Greg Troxel a écrit :
> BERTRAND Joël writes:
>
>> My server runs NetBSD for a very long time (if I remember, first
>> installation was done with NetBSD 4.0). Motherborad was changed, raid1/5
>> volumes also... But installation was done a long time ago and
Hello,
My server runs NetBSD for a very long time (if I remember, first
installation was done with NetBSD 4.0). Motherborad was changed, raid1/5
volumes also... But installation was done a long time ago and upgraded
from sources.
Now, I have some trouble to build
David Brownlee wrote:
On Fri, 29 Dec 2023 at 16:29, BERTRAND Joël wrote:
David Brownlee wrote:
On Wed, 27 Dec 2023 at 08:25, BERTRAND Joël wrote:
Hello,
Yesterday, I have changed my system disk (raid0). Thus, system has
rebuilt a 1 To raid1 volume and system has
BERTRAND Joël wrote:
Michael van Elst wrote:
joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
I have seen Michael has applied patch to fix ccb_timout to -10
kernel.
Thus, I have rebuilt my tree to have a unpatched kernel and I cannot now
access to my NAS over iSCSI
David Brownlee wrote:
On Wed, 27 Dec 2023 at 08:25, BERTRAND Joël wrote:
Hello,
Yesterday, I have changed my system disk (raid0). Thus, system has
rebuilt a 1 To raid1 volume and system has crashed three or four times.
First time :
[ 5235.028358] uvm_fault
Michael van Elst wrote:
joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
I have seen Michael has applied patch to fix ccb_timout to -10 kernel.
Thus, I have rebuilt my tree to have a unpatched kernel and I cannot now
access to my NAS over iSCSI. Of course, I have
Hello,
Yesterday, I have changed my system disk (raid0). Thus, system has
rebuilt a 1 To raid1 volume and system has crashed three or four times.
First time :
[ 5235.028358] uvm_fault(0x8190fbc0, 0xf6fc5a75b000, 2) -> e
[ 5235.028358] fatal page fault in
Hello,
I have seen Michael has applied patch to fix ccb_timout to -10 kernel.
Thus, I have rebuilt my tree to have a unpatched kernel and I cannot now
access to my NAS over iSCSI. Of course, I have reinstalled kernel /and/
userland.
In dmesg, I only obtain :
[
Martin Husemann a écrit :
> On Sat, Nov 18, 2023 at 08:14:32PM +0100, BERTRAND Joël wrote:
>> If I restart this server with a -10.0-Beta kernel, faulty ethernet
>> adapter is autoconfigured without trouble.
>
> Can you give more details of that kernel? Ideally source upd
Tobias Nygren a écrit :
> On Sat, 18 Nov 2023 20:14:32 +0100
> BERTRAND Joël wrote:
>
>> Maybe something is broken in recent changes in
>> src/sys/dev/pci/pci_resource.c, pcidevs_data.h or pcidevs.h.
>
> Since the attach function runs it does not se
Hello,
I have a server with a lot of wm interfaces and one re.
With last -10.0-RC1 kernel, this ethernet adapter is not configured and
dmesg contains :
ov 18 16:28:08 legendre /netbsd: [ 1.0066881] pci5 at ppb4 bus 5
Nov 18 16:28:08 legendre /netbsd: [ 1.0066881]
Nobody ?
-10.0 seems to be unusable with iscsi initior (targets are QNAP NAS).
System randomly panics, sometimes after few hours, sometimes after few
weeks. It's not related to I/O (last panic occurs when both iSCSI
targets are idle. QNAP firmware switchs off disks when there is
Hello,
I have filled PR/57669 as I have found another bug in iscsi initiator
on -10.0. This bug panic occurs twice the last week. First time, I
haven't debug kernel related to running kernel. Second time, I have one
but I'm unable to obtain more information. Seems to be related to
Problem solved. It was a misconfiguration in ISP gateway.
Regards,
JB
RVP a écrit :
> On Fri, 8 Sep 2023, BERTRAND Joël wrote:
>
>> Now, both Linux and NetBSD can send and receive IPv6 packets but
>> workstations on LAN cannot use IPv6 through NetBSD server.
