

2013-02-01 Thread Andre Oppermann
On 31.01.2013 23:25, Ian Lepore wrote: On Thu, 2013-01-31 at 18:13 +0100, Andre Oppermann wrote: On 28.01.2013 20:20, Alan Cox wrote: On 01/28/2013 08:22, Ian Lepore wrote: On Mon, 2013-01-28 at 00:09 -0600, Alan Cox wrote: On Sun, Jan 27, 2013 at 12:11 PM, Ian Lepore i...@freebsd.org wrote

Cleanup and untangling of kernel VM initialization

2013-02-01 Thread Andre Oppermann
As an outcome of the recent problems with auto-sizing and auto-tuning of the various kernel subsystems and related memory structures I've taken a closer look at the whole KVM inner working and initialization process. I've found the VM and KVM initialization to be somewhat obscure and stuck

Re: mounting root from NFS via ROOTDEVNAME

2013-01-31 Thread Andre Oppermann
On 31.01.2013 12:27, Eggert, Lars wrote: Hi, On Jan 30, 2013, at 22:43, Craig Rodrigues rodr...@crodrigues.org wrote: What you need to do is, before the FreeBSD kernel boots, your loader needs to export some environment variables. This will trigger the various behaviors in the FreeBSD mount

Re: Trouble with recent auto-tuning changes

2013-01-31 Thread Andre Oppermann
On 28.01.2013 20:20, Alan Cox wrote: On 01/28/2013 08:22, Ian Lepore wrote: On Mon, 2013-01-28 at 00:09 -0600, Alan Cox wrote: On Sun, Jan 27, 2013 at 12:11 PM, Ian Lepore i...@freebsd.org wrote: I ran into a panic while attempting to un-tar a large file on a DreamPlug (arm-based system)

Re: kmem_map auto-sizing and size dependencies

2013-01-23 Thread Andre Oppermann
On 23.01.2013 00:22, Artem Belevich wrote: On Mon, Jan 21, 2013 at 1:06 PM, Pawel Jakub Dawidek p...@freebsd.org wrote: On Fri, Jan 18, 2013 at 08:26:04AM -0800, m...@freebsd.org wrote: Should it be set to a larger initial value based on min(physical,KVM) space available? It needs to be

kmem_map auto-sizing and size dependencies

2013-01-18 Thread Andre Oppermann
The autotuning work is reaching into many places of the kernel and while trying to tie up all lose ends I've got stuck in the kmem_map and how it works or what its limitations are. During startup the VM is initialized and an initial kernel virtual memory map is setup in kmem_init() covering the

panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
FreeBSD bbb.ccc 10.0-CURRENT FreeBSD 10.0-CURRENT #0: Fri Nov 23 17:00:40 CET 2012 a...@bbb.ccc:/usr/obj/usr/src/head/sys/GENERIC amd64 #0 doadump (textdump=-2014022336) at pcpu.h:229 #1 0x8033e2d2 in db_fncall (dummy1=value optimized out, dummy2=value optimized out,

Re: panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
On 27.11.2012 16:05, Attilio Rao wrote: On Tue, Nov 27, 2012 at 11:26 AM, Andre Oppermann an...@freebsd.org wrote: FreeBSD bbb.ccc 10.0-CURRENT FreeBSD 10.0-CURRENT #0: Fri Nov 23 17:00:40 CET 2012 a...@bbb.ccc:/usr/obj/usr/src/head/sys/GENERIC amd64 #0 doadump (textdump=-2014022336

Re: panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
On 27.11.2012 16:06, Konstantin Belousov wrote: On Tue, Nov 27, 2012 at 12:26:44PM +0100, Andre Oppermann wrote: FreeBSD bbb.ccc 10.0-CURRENT FreeBSD 10.0-CURRENT #0: Fri Nov 23 17:00:40 CET 2012 a...@bbb.ccc:/usr/obj/usr/src/head/sys/GENERIC amd64 #0 doadump (textdump=-2014022336) at pcpu.h

