[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Changed in: linux (Ubuntu) Assignee: Dan Streetman (ddstreet) => (unassigned) ** Changed in: linux (Ubuntu Xenial) Assignee: Dan Streetman (ddstreet) => (unassigned) ** Changed in: linux (Ubuntu Yakkety) Assignee: Dan Streetman (ddstreet) => (unassigned) -- You received this

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Still not solved. Bug happens on Fresh install of Kubuntu 21.04 with reccomended HDD distribution on modern Lapotp (Ryzen5, 5500U). And on older Laptop (~2014) with Ubuntu 20.04 & 21.04, Kubuntu 21.04 and Lubuntu 20.04 & 20.10 & 21.04. (experienced often, sometimes every few hours) Kswapd0

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Still not solved. Linux 5.0.0-29-generic #31-Ubuntu SMP Thu Sep 12 13:05:32 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux This system has i5-9600K and 16 GB RAM, no swap. This happens everytime I run a VirtualbBox VM. The VM has got 4 GB RAM. I updated my VMs to current default settings for Windows

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Tags added: cscc -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux: Confirmed Status in linux package in Ubuntu: Fix Released

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Recently got a new laptop with a fresh install of Ubuntu 18.04 and now updated to kernel 4.19.21-041921-generic. It still happens even with 16 GB of memory and 4GB more in swap on SSD. What is more dangerous is now that laptop has hyperthreading it goes absolutely crazy and heats up insanely. At

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Bug watch added: Linux Kernel Bug Tracker #110501 https://bugzilla.kernel.org/show_bug.cgi?id=110501 -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Launchpad has imported 55 comments from the remote bug at https://bugzilla.kernel.org/show_bug.cgi?id=65201. If you reply to an imported comment from within Launchpad, your comment will be sent to the remote bug automatically. Read more about Launchpad's inter-bugtracker facilities at

Re: [Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Sorry ! Le jeu. 26 oct. 2017 à 14:55, Dan Streetman a écrit : > Mathieu, > > I'm not mailing you, this is a public bug report, you subscribed > yourself to this bug: > > 2017-01-26 10:14:29 Mathieu Perona bug added > subscriber Mathieu

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Mathieu, I'm not mailing you, this is a public bug report, you subscribed yourself to this bug: 2017-01-26 10:14:29 Mathieu Perona bug added subscriber Mathieu Perona -- You received this bug notification because you are a member of Kernel Packages, which is subscribed

Re: [Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Dear Dan, I am not sure you are mailing the right person. Anyway, the issue still arises when copying large files from a FAT drive to an EXT one. kswapd uses all available CPU power (but leaves much of the RAM unused) and copy throughput declines. Anyway, I solved the problem by transferring my

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

this bug is fix released. please open a new bug. note that you may just have been out of memory. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

8 months on and one of my systems is exhibiting what would appear to be the same bug... it was running Ubuntu 17.04 happily and just got upgraded to 17.10 with today's updates. (Yeah... upgrade, not reinstall... not enough time to re-download all the Insync files!) These were the first lines of

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

As a comment to those expecting that disabling swap will prevent kswapd from doing anything, that's incorrect. kswapd also is responsible for clearing out the page cache, so even with swap disabled you'll still see it doing work, especially during heavy IO that uses the page cache. For example,

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

As a complement to my previous comment: both computers have a significant amount of RAM (4 and 8 Go respectively) and the swap partition is shown as not used by the system monitor. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

As of 2017-01-26, I experience this bug on two 16.10 boxes. This kswap0d behavior is 100% reproductible when I copy large files (more than c. 500 Mo) from or to a NTFS hard drive. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This bug is fixed released already, any new problems should be opened in a new bug. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Running 4.8.13-100.fc23.i686+PAE, no desktop, swapon and swapoff, swappiness 0, 60, and 100. kswapd0 usage high while reading from /dev/sda (not mounted, internal SSD with 500+MB/s read). After stop reading, kswapd0 usage is gone. No Problem when reading from USB-HDD. Problem with high-speed