>>
>
> OK, so both legendre and rayleigh can ping6 the outside w
RVP a écrit :
> On Thu, 7 Sep 2023, BERTRAND Joël wrote:
>
>> But from LAN, IPv6 public network is unreachable. For example:
>> hilbert:[~] > ping6 www.google.fr
>> PING www.google.fr(par10s39-in-x03.1e100.net (2a00:1450:4007:807::2003))
>> 56 data bytes
>
Hello,
I use IPv6 for a while on a NetBSD server but I have replaced my old
ADSL connection for a new fiber connection.
With my old ISP, my IPv6 access was done through a VPN (OpenVPN/TAP) to
a Linux server I have installed in a datacenter. Now, my new ISP
provides IPv6
Martin Husemann a écrit :
> On Fri, Aug 25, 2023 at 09:50:59AM +0200, BERTRAND Joël wrote:
>> I suspect a mistake in npf kernel support introduced by last patches.
>
> The change is explained in PR 56990. If you think it broke previously
> correct and working configurat
Hello,
This morning, after a power outage, one of my NAS was not mounted by
system. Kernel was built yesterday from officiel -10_beta source tree.
With a kernel I have built last week, all NAS ran fine.
Network configuration :
- w0 and w1 : 192.168.12.1/24. w0 is
Hauke Fath a écrit :
> On 8/5/23 23:17, Martin Neitzel wrote:
>>> I have in -10 blAcklistd and blOcklistd. Is blacklistd now unsupported?
>>> Man pages seem to be very similar.
>>
>> It's just a renaming, and blocklistd gets continuing support. On
>> a "true" netbsd-10-release (not available
BERTRAND Joël a écrit :
> Martin Neitzel a écrit :
>> Hi Joel,
>>
>>> I have installed blacklistd on -10.0 and, if daemon runs fine, it
>>> doesn't block attacks. I have read several pages and I suppose I have
>>> done a misconfiguration somewhere.
&
Martin Neitzel a écrit :
> Hi Joel,
>
>> I have installed blacklistd on -10.0 and, if daemon runs fine, it
>> doesn't block attacks. I have read several pages and I suppose I have
>> done a misconfiguration somewhere.
>>
>> My configuration is very simple. I only have to block ssh.
Hello,
I have installed blacklistd on -10.0 and, if daemon runs fine, it
doesn't block attacks. I have read several pages and I suppose I have
done a misconfiguration somewhere.
My configuration is very simple. I only have to block ssh. thus, I have
written in
Strange.
I have rebooted my server and now, uplink runs as expected. I haven't
modify configuration. In the past, I've limited uplink throughput to 4
Mbps with altqd and I think this limit was not deleted as I have to kill
(with kill -9) altqd.
Best regards,
JKB
Michael van Elst a écrit :
> joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
>
>> CISCO FTTH adapter
>> ||
>> ||
>> netbsdLinux
>> |
>> |
>> lan
>
>> On NetBSD (-10) or workstations on LAN:
>> - 400 Mbps downlink;
>> - 4 (!) Mbps uplink, yes, 4
Hello,
I have replaced my old DSL connection (2Mbps) by a professionnal
FTTH/4G one.
CISCO FTTH adapter
||
||
netbsdLinux
|
|
lan
NetBSD and Linux (devuan) servers are directly connected to Cisco
adapter with public IPv4 addresses. No traffic
Hello,
I have patched my main server with if_tap.c patch. tap0 now runs as
expected but, when I have restarted system (that ran with a -10.0 BETA
kernel without this patch), it panics with :
[ 856605,576197] uvm_fault(0x8190e240, 0xe80ea992e000, 4) -> e
[
Hello,
As my server randomly crashes (deadlock) when it tries to acces to an
iSCSI NAS, I have upgraded my 9.3 installation to 10-BETA.
Network configuration :
2 NAS (iSCSI)
|
Hello,
For a very long time (I don't remember if it was from 9.0 or 9.1), my
main server randomly panics or enters in a deadlock when it tries to
access to an iSCSI NAS. This panics is not related to hardware failure
as I have changed motherboard, disks, memory wit spares
RVP a écrit :
> On Mon, 24 Oct 2022, BERTRAND Joël wrote:
>
>> This new configuration runs fine with X, but in console ou tty, if
>> delete and backspace are swapped, 'k' sends not a backspace also ! And I
>> don't understand why 'k' is modified...
