From a2f10eed677861dfdb4a158c456a5e39302fe96e Mon Sep 17 00:00:00 2001 From: Steven Koo Date: Thu, 7 Jan 2021 13:11:02 -0600 Subject: uhd: Check for overflow after timeout buff read Error processing has been moved to another thread, so it's possible that consecutive recv calls may miss the signalling that an overflow occurred. We have no guarantee that the flag had been set by the time the second recv call to find the errors occurs. This adds another check for an overflow after calling _get_aligned_buffs with a min 1ms timeout. Hopefully this is long enough for the error to propogate, but it's not guaranteed. Signed-off-by: Steven Koo --- host/lib/transport/super_recv_packet_handler.hpp | 6 ------ 1 file changed, 6 deletions(-) (limited to 'host/lib/transport') diff --git a/host/lib/transport/super_recv_packet_handler.hpp b/host/lib/transport/super_recv_packet_handler.hpp index c6947ba26..f428f01f1 100644 --- a/host/lib/transport/super_recv_packet_handler.hpp +++ b/host/lib/transport/super_recv_packet_handler.hpp @@ -238,12 +238,6 @@ public: return 0; } - // Just return if no samples requested - if (nsamps_per_buff == 0) { - metadata.reset(); - return 0; - } - size_t accum_num_samps = recv_one_packet(buffs, nsamps_per_buff, metadata, timeout); -- cgit v1.2.3