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Running Ubuntu 16.10 Yakkety. Old 4.4.0-45-generic kernel works nicely. All the new 4.8.0 kernels eventually go berzerk with kswapd0, just today the newest 4.8.0-32-generic. Normal usage, just a couple of terminals, Chromium, Nautilus windows and Evince PDF documents open. -- You received this

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

> I can see it every now and then with Yakkety and linux 4.8.0-27. > Can you advice any action? what do you mean by "every now and then"? you mean kswapd runs at 100% for a short time, occasionally? that's normal. > kswapd0 no longer takes 100% CPU, but it still emerges to the top of the list

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This bug was fixed in the package linux - 4.8.0-30.32 --- linux (4.8.0-30.32) yakkety; urgency=low * CVE-2016-8655 (LP: #1646318) - packet: fix race condition in packet_set_ring -- Brad Figg Thu, 01 Dec 2016 08:02:53 -0800 ** Changed in: linux

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Following this thread I had the same issue, running stock 16.04 (xenial) with kernel 4.4.0-38. I have upgraded the kernel to 4.8.10-040810 and the end result is the same but symptoms are a bit different: note: 1GB of RAM, no swap at all (old kernel) with 50% of RAM in buffers / cache, kswapd0

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

> Dan Streetman (ddstreet) wrote on 2016-10-01: #127 > > The patch series that fixes this is included in yakkety > (if anyone reproduces this on a yakkety kernel, please let me know), I can see it every now and then with Yakkety and linux 4.8.0-27. Can you advice any action? $ uname

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This bug was fixed in the package linux - 4.8.0-27.29 --- linux (4.8.0-27.29) yakkety; urgency=low [ Seth Forshee ] * Release Tracking Bug - LP: #1635377 * proc_keys_show crash when reading /proc/keys (LP: #1634496) - SAUCE: KEYS: ensure xbuf is large enough to fix

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This bug was fixed in the package linux - 4.8.0-27.29 --- linux (4.8.0-27.29) yakkety; urgency=low [ Seth Forshee ] * Release Tracking Bug - LP: #1635377 * proc_keys_show crash when reading /proc/keys (LP: #1634496) - SAUCE: KEYS: ensure xbuf is large enough to fix

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

After upgrading to 4.4.0-45 from 4.4.0-21 the issue seems to have gone away. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux:

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I have verified that the bug is fixed on 4.8.0-26.28 (yakkety), 4.4.0-43.63 (xenial) and 4.4.0-45.66 (xenial). Doing the same on 4.4.0-42.62 (xenial) reproduced the bug. All tests done on EC2 t2.small. ** Tags removed: verification-needed-yakkety ** Tags added: verification-done-yakkety -- You

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

If the verification apply also on 16.04, it does fix the issue. We had a server that triggered the bug at least once a day (I suspect unattended-upgrade run every morning to trigger it). Since the upgrade - 2 days and half ago - the server had no issue. -- You received this bug notification

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

The fix is already released in 16.04, make sure you have updated to linux-image 4.4.0-43.63 or later. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Will we see this fix make it to 16.04 LTS? -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux: Unknown Status in linux package in

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This bug is awaiting verification that the kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed- yakkety' to 'verification-done-yakkety'. If verification is not done by 5 working days

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This bug was fixed in the package linux - 4.4.0-43.63 --- linux (4.4.0-43.63) xenial; urgency=low [ Seth Forshee ] * Release Tracking Bug - LP: #1632375 * kswapd0 100% CPU usage (LP: #1518457) - SAUCE: (no-up) If zone is so small that watermarks are the same, stop

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Changed in: linux (Ubuntu Yakkety) Status: Fix Committed => Invalid -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux:

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Changed in: linux (Ubuntu Yakkety) Status: Confirmed => Fix Committed -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux:

