swalker has quit [Read error: Connection reset by peer]
swalker has joined #openwrt-devel
Staz97646298265307 has quit [Quit: The Lounge - https://thelounge.chat]
<schmars[m]> nbd: another: https://gist.github.com/pktpls/da28efa7fd957bfaaea459785a2a05af - again involves switching between 2ghz and 5ghz
ScrewDriver1337 has joined #openwrt-devel
rua has quit [Quit: Leaving.]
minimal has quit [Quit: Leaving]
rmilecki has quit [Quit: Konversation terminated!]
rmilecki has joined #openwrt-devel
noltari has quit [Quit: Bye ~ Happy Hacking!]
noltari has joined #openwrt-devel
valku has joined #openwrt-devel
radxanaoki has quit [Quit: radxanaoki]
nixuser has quit [Read error: Connection reset by peer]
nixuser has joined #openwrt-devel
<swalker> updated openwrt/upstream, https://sdwalker.github.io/uscan/index.html
valku has quit [Quit: valku]
goliath has joined #openwrt-devel
sorinello has joined #openwrt-devel
[Pokey] has quit [Ping timeout: 480 seconds]
raggi has joined #openwrt-devel
<nbd> schmars[m]: so this is with mt76.git manually updated to the latest version, not just the version used in latest openwrt master, right?
rua has joined #openwrt-devel
raggi has quit [Quit: upgrades]
raggi has joined #openwrt-devel
rua has quit [Quit: Leaving.]
zer0def has quit [Quit: zer0def]
zer0def has joined #openwrt-devel
radxanaoki has joined #openwrt-devel
<schmars[m]> nbd: yep, built an imagebuilder myself and plugged that into ny tooling
<schmars[m]> i really should activate phy1 debugging too i guess
radxanaoki has quit [Quit: radxanaoki]
<nbd> schmars[m]: what kind of device is this?
<schmars[m]> the two from the past days are zyxel nwa55axe, but since we've picked up debugging recently i've also crashed cudy x6 (that's mt7621 too)
<schmars[m]> the crashing devices are in public places where there's lots of coming and going, and also e.g. buses driving past slowlt
<schmars[m]> slowly
<nbd> so when it tries to recover, there is a kernel task that's hanging?
<nbd> or what's the main symptom?
<schmars[m]> wifi is "dead", and cpu load is elevated. the cpu load characteristics have been changing with the recovery commits, now the latest had only slightly elevated load while previously it was flat 9.0 load
<schmars[m]> i will have to check the task list later today when it crashes next time
<nbd> next time that happens, can you please do echo t > /proc/sysrq-trigger
<schmars[m]> ok will do
<schmars[m]> nbd: ah wait i forgot to reboot the device yesterday, it's still running in its crashed state. i've added sysrq to the gist: https://gist.github.com/pktpls/da28efa7fd957bfaaea459785a2a05af
<schmars[m]> if you want i can organize access, it's got public ipv6
<nbd> yes, i'd like to take a look
<schmars[m]> ok one sec, i'll just open up the ports on the gateways
<schmars[m]> pm me your ssh key
<KGB-0> https://tests.reproducible-builds.org/openwrt/openwrt_bcm47xx.html has been updated. (100.0% images and 100.0% packages reproducible in our current test framework.)
<T-Bone> nbd: hi, btw if you replied to saturday's email I haven't seen it: my VPS provider is kaput at the moment (whole DC offline due to cooling failure, so it's likely gonna take a while)
T-Bone is now known as f00b4r0
<nbd> f00b4r0: i did receive it, but wasn't able to look into it yet. just got back from vacation yesterday
<nbd> f00b4r0: what was the last mt76.git version that you tested?
<f00b4r0> oh i see, no worries. Sounds similar to what schmars experienced
<f00b4r0> yes
<f00b4r0> basically the MCU restart kicked in and then the kernel collapsed
rsalvaterra has quit []
rsalvaterra has joined #openwrt-devel
<owrt-images-builds> Build [#365](https://buildbot.openwrt.org/images/#/builders/97/builds/365) of `master_ixp4xx/generic` failed.
rua has joined #openwrt-devel
<mrkiko> anyone has a board where the "u-boot system environment" feature is used? i.e.: fw_printsys and friends? Was curious on how it's meant to be used and how vendors actually use it
<f00b4r0> looks like I'll have to spawn a replacement MX, last status update no longer provides "ETA to next update" ;P
<stintel> Mangix: pong
<stintel> is it too much to expect 200Mbps over IPsec VPN on a GL-iNet Beryl AX (Filogic)?
gromero has joined #openwrt-devel
<stintel> stopped qosify, tried packet_steering 0 and 1, flow_offloading and flow_offloading_hw 0 and 1, it seems to be completely impossible to stream even a 70Mbps video
<stintel> 47.98% [kernel] [k] default_idle_call
<stintel> 6.28% [kernel] [k] finish_task_switch.isra.0
<stintel> perf top makes me none the wiser
<stintel> load avg is 1
<stintel> sirq ~20%
<stintel> which for a 2 CPU system should also not be a bottleneck?
