This is a note to let you know that I've just added the patch titled cxlflash: Increase cmd_per_lun for better throughput to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: cxlflash-increase-cmd_per_lun-for-better-throughput.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From 83430833b4d4a9c9b23964babbeb1f36450f8136 Mon Sep 17 00:00:00 2001 From: "Manoj N. Kumar" <manoj@xxxxxxxxxxxxxxxxxx> Date: Fri, 4 Mar 2016 15:55:20 -0600 Subject: cxlflash: Increase cmd_per_lun for better throughput From: Manoj N. Kumar <manoj@xxxxxxxxxxxxxxxxxx> commit 83430833b4d4a9c9b23964babbeb1f36450f8136 upstream. With the current value of cmd_per_lun at 16, the throughput over a single adapter is limited to around 150kIOPS. Increase the value of cmd_per_lun to 256 to improve throughput. With this change a single adapter is able to attain close to the maximum throughput (380kIOPS). Also change the number of RRQ entries that can be queued. Signed-off-by: Manoj N. Kumar <manoj@xxxxxxxxxxxxxxxxxx> Acked-by: Matthew R. Ochs <mrochs@xxxxxxxxxxxxxxxxxx> Reviewed-by: Uma Krishnan <ukrishn@xxxxxxxxxxxxxxxxxx> Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx> Cc: Sumit Semwal <sumit.semwal@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/scsi/cxlflash/common.h | 8 +++++--- drivers/scsi/cxlflash/main.c | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) --- a/drivers/scsi/cxlflash/common.h +++ b/drivers/scsi/cxlflash/common.h @@ -34,7 +34,6 @@ extern const struct file_operations cxlf sectors */ -#define NUM_RRQ_ENTRY 16 /* for master issued cmds */ #define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry)) /* AFU command retry limit */ @@ -48,9 +47,12 @@ extern const struct file_operations cxlf index derivation */ -#define CXLFLASH_MAX_CMDS 16 +#define CXLFLASH_MAX_CMDS 256 #define CXLFLASH_MAX_CMDS_PER_LUN CXLFLASH_MAX_CMDS +/* RRQ for master issued cmds */ +#define NUM_RRQ_ENTRY CXLFLASH_MAX_CMDS + static inline void check_sizes(void) { @@ -149,7 +151,7 @@ struct afu_cmd { struct afu { /* Stuff requiring alignment go first. */ - u64 rrq_entry[NUM_RRQ_ENTRY]; /* 128B RRQ */ + u64 rrq_entry[NUM_RRQ_ENTRY]; /* 2K RRQ */ /* * Command & data for AFU commands. */ --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -2305,7 +2305,7 @@ static struct scsi_host_template driver_ .eh_device_reset_handler = cxlflash_eh_device_reset_handler, .eh_host_reset_handler = cxlflash_eh_host_reset_handler, .change_queue_depth = cxlflash_change_queue_depth, - .cmd_per_lun = 16, + .cmd_per_lun = CXLFLASH_MAX_CMDS_PER_LUN, .can_queue = CXLFLASH_MAX_CMDS, .this_id = -1, .sg_tablesize = SG_NONE, /* No scatter gather support */ Patches currently in stable-queue which might be from manoj@xxxxxxxxxxxxxxxxxx are queue-4.4/cxlflash-increase-cmd_per_lun-for-better-throughput.patch