Commit a4ff4312 authored by Shao Denghui's avatar Shao Denghui Committed by jiangdongxu
Browse files

iscsi: use dynamic single thread workqueue to improve performance 

euleros inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I94XYA


CVE: NA

-------------------------------------------------

On aarch64 NUMA machines, the kworker of iscsi created always jump
around across node boundaries. If it work on the different node even
different cpu package with the softirq of network interface, memcpy
with in iscsi_tcp_segment_recv will be slow down, and iscsi got an
terrible performance.

In this patch, we trace the cpu of softirq, and tell queue_work_on
to execute iscsi_xmitworker on the same NUMA node.

Signed-off-by: default avatarBiaoxiang Ye <yebiaoxiang@huawei.com>
Signed-off-by: default avatarshaodenghui <shaodenghui@huawei.com>
parent 7400907c

drivers/scsi/iscsi_tcp.c

+13 −0
Original line number Diff line number Diff line
@@ -170,6 +170,9 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) 
	struct iscsi_sw_tcp_conn *tcp_sw_conn;

	struct iscsi_tcp_conn *tcp_conn;

	struct iscsi_conn *conn;

#ifdef KWORKER_NUMA_AFFINITY

	int current_cpu;

#endif



	trace_sk_data_ready(sk);
@@ -180,6 +183,16 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk) 
		return;

	}

	tcp_conn = conn->dd_data;



#ifdef KWORKER_NUMA_AFFINITY

	/* save intimate cpu when in softirq */

	if (!sock_owned_by_user_nocheck(sk)) {

		current_cpu = smp_processor_id();

		if (conn->intimate_cpu != current_cpu)

			conn->intimate_cpu = current_cpu;

	}

#endif



	tcp_sw_conn = tcp_conn->dd_data;



	if (tcp_sw_conn->queue_recv)

drivers/scsi/libiscsi.c

+22 −2
Original line number Diff line number Diff line
@@ -89,9 +89,20 @@ inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn) 
{

	struct Scsi_Host *shost = conn->session->host;

	struct iscsi_host *ihost = shost_priv(shost);

#ifdef KWORKER_NUMA_AFFINITY

	int intimate_cpu = conn->intimate_cpu;



	if (ihost->workq) {

		/* we expect it to be excuted on the same numa of the intimate cpu */

		if ((intimate_cpu >= 0) && cpu_possible(intimate_cpu))

			queue_work_on(intimate_cpu, ihost->workq, &conn->xmitwork);

		else

			queue_work(ihost->workq, &conn->xmitwork);

	}

#else

	if (ihost->workq)

		queue_work(ihost->workq, &conn->xmitwork);

#endif

}

EXPORT_SYMBOL_GPL(iscsi_conn_queue_xmit);
@@ -2907,9 +2918,15 @@ struct Scsi_Host *iscsi_host_alloc(const struct scsi_host_template *sht, 
	ihost = shost_priv(shost);



	if (xmit_can_sleep) {

#ifdef KWORKER_NUMA_AFFINITY

		/* this kind of workqueue only support single work */

		ihost->workq = alloc_ordered_workqueue("iscsi_q_%d", __WQ_LEGACY | WQ_MEM_RECLAIM |

							__WQ_DYNAMIC, shost->host_no);

#else

		ihost->workq = alloc_workqueue("iscsi_q_%d",

				WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,

				1, shost->host_no);

#endif

		if (!ihost->workq)

			goto free_host;

	}
@@ -3190,6 +3207,9 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, 
	conn->c_stage = ISCSI_CONN_INITIAL_STAGE;

	conn->id = conn_idx;

	conn->exp_statsn = 0;

#ifdef KWORKER_NUMA_AFFINITY

	conn->intimate_cpu = -1;

#endif



	timer_setup(&conn->transport_timer, iscsi_check_transport_timeouts, 0);

include/scsi/libiscsi.h

+1 −0
Original line number Diff line number Diff line
@@ -266,6 +266,7 @@ struct iscsi_conn { 
	/* custom statistics */

	uint32_t		eh_abort_cnt;

	uint32_t		fmr_unalign_cnt;

	int			intimate_cpu;



	KABI_RESERVE(1)

	KABI_RESERVE(2)