<f00b4r0> unless all the work happens to be pinned to the same core
<stintel> 76: 80500157 0 GICv3 229 Level 15100000.ethernet
<stintel> 77: 86815950 0 GICv3 230 Level 15100000.ethernet
<stintel> interrupts seem to both go to same core
<f00b4r0> there you go
<stintel> not sure why that is, I would expect it to be spread
<stintel> # /etc/init.d/packet_steering restart
<stintel> pid 318's current affinity list: 0-1
<stintel> pid 318's new affinity list: 0
<stintel> pid 319's current affinity list: 0-1
<stintel> pid 319's new affinity list: 0
<f00b4r0> spreading IRQs is a tricky matter. Results are very architecturally dependent (wrt cache being shared between cores or not)
<stintel> with packet_steering 0 the affinity list is 0-1, with packet_steering 1 affinity list is 0
<stintel> but in both situations IRQs end up on core 0
<stintel> now those PIDs mentioned by the packet steering init script are kthreads napi/mtk_eth-5 napi/mtk_eth-6
<stintel> not sure what is going on
<stintel> pretty sure my 1st gen beryl handled all this fine
<stintel> and that's ramips/mt7621
ScrewDriver1337 has quit [Ping timeout: 480 seconds]
minimal has joined #openwrt-devel
tohojo has joined #openwrt-devel
valku has joined #openwrt-devel
<owrt-images-builds> Build [#363](https://buildbot.openwrt.org/images/#/builders/138/builds/363) of `master_bcm27xx/bcm2708` failed.
goliath has quit [Quit: SIGSEGV]
rua has quit [Quit: Leaving.]
ScrewDriver1337 has joined #openwrt-devel
valku has quit [Ping timeout: 480 seconds]
rua has joined #openwrt-devel
valku has joined #openwrt-devel
valku has quit [Quit: valku]
<Mangix> stintel: I think I wanted to ask if the M300 had switch controlled LEDs
goliath has joined #openwrt-devel
Staz97646298265307 has joined #openwrt-devel
<owrt-images-builds> Build [#358](https://buildbot.openwrt.org/images/#/builders/205/builds/358) of `master_mpc85xx/p1020` failed.
AtomiclyCursed2 has quit [Quit: ZNC 1.9.1 - https://znc.in]
ScrewDriver1337 has quit [Ping timeout: 480 seconds]
AtomiclyCursed has joined #openwrt-devel
danieli0 has joined #openwrt-devel
tohojo_ has joined #openwrt-devel
rsalvaterra_ has joined #openwrt-devel
stintel_ has joined #openwrt-devel
tomh- has joined #openwrt-devel
tohojo has quit [reticulum.oftc.net helix.oftc.net]
rsalvaterra has quit [reticulum.oftc.net helix.oftc.net]
zer0def has quit [reticulum.oftc.net helix.oftc.net]
goliath has quit [reticulum.oftc.net helix.oftc.net]
rmilecki has quit [reticulum.oftc.net helix.oftc.net]
Habbie has quit [reticulum.oftc.net helix.oftc.net]
GNUmoon has quit [reticulum.oftc.net helix.oftc.net]
KGB-0 has quit [reticulum.oftc.net helix.oftc.net]
danieli has quit [reticulum.oftc.net helix.oftc.net]
AndyCap has quit [reticulum.oftc.net helix.oftc.net]
tom- has quit [reticulum.oftc.net helix.oftc.net]
aparcar[m] has quit [reticulum.oftc.net helix.oftc.net]
PaulFertser has quit [reticulum.oftc.net helix.oftc.net]
stintel has quit [reticulum.oftc.net helix.oftc.net]
oliv3r[m] has quit [reticulum.oftc.net helix.oftc.net]
ynezz has quit [reticulum.oftc.net helix.oftc.net]
danieli0 is now known as danieli
PaulFertser_ has joined #openwrt-devel
goliath has joined #openwrt-devel
rsalvaterra has joined #openwrt-devel
zer0def has joined #openwrt-devel
AndyCap has joined #openwrt-devel
Habbie has joined #openwrt-devel
rmilecki has joined #openwrt-devel
tom- has joined #openwrt-devel
GNUmoon has joined #openwrt-devel
aparcar[m] has joined #openwrt-devel
stintel has joined #openwrt-devel
oliv3r[m] has joined #openwrt-devel
KGB-0 has joined #openwrt-devel
aparcar[m] has quit [Ping timeout: 480 seconds]
rmilecki has quit [Read error: No route to host]
stintel has quit [Ping timeout: 480 seconds]
tom- has quit [Ping timeout: 480 seconds]
goliath has quit [Ping timeout: 480 seconds]
rsalvaterra has quit [Ping timeout: 480 seconds]
zer0def has quit [Ping timeout: 480 seconds]
tohojo_ is now known as tohojo
goliath has joined #openwrt-devel
zer0def has joined #openwrt-devel
ynezz has joined #openwrt-devel
ynezz is now known as Guest2298
aparcar[m] has joined #openwrt-devel
tohojo has quit [Remote host closed the connection]
tohojo has joined #openwrt-devel
goliath has quit [Quit: SIGSEGV]
PaulFertser_ is now known as PaulFertser
ScrewDriver1337 has joined #openwrt-devel
gch981213 has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
gch981213 has joined #openwrt-devel
sorinello has quit [Ping timeout: 480 seconds]
radxanaoki has joined #openwrt-devel