nvmet-loop: Avoid preallocating big SGL for data

nvme_loop_create_io_queues() preallocates a big buffer for the IO SGL based
on SG_CHUNK_SIZE.

Modern DMA engines are often capable of dealing with very big segments so
the SG_CHUNK_SIZE is often too big. SG_CHUNK_SIZE results in a static 4KB
SGL allocation per command.

If a controller has lots of deep queues, preallocation for the sg list can
consume substantial amounts of memory. For nvmet-loop, nr_hw_queues can be
128 and each queue's depth 128. This means the resulting preallocation
for the data SGL is 128*128*4K = 64MB per controller.

Switch to runtime allocation for SGL for lists longer than 2 entries. This
is the approach used by NVMe PCI so it should be reasonable for NVMeOF as
well. Runtime SGL allocation has always been the case for the legacy I/O
path so this is nothing new.

Tested-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>

diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index a758bb3..4df4ebd 100644 (file)
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -76,7 +76,7 @@ static void nvme_loop_complete_rq(struct request *req)
 {
        struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
 
-       sg_free_table_chained(&iod->sg_table, SG_CHUNK_SIZE);
+       sg_free_table_chained(&iod->sg_table, NVME_INLINE_SG_CNT);
        nvme_complete_rq(req);
 }
 
@@ -156,7 +156,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
                iod->sg_table.sgl = iod->first_sgl;
                if (sg_alloc_table_chained(&iod->sg_table,
                                blk_rq_nr_phys_segments(req),
-                               iod->sg_table.sgl, SG_CHUNK_SIZE)) {
+                               iod->sg_table.sgl, NVME_INLINE_SG_CNT)) {
                        nvme_cleanup_cmd(req);
                        return BLK_STS_RESOURCE;
                }
@@ -342,7 +342,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
        ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
        ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
        ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
-               SG_CHUNK_SIZE * sizeof(struct scatterlist);
+               NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
        ctrl->admin_tag_set.driver_data = ctrl;
        ctrl->admin_tag_set.nr_hw_queues = 1;
        ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
@@ -516,7 +516,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
        ctrl->tag_set.numa_node = NUMA_NO_NODE;
        ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
        ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
-               SG_CHUNK_SIZE * sizeof(struct scatterlist);
+               NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
        ctrl->tag_set.driver_data = ctrl;
        ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1;
        ctrl->tag_set.timeout = NVME_IO_TIMEOUT;