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Also affects: linux (Ubuntu Xenial) Importance: Undecided Status: New ** Changed in: linux (Ubuntu Xenial) Status: New => Fix Committed ** Changed in: linux (Ubuntu Xenial) Importance: Undecided => High ** Changed in: linux (Ubuntu Xenial) Assignee: (unassigned) =>

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

On review of the patch series, it's simply too large and complex to backport for this situation; it makes, and depends on, a rather large amount of change to the mm subsystem, and there are easier and smaller ways to work around this bug in the xenial kernel. Specifically, a comparison of the Xen

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

The patch series that fixes this is included in yakkety (if anyone reproduces this on a yakkety kernel, please let me know), so this only needs fixing in xenial. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

The problem is a bit complex. The Xen hypervisor uses memory ballooning, to control how many memory pages the guest can use. The kernel enumerates its e820 memory at boot, and since it's only 1G in this case, it all gets placed into the DMA32 zone. Then later during boot when the Xen balloon

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I have the same issue on 16.04 -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux: Unknown Status in linux package in Ubuntu:

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Thanks #123 (as easy as?) works for me as a workaround. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux: Unknown Status in linux

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

>From man 7 udev: The udev rules are read from the files located in the system rules directory /lib/udev/rules.d, the volatile runtime directory /run/udev/rules.d and the local administration directory /etc/udev/rules.d. All rules files are collectively sorted and processed in lexical order,

Re: [Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Did you try this from Rasmussen up above? sudo touch /etc/udev/rules.d/40-vm-hotadd.rules reboot That fixed it for me on EC2 On Saturday, 3 September 2016, Andy Robertson wrote: > All of my t2.micro & nano instances are affected by this in AWS EC2 > after upgrading

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1518457/comments/69 Seems to have resolved all this issues on AWS t2.micro instances. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

All of my t2.micro & nano instances are affected by this in AWS EC2 after upgrading to Ubuntu16. doing "echo 1 > /proc/sys/vm/drop_caches" (also tried echo 3) works for a short period of time, but it comes back within a few minutes. I moved a couple instances over to f1.micro on GCP / GCE (1

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I wrote a tiny batch script to reliably reproduce the bug. It mounts a tmpfs filesystem and writes a file that fills 98% of the currently available memory. You can also pass it a custom percentage, like: ./fillmem.sh 95 <95% is hit and miss on a newly launched instance. 98% (the default) has

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

The original description says "kswapd0 falls into a busy loop and spins on 100% CPU usage indefinitely". But I think, while the effect may be similar, the actual behavior is a bit different. I think what is happening is that kswapd is accessing pages of memory that are causing the hypervisor

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

To add - these servers are all built on the official Ubuntu Amazon EC2 AMIs of the 'ebs-ssd' variety. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

We have been seeing this issue intermittently on a set of servers that were running Ubuntu 15.10 and then 16.04. After overriding that udev vm hotadd rule as suggested above a couple weeks ago, the issue has yet to return (not a conclusive result, but so far so good). -- You received this bug

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I have run into this issue when using the goofys s3 fuse filesystem (https://github.com/kahing/goofys) on a t2.small instances when copying large files (which causes many memory buffers to be allocated). I think anything that stresses the memory subsystem will be able to trigger it. -- You

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I've tried this on t1.micro (PV) and t2.micro (HVM) instances in eu-west-1. To reproduce, I used the following two commands: sudo apt install docker.io sudo docker run -p 80:8080 cptactionhank/atlassian-jira The startup should work, but navigate to http://instanceaddress/ and choose "I'll set it

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Is this known to affect paravirtualized instances, or is it restricted to hvm? Can anyone tell me what conditions I need to create this in a fresh instance? I'll spin up a PV t2.nano and see if I can reproduce it there. -- You received this bug notification because you are a member of Kernel

