-
Notifications
You must be signed in to change notification settings - Fork 335
Redundant scheduler behaviour #271
Comments
Can you share a packet-trace? Thanks! Also, please provide details as to which version of MPTCP is installed and what the configuration is. |
Hi, Sorry to get back late. Did some further analysis. Below is the tcpdump logs for a session (Redacted server IP to 1.2.3.4):
Configs:
Further analysis:
So can you confirm this is the expected behaviour acc. to current implementation of the scheduler |
Yeah, looking more at this code, it seems like when the send-buffer is full, we are not sending the data in a redundant way. I will reach out to the author of this module to see if he has cycles to work on it. |
I will try to have a look next weekend. |
Looking at the provided trace, it really looks a bit fishy. I annotated the trace a bit:
I will try to reproduce your setup and update this thread in a few days. |
I just tested a basic setup with the recent mptcp release, two subflows, iperf, and the redundant scheduler. There, it works as expected, i.e., both subflows are saturated but the overall throughput is the throughput of the best subflow. Thus, there are at least a few configurations which are working ;-) @sujithrengan : Can you share some more details about your testsetup, e.g., i) can you share your sample application, ii) which Nagle configuration you are using, iii) if there is any particular reason for the 1268 packet size. Did you try other applications, e.g., iPerf or SSH? |
spdxcheck.py complains: include/linux/platform_data/gpio/gpio-amd-fch.h: 1:28 Invalid License ID: GPL+ which is correct because GPL+ is not a valid identifier. Of course this could have been caught by checkpatch.pl _before_ submitting or merging the patch. WARNING: 'SPDX-License-Identifier: GPL+ */' is not supported in LICENSES/... multipath-tcp#271: FILE: include/linux/platform_data/gpio/gpio-amd-fch.h:1: +/* SPDX-License-Identifier: GPL+ */ Fix it under the assumption that the author meant GPL-2.0+, which makes sense as the corresponding C file is using that identifier. Fixes: e09d168 ("gpio: AMD G-Series PCH gpio driver") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
[ Upstream commit 889d916 ] restrack should only be attached to a cm_id while the ID has a valid device pointer. It is set up when the device is first loaded, but not cleared when the device is removed. There is also two copies of the device pointer, one private and one in the public API, and these were left out of sync. Make everything go to NULL together and manipulate restrack right around the device assignments. Found by syzcaller: BUG: KASAN: wild-memory-access in __list_del include/linux/list.h:112 [inline] BUG: KASAN: wild-memory-access in __list_del_entry include/linux/list.h:135 [inline] BUG: KASAN: wild-memory-access in list_del include/linux/list.h:146 [inline] BUG: KASAN: wild-memory-access in cma_cancel_listens drivers/infiniband/core/cma.c:1767 [inline] BUG: KASAN: wild-memory-access in cma_cancel_operation drivers/infiniband/core/cma.c:1795 [inline] BUG: KASAN: wild-memory-access in cma_cancel_operation+0x1f4/0x4b0 drivers/infiniband/core/cma.c:1783 Write of size 8 at addr dead000000000108 by task syz-executor716/334 CPU: 0 PID: 334 Comm: syz-executor716 Not tainted 5.11.0+ multipath-tcp#271 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0xbe/0xf9 lib/dump_stack.c:120 __kasan_report mm/kasan/report.c:400 [inline] kasan_report.cold+0x5f/0xd5 mm/kasan/report.c:413 __list_del include/linux/list.h:112 [inline] __list_del_entry include/linux/list.h:135 [inline] list_del include/linux/list.h:146 [inline] cma_cancel_listens drivers/infiniband/core/cma.c:1767 [inline] cma_cancel_operation drivers/infiniband/core/cma.c:1795 [inline] cma_cancel_operation+0x1f4/0x4b0 drivers/infiniband/core/cma.c:1783 _destroy_id+0x29/0x460 drivers/infiniband/core/cma.c:1862 ucma_close_id+0x36/0x50 drivers/infiniband/core/ucma.c:185 ucma_destroy_private_ctx+0x58d/0x5b0 drivers/infiniband/core/ucma.c:576 ucma_close+0x91/0xd0 drivers/infiniband/core/ucma.c:1797 __fput+0x169/0x540 fs/file_table.c:280 task_work_run+0xb7/0x100 kernel/task_work.c:140 exit_task_work include/linux/task_work.h:30 [inline] do_exit+0x7da/0x17f0 kernel/exit.c:825 do_group_exit+0x9e/0x190 kernel/exit.c:922 __do_sys_exit_group kernel/exit.c:933 [inline] __se_sys_exit_group kernel/exit.c:931 [inline] __x64_sys_exit_group+0x2d/0x30 kernel/exit.c:931 do_syscall_64+0x2d/0x40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 255d0c1 ("RDMA/cma: rdma_bind_addr() leaks a cma_dev reference count") Link: https://lore.kernel.org/r/3352ee288fe34f2b44220457a29bfc0548686363.1620711734.git.leonro@nvidia.com Signed-off-by: Shay Drory <shayd@nvidia.com> Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Hi,
I have been testing MPTCP redundant scheduler.
Test setup:
Behaviour:
Initial data packets that are less than 1 MSS are scheduled in both the interfaces. (
58fa7ad
patch is applied in the device)When uploading the file ~10kB, the data packets are not redundantly scheduled, but behaves like default scheduler. When trying the same upload with a larger file ~1mB, initial 15-20 packets are not redundantly sent, but later packets are redundantly sent.
Also, after the upload, final data packets that are less than 1 MSS are again redundantly scheduled in both the interfaces.
I'm not sure why the data packets during upload is not redundantly sent always.
Any help would be much appreciated. Thanks in advance.
The text was updated successfully, but these errors were encountered: