scsi: megaraid_sas - throttle io if FW is busy
Subsystems (2)
PATCH 3/5 scsi: megaraid_sas - throttle io if FW is busy
Checks added in megasas_queue_command to know if FW is able to process commands within timeout period. If number of retries is 2 or greater, the driver stops sending cmd to FW. IO is resumed if pending cmd count reduces to 16 or 5 seconds has elapsed from the time cmds were last sent to FW.
---
drivers/scsi/megaraid/megaraid_sas.c | 27 +++++++++++++++++++++++++ drivers/scsi/megaraid/megaraid_sas.h | 3 ++ 2 files changed, 30 insertions(+)
drivers/scsi/megaraid/megaraid_sas.c +27 -0
@@ -839,6 +839,7 @@ megasas_queue_command(struct scsi_cmnd *u32 frame_count;struct megasas_cmd *cmd;struct megasas_instance *instance; +unsigned long sec; instance = (struct megasas_instance *) scmd->device->host->hostdata;
@@ -856,6 +857,23 @@ megasas_queue_command(struct scsi_cmnd * goto out_done; } +/* Check if we can process cmds */ +if (instance->is_busy){ + sec = (jiffies - instance->last_time) /HZ ; +if (sec<5 ) +return SCSI_MLQUEUE_HOST_BUSY ; +else { + instance->is_busy=0 ; + instance->last_time=0 ; + } + } + +if (scmd->retries>1 ){ +/* FW is busy */ + instance->is_busy=1 ; + instance->last_time=jiffies; + } + cmd =megasas_get_cmd (instance);if (!cmd)return SCSI_MLQUEUE_HOST_BUSY ;
@@ -1200,6 +1218,7 @@ megasas_complete_cmd(struct megasas_inst {int exception =0 ;struct megasas_header *hdr = &cmd->frame->hdr; +int outstanding;if (cmd->scmd) { cmd->scmd->SCp.ptr = (char *)0 ;
@@ -1313,6 +1332,12 @@ megasas_complete_cmd(struct megasas_inst hdr->cmd);break ; } + +if (instance->is_busy){ + outstanding =atomic_read (&instance->fw_outstanding); +if (outstanding<17 ) + instance->is_busy=0 ; + } }/**
@@ -2384,6 +2409,8 @@ megasas_probe_one(struct pci_dev *pdev, instance->init_id =MEGASAS_DEFAULT_INIT_ID ; megasas_dbg_lvl =0 ; + instance->is_busy =0 ; + instance->last_time =0 ;/* * Initialize MFI Firmware
drivers/scsi/megaraid/megaraid_sas.h +3 -0
@@ -1102,6 +1102,9 @@ struct megasas_instance {atomic_t fw_outstanding;u32 hw_crit_error; +u8 is_busy; +unsigned long last_time; +struct megasas_instance_template *instancet;struct tasklet_struct isr_tasklet; };
drivers/scsi/megaraid/megaraid_sas.c +27 -0
@@ -839,6 +839,7 @@ megasas_queue_command(struct scsi_cmnd *u32 frame_count;struct megasas_cmd *cmd;struct megasas_instance *instance; +unsigned long sec; instance = (struct megasas_instance *) scmd->device->host->hostdata;
@@ -856,6 +857,23 @@ megasas_queue_command(struct scsi_cmnd * goto out_done; } +/* Check if we can process cmds */ +if (instance->is_busy){ + sec = (jiffies - instance->last_time) /HZ ; +if (sec<5 ) +return SCSI_MLQUEUE_HOST_BUSY ; +else { + instance->is_busy=0 ; + instance->last_time=0 ; + } + } + +if (scmd->retries>1 ){ +/* FW is busy */ + instance->is_busy=1 ; + instance->last_time=jiffies; + } + cmd =megasas_get_cmd (instance);if (!cmd)return SCSI_MLQUEUE_HOST_BUSY ;
@@ -1200,6 +1218,7 @@ megasas_complete_cmd(struct megasas_inst {int exception =0 ;struct megasas_header *hdr = &cmd->frame->hdr; +int outstanding;if (cmd->scmd) { cmd->scmd->SCp.ptr = (char *)0 ;
