From: Stephen M. Cameron <scame...@beardog.cce.hp.com> When commands sent down the "fast path" fail, they must be re-tried down the normal RAID path. We do this by kicking i/o's back to the scsi mid layer with a DID_SOFT_ERROR status, which causes them to be retried. This won't work for SG_IO's and other non REQ_TYPE_FS i/o's which could get kicked all the way back to the application, which may have no idea that the command needs resubmitting and likely no way to resubmit it in such a way the that driver can recognize it as a resubmit and send it down the normal RAID path. So we just always send non REQ_TYPE_FS i/o's down the normal RAID path, never down the "fast path".
Signed-off-by: Stephen M. Cameron <scame...@beardog.cce.hp.com> --- drivers/scsi/hpsa.c | 3 ++- 1 files changed, 2 insertions(+), 1 deletions(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index a70b3fc..f1ebb8c 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -2330,7 +2330,8 @@ static int hpsa_scsi_queue_command_lck(struct scsi_cmnd *cmd, if ((likely(h->transMethod & CFGTBL_Trans_io_accel1)) && (dev->ioaccel_handle) && ((cmd->cmnd[0] == READ_10) || (cmd->cmnd[0] == WRITE_10)) && - (scsi_sg_count(cmd) <= IOACCEL1_MAXSGENTRIES)) + (scsi_sg_count(cmd) <= IOACCEL1_MAXSGENTRIES) && + likely(cmd->request->cmd_type == REQ_TYPE_FS)) return hpsa_scsi_ioaccel_queue_command(h, c); c->Header.ReplyQueue = 0; /* unused in simple mode */ -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html