aboutsummaryrefslogtreecommitdiffstats
path: root/scripts/patch-kernel
diff options
context:
space:
mode:
authorAndrei Pelinescu-Onciul <andrei@iptel.org>2009-11-29 00:14:02 -0800
committerDavid S. Miller <davem@davemloft.net>2009-11-29 00:14:02 -0800
commit5fdd4baef6195a1f2960e901c8877e2105f832ca (patch)
tree198a3f2df2bea3c5239c95957e21f3680908ddf6 /scripts/patch-kernel
parentpktgen: Fix netdevice unregister (diff)
downloadlinux-5fdd4baef6195a1f2960e901c8877e2105f832ca.tar.gz
linux-5fdd4baef6195a1f2960e901c8877e2105f832ca.zip
sctp: on T3_RTX retransmit all the in-flight chunks
When retransmitting due to T3 timeout, retransmit all the in-flight chunks for the corresponding transport/path, including chunks sent less then 1 rto ago. This is the correct behaviour according to rfc4960 section 6.3.3 E3 and "Note: Any DATA chunks that were sent to the address for which the T3-rtx timer expired but did not fit in one MTU (rule E3 above) should be marked for retransmission and sent as soon as cwnd allows (normally, when a SACK arrives). ". This fixes problems when more then one path is present and the T3 retransmission of the first chunk that timeouts stops the T3 timer for the initial active path, leaving all the other in-flight chunks waiting forever or until a new chunk is transmitted on the same path and timeouts (and this will happen only if the cwnd allows sending new chunks, but since cwnd was dropped to MTU by the timeout => it will wait until the first heartbeat). Example: 10 packets in flight, sent at 0.1 s intervals on the primary path. The primary path is down and the first packet timeouts. The first packet is retransmitted on another path, the T3 timer for the primary path is stopped and cwnd is set to MTU. All the other 9 in-flight packets will not be retransmitted (unless more new packets are sent on the primary path which depend on cwnd allowing it, and even in this case the 9 packets will be retransmitted only after a new packet timeouts which even in the best case would be more then RTO). This commit reverts d0ce92910bc04e107b2f3f2048f07e94f570035d and also removes the now unused transport->last_rto, introduced in b6157d8e03e1e780660a328f7183bcbfa4a93a19. p.s The problem is not only when multiple paths are there. It can happen in a single homed environment. If the application stops sending data, it possible to have a hung association. Signed-off-by: Andrei Pelinescu-Onciul <andrei@iptel.org> Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'scripts/patch-kernel')
0 files changed, 0 insertions, 0 deletions
it() to do state initializationHuazhong Tan1-10/+19 2021-08-27net: hns3: add macros for mac speeds of firmware commandGuangbin Huang2-18/+31 2021-08-27mptcp: make the locking tx schema more readablePaolo Abeni1-3/+7 2021-08-27mptcp: optimize the input options processingPaolo Abeni1-34/+37 2021-08-27mptcp: consolidate in_opt sub-options fields in a bitmaskPaolo Abeni4-73/+63 2021-08-27mptcp: better binary layout for mptcp_options_receivedPaolo Abeni2-15/+13 2021-08-27mptcp: do not set unconditionally csum_reqd on incoming optPaolo Abeni1-3/+1 2021-08-26tcp: enable mid stream window clampNeil Spring1-0/+1 2021-08-26net/mlx5: DR, Add support for update FTEYevgeny Kliteynik1-9/+30 2021-08-26net/mlx5: DR, Improve rule tracking memory consumptionYevgeny Kliteynik3-86/+83 2021-08-26net/mlx5: DR, Remove rehash ctrl struct from dr_htblYevgeny Kliteynik3-21/+24 2021-08-26net/mlx5: DR, Remove HW specific STE type from nic domainYevgeny Kliteynik10-45/+61 2021-08-26net/mlx5: DR, Merge DR_STE_SIZE enumsYevgeny Kliteynik1-3/+0 2021-08-26net/mlx5: DR, Skip source port matching on FDB RX domainYevgeny Kliteynik1-1/+13 2021-08-26net/mlx5: DR, Add ignore_flow_level support for multi-dest flow tablesYevgeny Kliteynik6-6/+18 2021-08-26net/mlx5: DR, Use FW API when updating FW-owned flow tableYevgeny Kliteynik1-0/+3 2021-08-26net/mlx5: DR, replace uintN_t with kernel-style typesYevgeny Kliteynik2-6/+6 2021-08-26net/mlx5: DR, Support IPv6 matching on flow label for STEv0Yevgeny Kliteynik1-0/+6 2021-08-26net/mlx5: DR, Reduce print level for FT chaining level checkBodong Wang1-2/+2 2021-08-26net/mlx5: DR, Warn and ignore SW steering rule insertion on QP errYevgeny Kliteynik2-2/+15 2021-08-26net/mlx5: DR, Improve error flow in actions_build_ste_arrYevgeny Kliteynik1-16/+56 2021-08-26net/mlx5: DR, Enable QP retransmissionYevgeny Kliteynik1-0/+1 2021-08-26net/mlx5: DR, Enable VLAN pop on TX and VLAN push on RXYevgeny Kliteynik3-9/+118 2021-08-26net/mlx5: DR, Split modify VLAN state to separate pop/push statesYevgeny Kliteynik1-26/+27 2021-08-26net/mlx5: DR, Added support for REMOVE_HEADER packet reformatYevgeny Kliteynik5-7/+96 2021-08-26Revert "net: really fix the build..."Kalle Valo6-30/+8 2021-08-26net: hns3: fix get wrong pfc_en when query PFC configurationGuangbin Huang1-11/+2 2021-08-26net: hns3: fix GRO configuration error after resetYufeng Mo4-10/+30 2021-08-26net: hns3: change the method of getting cmd index in debugfsYufeng Mo2-7/+8 2021-08-26net: hns3: fix duplicate node in VLAN listGuojia Liao1-1/+5 2021-08-26net: hns3: fix speed unknown issue in bond 4Yonglong Liu3-3/+3 2021-08-26net: hns3: add waiting time before cmdq memory is releasedYufeng Mo4-2/+13 2021-08-26net: hns3: clear hardware resource when loading driverYufeng Mo2-0/+29 2021-08-26net: fix NULL pointer reference in cipso_v4_doi_free王贇1-8/+10 2021-08-26net: Add driver for LiteX's LiteETH network interfaceJoel Stanley5-0/+351