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Can this workaround please be added to the official EC2 images? EC2 cannot hot swap CPU or memory from what I know. Having this workaround built in would mean not having to reboot every newly launched instance. -- You received this bug notification because you are a member of Kernel Packages,

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

The suggested workaround works for me also on AWS instances with 15.10: sudo touch /etc/udev/rules.d/40-vm-hotadd.rules reboot Been stable now for over a week. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Is there a fix for this that doesn't require a reboot / something I could add to an ec2 instance's user_data? -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100%

Re: [Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Thank you so much Rasmus! Your solution worked for me: sudo touch /etc/udev/rules.d/40-vm-hotadd.rules reboot I could always trigger the CPU usage bug with this: stress --cpu 8 --io 4 --vm 7 --vm-bytes 128M --vm-hang 3 --timeout 60s If running it once didn't work, a second run would do it. Now

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I had this issue too on AWS. In my case, it was the udev rule for vm-hotadd and the fix as mentioned previously basically came down to "touch /etc/udev/rules.d/40-vm- hotadd.rules" which effectively disables the /lib/udev/rules.d/40-vm- hotadd.rules file (after a reboot). The udev rule basically

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I'm also facing the kswap0 99% CPU issue. Typically, I notice it start minutes after boot time, but restarting the MongoDB process on the server will temporarily fix it, however the process will usually pop up again randomly. I used to run test instances of MongoDB on AWS t2.micros with no issues

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I can confirm that this issue also exist on AWS c4.large (vCPU 2, mem 3,75 GiB). $ uname -a Linux server 4.4.0-22-generic #39-Ubuntu SMP Thu May 5 16:53:32 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux $ free -m totalusedfree shared buff/cache available Mem:

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Is the ability to repro a hold-up on this issue? I can spend time to provide STRs on an EC2 instance using the latest official 16.04 image, but I don't want to go through the effort if repro isn't really a hold- up. -- You received this bug notification because you are a member of Kernel

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Whoops, it does seem to happen on 4.6.1-2, although the condition are different. It seems, does anyone have a sure fire repro case? -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I've fixed this in Arch Linux by moving to the 4.6.1-2-ARCH kernel, when previously on the 4.5.? kernel. This problem also doesn't occur in either the 4.0.7-2 or the 3.16-2 kernels for me at least. I hear this is happening mostly on the 4.4.0-* kernel, which doesn't seem to be an option in the

Re: [Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I've had the issue mostly when running with no swap. I added 1GB swap file and it fixed it on the machine with less memory usage, but the machine with the database (using more memory most of the time) still has the bug occur about once a day. Ubuntu 16.04 for both, not happening on 14.04. Sent

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I face the same issue, running a t2.micro (1 GB) for a Nginx/Ruby application with really low demand. The kswapd0 process takes the CPU to 100% and the overall system performance is downgraded. Linux server 4.4.0-22-generic #40-Ubuntu SMP Thu May 12 22:03:46 UTC 2016 x86_64 x86_64 x86_64

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Actually, this is even a problem with no active swap partition. What is the actual problem here? Is kswapd0 just running for no reason? -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Nope, setting it to performance doesn't seems to help. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in Linux: Unknown Status in linux

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

They seem to be set to "powersave", which is kinda ironic. I've set them to performance and will report back later. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

OOI, does this fix this? | for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor; do sudo sh -c "echo performance > $i"; done If so, was the scaling governor set to "ondemand" by any chance? -- You received this bug notification because you are a member of Kernel Packages, which is

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I can confirm that setting vm.min_free_kbytes=67584 on my 2gb chromebook does not work for me (https://i.imgur.com/I7vEE5C.png) After restarting and running heavy processes, kswapd0 still uses 100% cpu until I reboot or run this follow very unfortunate script. #!/bin/bash if [ "$EUID" -ne 0 ];

