kernel-packages team mailing list archive

[Shyam <1206837@xxxxxxxxxxxxxxxxxx>]

Public bug reported:

We have a Ubuntu Raring server running kernel 3.8.13-030813-generic

We use iscsi to consume LUNs out of a storage array in the backend. When
the server is loaded we run into the issue of iSCSI device discovery
failing to scan partitions on LUNs with

Jul 30 12:12:01 srv1 kernel: [101661.119322] kworker/u:20: page allocation failure: order:4, mode:0x10c0d0
Jul 30 12:12:01 srv1 kernel: [101661.119327] Pid: 32539, comm: kworker/u:20 Tainted: GF       W  O 3.8.13-030813-generic #201305111843
Jul 30 12:12:01 srv1 kernel: [101661.119329] Call Trace:
Jul 30 12:12:01 srv1 kernel: [101661.119340]  [<ffffffff8113ac96>] warn_alloc_failed+0xf6/0x150
Jul 30 12:12:01 srv1 kernel: [101661.119345]  [<ffffffff8113e156>] ? drain_local_pages+0x16/0x20
Jul 30 12:12:01 srv1 kernel: [101661.119350]  [<ffffffff810bc8e0>] ? on_each_cpu_mask+0x50/0x70
Jul 30 12:12:01 srv1 kernel: [101661.119354]  [<ffffffff8113e8ce>] __alloc_pages_nodemask+0x76e/0x9b0
Jul 30 12:12:01 srv1 kernel: [101661.119359]  [<ffffffff8117af3a>] alloc_pages_current+0xba/0x170
Jul 30 12:12:01 srv1 kernel: [101661.119363]  [<ffffffff81139aae>] __get_free_pages+0xe/0x40
Jul 30 12:12:01 srv1 kernel: [101661.119367]  [<ffffffff8118427f>] kmalloc_order_trace+0x3f/0xd0
Jul 30 12:12:01 srv1 kernel: [101661.119373]  [<ffffffff8133af30>] check_partition+0x30/0x200
Jul 30 12:12:01 srv1 kernel: [101661.119376]  [<ffffffff8133ac58>] rescan_partitions+0xb8/0x2b0
Jul 30 12:12:01 srv1 kernel: [101661.119381]  [<ffffffff811d52cb>] __blkdev_get+0x39b/0x480
Jul 30 12:12:01 srv1 kernel: [101661.119386]  [<ffffffff8107f7eb>] ? bit_waitqueue+0x1b/0xc0
Jul 30 12:12:01 srv1 kernel: [101661.119389]  [<ffffffff811d540e>] blkdev_get+0x5e/0x1e0
Jul 30 12:12:01 srv1 kernel: [101661.119393]  [<ffffffff81337a82>] register_disk+0x172/0x190
Jul 30 12:12:01 srv1 kernel: [101661.119396]  [<ffffffff81338334>] add_disk+0xb4/0x230
Jul 30 12:12:01 srv1 kernel: [101661.119403]  [<ffffffff814bba76>] sd_probe_async+0x126/0x220
Jul 30 12:12:01 srv1 kernel: [101661.119407]  [<ffffffff8108704f>] async_run_entry_fn+0xaf/0x1d0
Jul 30 12:12:01 srv1 kernel: [101661.119410]  [<ffffffff81078b81>] process_one_work+0x141/0x490
Jul 30 12:12:01 srv1 kernel: [101661.119413]  [<ffffffff81079b48>] worker_thread+0x168/0x400
Jul 30 12:12:01 srv1 kernel: [101661.119416]  [<ffffffff810799e0>] ? manage_workers+0x120/0x120
Jul 30 12:12:01 srv1 kernel: [101661.119419]  [<ffffffff8107f050>] kthread+0xc0/0xd0
Jul 30 12:12:01 srv1 kernel: [101661.119423]  [<ffffffff8107ef90>] ? flush_kthread_worker+0xb0/0xb0
Jul 30 12:12:01 srv1 kernel: [101661.119429]  [<ffffffff816f61ec>] ret_from_fork+0x7c/0xb0
Jul 30 12:12:01 srv1 kernel: [101661.119432]  [<ffffffff8107ef90>] ? flush_kthread_worker+0xb0/0xb0

We see this issue is fixed in 3.9 kernels with the following commit

https://github.com/torvalds/linux/commit/ac2e5327a5e4f6477afc6a3b3b0dc6e0476d71d4

Kindly request you to pull this patch into Ubuntu raring stable 3.8 kernel version as detailed in 
http://lwn.net/Articles/550581/

Thank You

** Affects: linux (Ubuntu)
     Importance: Undecided
         Status: Incomplete


** Tags: raring

-- 
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/1206837

Title:
  Ubuntu Raring Kernel - pull patch block/partitions: optimize memory
  allocation in check_partition

