Peer API RMA changes + SHM clean up #2
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
shijin-aws
approved these changes
Mar 17, 2023
sunkuamzn
commented
Mar 17, 2023
prov/efa/src/rdm/rxr_rma.c
Outdated
|
|
||
| if (peer->is_local && rxr_ep->use_shm_for_tx) { | ||
| use_lower_ep_read = true; | ||
| // msg_clone->addr = peer->shm_fiaddr; |
Collaborator
Author
There was a problem hiding this comment.
The fi_rma_bw test passes when I use msg and msg_clone. I don't know how that's possible..
I have to use msg_clone to set the address because the input parameter msg is const. Using msg_clone generates a compiler warning.
Owner
There was a problem hiding this comment.
fabtests only has 1 peer that that the shm_fiaddr could be the same with efa addr. We should use shm_fiaddr for any fi_* call for shm
Collaborator
Author
There was a problem hiding this comment.
I see OK
What's the best way to do this? The msg_clone idea which I have here generates a compiler warning. I could do a memcpy but that would be more expensive?
Owner
There was a problem hiding this comment.
There are rxr_msg_construct and rxr_tmsg_construct in rxr_msg.h. You can do similar things to have a function to construct a new fi_rma_msg
Signed-off-by: Sai Sunku <[email protected]>
Signed-off-by: Sai Sunku <[email protected]>
Signed-off-by: Sai Sunku <[email protected]>
shijin-aws
pushed a commit
that referenced
this pull request
Sep 12, 2023
If a posted receive matches with a saved receive, we may need to increment the rx counter. Set the rx counter increment callback to match that of the posted receive. This fixes an assert in xnet_cntr_inc() accessing a NULL cntr_inc function pointer. Program received signal SIGABRT, Aborted. 0x0000155552d4d37f in raise () from /lib64/libc.so.6 #0 0x0000155552d4d37f in raise () from /lib64/libc.so.6 #1 0x0000155552d37db5 in abort () from /lib64/libc.so.6 #2 0x0000155552d37c89 in __assert_fail_base.cold.0 () from /lib64/libc.so.6 #3 0x0000155552d45a76 in __assert_fail () from /lib64/libc.so.6 #4 0x00001555522967f9 in xnet_cntr_inc (ep=0x6e4c70, xfer_entry=0x6f7a30) at prov/tcp/src/xnet_cq.c:347 #5 0x0000155552296836 in xnet_report_cntr_success (ep=0x6e4c70, cq=0x6ca930, xfer_entry=0x6f7a30) at prov/tcp/src/xnet_cq.c:354 #6 0x000015555229970d in xnet_complete_saved (saved_entry=0x6f7a30) at prov/tcp/src/xnet_progress.c:153 #7 0x0000155552299961 in xnet_recv_saved (saved_entry=0x6f7a30, rx_entry=0x6f7840) at prov/tcp/src/xnet_progress.c:188 #8 0x00001555522946f8 in xnet_srx_tag (srx=0x6dd1c0, recv_entry=0x6f7840) at prov/tcp/src/xnet_srx.c:445 #9 0x0000155552294bb1 in xnet_srx_trecv (ep_fid=0x6dd1c0, buf=0x6990c4, len=4, desc=0x0, src_addr=0, tag=21474836494, ignore=3458764513820540928, context=0x7ffffffeb180) at prov/tcp/src/xnet_srx.c:558 #10 0x000015555228f60e in fi_trecv (ep=0x6dd1c0, buf=0x6990c4, len=4, desc=0x0, src_addr=0, tag=21474836494, ignore=3458764513820540928, context=0x7ffffffeb180) at ./include/rdma/fi_tagged.h:91 #11 0x00001555522900a7 in xnet_rdm_trecv (ep_fid=0x6d9fe0, buf=0x6990c4, len=4, desc=0x0, src_addr=0, tag=21474836494, ignore=3458764513820540928, context=0x7ffffffeb180) at prov/tcp/src/xnet_rdm.c:212 Signed-off-by: Sean Hefty <[email protected]>
shijin-aws
added a commit
that referenced
this pull request
Nov 24, 2025
We need such barrier in two transitions: 1. from wqe write to doorbell ring 2. from doorbell ring to wqe write. For #2, we currently have the barrier right after the doorbell ring, which is different from rdma-core implementation that has the doorbell right in the next wr_start, and according to benchmark such choice hurts performance on ARM platform. This patch moves the #2 barrier to the beginning of wr start, before the wqe write, to be consistent with rdma-core and improves the performance. Signed-off-by: Shi Jin <[email protected]>
shijin-aws
added a commit
that referenced
this pull request
Nov 25, 2025
We need such barrier in two transitions: 1. from wqe write to doorbell ring 2. from doorbell ring to wqe write. For #2, we currently have the barrier right after the doorbell ring, which is different from rdma-core implementation that has the doorbell right in the next wr_start, and according to benchmark such choice hurts performance on ARM platform. This patch moves the #2 barrier to the beginning of wr start, before the wqe write, to be consistent with rdma-core and improves the performance. Signed-off-by: Shi Jin <[email protected]>
shijin-aws
added a commit
that referenced
this pull request
Dec 1, 2025
We need such barrier in two transitions: 1. from wqe write to doorbell ring 2. from doorbell ring to wqe write. For #2, we currently have the barrier right after the doorbell ring, which is different from rdma-core implementation that has the doorbell right in the next wr_start, and according to benchmark such choice hurts performance on ARM platform. This patch moves the #2 barrier to the beginning of wr start, before the wqe write, to be consistent with rdma-core and improves the performance. Signed-off-by: Shi Jin <[email protected]> (cherry picked from commit c4937ed)
shijin-aws
added a commit
that referenced
this pull request
Dec 29, 2025
We need such barrier in two transitions: 1. from wqe write to doorbell ring 2. from doorbell ring to wqe write. For #2, we currently have the barrier right after the doorbell ring, which is different from rdma-core implementation that has the doorbell right in the next wr_start, and according to benchmark such choice hurts performance on ARM platform. This patch moves the #2 barrier to the beginning of wr start, before the wqe write, to be consistent with rdma-core and improves the performance. Signed-off-by: Shi Jin <[email protected]> (cherry picked from commit c4937ed)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.