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Bug watch added: Linux Kernel Bug Tracker #65201 http://bugzilla.kernel.org/show_bug.cgi?id=65201 ** Also affects: linux via http://bugzilla.kernel.org/show_bug.cgi?id=65201 Importance: Unknown Status: Unknown -- You received this bug notification because you are a member of

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I can confirm after after 6 days uptime: my hotfix (echo "vm.min_free_kbytes=67584" > /etc/sysctl.d/60-workaround-kswapd- allcpu.conf) still works. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I can the following hotfix works for me for several days on a 2GB Ram system: echo "vm.min_free_kbytes=67584" > /etc/sysctl.d/60-workaround-kswapd- allcpu.conf after that: reboot. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I last commented when I was on 15.10, but was just hit by this on 16.04. Again, EC2 t2.micro instance. $ uname -a Linux ip-172-31-45-223 4.4.0-22-generic #40-Ubuntu SMP Thu May 12 22:03:46 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux $ top top - 21:32:32 up 6 days, 20 min, 1 user, load average:

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Fresh install of 16.04 on EC2 Nano instance, and kswapd0 takes most of the CPU when running a job with high CPU and high IO. I've resorted to running the following command every minute as a cron task: # m hdom mon dow command *****echo 3 >

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Same issue here, uname -a 4.4.0-22-generic #39-Ubuntu SMP Thu May 5 16:53:32 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux free -m totalusedfree shared buff/cache available Mem: 1836 681608 12 1591722 Swap:

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I'm also seeing this on 16.04 on an AWS nano (~0.5GB RAM). More than happy to help troubleshoot this if people let me know what info is needed. Here's some basic info from my machine: $ uname -a 4.4.0-22-generic #39-Ubuntu SMP Thu May 5 16:53:32 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux $ free

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Confirm. Linux impulse-X55VD 4.6.0-040600rc6-generic #201605012031 SMP Mon May 2 00:33:26 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I can see this bug on a system recently upgraded from Ubuntu 15.04 to 16.04. I did not see this behaviour before upgrading. The system is an Intel NUC Desktop with 8 GB RAM and kswapd0 completely locks up the system after a while. -- You received this bug notification because you are a member

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

In the earliest linked report of this bug the deadlock occured also with 8GB RAM (and still the case in 15.10). Will test 16.04 later when it stabilizes. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I can confirm this bug is only triggered when the machine got 2-3GB RAM or less. I got two identical machines running Ubuntu 16.04. One got 8Gb of RAM and on this machine kswapd0 doesn't deadlock at 100% CPU Usage. On my 2GB RAM machine the issue is worse than under Ubuntu 15.10 -- You

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I can also confirm the bug ist still present in Xubuntu 16.04 LTS desktop 4.4.0-21-generic #37-Ubuntu SMP Mon Apr 18 18:33:37 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

confirmed on released version of 16.04 LTS desktop # uname -a Linux laptop 4.4.0-21-generic #37-Ubuntu SMP Mon Apr 18 18:33:37 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

After reading 82 comments, I'm not sure if this is a kernel or udev (or other) bug. Any clues if anyone's working on this in relevant upstreams? -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This is also affecting Ubuntu 15.10 Kernel 4.2.0-35-generic I have 700MB free RAM 400 MB Cached and kswapd0 is taking more than 99% of the CPU. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

This has also been affecting me on a t2.micro EC2 instance with Ubuntu 15.10, most recently occurred with: 4.2.0-30-generic #36-Ubuntu SMP Fri Feb 26 00:58:07 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux For me it often triggers when installing updates (probably kernel ones in particular). Otherwise

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Alexander, please note that if a kernel process name contains "swap" as a substring, it does not immediately mean that this process exclusively does process memory swap-in/swap-out. kswapd is a kernel process name for an important piece of memory management subsystem: it frees pages by flushing

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I don't know, if the following comment be relevant to this particular bug, but here it is: * If there is no swap, the kernel should not try to swap. As simple as this. If there is no swap file or partition, and there is kswapd0 in top, if even it doesn't consume 100% of CPU, it is a bug.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