Re: panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
On 27.11.2012 16:40, Andriy Gapon wrote: on 27/11/2012 17:38 Andre Oppermann said the following: Clang doing a manual kernel build of my work tree with make -j8 kernel. This sounds like a process that may have triggered the problem. But is it the process that made the syscall in the backtrace

Re: panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
On 27.11.2012 16:51, Konstantin Belousov wrote: On Tue, Nov 27, 2012 at 04:38:12PM +0100, Andre Oppermann wrote: On 27.11.2012 16:06, Konstantin Belousov wrote: On Tue, Nov 27, 2012 at 12:26:44PM +0100, Andre Oppermann wrote: FreeBSD bbb.ccc 10.0-CURRENT FreeBSD 10.0-CURRENT #0: Fri Nov 23 17

Re: panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
On 27.11.2012 17:42, Alan Cox wrote: On 11/27/2012 09:06, Konstantin Belousov wrote: On Tue, Nov 27, 2012 at 12:26:44PM +0100, Andre Oppermann wrote: FreeBSD bbb.ccc 10.0-CURRENT FreeBSD 10.0-CURRENT #0: Fri Nov 23 17:00:40 CET 2012 a...@bbb.ccc:/usr/obj/usr/src/head/sys/GENERIC amd64 #0

Re: panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
On 27.11.2012 19:27, Alan Cox wrote: On 11/27/2012 12:08, Andre Oppermann wrote: On 27.11.2012 17:42, Alan Cox wrote: On 11/27/2012 09:06, Konstantin Belousov wrote: On Tue, Nov 27, 2012 at 12:26:44PM +0100, Andre Oppermann wrote: FreeBSD bbb.ccc 10.0-CURRENT FreeBSD 10.0-CURRENT #0: Fri Nov

Re: panic: vm_object_madvise: page 0xfffffe0413c58630 is fictitious

2012-11-27 Thread Andre Oppermann
On 27.11.2012 20:16, Alan Cox wrote: On 11/27/2012 12:43, Andre Oppermann wrote: On 27.11.2012 19:27, Alan Cox wrote: On 11/27/2012 12:08, Andre Oppermann wrote: On 27.11.2012 17:42, Alan Cox wrote: On 11/27/2012 09:06, Konstantin Belousov wrote: On Tue, Nov 27, 2012 at 12:26:44PM +0100

Re: svn commit: r242910 - in user/andre/tcp_workqueue/sys: kern sys

2012-11-14 Thread Andre Oppermann
On 14.11.2012 03:10, Alfred Perlstein wrote: Andre, do you think the variable realmem could be exported as something like kmemsize or something? Or maybe a function call to subr_param.c? The reason I ask is that I would like to scale things like number of default sysv semaphores to something

Looking for bge(4) , bce(4) and igb(4) cards

2012-11-14 Thread Andre Oppermann
Hello I currently working on a number of drivers for popular network cards and extend them with automatic hybrid interrupt/polling ithread processing with life-lock prevention (so that the driver can't consume all CPU when under heavy load or attack). To properly test this I need the proper

polling's future [was: Re: Dynamic Ticks/HZ]

2012-11-06 Thread Andre Oppermann
On 05.11.2012 17:57, Luigi Rizzo wrote: On Mon, Nov 05, 2012 at 04:25:36PM +, Joe Holden wrote: Luigi Rizzo wrote: On Mon, Nov 05, 2012 at 08:11:41AM -0500, Ryan Stone wrote: On Mon, Nov 5, 2012 at 4:40 AM, Joe Holden li...@rewt.org.uk wrote: doh, running kernel wasn't as GENERIC as I

Re: polling's future [was: Re: Dynamic Ticks/HZ]

2012-11-06 Thread Andre Oppermann
On 06.11.2012 11:27, Poul-Henning Kamp wrote: In message 5098e526.6070...@freebsd.org, Andre Oppermann writes: Hi Luigi, do you agree on polling having outlived its usefulness in the light of interrupt moderating NIC's and SMP complications/disadvantages? Can I just point out

Re: polling's future [was: Re: Dynamic Ticks/HZ]

