-
Notifications
You must be signed in to change notification settings - Fork 1
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
UCT/IB/BASE: use random roce path factor to achieve high reliability. #127
Conversation
622a827
to
40521c7
Compare
src/uct/ib/base/ib_iface.c
Outdated
udp_sport = iface->config.roce_path_factor * path_index; | ||
if (iface->config.en_random_factor) { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
indent
src/uct/ib/base/ib_iface.c
Outdated
udp_sport = iface->config.roce_path_factor * path_index; | ||
udp_sport = iface->config.roce_path_factor * path_index; | ||
if (iface->config.en_random_factor) { | ||
assert(iface->config.roce_path_factor <= UCT_IB_ROCE_MAX_PATH_FACTOR); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ucs_assert
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@yosefe Already applied this comment:
#127 (comment)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@leibin2014 pls squash before merge
@yosefe Done. Thanks! |
UCT/IB/BASE: use random roce path factor to achieve high reliability.
When the switches on the current path have problem, the application can disconnect and reconnect again to achieve high reliability. A random roce path factor will be generated to find different sport and use different path.