Bug #41169
beast frontend throws an exception when running out of FDs
% Done:
0%
Source:
Development
Tags:
beast
Backport:
luminous mimic nautilus
Regression:
No
Severity:
3 - minor
Reviewed:
Description
the problem could be transient, and later connections may be successful after the load goes down.
to reproduce the issue you can set:
ulimit -n 128
and execute multiple clients in parallel.
code is here: https://github.com/ceph/ceph/blob/master/src/rgw/rgw_asio_frontend.cc#L570
void AsioFrontend::accept(Listener& l, boost::system::error_code ec)
{
if (!l.acceptor.is_open()) {
return;
} else if (ec == boost::asio::error::operation_aborted) {
return;
} else if (ec) {
throw ec;
}
Related issues
History
#1 Updated by Brad Hubbard about 4 years ago
- Project changed from Ceph to rgw
#2 Updated by Yuval Lifshitz about 4 years ago
- Assignee set to Yuval Lifshitz
#3 Updated by Casey Bodley about 4 years ago
- Status changed from New to 7
- Tags set to beast
- Backport set to luminous mimic nautilus
- Pull request ID set to 29587
#4 Updated by Casey Bodley about 4 years ago
- Status changed from 7 to Pending Backport
- Priority changed from Normal to High
#5 Updated by Nathan Cutler about 4 years ago
- Copied to Backport #41265: mimic: beast frontend throws an exception when running out of FDs added
#6 Updated by Nathan Cutler about 4 years ago
- Copied to Backport #41266: luminous: beast frontend throws an exception when running out of FDs added
#7 Updated by Nathan Cutler about 4 years ago
- Copied to Backport #41267: nautilus: beast frontend throws an exception when running out of FDs added
#8 Updated by Nathan Cutler almost 4 years ago
- Status changed from Pending Backport to Resolved
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are in status "Resolved" or "Rejected".