2012-11-06 Thread Andre Oppermann
On 06.11.2012 12:30, Luigi Rizzo wrote: On Tue, Nov 06, 2012 at 11:23:34AM +0100, Andre Oppermann wrote: ... Hi Luigi, do you agree on polling having outlived its usefulness in the light of interrupt moderating NIC's and SMP complications/disadvantages? yes, we should let it rest in peace

Re: polling's future [was: Re: Dynamic Ticks/HZ]

2012-11-06 Thread Andre Oppermann
On 06.11.2012 12:02, Fabien Thomas wrote: Hi Luigi, do you agree on polling having outlived its usefulness in the light of interrupt moderating NIC's and SMP complications/disadvantages? If you have only one interface yes polling is not really necessary. If you have 10 interfaces the

Re: weird network problems on current since 10/28/2012

2012-11-05 Thread Andre Oppermann
On 05.11.2012 02:39, Manfred Antar wrote: At 01:57 PM 11/4/2012, you wrote: On 04.11.2012 21:15, Andreas Tobler wrote: On 04.11.12 14:57, Andre Oppermann wrote: On 04.11.2012 13:11, Kim Culhan wrote: On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: On 2012-11-04 02:13, Manfred Antar

Re: weird network problems on current since 10/28/2012

2012-11-04 Thread Andre Oppermann
On 04.11.2012 02:13, Manfred Antar wrote: At 03:29 PM 11/3/2012, Adrian Chadd wrote: On 3 November 2012 10:40, Manfred Antar n...@pozo.com wrote: i have problem connecting to freebsd box on local network since last sunday. the last kernel that works: FreeBSD 10.0-CURRENT #0: Sun Oct 28

Re: weird network problems on current since 10/28/2012

2012-11-04 Thread Andre Oppermann
On 04.11.2012 13:11, Kim Culhan wrote: On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: On 2012-11-04 02:13, Manfred Antar wrote: At 03:29 PM 11/3/2012, Adrian Chadd wrote: On 3 November 2012 10:40, Manfred Antar n...@pozo.com wrote: i have problem connecting to freebsd box on local

Re: kernel module parallel build?

2012-11-04 Thread Andre Oppermann
On 22.10.2012 15:28, John Baldwin wrote: On Sunday, October 21, 2012 7:11:10 am Andre Oppermann wrote: What's keeping kernel modules from building in parallel with make -j8? They don't for you? They do for me either via 'make buildkernel' or the old method. They do, but only partially

Re: weird network problems on current since 10/28/2012

2012-11-04 Thread Andre Oppermann
On 04.11.2012 21:15, Andreas Tobler wrote: On 04.11.12 14:57, Andre Oppermann wrote: On 04.11.2012 13:11, Kim Culhan wrote: On Sun, November 4, 2012 6:21 am, Dimitry Andric wrote: On 2012-11-04 02:13, Manfred Antar wrote: At 03:29 PM 11/3/2012, Adrian Chadd wrote: After the commit

Re: maxusers (thus mbuf etc.) autotuning capped at 384

2012-10-24 Thread Andre Oppermann
On 24.10.2012 16:26, Vadim Goncharov wrote: Hi, We have 'maxusers' tunable which affects many other tunables, e.g. number of network mbuf/clusters which is often too low on current machines. The mbuf/cluster limit can be rethought as well. Since it all comes out of UMA and is not

ZERO_COPY_SOCKETS kernel option removed

2012-10-23 Thread Andre Oppermann
The ZERO_COPY_SOCKETS kernel option has been removed from HEAD today. Please see the explanation in the attached commit message. -- Andre ---BeginMessage--- Author: andre Date: Tue Oct 23 16:33:43 2012 New Revision: 241955 URL: http://svn.freebsd.org/changeset/base/241955 Log: Note the

Re: [ZFS] Server periodically become unavailable

2012-10-22 Thread Andre Oppermann
On 20.10.2012 15:11, Vladislav Prodan wrote: FreeBSD 9.1-PRERELEASE #0: Wed Jul 25 01:40:56 EEST 2012 I have the server: 8 cores AMD, 16GB RAM, 4x3TB HDD in RAID10 for ZFS. Sometime wheels fall off the server and the network. Can this clean-up memory for ZFS cache? I enclose a picture with

kernel module parallel build?