>>
>>
Hello,
I want to swap delete and backspace. Thus, I have added in
/etc/rc.local :
/sbin/wsconsctl -w map+="keycode 14 = BackSpace" > /dev/null
/sbin/wsconsctl -w map+="keycode 211 = Delete" > /dev/null
This new configuration runs fine with X, but in console ou tty, if
Please forget. There is a bug in readline library that only occurs on
NetBSD. I suppose pkgsrc readline is patched.
Hello,
I'm trying to update my RPL/2 installation on NetBSD
(http://www.rpl2.net). Program was configured with :
../rpl/configure --enable-native --disable-motif --disable-rplcas
Last year, it was built without any trouble. Now, link stage aborts
with :
Hello,
In last july, I have filled PR-5625 as one of my NetBSD servers
randomly panics (several times by month), mainly on heavy iSCSI I/O
(initiator). This server acts as main server for diskless workstations
(NFSv3 and iSCSI for swap) and when it panics or enters in a deadlock,
I have tried to use ping -g but I'm not sure I have understood -g
option.
legendre# ping -g 192.168.15.19 8.8.8.8
PING dns.google (8.8.8.8): 56 data bytes
^C
dns.google PING Statistics
3 packets transmitted, 0 packets received, 100.0% packet loss
Of course, 192.168.15.19
RVP a écrit :
> On Wed, 8 Jun 2022, BERTRAND Joël wrote:
>
>> For example, how can I ping a server on WAN side through
>> 192.168.15.19 gateway and with 192.168.15.20 default route ?
>>
>
> Don't need to do that: just ping the host and if ping fails,
> switch r
Niels Dettenbach a écrit :
> Am Mittwoch, 8. Juni 2022, 09:38:30 CEST schrieb BERTRAND Joël:
>> Now, I'm trying to automatically change default route (from
>> 192.168.15.20 to 192.168.15.19 and reciprocally) when DSL connection is
>> down.
> there are lot of dif
Hello,
For a long time (9 months), my DSL connection is unstable. Thus, I have
bought last Saturday a 4G Ethernet modem. Now, my WAN connection is :
wm2 (192.168.15.14)
+ DSL modem (Archer VR400, 192.168.15.20)
+ 4G modem (TL-MR6400, 192.168.15.19)
Now, I'm
RVP a écrit :
> On Mon, 6 Jun 2022, BERTRAND Joël wrote:
>
>> [ 216.670] (--) Using wscons driver on /dev/ttyE4 in pcvt
>> compatibility mode (version 3.32)
>> [ 216.670] (--) using VT number 5
>>
>
> That's what it says, but, looks like it's actuall
RVP a écrit :
> On Sun, 5 Jun 2022, BERTRAND Joël wrote:
>
>> When NetBSD starts, wdm is launched, mouse works fine, but
>> keyboard not
>> ! I cannot switch from X console to ttyE1, but from a remote server, if
>> I kill X or wdm, I see that keyboard has sent c
Hello,
My main server (Netbsd-9 from cvs tree) doesn't run X until yesterday
as I have to configure a new 4G modem (my DSL line is broken...). Thus,
I have configured Xorg, Windowmaker and wdm.
legendre:[/etc] > uname -a
NetBSD legendre.systella.fr 9.2_STABLE NetBSD 9.2_STABLE
Dima Veselov a écrit :
> Thanks for a hint. I have recompiled 9-STABLE kernel with DEBUG and
> LOCKDEBUG. Is it enough to run server with serial console or I can get
> something useful from GDB when the freeze will happen?
Since freezes appear, I have tried to access to kernel debugger
Dima Veselov a écrit :
> On Thu, Mar 03, 2022 at 12:17:32PM +, Stephen Borrill wrote:
>> On Wed, 2 Mar 2022, Dima Veselov wrote:
>>> I have two similar NetBSD boxes, one is under 9_STABLE and the other is
>>> old 8_STABLE. Sometimes one or another or even both get hit by something
>>> and OS
BERTRAND Joël a écrit :
> BERTRAND Joël a écrit :
>> matthew green a écrit :
>>> i wonder if this is lack of buf_destroy() in rf_FreeDiskQueueData(),
>>> to match the buf_init() in rf_CreateDiskQueueData().
>>>
>>> can you try this patch?
>&g
matthew green a écrit :
> i wonder if this is lack of buf_destroy() in rf_FreeDiskQueueData(),
> to match the buf_init() in rf_CreateDiskQueueData().
>
> can you try this patch?
