If the "from" (input) side for a given transfer is 0, and we can't complete the write right away, what we need to be waiting for is for output readiness on side 1, not 0, and the other way around as well. This causes random transfer failures for local TCP connections, depending if we ever need to wait for output readiness. Reported-by: Paul Holzinger <pholzing(a)redhat.com> Link: https://github.com/containers/podman/issues/23517 Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- tcp_splice.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcp_splice.c b/tcp_splice.c index 473562b..483e45d 100644 --- a/tcp_splice.c +++ b/tcp_splice.c @@ -577,7 +577,7 @@ eintr: if (conn->read[fromsidei] == conn->written[fromsidei]) break; - conn_event(c, conn, OUT_WAIT(fromsidei)); + conn_event(c, conn, OUT_WAIT(!fromsidei)); break; } -- 2.43.0