Skip to content
GitLab
  1. 18 Aug, 2018 1 commit
  3. 16 Aug, 2018 5 commits
  5. 15 Aug, 2018 2 commits
  7. 14 Aug, 2018 3 commits
  9. 13 Aug, 2018 3 commits
  11. 11 Aug, 2018 5 commits
  13. 10 Aug, 2018 1 commit
  15. 09 Aug, 2018 2 commits
  17. 07 Aug, 2018 3 commits
  19. 06 Aug, 2018 1 commit
    • Tim Wickberg's avatar
      Modify slurm_send_only_node_msg() to catch issues with socket. · 06582da8
      Tim Wickberg authored 
      There are subtle issues involved in treating a TCP transmission
as a unidirectional message delivery layer.

The original code path looks like: connect(), write(), close().
But Linux handles the write() and close() asynchronously behind the
scenes, and does not block until that write() has been ACK'd by the
remote end. So the write() and close() may succeed, even with data
still in flight. A communication error - and message loss - would
have been silently ignored, leading to unreliable message transmission.

Worse yet, one side of the connection would believe it sent the message,
while the receive side swears it never saw the packets. This leads to
infrequent and yet seemingly impossible data loss, and a very tough
bug to chase down.

This teardown code tries to force the connection to shut down in an
orderly manner, giving Slurm a chance to catch a connection problem
and the upstream calling path an opportunity to retransmit.

This teardown code is based on an approach described in Section 7.5
of "UNIX Network Programming" Volume 1 (Third Edition), specifically
the subsection regarding SO_LINGER. (And also covers why SO_LINGER is
not sufficent to prevent this issue.)

Bug 5164.
      06582da8
  21. 04 Aug, 2018 1 commit
  23. 31 Jul, 2018 1 commit
  25. 27 Jul, 2018 2 commits
  27. 19 Jul, 2018 4 commits
  29. 18 Jul, 2018 3 commits
  31. 17 Jul, 2018 3 commits