I can, but I don't know when I can reboot this server to test. I hope
in a few days.
Best regards,
SAITOH Masanobu a écrit :
> On 2021/12/09 22:05, BERTRAND Joël wrote:
>> SAITOH Masanobu a écrit :
>>> I think it would worth to try LOCKDEBUG.
>>
>> I have tried, but a kernel built with LOCKDEBUG panics during boot
>> (very early).
>
> Please show
SAITOH Masanobu a écrit :
> I think it would worth to try LOCKDEBUG.
I have tried, but a kernel built with LOCKDEBUG panics during boot
(very early).
You will find in attachement my config file.
Best regards,
JKB
# $NetBSD: GENERIC,v 1.531.2.10 2020/07/07
Hello,
My main server runs NetBSD 9.2 (STABLE). It has 16 GB of RAM, an i7 CPU
(i7-4770), a lot of disks (wd0/wd1 configured as ccd [swap for diskless
workstation], wd2/wd3 as raid level 1 [system], wd4/wd5/wd6 as raid
level 5 [home] and an external NAS [iscsi target, bacula archives]). It
Chavdar Ivanov a écrit :
> On Sat, 12 Jun 2021 at 19:30, Michael van Elst wrote:
>>
>> On Sat, Jun 12, 2021 at 05:02:11PM +0100, Chavdar Ivanov wrote:
>>
>>> Not that this has any connection to your problem, but I'd nevertheless
>>> add my 5c about istgt - I have been serving zvols for perhaps
Michael van Elst a écrit :
> joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
>
>>> If you have a version of the kernel with debug symbols, you could
>>> use addr2line to identify the instruction that caused the uvm_fault
>>> at address 0x802280cc. Without debug symbols
Michael van Elst a écrit :
> joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
>
>> Hello,
>
>> I can see some panics on a server that exports iSCSI volumes (istgt on
>> a CCB device) to some workstations. dmesg always contains this kind of
>> backtrace :
>
> That
Hello,
I can see some panics on a server that exports iSCSI volumes (istgt on
a CCB device) to some workstations. dmesg always contains this kind of
backtrace :
[ 308324,087343] S-1C-1: ccb_timeout: num=1 total=1 disp=0
[ 308324,087343] uvm_fault(0x81585e20, 0x0, 2) -> e
Michael van Elst a écrit :
> On Tue, Mar 09, 2021 at 11:24:13AM +0100, BERTRAND Joël wrote:
>> Hello,
>>
>> Last snday was the day of my full backup. Now, if iSCSI target runs
>> faster, my NetBSD server can enter in a dead lock after a few bacula
>>
Hello,
Last snday was the day of my full backup. Now, if iSCSI target runs
faster, my NetBSD server can enter in a dead lock after a few bacula
volumes. First try, lock after 41 volumes. Second one after 2 volumes,
third one after 7 volumes.
Keyboard is locked, no panic,
RVP a écrit :
> On Tue, 9 Feb 2021, BERTRAND Joël wrote:
>
>> You can downloaded https://hilbert.systella.fr/public/1.dump.xz
>
> Ah, I get a 403 when downloading from SDF:
> $ ftp https://hilbert.systella.fr/public/1.dump.xz
> Requesting https://hilbert.systella.f
RVP a écrit :
> isns_cd is probably the iSNS server, not the iSCSI target server:
>
> https://github.com/open-iscsi/open-isns
Oops, sorry...
In /etc/init.d/iscsitrgt.sh, I have :
...
FBDISK_SH=/etc/init.d/fbdisk.sh
ISCSI_TARGET_KO=/lib/modules/misc/target_core_mod.ko
RVP a écrit :
> On Mon, 8 Feb 2021, BERTRAND Joël wrote:
>
>> I haven't spare disks enough. Thus, I have created a disk image on a
>> Linux laptop (with an old AMD E-450), installed istgt and exported this
>> disk.
