Server hung or hung_task panic, blocked task waiting on a read of a memory page

Solution In Progress - Updated -

Issue

  • Server is hung and/or hung_task panic was tripped, and oldest blocked task(s) are seen in a read() system call, ending up in sync_page -> io_schedule
  • Blocked task with backtrace similar to the following. What does this mean and what are the next steps?
Call Trace:
 [<ffffffff800637de>] io_schedule+0x3f/0x67
 [<ffffffff80028bf0>] sync_page+0x3e/0x43
 [<ffffffff80063922>] __wait_on_bit_lock+0x36/0x66
 [<ffffffff8003f980>] __lock_page+0x5e/0x64
 [<ffffffff8000c425>] do_generic_mapping_read+0x1df/0x359
 [<ffffffff8000c6eb>] __generic_file_aio_read+0x14c/0x198
 [<ffffffff800c9eca>] generic_file_read+0xac/0xc5
 [<ffffffff8000b721>] vfs_read+0xcb/0x171
 [<ffffffff80011d15>] sys_read+0x45/0x6e
 [<ffffffff8005d28d>] tracesys+0xd5/0xe0

Environment

  • Red Hat Enterprise Linux 5
  • any process doing reads to any filesystem

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase of over 48,000 articles and solutions.

Current Customers and Partners

Log in for full access

Log In