Commit 739c6d7c authored by Konrad Sztyber's avatar Konrad Sztyber Committed by Tomasz Zawadzki
Browse files

nvme/tcp: check for EAGAIN when flushing socket 



The bahavior of spdk_sock_flush() was changed in 5433004e to return the
number of flushed bytes and -1 with errno set to EAGAIN in case nothing
has been flushed (instead of returning 0).  Therefore, we shouldn't
treat EAGAIN as an error in nvme_tcp_qpair_process_completions().

Signed-off-by: default avatarKonrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I5473488b5b408cdc739921046f1a0cc2c98f98de
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16643


Tested-by: default avatarSPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: default avatarAleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: default avatarJim Harris <james.r.harris@intel.com>
parent 25b0c20c

lib/nvme/nvme_tcp.c

+1 −1
Original line number Diff line number Diff line
@@ -1746,7 +1746,7 @@ nvme_tcp_qpair_process_completions(struct spdk_nvme_qpair *qpair, uint32_t max_c 


	if (qpair->poll_group == NULL) {

		rc = spdk_sock_flush(tqpair->sock);

		if (rc < 0) {

		if (rc < 0 && errno != EAGAIN) {

			SPDK_ERRLOG("Failed to flush tqpair=%p (%d): %s\n", tqpair,

				    errno, spdk_strerror(errno));

			if (spdk_unlikely(tqpair->qpair.ctrlr->timeout_enabled)) {