2012-10-21 Thread Andre Oppermann
What's keeping kernel modules from building in parallel with make -j8? -- Andre ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to

Re: sysctl kern.ipc.somaxconn limit 65535 why?

2012-10-03 Thread Andre Oppermann
On 03.10.2012 22:03, Adrian Chadd wrote: Hi, somaxconn is the connection queue depth. If it's sitting at a couple hundred thousand then something else is going crazily wrong. I understand your frustration, but there's a lot of instances where the application just isn't doing things right and

Re: Some performance measurements on the FreeBSD network stack

2012-04-24 Thread Andre Oppermann
On 19.04.2012 22:46, Luigi Rizzo wrote: On Thu, Apr 19, 2012 at 10:05:37PM +0200, Andre Oppermann wrote: On 19.04.2012 15:30, Luigi Rizzo wrote: I have been running some performance tests on UDP sockets, using the netsend program in tools/tools/netrate/netsend and instrumenting the source code

Re: Some performance measurements on the FreeBSD network stack

2012-04-20 Thread Andre Oppermann
On 20.04.2012 10:26, Alexander V. Chernikov wrote: On 20.04.2012 01:12, Andre Oppermann wrote: On 19.04.2012 22:34, K. Macy wrote: If the number of peers is bounded then you can use the flowtable. Max PPS is much higher bypassing routing lookup. However, it doesn't scale From my experience

Re: Some performance measurements on the FreeBSD network stack

2012-04-20 Thread Andre Oppermann
On 20.04.2012 08:35, Luigi Rizzo wrote: On Fri, Apr 20, 2012 at 12:37:21AM +0200, Andre Oppermann wrote: On 20.04.2012 00:03, Luigi Rizzo wrote: On Thu, Apr 19, 2012 at 11:20:00PM +0200, Andre Oppermann wrote: On 19.04.2012 22:46, Luigi Rizzo wrote: The allocation happens while the code has

Re: Some performance measurements on the FreeBSD network stack

2012-04-19 Thread Andre Oppermann
On 19.04.2012 15:30, Luigi Rizzo wrote: I have been running some performance tests on UDP sockets, using the netsend program in tools/tools/netrate/netsend and instrumenting the source code and the kernel do return in various points of the path. Here are some results which I hope you find

Re: Some performance measurements on the FreeBSD network stack

2012-04-19 Thread Andre Oppermann
On 19.04.2012 22:34, K. Macy wrote: This is indeed a big problem. I'm working (rough edges remain) on changing the routing table locking to an rmlock (read-mostly) which This only helps if your flows aren't hitting the same rtentry. Otherwise you still convoy on the lock for the rtentry

Re: Some performance measurements on the FreeBSD network stack

2012-04-19 Thread Andre Oppermann
On 19.04.2012 22:46, Luigi Rizzo wrote: On Thu, Apr 19, 2012 at 10:05:37PM +0200, Andre Oppermann wrote: On 19.04.2012 15:30, Luigi Rizzo wrote: I have been running some performance tests on UDP sockets, using the netsend program in tools/tools/netrate/netsend and instrumenting the source code

Re: Some performance measurements on the FreeBSD network stack

2012-04-19 Thread Andre Oppermann
On 19.04.2012 23:17, K. Macy wrote: This only helps if your flows aren't hitting the same rtentry. Otherwise you still convoy on the lock for the rtentry itself to increment and decrement the rtentry's reference count. The rtentry lock isn't obtained anymore. While the rmlock read lock is

Re: Some performance measurements on the FreeBSD network stack

2012-04-19 Thread Andre Oppermann
On 20.04.2012 00:03, Luigi Rizzo wrote: On Thu, Apr 19, 2012 at 11:20:00PM +0200, Andre Oppermann wrote: On 19.04.2012 22:46, Luigi Rizzo wrote: The allocation happens while the code has already an exclusive lock on so-snd_buf so a pool of fresh buffers could be attached there. Ah

Re: strange ping response times...