>>
>> legendre# dd if=/dev/rsd1a of=/dev
RVP a écrit :
> On Mon, 8 Feb 2021, BERTRAND Joël wrote:
>
>> I have captured tcpdump output on both adapters (I post only one
>> second) :
>>
>> wm0 (to euclide) :
>> 14:06:09.014969 IP legendre.systella.fr.65508 >
>> euclide.systella.fr.isc
Michael van Elst a écrit :
> On Mon, Feb 08, 2021 at 11:40:43AM +0100, BERTRAND Joël wrote:
>> Michael van Elst a écrit :
>>> For the "dd"-test of iSCSI, use the raw devices (not block devices,
>>> not files in a filesystem) and a block size of 1MB. Only
Michael van Elst a écrit :
> On Mon, Feb 08, 2021 at 11:40:43AM +0100, BERTRAND Joël wrote:
>> Michael van Elst a écrit :
>>> For the "dd"-test of iSCSI, use the raw devices (not block devices,
>>> not files in a filesystem) and a block size of 1MB. Only
Michael van Elst a écrit :
> The in-kernel initiator logs debug info when you set hw.iscsi.debug
> to a debug level > 0.
>
> 1 -> basic start/stop events, ioctls
> 5 -> more events, log commands and queue status
> 9 -> add handshake events
> 10 -> trace communication, task management, scsipi
Michael van Elst a écrit :
> For the "dd"-test of iSCSI, use the raw devices (not block devices,
> not files in a filesystem) and a block size of 1MB. Only if that
> works ok, it makes sense to look at filesystem I/O, i.e. your /opt
> filesystem.
If I do that in write mode, I suppose I
RVP a écrit :
> On Sun, 7 Feb 2021, BERTRAND Joël wrote:
>
>>> c) Does squid do anything there?
>>
>> Squid is used for proxy as my DSL connection is very poor.
>
> Does it store its cache on /opt?
No. Squid's cache is on /var (a local vol
RVP a écrit :
> On Sun, 7 Feb 2021, BERTRAND Joël wrote:
>
> 1. Can you provide more info. on what /opt is used for?
> For example,
> a) You mentioned diskless workstations.
> Are you exporting /opt to any of them via NFS/SMB?
Nope. /opt is only used by bacu
RVP a écrit :
> On Sat, 6 Feb 2021, BERTRAND Joël wrote:
>
>> iperf Done.
>>
>
> Thanks for those tests.
You're welcome.
>> But with these both tests and 3st one when Linux acts as initiator, I
>> think we can exclude an issue in NAS.
&
RVP a écrit :
> Can you do an i3perf test between euclide and legendre using
> one of the ARM binaries from here:
>
> https://iperf.fr/iperf-download.php
>
> Do two tests; for both the server end should be on euclide.
>
> 1. A standard test with any server port you choose.
> 2. A test with the
RVP a écrit :
> On Sat, 6 Feb 2021, BERTRAND Joël wrote:
>
>> Legendre runs with 9.1_STABLE (CUSTOM). It runs with a customized
>> kernel as it requires ALTQ support.
>
> ALTQ, eh? Well, well... anything being done on wm0? Remember, we
> were never able to do a strai
Ottavio Caruso a écrit :
> Just curious: is there any other poor soul like me who, for a number of
> reasons, must use *cough* Yahoo mail and gets all emails from @sdf.org
> sent to the spam folder (one more reason for me to use Gmane as a
> reader)? Setting up any sort of filters doesn't work.
RVP a écrit :
> On Fri, 5 Feb 2021, BERTRAND Joël wrote:
>
>> But even if dd is done over block device, throughput is correct
>> without network.
>>
>
> What's the network throughput like when a client machine (eg.
> hilbert) reads/writes data on this exported
Michael van Elst a écrit :
> On Fri, Feb 05, 2021 at 01:49:12PM +0100, BERTRAND Joël wrote:
>>
>> First test : CPUfreq=3400 MHz
>> legendre# dd if=/dev/zero of=/dev/sd1 bs=1m count=1
>> 1+0 records in
>> 1+0 records out
>> 1048576 bytes tran
Michael van Elst a écrit :
> On Fri, Feb 05, 2021 at 12:44:26PM +0100, BERTRAND Joël wrote:
>
>> With or without -c, I haven't understood how this initiator works. It
>> always aborts with error (but only returns to shell prompt after a ^C).
>
> It's based on
RVP a écrit :
> On Fri, 5 Feb 2021, Mike Pumford wrote:
>
>> I think estd might need some reworking for the now hugely multi-core
>> processors in modern systems as average CPU is no longer a useful
>> way to make an optimum performance decision on a multi-core system.
>>
>
> I run estd not for
RVP a écrit :
> On Fri, 5 Feb 2021, BERTRAND Joël wrote:
>
>> Nope. There is a /usr/sbin/iscsi-initiator provided by NetBSD itself.
