[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2021-10-13 Thread Steve Langasek
The Precise Pangolin has reached end of life, so this bug will not be fixed for that release ** Changed in: linux (Ubuntu Precise) Status: Triaged => Won't Fix -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launch

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2014-06-26 Thread Jamie Strandboge
** Changed in: linux (Ubuntu Quantal) Status: Triaged => Won't Fix -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1064521 Title: Kernel I/O scheduling writes starving reads, local DoS To mana

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2014-05-19 Thread Ivan Baldo
And now what happens with Ubuntu 14.04? (yeah, too lazy myself to test, sorry) -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1064521 Title: Kernel I/O scheduling writes starving reads, local DoS To

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2013-11-28 Thread Christopher M. Penalver
** Tags added: bios-outdated-2.6.1 needs-upstream-testing regression- release -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1064521 Title: Kernel I/O scheduling writes starving reads, local DoS To

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-17 Thread Alexandre Kandalintsev
Disabling AIO and changing allocator to SLOB relaxed the problem. With other allocators like SLAB and SLUB I see no improvement. -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1064521 Title: Kernel I

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-12 Thread Joseph Salisbury
Thread on LKML: https://lkml.org/lkml/2012/10/11/177 ** Tags added: kernel-bug-exists-upstream kernel-da-key quantal ** Also affects: linux (Ubuntu Precise) Importance: Undecided Status: New ** Also affects: linux (Ubuntu Quantal) Importance: Medium Status: Confirmed ** Cha

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-12 Thread Ric Gamble
11:55 log file ** Attachment added: "11:55 log file" https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1064521/+attachment/3396240/+files/logfile_11_55_12_10_2012.log -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-12 Thread Ric Gamble
11:35 log file ** Attachment added: "11:35 log file" https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1064521/+attachment/3396239/+files/logfile_11_35_12_10_2012.log -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-12 Thread Ric Gamble
11:17 log file ** Attachment added: "11:17 log file" https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1064521/+attachment/3396238/+files/logfile_11_17_12_10_2012.log -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-12 Thread Ric Gamble
I have upgraded our Kernel to 3.6.1 (cat /proc/version output) Linux version 3.6.1-030601-generic (apw@gomeisa) (gcc version 4.6.3 (Ubuntu/Linaro 4.6.3-1ubuntu5) ) #201210071322 SMP Sun Oct 7 17:23:28 UTC 2012 And ran the DD test with the sql-test2.py script also running, the quantal kernel app

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Joseph Salisbury
** Changed in: linux (Ubuntu) Importance: Undecided => Medium -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1064521 Title: Kernel I/O scheduling writes starving reads, local DoS To manage notifi

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
Output of ( while /bin/true ; do date ; cat /proc/meminfo ; vmstat 1 2 ; echo " "; sleep 1 ; done ) > mylog files edited to show only data which matches previously attached log files File for run starting at 10:11 ** Attachment added: "10:11+ log file" https://bugs.launchpad.net/ubuntu/+sour

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
sql-test2.py log file output from run started 10:11 this morning ** Attachment added: "10:11 sql-test2.py log file" https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1064521/+attachment/3394572/+files/logfile_10_11_11_10_2012.log -- You received this bug notification because you are a mem

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
Output of ( while /bin/true ; do date ; cat /proc/meminfo ; vmstat 1 2 ; echo " "; sleep 1 ; done ) > mylog files edited to show only data which matches previously attached log files File for run starting at 10:46 ** Attachment added: "10:26+ log file" https://bugs.launchpad.net/ubuntu/+sou

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
Output of ( while /bin/true ; do date ; cat /proc/meminfo ; vmstat 1 2 ; echo " "; sleep 1 ; done ) > mylog files edited to show only data which matches previously attached log files File for run starting at 10:21 ** Attachment added: "10:21+ log file" https://bugs.launchpad.net/ubuntu/+sou

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
log file 2 ** Attachment added: "log2" https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1064521/+attachment/3394541/+files/logfile_10_21_11_10_2012.log -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
Please find attached log files generated by the sql-test2.py script attached above. These were generated while running "dd if=/dev/zero of=- bs=1M count=5 | dd if=- of=myfile bs=1M count=5" On the hardware described at the start of the bug with the deadline scheduler active. You can see

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
file attached here ** Attachment added: "updated sql-test2.py script" https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1064521/+attachment/3394456/+files/sql-test2.py -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bug

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Ric Gamble
Please find attached the updated sql-test2.py script It should be run in the same way as the previous one, however the output has been reformatted to show sql query execution time -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https:

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-11 Thread Alex Bligh
Easier way of replicating: dd if=/dev/zero of=- bs=1M count=5 | dd if=- of=myfile bs=1M count=5 (two dd's to prevent dd optimisation of /dev/zero writes), whilst running Ric's script (he's just about to upload a better version. -- You received this bug notification because you are a mem

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-10 Thread Ric Gamble
Please find attached sql-test.py. This script requires mysql to be installed on the test platform and to be run with sudo if the user is not root. It will create a database called test_db and a table called test in the local mySQL instance. It will then update and select from the test table ever

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-10 Thread Alex Bligh
This is related to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1008400 The outcome of bug 1008400 is (I think) 'this is fixed on Quantal by changing the default IO scheduler to Deadline'. Two problems with that: 1. We see the same problem (but to a lesser extent) on the deadline sched

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-09 Thread Alex Bligh
** Changed in: linux (Ubuntu) Status: Incomplete => Confirmed -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1064521 Title: Kernel I/O scheduling writes starving reads, local DoS To manage no

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-09 Thread Alex Bligh
apport information ** Tags added: apport-collected ** Description changed: On the Precise default kernel, it is possible by executing zcat on a large file for an unprivileged user to disrupt I/O sufficiently that it causes serious disruption. Serious disruption means (e.g.) a single M

[Bug 1064521] Re: Kernel I/O scheduling writes starving reads, local DoS

2012-10-09 Thread Marc Deslauriers
** Visibility changed to: Public -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1064521 Title: Kernel I/O scheduling writes starving reads, local DoS To manage notifications about this bug go to: ht