2012-04-11 Thread Andre Oppermann
On 11.04.2012 01:32, Luigi Rizzo wrote: On Tue, Apr 10, 2012 at 07:05:00PM -0400, Barney Wolff wrote: CPU cache? Cx states? powerd? powerd is disabled, and i am going down to C1 at most sysctl -a | grep cx hw.acpi.cpu.cx_lowest: C1 dev.cpu.0.cx_supported: C1/1 C2/80

Re: strange ping response times...

2012-04-11 Thread Andre Oppermann
On 11.04.2012 13:00, Luigi Rizzo wrote: On Wed, Apr 11, 2012 at 12:35:10PM +0200, Andre Oppermann wrote: On 11.04.2012 01:32, Luigi Rizzo wrote: On Tue, Apr 10, 2012 at 07:05:00PM -0400, Barney Wolff wrote: CPU cache? Cx states? powerd? powerd is disabled, and i am going down to C1 at most

Re: Potential deadlock on mbuf

2012-04-03 Thread Andre Oppermann
On 02.04.2012 18:21, Alexandre Martins wrote: Dear, I have currently having troubles with a basic socket stress. The socket are setup to use non-blocking I/O. During this stress-test, the kernel is running mbuf exhaustion, the goal is to see system limits. If the program make a write on a

Re: quick summary results with ixgbe (was Re: datapoints on 10G throughput with TCP ?

2011-12-08 Thread Andre Oppermann
On 08.12.2011 14:11, Lawrence Stewart wrote: On 12/08/11 05:08, Luigi Rizzo wrote: On Wed, Dec 07, 2011 at 11:59:43AM +0100, Andre Oppermann wrote: On 06.12.2011 22:06, Luigi Rizzo wrote: ... Even in my experiments there is a lot of instability in the results. I don't know exactly where

Re: quick summary results with ixgbe (was Re: datapoints on 10G throughput with TCP ?

2011-12-08 Thread Andre Oppermann
On 08.12.2011 16:34, Luigi Rizzo wrote: On Fri, Dec 09, 2011 at 12:11:50AM +1100, Lawrence Stewart wrote: On 12/08/11 05:08, Luigi Rizzo wrote: ... I ran a bunch of tests on the ixgbe (82599) using RELENG_8 (which seems slightly faster than HEAD) using MTU=1500 and various combinations of

Re: datapoints on 10G throughput with TCP ?

2011-12-07 Thread Andre Oppermann
On 06.12.2011 22:06, Luigi Rizzo wrote: On Tue, Dec 06, 2011 at 07:40:21PM +0200, Daniel Kalchev wrote: I see significant difference between number of interrupts on the Intel and the AMD blades. When performing a test between the Intel and AMD blades, the Intel blade generates 20,000-35,000

subversion-freebsd dependencies

2011-10-06 Thread Andre Oppermann
On a newly installed development machine I installed subversion-freebsd from ports and ended up with a huge dependency chain. Eventually I got the usual gnu-hell (auto-*, lib*), but also python27, tcl-8.5, perl-5.12 and m4. This is a bit too much. The last four should not be required to check

Re: Examining the VM splay tree effectiveness

2010-10-01 Thread Andre Oppermann
On 30.09.2010 19:51, Ivan Voras wrote: On 09/30/10 18:37, Andre Oppermann wrote: Both the vmmap and page table make use of splay trees to manage the entries and to speed up lookups compared to long to traverse linked lists or more memory expensive hash tables. Some structures though do have

Re: Examining the VM splay tree effectiveness

2010-10-01 Thread Andre Oppermann
On 01.10.2010 06:49, Matthew Dillon wrote: I don't remember the reference but I read a comprehensive comparison between various indexing methods about a year ago and the splay tree did considerably better than a RB-tree. The RB-tree actually did fairly poorly. It heavily

