qemu_rdma_write_one() waits for an earlier write that shares the same registration chunk, even when the dirty ranges do not overlap. This serializes sparse writes and leaves send queue capacity unused.
RAM round notifiers now provide the completion barrier before a newer page version can be sent, and the obsolete unregister path no longer requires per-chunk serialization. Remove the wait. The global nb_sent count continues to manage CQ and send queue resources. Signed-off-by: Yanfei Xu <[email protected]> Reviewed-by: Peter Xu <[email protected]> --- migration/rdma.c | 19 +------------------ migration/trace-events | 1 - 2 files changed, 1 insertion(+), 19 deletions(-) diff --git a/migration/rdma.c b/migration/rdma.c index 16e9c6c30e..6f9b474e29 100644 --- a/migration/rdma.c +++ b/migration/rdma.c @@ -1740,7 +1740,7 @@ static int qemu_rdma_write_one(RDMAContext *rdma, struct ibv_sge sge; struct ibv_send_wr send_wr = { 0 }; struct ibv_send_wr *bad_wr; - int reg_result_idx, ret, count = 0; + int reg_result_idx, ret; uint64_t chunk, chunks; uint64_t chunk_size = migrate_rdma_chunk_size(); uint8_t *chunk_start, *chunk_end; @@ -1772,23 +1772,6 @@ retry: chunk_end = ram_chunk_end(block, chunk + chunks); - - while (test_bit(chunk, block->transit_bitmap)) { - (void)count; - trace_rdma_write_one_block(count++, current_index, chunk, - sge.addr, length, rdma->nb_sent, block->nb_chunks); - - ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL); - - if (ret < 0) { - error_setg(errp, "Failed to Wait for previous write to complete " - "block %d chunk %" PRIu64 - " current %" PRIu64 " len %" PRIu64 " %d", - current_index, chunk, sge.addr, length, rdma->nb_sent); - return -1; - } - } - if (!rdma->pin_all) { if (!block->remote_keys[chunk]) { /* diff --git a/migration/trace-events b/migration/trace-events index a9b02b3113..70d083f3fe 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -243,7 +243,6 @@ rdma_register_odp_mr(const char *name) "Try to register On-Demand Paging memory rdma_advise_mr(const char *name, uint32_t len, uint64_t addr, const char *res) "Try to advise block %s prefetch at %" PRIu32 "@0x%" PRIx64 ": %s" rdma_resolve_host_trying(const char *host, const char *ip) "Trying %s => %s" rdma_write_flush(int sent) "sent total: %d" -rdma_write_one_block(int count, int block, uint64_t chunk, uint64_t current, uint64_t len, int nb_sent, int nb_chunks) "(%d) Not clobbering: block: %d chunk %" PRIu64 " current %" PRIu64 " len %" PRIu64 " %d %d" rdma_write_one_post(uint64_t chunk, long addr, long remote, uint32_t len) "Posting chunk: %" PRIu64 ", addr: 0x%lx remote: 0x%lx, bytes %" PRIu32 rdma_write_one_queue_full(void) "" rdma_write_one_recvregres(int mykey, int theirkey, uint64_t chunk) "Received registration result: my key: 0x%x their key 0x%x, chunk %" PRIu64 -- 2.20.1