The workaround fixes the issue in Xenial Xerus (development branch) as well. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in linux

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I confirm that the bug is present on Amazon t2.nano instance with Ubuntu 15.10, kernel 4.2.0-30-generic, and can only be worked around by commenting out line 2 in /lib/udev/rules.d/40-vm-hotadd.rules. -- You received this bug notification because you are a member of Kernel Packages, which is

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I'm seeing this issue in Ubuntu Xenial Xerus (development branch). -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1518457 Title: kswapd0 100% CPU usage Status in linux package in

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

As part of my workaround/fix I downgraded udev and upgraded RAM from 3GB to 8GB on my homeserver. Now I am experiencing the following which can't be normal either: top - 13:50:48 up 1 day, 19:29, 1 user, load average: 0,11, 0,15, 0,14 tasks: 200 total, 1 running, 198 sleeping, 0 stopped,

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

One more note to anyone else trying to debug this: I can reproduce quite reliably by copying a 3GiB file from S3 onto a gp2 EBS volume using `aws s3 cp`. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

** Changed in: linux (Ubuntu) Status: In Progress => Confirmed ** Changed in: linux (Ubuntu) Assignee: Joseph Salisbury (jsalisbury) => (unassigned) -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I did some experimentation, and I can reproduce @oystein-gisnas's result that nuking that file from `/lib/udev/rules.d/` and rebooting fixes the issue. However, removing that file and restarting udev does *not* seem to fix the issue. So I suspect the problem is not with udev, but rather with some

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Confirmed Nelson Elhage's workaround: copy /lib/udev/rules.d/40-vm- hotadd.rules to /etc/udev/rules.d/ and comment out line 2 and reboot. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Some further debugging: On my t2.micro test case, the machine comes up with 9 memory devices, the last of which is offline at boot. Bringing that device online by hand (with the udev rules disabled) triggers the bug. # echo online > /sys/devices/system/memory/memory8/state So something about

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

I've bisected systemd and found the commit that triggers the bug. http://bazaar.launchpad.net/~thopiekar/systemd/systemd-packaging-ubuntu- wily/revision/1706 seems to be the one. The commit is a bugfix that effectively enables hotadd for Xen. That can explain why more or less only Ubuntu 15.10 is

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Could someone with good udev/kernel knowledge try to debug what's going wrong with this hotadd? I've tried to run systemd-udevd in debug mode, but it didn't show anything of interest. https://wiki.ubuntu.com/DebuggingUdev is outdated, and I don't know how to go on with debugging. -- You received

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

A workaround that seems to work for me (and one that doesn't involve dropping caches periodically) is to downgrade udev to 219-7ubuntu6 (as suggested by Øystein above). On 15.10 wily, add vivid-updates to your apt sources to be downgrade to this version of udev. I noticed this bug is more likely

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

As an addendum, is there a quick-fix for this? Meaning: can I revert to kernel 3.xsomething easily in Ubuntu? Or are there all types of unwelcome side effects to dropping from new-hotness to old-coldness, kernel-wise? signed, pro linux sysadmin for many years, back in the 2000's, now only

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Marten Not a fix, but a workaround. (Well, of course every server is different - but works good for me for now!) Create in /etc/cron.hourly/ something like kswapd. chmod +x kswapd Then into it drop: echo 1 > /proc/sys/vm/drop_caches You'll get a lot of [649613.095072] kswapd (29670):

[Kernel-packages] [Bug 1518457] Re: kswapd0 100% CPU usage

Egads, the thick plottens... turns out I have some type of error in my system. In particular: marten@MacMini-New:/usr/local/bin$ cat /proc/meminfo |grep MemTotal MemTotal: 859916 kB Yes you read that right, 860Mb. That's clearly incorrect. I'll go and see if I can put in something

  1   2   >