Very interesting paper: An Analysis of Linux Scalability to many Cores

2010-10-01 Thread Andre Oppermann
Just saw the link to a very interesting paper on SMP scalability. A very good read and highly relevant for our efforts as well. In certain areas we may already fare better, in others we still have some work to do. An Analysis of Linux Scalability to many Cores ABSTRACT This paper analyzes the

Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
Just for the kick of it I decided to take a closer look at the use of splay trees (inherited from Mach if I read the history correctly) in the FreeBSD VM system suspecting an interesting journey. The VM system has two major structures: 1) the VM map which is per process and manages its address

Re: Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
On 30.09.2010 18:37, Andre Oppermann wrote: Just for the kick of it I decided to take a closer look at the use of splay trees (inherited from Mach if I read the history correctly) in the FreeBSD VM system suspecting an interesting journey. Correcting myself regarding the history: The splay

Re: Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
On 30.09.2010 19:15, Matthew Fleming wrote: On Thu, Sep 30, 2010 at 9:37 AM, Andre Oppermannan...@freebsd.org wrote: Just for the kick of it I decided to take a closer look at the use of splay trees (inherited from Mach if I read the history correctly) in the FreeBSD VM system suspecting an

Re: Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
On 30.09.2010 19:24, Roman Divacky wrote: are you aware of Summer of Code 2008 project by Mayur Shardul? I remember that there was this project but I never saw any numbers or other outcome of it. Haven't checked p4 to look at the code though. -- Andre quoting:

Re: Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
On 30.09.2010 20:01, Alan Cox wrote: On Thu, Sep 30, 2010 at 12:37 PM, Andre Oppermannan...@freebsd.org wrote: On 30.09.2010 18:37, Andre Oppermann wrote: Just for the kick of it I decided to take a closer look at the use of splay trees (inherited from Mach if I read the history correctly

Re: Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
On 30.09.2010 20:38, Alfred Perlstein wrote: Andre, Your observations on the effectiveness of the splay tree mirror the concerns I have with it when I read about it. I have always wondered though if the splay-tree algorithm was modified to only perform rotations when a lookup required more

Re: Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
On 30.09.2010 20:04, Roman Divacky wrote: On Thu, Sep 30, 2010 at 07:49:00PM +0200, Roman Divacky wrote: On Thu, Sep 30, 2010 at 07:46:32PM +0200, Andre Oppermann wrote: On 30.09.2010 19:24, Roman Divacky wrote: are you aware of Summer of Code 2008 project by Mayur Shardul? I remember

Re: Examining the VM splay tree effectiveness

2010-09-30 Thread Andre Oppermann
On 30.09.2010 23:44, Andre Oppermann wrote: On 30.09.2010 20:04, Roman Divacky wrote: On Thu, Sep 30, 2010 at 07:49:00PM +0200, Roman Divacky wrote: On Thu, Sep 30, 2010 at 07:46:32PM +0200, Andre Oppermann wrote: On 30.09.2010 19:24, Roman Divacky wrote: are you aware of Summer of Code 2008

Re: TCP loopback socket fusing

2010-09-15 Thread Andre Oppermann
On 15.09.2010 17:19, Bjoern A. Zeeb wrote: On Mon, 13 Sep 2010, Andre Oppermann wrote: Hey, When a TCP connection via loopback back to localhost is made the whole send, segmentation and receive path (with larger packets though) is still executed. This has some considerable overhead. To short

Re: TCP loopback socket fusing

2010-09-14 Thread Andre Oppermann
to that effect is already in the patch. -- Andre Fabien On 13 sept. 2010, at 13:33, Andre Oppermann wrote: When a TCP connection via loopback back to localhost is made the whole send, segmentation and receive path (with larger packets though) is still executed. This has some considerable overhead

Re: TCP loopback socket fusing

2010-09-14 Thread Andre Oppermann
On 14.09.2010 12:12, Ian FREISLICH wrote: Fabien Thomas wrote: Great, This will maybe kill the long time debate about my loopback is slow vs linux To have the best of both world what about a socket option to enable/disable fusing: can be useful when you need to see some connection packetized.

