scsi: zfcp: early returns for traces disabled via level
This patch adds early checks to avoid burning CPU cycles on the assembly of trace entries which would be skipped anyway. Introduce a static const variable to keep the trace level to check with debug_level_enabled() in sync with the actual trace emit with debug_event(). In order not to refactor the SAN tracing too much, simply use a define instead. This change is only for the non / semi hot paths, while the actual (I/O) hot path was already improved earlier: zfcp_dbf_scsi() is already guarded by its only caller _zfcp_dbf_scsi() since commit dcd20e23 ("[SCSI] zfcp: Only collect SCSI debug data for matching trace levels"). zfcp_dbf_hba_fsf_res() is already guarded by its only caller zfcp_dbf_hba_fsf_response() since commit 2e261af8 ("[SCSI] zfcp: Only collect FSF/HBA debug data for matching trace levels"). Signed-off-by: NMartin Peschke <mpeschke@linux.vnet.ibm.com> [maier@linux.vnet.ibm.com: rebase, reword, default level 3 branch prediction] Signed-off-by: NSteffen Maier <maier@linux.vnet.ibm.com> Reviewed-by: NBenjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: NBenjamin Block <bblock@linux.vnet.ibm.com> Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Showing
想要评论请 注册 或 登录