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

Default write inline value (220) could be too large #139

Closed
Pusnow opened this issue Feb 8, 2022 · 1 comment
Closed

Default write inline value (220) could be too large #139

Pusnow opened this issue Feb 8, 2022 · 1 comment

Comments

@Pusnow
Copy link

Pusnow commented Feb 8, 2022

In perftest, default WRITE_INLINE is 220:

#define DEF_INLINE_WRITE (220)

However, 220 max_inline_data could be too large for some devices (e.g., Intel E810 only support max_inline_data less than 102).
Pertest has option (-I) to change the value, but users may not be aware of the option, and output is a bit unfriendly.

Output of ./ib_write_lat -s 64 -c RC -d irdma0 -n 1000 -i 1:


************************************
* Waiting for client to connect... *
************************************
Unable to create QP.
Failed to create QP.
 Couldn't create IB resources
@sshaulnv
Copy link
Contributor

sshaulnv commented Jul 19, 2022

The creation of QP is made by ibv_create_qp().
When the value of the max_inline_data is invalid or too big, the function return EINVAL or ENOMEM respectively on the errno,
this kind of an errors can be caused by:

  • EINVAL: Invalid pd, send_cq, recv_cq, srq or invalid value provided in max_send_wr, max_recv_wr, max_send_sge, max_recv_sge or in max_inline_data.
  • ENOMEM: Not enough resources to complete this operation.

Therefore, we can't determine what the exact invalid resource value that failed the QP creation, and this is why the output is as it is.

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

No branches or pull requests

3 participants