Re: [arch-general] Help diagnosing kworker 'bug'
Hi On Tue, Aug 5, 2014 at 4:37 PM, Oon-Ee Ng wrote: > Yesterday night I noticed (just before performing an update my conky > showing high continuous writing to root. iotop -Pa shows this:- > > Total DISK READ : 0.00 B/s | Total DISK WRITE : 8.93 M/s > Actual DISK READ: 0.00 B/s | Actual DISK WRITE: 11.06 M/s > PID PRIO USER DISK READ DISK WRITE SWAPIN IO>COMMAND > 112 be/4 root 0.00 B 64.91 M 0.00 % 24.34 % [kworker/u16:3] > 11936 be/4 root 0.00 B 0.00 B 0.00 % 0.06 % [kworker/1:1] > 28794 be/4 root 0.00 B 36.00 K 0.00 % 0.00 % [kworker/u16:1] > > This is after roughly 6-7 seconds, and 65 MB has already been written > by that kworker thread. How long this IO activity takes? Could it be some kind of automatic defragmentation or some other internal btrfs background optimization? A good idea is to check btrfs changelog for 3.16 kernel release. > > As I said, this was already happening before an upgrade. I ran the > upgrade anyway, which upgraded linux to 3.16-2, and still got the same > thing. Yes, I'm using [testing]. > > Any ideas on how to proceed? Next thing I'm going to try is > downgrading linux to 3.15, but I thought I'd post this here first in > case I don't make it back. 'perf' is a great and very powerful tool that allow to debug problems like this. Run '# perf top -g -p $PID' and it will show where the process spends *cpu cycles*. It should be enough to understand what kworker thread does. For all curious minds I highly recommend to read this tutorial https://perf.wiki.kernel.org/index.php/Tutorial
Re: [arch-general] Help diagnosing kworker 'bug'
On Wed, Aug 6, 2014 at 7:37 AM, Oon-Ee Ng wrote: > Any ideas on how to proceed? Next thing I'm going to try is > downgrading linux to 3.15, but I thought I'd post this here first in > case I don't make it back. And I made it back alive. 3.15.8-1 does not have the same problem. Also downgraded bbswitch to 0.8-14, nvidia t 340.24-3, linux-headers to 3.15.8-1, virtualbox-host-modules to 4.3.14-3, vhba-module to 20140629-5, and lirc-utils to 1:0.9.0-75. Should I open a bug report? I don't think I have sufficient detail, in particular because I don't know how to track down what caused that kworker process. My system is an i7 laptop, the hard disc partitions (including root) are btrfs formatted. Previous Arch Linux bbs posts regarding kworker I/O activity is not as serious as what I'm seeing and seemed to affect ext4. Again, suggestions are appreciated.
[arch-general] Help diagnosing kworker 'bug'
Yesterday night I noticed (just before performing an update my conky showing high continuous writing to root. iotop -Pa shows this:- Total DISK READ : 0.00 B/s | Total DISK WRITE : 8.93 M/s Actual DISK READ: 0.00 B/s | Actual DISK WRITE: 11.06 M/s PID PRIO USER DISK READ DISK WRITE SWAPIN IO>COMMAND 112 be/4 root 0.00 B 64.91 M 0.00 % 24.34 % [kworker/u16:3] 11936 be/4 root 0.00 B 0.00 B 0.00 % 0.06 % [kworker/1:1] 28794 be/4 root 0.00 B 36.00 K 0.00 % 0.00 % [kworker/u16:1] This is after roughly 6-7 seconds, and 65 MB has already been written by that kworker thread. As I said, this was already happening before an upgrade. I ran the upgrade anyway, which upgraded linux to 3.16-2, and still got the same thing. Yes, I'm using [testing]. Any ideas on how to proceed? Next thing I'm going to try is downgrading linux to 3.15, but I thought I'd post this here first in case I don't make it back.
[arch-general] Mailing list posting style (was: [aur-general] Compiz package naming)
Hi, Disclaimer: I'm trying to write this as friendly as possible, but I want to get the point across so please excuse slightly harsh wording and the length of the mail. Please understand that this mail is directed to all list members, not only those who participated in the thread on aur-general. It happens every now and then, but this thread is probably one of the worse ones. I know it's sometimes easy to forget, but a 16 level deep quote with 420+ lines of quoted content and about 6 lines of original content is not, by any stretch of imagination, okay. Please do not quote the entire thread in every reply and do not reply above the quote(s). A general rule of thumb is to quote only what's necessary to understand the reply. If you need context, please use bottom-posting or IMHO better yet interleaved quoting[1] (I also suggest to read the entire page) and limit your quote to as few lines as possible/necessary. Also feel free to summarise the original mails or write your reply in such a way that it can be understood without context which means that you can omit the quote entirely. [1] https://en.wikipedia.org/wiki/Posting_style#Interleaved_style Please also be aware that some mail clients will add line breaks after 80 characters and original text is normally wrapped after ~72 which means you get about 4 levels of quoting until text starts wrapping which makes it very hard to read. Generally, if your reply is shorter than the quoted message you might do something wrong. If you quote the entire message you likely do something wrong. If you quote the entire thread for 16 levels you *really* do something very wrong, no exception here, sorry. Also if you need any proof try to read this message[2] without reading the original messages directly (only read the quotes in the linked message). Note that the start of the thread is somewhere in the middle (you can search for "Hello AUR general & Compiz package maintainers") thanks to top/bottom/interleaved quoting styles being mixed. [2] https://mailman.archlinux.org/pipermail/aur-general/2014-August/029292.html I'm also sending this to arch-general as a reminder because I've seen a few topposters/fullquoters there as well. Let's please all work together here so something like this doesn't happen again. If you see this happening in a thread that you participate in, please speak up (early) and make sure your own reply breaks the chain. Thanks for your consideration, Florian signature.asc Description: OpenPGP digital signature
