When SCSI-MQ is enabled, the SCSI-MQ layers will do pre-allocation of
MQ resources based on shost values set by the driver. In newer cases
of the driver, which attempts to set nr_hw_queues to the cpu count,
the multipliers become excessive, with a single shost having SCSI-MQ
pre-allocation reaching into the multiple GBytes range. NPIV, which
creates additional shosts, only multiply this overhead. On lower-memory
systems, this can exhaust system memory very quickly, resulting in a
system crash or failures in the driver or elsewhere due to low memory
conditions.
After testing several scenarios, the situation can be mitigated by
limiting the value set in shost->nr_hw_queues to 4. Although the shost
values were changed, the driver still had per-cpu hardware queues of
its own that allowed parallelization per-cpu. Testing revealed that
even with the smallish number for nr_hw_queues for SCSI-MQ, performance
levels remained near maximum with the within-driver affiinitization.
A module parameter was created to allow the value set for the
nr_hw_queues to be tunable.
Signed-off-by: Dick Kennedy <dick.kennedy@xxxxxxxxxxxx>
Signed-off-by: James Smart <jsmart2021@xxxxxxxxx>
---
drivers/scsi/lpfc/lpfc.h | 1 +
drivers/scsi/lpfc/lpfc_attr.c | 17 +++++++++++++++++
drivers/scsi/lpfc/lpfc_init.c | 12 ++++++++----
drivers/scsi/lpfc/lpfc_sli4.h | 5 +++++
4 files changed, 31 insertions(+), 4 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 2c3bb8a966e5..bade2e025ecf 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -824,6 +824,7 @@ struct lpfc_hba {
uint32_t cfg_cq_poll_threshold;
uint32_t cfg_cq_max_proc_limit;
uint32_t cfg_fcp_cpu_map;
+ uint32_t cfg_fcp_mq_threshold;
uint32_t cfg_hdw_queue;
uint32_t cfg_irq_chann;
uint32_t cfg_suppress_rsp;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index ea62322ffe2b..d267f57d1738 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -5709,6 +5709,19 @@ LPFC_ATTR_RW(nvme_embed_cmd, 1, 0, 2,
"Embed NVME Command in WQE");
/*
+ * lpfc_fcp_mq_threshold: Set the number of Hardware Queues the driver
+ * will advertise it supports to the SCSI layer.
+ *
+ * 0 = Configure nr_hw_queues by the number of CPUs or HW queues.
+ * 1,128 = Manually specify nr_hw_queue value to be advertised,
+ *
+ * Value range is [0,128]. Default value is 4.
+ */
+LPFC_ATTR_R(fcp_mq_threshold, LPFC_FCP_MQ_THRESHOLD_DEF,
+ LPFC_FCP_MQ_THRESHOLD_MIN, LPFC_FCP_MQ_THRESHOLD_MAX,
+ "Set the number of SCSI Queues advertised");
+
+/*
* lpfc_hdw_queue: Set the number of Hardware Queues the driver
* will advertise it supports to the NVME and SCSI layers. This also
* will map to the number of CQ/WQ pairs the driver will create.
@@ -6030,6 +6043,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
&dev_attr_lpfc_cq_poll_threshold,
&dev_attr_lpfc_cq_max_proc_limit,
&dev_attr_lpfc_fcp_cpu_map,
+ &dev_attr_lpfc_fcp_mq_threshold,
&dev_attr_lpfc_hdw_queue,
&dev_attr_lpfc_irq_chann,
&dev_attr_lpfc_suppress_rsp,
@@ -7112,6 +7126,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
/* Initialize first burst. Target vs Initiator are different. */
lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb);
lpfc_nvmet_fb_size_init(phba, lpfc_nvmet_fb_size);
+ lpfc_fcp_mq_threshold_init(phba, lpfc_fcp_mq_threshold);
lpfc_hdw_queue_init(phba, lpfc_hdw_queue);
lpfc_irq_chann_init(phba, lpfc_irq_chann);
lpfc_enable_bbcr_init(phba, lpfc_enable_bbcr);
@@ -7135,6 +7150,8 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
phba->cfg_enable_pbde = 0;
/* A value of 0 means use the number of CPUs found in the system */
+ if (phba->cfg_fcp_mq_threshold == 0)
+ phba->cfg_fcp_mq_threshold = phba->sli4_hba.num_present_cpu;
if (phba->cfg_hdw_queue == 0)
phba->cfg_hdw_queue = phba->sli4_hba.num_present_cpu;
if (phba->cfg_irq_chann == 0)
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index faf43b1d3dbe..3e387ee95610 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -4309,10 +4309,14 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
shost->max_cmd_len = 16;
if (phba->sli_rev == LPFC_SLI_REV4) {
- if (phba->cfg_fcp_io_sched == LPFC_FCP_SCHED_BY_HDWQ)
- shost->nr_hw_queues = phba->cfg_hdw_queue;
- else
- shost->nr_hw_queues = phba->sli4_hba.num_present_cpu;
+ if (phba->cfg_fcp_mq_threshold > phba->sli4_hba.num_present_cpu)
+ phba->cfg_fcp_mq_threshold =
+ phba->sli4_hba.num_present_cpu;
+ if (phba->cfg_fcp_io_sched == LPFC_FCP_SCHED_BY_HDWQ &&
+ phba->cfg_fcp_mq_threshold > phba->cfg_hdw_queue)
+ phba->cfg_fcp_mq_threshold = phba->cfg_hdw_queue;
+
+ shost->nr_hw_queues = phba->cfg_fcp_mq_threshold;
shost->dma_boundary =
phba->sli4_hba.pc_sli4_params.sge_supp_len-1;
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 3aeca387b22a..ccd0392720e3 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -44,6 +44,11 @@
#define LPFC_HBA_HDWQ_MAX 128
#define LPFC_HBA_HDWQ_DEF 0
+/* FCP MQ queue count limiting */
+#define LPFC_FCP_MQ_THRESHOLD_MIN 0
+#define LPFC_FCP_MQ_THRESHOLD_MAX 128
+#define LPFC_FCP_MQ_THRESHOLD_DEF 4
+
/* Common buffer size to accomidate SCSI and NVME IO buffers */
#define LPFC_COMMON_IO_BUF_SZ 768
--
2.13.7
