Hi Sagi
With this patch, the NULL pointer fixed now.
But from below log, we can see it will continue reconnecting in 10
seconds and cannot be stopped.
[36288.963890] Broke affinity for irq 16
[36288.983090] Broke affinity for irq 28
[36289.003104] Broke affinity for irq 90
[36289.020488] Broke affinity for irq 93
[36289.036911] Broke affinity for irq 97
[36289.053344] Broke affinity for irq 100
[36289.070166] Broke affinity for irq 104
[36289.088076] smpboot: CPU 1 is now offline
[36302.371160] nvme nvme0: reconnecting in 10 seconds
[36312.953684] blk_mq_reinit_tagset: tag is null, continue
[36312.983267] nvme nvme0: Connect rejected: status 8 (invalid service ID).
[36313.017290] nvme nvme0: rdma_resolve_addr wait failed (-104).
[36313.044937] nvme nvme0: Failed reconnect attempt, requeueing...
[36323.171983] blk_mq_reinit_tagset: tag is null, continue
[36323.200733] nvme nvme0: Connect rejected: status 8 (invalid service ID).
[36323.233820] nvme nvme0: rdma_resolve_addr wait failed (-104).
[36323.261027] nvme nvme0: Failed reconnect attempt, requeueing...
[36333.412341] blk_mq_reinit_tagset: tag is null, continue
[36333.441346] nvme nvme0: Connect rejected: status 8 (invalid service ID).
[36333.476139] nvme nvme0: rdma_resolve_addr wait failed (-104).
[36333.502794] nvme nvme0: Failed reconnect attempt, requeueing...
[36343.652755] blk_mq_reinit_tagset: tag is null, continue
[36343.682103] nvme nvme0: Connect rejected: status 8 (invalid service ID).
[36343.716645] nvme nvme0: rdma_resolve_addr wait failed (-104).
[36343.743581] nvme nvme0: Failed reconnect attempt, requeueing...
[36353.893103] blk_mq_reinit_tagset: tag is null, continue
[36353.921041] nvme nvme0: Connect rejected: status 8 (invalid service ID).
[36353.953541] nvme nvme0: rdma_resolve_addr wait failed (-104).
[36353.983528] nvme nvme0: Failed reconnect attempt, requeueing...
[36364.133544] blk_mq_reinit_tagset: tag is null, continue
[36364.162012] nvme nvme0: Connect rejected: status 8 (invalid service ID).
[36364.195002] nvme nvme0: rdma_resolve_addr wait failed (-104).
[36364.221671] nvme nvme0: Failed reconnect attempt, requeueing...
Yep... looks like we don't take into account that we can't use all the
queues now...
Does this patch help:
--
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 29ac8fcb8d2c..25af3f75f6f1 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -337,8 +337,6 @@ static int __nvme_rdma_init_request(struct
nvme_rdma_ctrl *ctrl,
struct ib_device *ibdev = dev->dev;
int ret;
- BUG_ON(queue_idx >= ctrl->queue_count);
-
ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct
nvme_command),
DMA_TO_DEVICE);
if (ret)
@@ -647,8 +645,22 @@ static int nvme_rdma_connect_io_queues(struct
nvme_rdma_ctrl *ctrl)
static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
{
+ struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+ unsigned int nr_io_queues;
int i, ret;
+ nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+ ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
+ if (ret)
+ return ret;
+
+ ctrl->queue_count = nr_io_queues + 1;
+ if (ctrl->queue_count < 2)
+ return 0;
+
+ dev_info(ctrl->ctrl.device,
+ "creating %d I/O queues.\n", nr_io_queues);
+
for (i = 1; i < ctrl->queue_count; i++) {
ret = nvme_rdma_init_queue(ctrl, i,
ctrl->ctrl.opts->queue_size);
@@ -1793,20 +1805,8 @@ static const struct nvme_ctrl_ops
nvme_rdma_ctrl_ops = {
static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl)
{
- struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
int ret;
- ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
- if (ret)
- return ret;
-
- ctrl->queue_count = opts->nr_io_queues + 1;
- if (ctrl->queue_count < 2)
- return 0;
-
- dev_info(ctrl->ctrl.device,
- "creating %d I/O queues.\n", opts->nr_io_queues);
-
--
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