Re: TCP loopback socket fusing

2010-09-14 Thread Andre Oppermann
On 14.09.2010 12:35, Maxim Dounin wrote: Hello! On Tue, Sep 14, 2010 at 12:12:03PM +0200, Ian FREISLICH wrote: Fabien Thomas wrote: Great, This will maybe kill the long time debate about my loopback is slow vs linux To have the best of both world what about a socket option to enable/disable

Re: TCP loopback socket fusing

2010-09-14 Thread Andre Oppermann
On 14.09.2010 18:08, Fabien Thomas wrote: On 14 sept. 2010, at 17:41, Andre Oppermann wrote: On 14.09.2010 11:18, Fabien Thomas wrote: Great, This will maybe kill the long time debate about my loopback is slow vs linux To have the best of both world what about a socket option to enable

TCP loopback socket fusing

2010-09-13 Thread Andre Oppermann
When a TCP connection via loopback back to localhost is made the whole send, segmentation and receive path (with larger packets though) is still executed. This has some considerable overhead. To short-circuit the send and receive sockets on localhost TCP connections I've made a proof-of-concept

Re: TCP loopback socket fusing

2010-09-13 Thread Andre Oppermann
On 13.09.2010 14:45, Poul-Henning Kamp wrote: In message4c8e0c1e.2020...@networx.ch, Andre Oppermann writes: To short-circuit the send and receive sockets on localhost TCP connections I've made a proof-of-concept patch that directly places the data in the other side's socket buffer without

Re: TSO panic

2010-09-03 Thread Andre Oppermann
On 02.09.2010 00:11, ben wilber wrote: On Sep 1, 2010, at 8:57 AM, Andre Oppermann wrote: On 01.09.2010 01:13, ben wilber wrote: Hi, I just upgraded from r210042 to r212073 and keep getting the panic introduced in r211317: panic: tcp_output: len= tso_segsz Please try the attached patch

Re: TSO panic

2010-09-02 Thread Andre Oppermann
On 02.09.2010 00:11, ben wilber wrote: On Sep 1, 2010, at 8:57 AM, Andre Oppermann wrote: On 01.09.2010 01:13, ben wilber wrote: Hi, I just upgraded from r210042 to r212073 and keep getting the panic introduced in r211317: panic: tcp_output: len= tso_segsz Please try the attached patch

Re: TSO panic

2010-09-01 Thread Andre Oppermann
On 01.09.2010 01:13, ben wilber wrote: Hi, I just upgraded from r210042 to r212073 and keep getting the panic introduced in r211317: panic: tcp_output: len= tso_segsz Please try the attached patch and report back whether it fixes the issue. I'm a bit in a hurry right now and can respond

Re: [PATCH] fixes of tcp_hostcache.c

2003-12-02 Thread Andre Oppermann
Greetings, I found two calls of bcopy() in tcp_hostcache.c got the source and the destination pointer wrongly. # Perhaps the author got confused with memcpy(), I guess. Indeed. Originally these were memcpy calls and I've been asked to change them to bcopy calls. Which I did. It didn't

Re: Fix for 5.2-BETA lockup problems

2003-11-28 Thread Andre Oppermann
M. Warner Losh wrote: In message: [EMAIL PROTECTED] Andre Oppermann [EMAIL PROTECTED] writes: : Please try the attached patch which should fix it. I've been having crashes all the time since the hostcache went into the tree. I've been running a few hours with this patch

[Fwd: cvs commit: src/sys/netinet tcp_hostcache.c]

2003-11-28 Thread Andre Oppermann
This is the committed fix for the lockup problems a couple of you have experienced. If you don't have this fix already please re- cvsup and remake the kernel. -- Andre---BeginMessage--- andre 2003/11/28 08:33:03 PST FreeBSD src repository Modified files: sys/netinet

Fix for 5.2-BETA lockup problems

2003-11-27 Thread Andre Oppermann
Hello all, I've found what probably is going wrong in tcp_hostcache. The problem is me cutting corners (what goes around comes around...) in tcp_hc_insert when the bucket limit is reached. I made the #if 0 too big and the bucket was not removed from the tailqueue when we hit the bucket limit.

  1   2   >