From bbb490053173b737604a87af03f2113fb1c279a0 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 17 Sep 2025 17:12:55 -0500 Subject: scsi: target: Move LUN stats to per-CPU The atomic use in the main I/O path is causing perf issues when using higher performance backend devices and multiple queues (more than 10 when using vhost-scsi) like with this fio workload: [global] bs=4K iodepth=128 direct=1 ioengine=libaio group_reporting time_based runtime=120 name=standard-iops rw=randread numjobs=16 cpus_allowed=0-15 To fix this issue, move the LUN stats to per CPU. Note: I forgot to include this patch with the delayed/ordered per CPU tracking and per device/device entry per CPU stats. With this patch you get the full 33% improvements when using fast backends, multiple queues and multiple IO submiters. Signed-off-by: Mike Christie Reviewed-by: Dmitry Bogdanov Link: https://patch.msgid.link/20250917221338.14813-4-michael.christie@oracle.com Signed-off-by: Martin K. Petersen --- include/target/target_core_base.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/target') diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 27e1f9d5f0c6..372da2eadf54 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -744,9 +744,9 @@ struct se_port_stat_grps { }; struct scsi_port_stats { - atomic_long_t cmd_pdus; - atomic_long_t tx_data_octets; - atomic_long_t rx_data_octets; + u64 cmd_pdus; + u64 tx_data_octets; + u64 rx_data_octets; }; struct se_lun { @@ -773,7 +773,7 @@ struct se_lun { spinlock_t lun_tg_pt_gp_lock; struct se_portal_group *lun_tpg; - struct scsi_port_stats lun_stats; + struct scsi_port_stats __percpu *lun_stats; struct config_group lun_group; struct se_port_stat_grps port_stat_grps; struct completion lun_shutdown_comp; -- cgit v1.2.3