NVMe: allow discard timeouts to be configurable
Subsystems (2)
PATCH v2 1/1 NVMe: allow discard timeouts to be configurable
On some devices, size of discard will impact how long it takes to process, and full device discards can run into the 1-2min range. The default IO timeout is 30 seconds, and even though that is configurable, it'd be nice to keep that at a lower value and add a separate module parameter for discard timeouts.
This patch adds that module parameter, and also defaults timeouts to 300 seconds instead of 30 seconds. That _should_ be enough for everyone.
Signed-off-by Jens Axboe <axboe at fb.com>
---
Changes since v1:
- Move timeout setting into the DISCARD branch of request setup earlier, which saves a branch.
nvme-core.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
drivers/block/nvme-core.c +10 -0
@@ -58,6 +58,10 @@ unsigned char nvme_io_timeout = 30;module_param_named (io_timeout, nvme_io_timeout, byte,0644 );MODULE_PARM_DESC (io_timeout,"timeout in seconds for I/O" ); +unsigned int nvme_discard_timeout =300 ; +module_param_named (discard_timeout, nvme_discard_timeout, uint,0644 ); +MODULE_PARM_DESC (discard_timeout,"timeout in seconds for discard I/O" ); +static unsigned char shutdown_timeout =5 ;module_param (shutdown_timeout, byte,0644 );MODULE_PARM_DESC (shutdown_timeout,"timeout in seconds for controller shutdown" );
@@ -848,6 +852,12 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, goto retry_cmd;iod_list (iod)[0 ] = (__le64 *)range; iod->npages =0 ; + +/* +* Set the discard specific timeout here, before calling +* nvme_set_info() which does blk_mq_start_request(). +*/ + req->timeout = nvme_discard_timeout *HZ ; }else if (req->nr_phys_segments) { dma_dir =rq_data_dir (req) ?DMA_TO_DEVICE :DMA_FROM_DEVICE ;
Signature · 1 line
Jens Axboe