** Description changed:

  Hi all,
  
  In linux-4.15, which is used as hwe-edge in xenial, there's an unexpected 
behavior. It results in latency spikes of generic_make_request() function call.
  How to reproduce:
-   1. Run fio:
-   fio --name=test --rw=randwrite --direct=1 --filename=/dev/sdt --iodepth=1 
--fsync=1 --ioengine=libaio --write_lat_log loglat
-   2. While fio is writing to the device, change nr_requests setting to the 
same value as current:
-   echo 256 > /sys/block/sdt/queue/nr_requests
-   or: if scheduler is already none:
-   echo none > /sys/block/sdt/queue/scheduler
-   3. Stop fio and check slat log:
-   ...
-   3980, 16, 1, 4096
-   3999, 17, 1, 4096
-   4010, 19, 1, 4096
-   4020, 18, 1, 4096
-   4045, 10821, 1, 4096
-   4054, 25, 1, 4096
-   4070, 12, 1, 4096
-   4083, 17, 1, 4096
-   4094, 16, 1, 4096
-   4111, 17, 1, 4096
-   ...
+   1. Run fio:
+   fio --name=test --rw=randwrite --direct=1 --filename=/dev/sdt --iodepth=1 
--fsync=1 --ioengine=libaio --write_lat_log loglat
+   2. While fio is writing to the device, change nr_requests setting to the 
same value as current:
+   echo 256 > /sys/block/sdt/queue/nr_requests
+   or: if scheduler is already none:
+   echo none > /sys/block/sdt/queue/scheduler
+   3. Stop fio and check slat log:
+ 
+   https://bit.ly/2BtN52W
+   ...
+   3980, 16, 1, 4096
+   3999, 17, 1, 4096
+   4010, 19, 1, 4096
+   4020, 18, 1, 4096
+   4045, 10821, 1, 4096
+   4054, 25, 1, 4096
+   4070, 12, 1, 4096
+   4083, 17, 1, 4096
+   4094, 16, 1, 4096
+   4111, 17, 1, 4096
+   ... 
  
  There're a few patches to fix this behavior:
- 
https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git/commit/?h=for-5.1/block&id=e5fa81408fb43ebabde65938ef8b20ae879017e7
- 
https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git/commit/?h=for-5.1/block&id=fbd72127c975dc8e532ecc73d52f3b1b00935bec
+ https://bit.ly/2BtN52W
+ https://bit.ly/2BtN52W
  
  This behavior affects production systems, because every change uevent
  triggers udev to change settings prior to udev rules. Some software, for
  example arcconf (tool for managing adaptec HBA adapters) triggers
  uevents for every block device. So, every call to arcconf utility
  results in latency spike.
  
  Could this be backported to 4.15 kernel for xenial/bionic?

-- 
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1815733

Title:
  unnecessary request_queue freeze

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+bug/1815733/+subscriptions

-- 
ubuntu-bugs mailing list
ubuntu-bugs@lists.ubuntu.com
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs

Reply via email to