@@ -1313,6 +1332,12 @@ megasas_complete_cmd(struct megasas_inst hdr->cmd);break ; } + +if (instance->is_busy){ + outstanding =atomic_read (&instance->fw_outstanding); +if (outstanding<17 ) + instance->is_busy=0 ; + } }/**
@@ -2384,6 +2409,8 @@ megasas_probe_one(struct pci_dev *pdev, instance->init_id =MEGASAS_DEFAULT_INIT_ID ; megasas_dbg_lvl =0 ; + instance->is_busy =0 ; + instance->last_time =0 ;/* * Initialize MFI Firmware
drivers/scsi/megaraid/megaraid_sas.h +3 -0
@@ -1102,6 +1102,9 @@ struct megasas_instance {atomic_t fw_outstanding;u32 hw_crit_error; +u8 is_busy; +unsigned long last_time; +struct megasas_instance_template *instancet;struct tasklet_struct isr_tasklet; };
Quoted 25 lines · Sumant Patro
Checks added in
megasas_queue_commandto know if FW is able to process commands within timeout period. If number of retries is 2 or greater, the driver stops sending cmd to FW. IO is resumed if pending cmd count reduces to 16 or 5 seconds has elapsed from the time cmds were last sent to FW.Signed-off-by Sumant Patro <[email protected]>---
drivers/scsi/megaraid/megaraid_sas.c | 27 +++++++++++++++++++++++++ drivers/scsi/megaraid/megaraid_sas.h | 3 ++ 2 files changed, 30 insertions(+)diff -uprN
2.6.new-p2/drivers/scsi/megaraid/megaraid_sas.c2.6.new-p3/drivers/scsi/megaraid/megaraid_sas.cdrivers/scsi/megaraid/megaraid_sas.c +1
-0@@ -839,6 +839,7 @@ megasas_queue_command(struct scsi_cmnd *u32 frame_count;struct megasas_cmd *cmd;struct megasas_instance *instance; +unsigned long sec; instance = (struct megasas_instance *) scmd->device->host->hostdata;
drivers/scsi/megaraid/megaraid_sas.c megasas_queue_command(struct scsi_cmnd * · line 861
Quoted 5 lines
drivers/scsi/megaraid/megaraid_sas.c +2
-0@@ -856,6 +857,23 @@ megasas_queue_command(struct scsi_cmnd * goto out_done; } +/* Check if we can process cmds */ +if (instance->is_busy){
^ ^
space needed per linux coding style (and the rest of the file
drivers/scsi/megaraid/megaraid_sas.c megasas_queue_command(struct scsi_cmnd * · line 862
Quoted 1 line
drivers/scsi/megaraid/megaraid_sas.c +1
-0+ sec = (jiffies - instance->last_time) /HZ ;
please don't do this. You want to be using time_before() and jiffies_to_msecs(). The space problems apply to the rest of the code
drivers/scsi/megaraid/megaraid_sas.c megasas_queue_command(struct scsi_cmnd * · line 871
Quoted 9 lines
drivers/scsi/megaraid/megaraid_sas.c +9
-0+if (sec<5 ) +return SCSI_MLQUEUE_HOST_BUSY ; +else { + instance->is_busy=0 ; + instance->last_time=0 ; + } + } + +if (scmd->retries>1 ){
I really don't think this is a good indicator of your firmware necessarily having problems; I really think you might want to look at other indicators ... jiffies_at_alloc might be better, or even throttling from the abort handler, which must have been called before you get to here if the command is actually timing out.
Timeout and abort has it's own throttle anyway, since we quiesce the host before beginning error recovery ... are you sure this scheme actually solves anything for your device?
James