>>
>
> I see. It's refuse(3)-based so I don't expect great performance
> with it. Did you run it with the `-c' flag for your test?
like what we are seeing here, isn't it?: "small"
> I/O transfers of 1GB easily exceed 100MBPS; but 10 GB ones get
> capped at 10MBPS.
>
> On Fri, 5 Feb 2021, BERTRAND Joël wrote:
>
>> To be sure that this issue does come from qNAP NAS, I have tried to
>> re
Michael van Elst a écrit :
> On Fri, Feb 05, 2021 at 09:03:28AM +0100, BERTRAND Joël wrote:
>> LUN0 Storage /dev/dk6 Auto
>>
>> I can change dk6 by rdk6, but it's not a solution to fix issue with
>> iscsid, when NetBSD initiator tries to use a iSCSI target
RVP a écrit :
> On Thu, 4 Feb 2021, Michael van Elst wrote:
>
>> r...@sdf.org (RVP) writes:
>>
>>> Look at the `enabled' and `ec_enabled' capabilities. Most of them are
>>> off. Not sure if they make much of a difference...
>>
>> The capabilities that aren't 'enabled' by default aren't tested
>
>>
>> That should never happen. Can you verify that /dev/null is a device
>> and not a file ?
Of course :
legendre:[/dev] > ls -l null
crw-rw-rw- 1 root wheel 2, 2 Feb 5 08:50 null
> Yes. That puzzled me too; and your idea would explain that speed
> difference.
RVP a écrit :
> On Thu, 4 Feb 2021, BERTRAND Joël wrote:
>
>> Michael van Elst a écrit :
>>> Over a real network with higher latencies than loopback the effect
>>> is much larger, especially for reading,
>>
>> Sure. But since Linux initiator can
Michael van Elst a écrit :
> Over a real network with higher latencies than loopback the effect
> is much larger, especially for reading,
Sure. But since Linux initiator can reach more than 100 MBps, NetBSD
should obtain a throughout grater than 10 MBps with the same target...
I
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA512
Greg Troxel a écrit :
>
> BERTRAND Joël writes:
>
>> I have tried to mount on NAS a NFS volume exported by NetBSD.
>> From NAS, dd if=/dev/zero of=test count=1000 bs=1M shows a
>> throughput to NetBSD server less t
RVP a écrit :
> Yes. Try tests 2 & 3 afterwards.
OK. Now NAS runs with 4GB. And iSCSI volume is mounted without log
option. Same results on 2 and 3. I have upgraded NAS firmware also and a
new information is available : "wait state" in CPU monitoring. This
parameter doesn't exceed 1.1%
RVP a écrit :
> On Wed, 3 Feb 2021, BERTRAND Joël wrote:
>
>> raid0 and dk0 (raid1) are local disks, dk5 is my qNAP NAS.
>
> Of course. You mentioned it was iSCSI.
>
>> legendre# dd if=/dev/zero of=/opt/bacula/test.dd count=100 bs=1m
>> 100+0 records in
>&g
RVP a écrit :
>> legendre# dd if=/dev/zero of=/opt/bacula/test.dd count=10 bs=100m
>> 10+0 records in
>> 10+0 records out
>> 1048576000 bytes transferred in 53.396 secs (19637725 bytes/sec)
>
> This is odd. How much of RAM do you have on the NetBSD client? And,
> how much disk space is free?
A
Paul Ripke a écrit :
>> legendre# dd if=/dev/zero of=/opt/bacula/test.dd count=10 bs=10m
>> 10+0 records in
>> 10+0 records out
>> 104857600 bytes transferred in 0.537 secs (195265549 bytes/sec)
>> legendre# dd if=/dev/zero of=/opt/bacula/test.dd count=10 bs=100m
>> 10+0 records in
>> 10+0 records
Michael van Elst a écrit :
> On Tue, Feb 02, 2021 at 03:55:10PM +0100, BERTRAND Joël wrote:
>> Michael van Elst a écrit :
>>> joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
>>>
>>>>But jumbo frames and Intel adapter don't increase N
Michael van Elst a écrit :
> joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
>
>> But jumbo frames and Intel adapter don't increase NAS throughput :
>> 204Mb 407Mb 611Mb 814Mb
>
> Where does this information come from?
