Branch: refs/heads/master
Home: https://github.com/kronosnet/kronosnet
Commit: d2a30ac0135c15eebce25a89f943e9062e1b3f6c
https://github.com/kronosnet/kronosnet/commit/d2a30ac0135c15eebce25a89f943e…
Author: Christine Caulfield <ccaulfie(a)redhat.com>
Date: 2020-01-24 (Fri, 24 Jan 2020)
Changed paths:
M libknet/transport_udp.c
Log Message:
-----------
[udp] don't make socket spin if a network I/F is down
UDP treats ENETUNREACH as a temporary error and just retries,
but this causes the TX thread to spin just doing sendto() therefore
blocking all other traffic.
(To reproduce this try starting corosync with 2 links configured in
corosync.conf but only one of them configured to the 'right' address
- it will spin in a tight loop and need to be killed with -9)
SCTP does not seem to suffer from this.
Commit: e40c7cb51e25af25bc967210e4ec0a7fb5d46b42
https://github.com/kronosnet/kronosnet/commit/e40c7cb51e25af25bc967210e4ec0…
Author: Fabio M. Di Nitto <fdinitto(a)redhat.com>
Date: 2020-01-24 (Fri, 24 Jan 2020)
Changed paths:
M libknet/transport_udp.c
Log Message:
-----------
Merge pull request #278 from kronosnet/dont-spin-enetunreach
[udp] don't make socket spin if a network I/F is down
Compare: https://github.com/kronosnet/kronosnet/compare/fa6565c72aa7...e40c7cb51e25
Branch: refs/heads/dont-spin-enetunreach
Home: https://github.com/kronosnet/kronosnet
Commit: d2a30ac0135c15eebce25a89f943e9062e1b3f6c
https://github.com/kronosnet/kronosnet/commit/d2a30ac0135c15eebce25a89f943e…
Author: Christine Caulfield <ccaulfie(a)redhat.com>
Date: 2020-01-24 (Fri, 24 Jan 2020)
Changed paths:
M libknet/transport_udp.c
Log Message:
-----------
[udp] don't make socket spin if a network I/F is down
UDP treats ENETUNREACH as a temporary error and just retries,
but this causes the TX thread to spin just doing sendto() therefore
blocking all other traffic.
(To reproduce this try starting corosync with 2 links configured in
corosync.conf but only one of them configured to the 'right' address
- it will spin in a tight loop and need to be killed with -9)
SCTP does not seem to suffer from this.
Branch: refs/heads/dont-spin-enetunreach
Home: https://github.com/kronosnet/kronosnet
Commit: 5a11955f722dc950ab5fffaf074c8942d13bf86d
https://github.com/kronosnet/kronosnet/commit/5a11955f722dc950ab5fffaf074c8…
Author: Christine Caulfield <ccaulfie(a)redhat.com>
Date: 2020-01-24 (Fri, 24 Jan 2020)
Changed paths:
M libknet/transport_udp.c
Log Message:
-----------
[udp] don't make socket spin if a network I/F is down
UDP treats ENETUNREACH as a temporary error and just retries,
but this causes the TX thread to spin just doing sendto() therefore
blocking all other traffic.
(To reproduce this try starting corosync with 2 links configured in
corosync.conf but only one of them configured to the 'right' address
- it will spin in a tight loop and need to be killed with -9)
SCTP does not seem to suffer from this.
Branch: refs/heads/dont-spin-enetunreach
Home: https://github.com/kronosnet/kronosnet
Commit: e961b6bed9f3f2e3fee9720a984eb795d2bc31bb
https://github.com/kronosnet/kronosnet/commit/e961b6bed9f3f2e3fee9720a984eb…
Author: Christine Caulfield <ccaulfie(a)redhat.com>
Date: 2020-01-24 (Fri, 24 Jan 2020)
Changed paths:
M libknet/transport_udp.c
Log Message:
-----------
[udp] don't make socket spin if a network I/F is down
UDP treats ENETUNREACH as a temporary error and just retries,
but this causes the TX thread to spin just down sendto() therefore
blocking all other traffic.
(To reproduce this try starting corosync with 2 links configured in
corosync/conf but only one of them configured to the 'right' address
- it will spin in a tight loop and need to be killed with -9)
SCTP does not seem to suffer from this.