summaryrefslogtreecommitdiffstats
path: root/drivers/nvme
diff options
context:
space:
mode:
authorIsrael Rukshin <israelr@mellanox.com>2019-11-24 18:38:31 +0200
committerKeith Busch <kbusch@kernel.org>2019-11-27 02:14:01 +0900
commitb1ae1a238900474a9f51431c0f7f169ade1faa19 (patch)
tree64451d3a747ecfe0e757d5a49b2f29953a1680d2 /drivers/nvme
parent38e1800275d3af607e4df92ff49dc2cf442586a4 (diff)
downloadlinux-b1ae1a238900474a9f51431c0f7f169ade1faa19.tar.bz2
nvme-fc: Avoid preallocating big SGL for data
nvme_fc_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 nvme-fc, 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. Reviewed-by: Max Gurtovoy <maxg@mellanox.com> Reviewed-by: James Smart <james.smart@broadcom.com> Signed-off-by: Israel Rukshin <israelr@mellanox.com> Signed-off-by: Keith Busch <kbusch@kernel.org>
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/fc.c8
1 files changed, 4 insertions, 4 deletions
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 679a721ae229..13cb00e56cac 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -95,7 +95,7 @@ struct nvme_fc_fcp_op {
struct nvme_fcp_op_w_sgl {
struct nvme_fc_fcp_op op;
- struct scatterlist sgl[SG_CHUNK_SIZE];
+ struct scatterlist sgl[NVME_INLINE_SG_CNT];
uint8_t priv[0];
};
@@ -2141,7 +2141,7 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
freq->sg_table.sgl = freq->first_sgl;
ret = sg_alloc_table_chained(&freq->sg_table,
blk_rq_nr_phys_segments(rq), freq->sg_table.sgl,
- SG_CHUNK_SIZE);
+ NVME_INLINE_SG_CNT);
if (ret)
return -ENOMEM;
@@ -2150,7 +2150,7 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl,
op->nents, rq_dma_dir(rq));
if (unlikely(freq->sg_cnt <= 0)) {
- sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE);
+ sg_free_table_chained(&freq->sg_table, NVME_INLINE_SG_CNT);
freq->sg_cnt = 0;
return -EFAULT;
}
@@ -2173,7 +2173,7 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents,
rq_dma_dir(rq));
- sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE);
+ sg_free_table_chained(&freq->sg_table, NVME_INLINE_SG_CNT);
freq->sg_cnt = 0;
}