RVP a écrit :
> On Tue, 2 Feb 2021, BERTRAND Joël wrote:
>
>> dd immediatly returns when is it followed by a pipe...
>>
>> legendre:[~] > dd if=/dev/zero bs=32k count=1 progress=3051 | nc -N
>> 192.168.12.2 9123
>> legendre:[~] >
>>
&g
RVP a écrit :
> On Tue, 2 Feb 2021, BERTRAND Joël wrote:
>
>> No, I have verified before my first message :
>>
>
> Can you do a pure network throughput like this:
>
> On the NetBSD side:
> $ PB=$((100*1000*1000/(32*1024)))
> $ dd if=/dev/zero bs=32k count
RVP a écrit :
> On Tue, 2 Feb 2021, BERTRAND Joël wrote:
>
>>> 1. Are ethernet cards on either end gigabit adapters?
>>
>> Yes.
>>
>>> 2. Are the cards configured as such by their respective OSes?
>>> (use ifconfig -v ifname)
>>
&g
RVP a écrit :
> BERTRAND Joel wrote:
>
>> Now jumbo frames are enabled
>> ...
>> With old Realtek and MTU 1500, throughput was about 10 Mbytes/s.
>> With a new Intel adapter and jumbo frames, I obtain the same result
>> ...
>> I suppose there is somewhere a bottleneck, but where ?
>
> 1. Are
Hello,
Now jumbo frames are enabled :
23:27:55.227343 IP legendre.systella.fr.58386 >
euclide.systella.fr.iscsi-target: Flags [.], seq 3959352:3968300, ack
2593, win 4438, options [nop,nop,TS val 192 ecr 896198099], length 8948
23:27:55.227350 IP legendre.systella.fr.58386 >
Hello,
Now jumbo frames are enabled :
23:27:55.227343 IP legendre.systella.fr.58386 >
euclide.systella.fr.iscsi-target: Flags [.], seq 3959352:3968300, ack
2593, win 4438, options [nop,nop,TS val 192 ecr 896198099], length 8948
23:27:55.227350 IP legendre.systella.fr.58386 >
Michael van Elst a écrit :
> joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
>
>> I will try to restart iscsid but I'm pretty sure this system was
>> rebooted with new mtu in /etc/ifconfig.wm0.
>
> iscsid doesn't really allow a sane restart. Existing connections stay
>
Michael van Elst a écrit :
> joel.bertr...@systella.fr (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:
>
>> Of course, I have reconfigured all interfaces, and wm0's mtu is set to
>> 9000 :
>> legendre# ifconfig wm0
>> wm0: flags=0x8843 mtu 9000
>> ...
>
>> On qNAP, I have set also mtu to
Hello,
I'm not sure you remember I have tried to use a few weeks ago a qNAP
NAS (iSCSI) with a 9.1 NetBSD server without success as re driver panics
when mtu is greater than 1500 bytes.
This morning, I have replaced this old PCI Realtek adapter by a new one
(dual Gbe,
> FWIW, I had the same experience with file servers. Seagate comes last
> when I have to order the list of manufacturers from which to buy.
> Western Digital, it depends on the series---but if a disk is bad,
> it is bad from the very beginning (unusable on arrival). I had good
> experience with
Riccardo Mottola a écrit :
> Then this is the data for the third day (each time I did a power-off
> reboot, so it is not continuous operation, I shut down the laptop at night)
>
> SMART supported, SMART enabled
> id value thresh crit collect reliability description raw
> 1 60
Rocky Hotas a écrit :
> Hello!
> Consider a NetBSD 9.0 (release) system using both npf and altqd. This
> machine has two NICs and it is a gateway. First NIC is connected to a
> LAN, with multiple hosts, and second NIC is connected to the modem.
> With npf, the following is applied:
>
> map
Jonathan A. Kollasch a écrit :
> On Wed, Oct 21, 2020 at 11:47:41AM +0200, BERTRAND Joël wrote:
>> Hello,
>>
>> As re(4) doesn't run as expected with jumbo frames enabled, I am
>> considering changing my network card. I would like to know if the
>> i225-
Hello,
As re(4) doesn't run as expected with jumbo frames enabled, I am
considering changing my network card. I would like to know if the
i225-LM chipset is supported by NetBSD (9). I have seen that some newer
10 Gbe are supported but no information about i225. Of course, with
1 - 100 of 221 matches
Mail list logo