Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

sync #26

Merged
merged 222 commits into from
Jan 8, 2021
Merged

sync #26

merged 222 commits into from
Jan 8, 2021

Conversation

leibin2014
Copy link
Owner

What

Describe what this PR is doing.

Why ?

Justification for the PR. If there is existing issue/bug please reference. For
bug fixes why and what can be merged in a single item.

How ?

It is optional but for complex PRs please provide information about the design,
architecture, approach, etc.

Sergey Oblomov and others added 30 commits November 26, 2020 11:41
- added support of keepalive feature for TCP transport
- If single fragment AM received without UCP_AM_SEND_REPLY flag it
  should be delivered to the user even if the corresponding rx ep is
  closed/failed.
- If single fragment AM received with UCP_AM_SEND_REPLY flag it
  should be droppped if the corresponding rx ep is closed/failed,
  because reply ep can not be provided in the data callback.
- If some fragment of multi-fragmented AM received and the corresponding rx ep
  is closed/failed, this fragment should be dropped regardless of send AM flags
  (no way to assemble a message without aux info storedd in ep extension)
- If AM RTS is received and the corresponding rx ep is closed/failed,
  this RTS should be droppped and ATS with EP_TIMEOUT should be sent
  back to the sender.
* Renaming from wfe to wait_mem
* Using average of ten performance runs as a reference point
* Moving wait_mem to ucp_perf
* Code styling fixes

Signed-off-by: Pavel Shamis (Pasha) <[email protected]>
UCP/EP/CLOSE: Make close EP discard lanes directly
…heck

TEST/TAG: Fix tag test to check inline data flag
GTEST: Moving memory_wait test to perf
yosefe and others added 28 commits January 2, 2021 19:38
…daemon-server-loop

TOOLS/VFS: Implement mount daemon server loop
…and-expose

UCS/VFS: Connect to daemon and expose dummy filesystem
In order to catch cuda memory events even when Cuda is statically
linked, use bistro.
JENKINS: test CM's fallback in client-server testing
Make memory hooks work with static libcudart, by using bistro hooks for cuda driver API
UCT/IB/MLX5: DV UAR alloc type NC support
…-req

UCP/EP: set callback on close request.
Allows passing Cuda -L<path> flag to static build example, without
passing -lcudart.
test_sockaddr.cc - NEGATIVE_RETURNS - "index" is passed to a parameter
that cannot be negative. [Note: The source code implementation of the
function has been overridden by a builtin model.]

uct_cm.c - PRINTF_ARGS - Argument "self->iface" to format specifier "%p"
was expected to have pointer type but has type "struct uct_base_iface".

ucp_hello_world.c - USE_AFTER_FREE - Dereferencing freed pointer "msg"

wireup_cm.c - USE_AFTER_FREE - Passing freed pointer "conn_request" as
an argument to "ucs_log_dispatch" ("uct_listener_reject" frees
"conn_request".).
UCP/WIREUP: Allow EP check during WIREUP phase
…rt-static-is

CUDA/TEST: Check if libcudart_static is present for memory hook test
UCP/UCT/TEST/EXAMPLES: Fix several coverity issues.
Get device/vendor ids of SF from its parent PCI
UCS/DATASTRUCT: Add allow_list data struct
@leibin2014 leibin2014 merged commit b6edc2f into leibin2014:bf2 Jan 8, 2021
@leibin2014 leibin2014 mentioned this pull request Jan 8, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.