Status in “linux” package in Ubuntu:
  Incomplete

Bug description:
  We have a Ubuntu Raring server running kernel 3.8.13-030813-generic

  We use iscsi to consume LUNs out of a storage array in the backend.
  When the server is loaded we run into the issue of iSCSI device
  discovery failing to scan partitions on LUNs with

  Jul 30 12:12:01 srv1 kernel: [101661.119322] kworker/u:20: page allocation failure: order:4, mode:0x10c0d0
  Jul 30 12:12:01 srv1 kernel: [101661.119327] Pid: 32539, comm: kworker/u:20 Tainted: GF       W  O 3.8.13-030813-generic #201305111843
  Jul 30 12:12:01 srv1 kernel: [101661.119329] Call Trace:
  Jul 30 12:12:01 srv1 kernel: [101661.119340]  [<ffffffff8113ac96>] warn_alloc_failed+0xf6/0x150
  Jul 30 12:12:01 srv1 kernel: [101661.119345]  [<ffffffff8113e156>] ? drain_local_pages+0x16/0x20
  Jul 30 12:12:01 srv1 kernel: [101661.119350]  [<ffffffff810bc8e0>] ? on_each_cpu_mask+0x50/0x70
  Jul 30 12:12:01 srv1 kernel: [101661.119354]  [<ffffffff8113e8ce>] __alloc_pages_nodemask+0x76e/0x9b0
  Jul 30 12:12:01 srv1 kernel: [101661.119359]  [<ffffffff8117af3a>] alloc_pages_current+0xba/0x170
  Jul 30 12:12:01 srv1 kernel: [101661.119363]  [<ffffffff81139aae>] __get_free_pages+0xe/0x40
  Jul 30 12:12:01 srv1 kernel: [101661.119367]  [<ffffffff8118427f>] kmalloc_order_trace+0x3f/0xd0
  Jul 30 12:12:01 srv1 kernel: [101661.119373]  [<ffffffff8133af30>] check_partition+0x30/0x200
  Jul 30 12:12:01 srv1 kernel: [101661.119376]  [<ffffffff8133ac58>] rescan_partitions+0xb8/0x2b0
  Jul 30 12:12:01 srv1 kernel: [101661.119381]  [<ffffffff811d52cb>] __blkdev_get+0x39b/0x480
  Jul 30 12:12:01 srv1 kernel: [101661.119386]  [<ffffffff8107f7eb>] ? bit_waitqueue+0x1b/0xc0
  Jul 30 12:12:01 srv1 kernel: [101661.119389]  [<ffffffff811d540e>] blkdev_get+0x5e/0x1e0
  Jul 30 12:12:01 srv1 kernel: [101661.119393]  [<ffffffff81337a82>] register_disk+0x172/0x190
  Jul 30 12:12:01 srv1 kernel: [101661.119396]  [<ffffffff81338334>] add_disk+0xb4/0x230
  Jul 30 12:12:01 srv1 kernel: [101661.119403]  [<ffffffff814bba76>] sd_probe_async+0x126/0x220
  Jul 30 12:12:01 srv1 kernel: [101661.119407]  [<ffffffff8108704f>] async_run_entry_fn+0xaf/0x1d0
  Jul 30 12:12:01 srv1 kernel: [101661.119410]  [<ffffffff81078b81>] process_one_work+0x141/0x490
  Jul 30 12:12:01 srv1 kernel: [101661.119413]  [<ffffffff81079b48>] worker_thread+0x168/0x400
  Jul 30 12:12:01 srv1 kernel: [101661.119416]  [<ffffffff810799e0>] ? manage_workers+0x120/0x120
  Jul 30 12:12:01 srv1 kernel: [101661.119419]  [<ffffffff8107f050>] kthread+0xc0/0xd0
  Jul 30 12:12:01 srv1 kernel: [101661.119423]  [<ffffffff8107ef90>] ? flush_kthread_worker+0xb0/0xb0
  Jul 30 12:12:01 srv1 kernel: [101661.119429]  [<ffffffff816f61ec>] ret_from_fork+0x7c/0xb0
  Jul 30 12:12:01 srv1 kernel: [101661.119432]  [<ffffffff8107ef90>] ? flush_kthread_worker+0xb0/0xb0

  We see this issue is fixed in 3.9 kernels with the following commit

  https://github.com/torvalds/linux/commit/ac2e5327a5e4f6477afc6a3b3b0dc6e0476d71d4

  Kindly request you to pull this patch into Ubuntu raring stable 3.8 kernel version as detailed in 
  http://lwn.net/Articles/550581/

  Thank You

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1206837/+subscriptions