iscsi: use dynamic single thread workqueue to improve performance

euleros inclusion
category: feature
feature: Implement NUMA affinity for order workqueue

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

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.

The performance data as below:
fio cmd:
fio -filename=/dev/disk/by-id/wwn-0x6883fd3100a2ad260036281700000000
-direct=1 -iodepth=32 -rw=read -bs=64k -size=30G -ioengine=libaio
-numjobs=1 -group_reporting -name=mytest -time_based -ramp_time=60
-runtime=60

before patch:
Jobs: 1 (f=1): [R] [52.5% done] [852.3MB/0KB/0KB /s] [13.7K/0/0 iops] [eta 00m:57s]
Jobs: 1 (f=1): [R] [53.3% done] [861.4MB/0KB/0KB /s] [13.8K/0/0 iops] [eta 00m:56s]
Jobs: 1 (f=1): [R] [54.2% done] [868.2MB/0KB/0KB /s] [13.9K/0/0 iops] [eta 00m:55s]

after pactch:
Jobs: 1 (f=1): [R] [53.3% done] [1070MB/0KB/0KB /s] [17.2K/0/0 iops] [eta 00m:56s]
Jobs: 1 (f=1): [R] [55.0% done] [1064MB/0KB/0KB /s] [17.3K/0/0 iops] [eta 00m:54s]
Jobs: 1 (f=1): [R] [56.7% done] [1069MB/0KB/0KB /s] [17.1K/0/0 iops] [eta 00m:52s]

cpu info:
Architecture:          aarch64
Byte Order:            Little Endian
CPU(s):                128
On-line CPU(s) list:   0-127
Thread(s) per core:    1
Core(s) per socket:    64
Socket(s):             2
NUMA node(s):          4
Model:                 0
CPU max MHz:           2600.0000
CPU min MHz:           200.0000
BogoMIPS:              200.00
L1d cache:             64K
L1i cache:             64K
L2 cache:              512K
L3 cache:              32768K
NUMA node0 CPU(s):     0-31
NUMA node1 CPU(s):     32-63
NUMA node2 CPU(s):     64-95
NUMA node3 CPU(s):     96-127
Signed-off-by: NBiaoxiang Ye <yebiaoxiang@huawei.com>
Acked-by: NHanjun Guo <guohanjun@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

drivers/scsi/iscsi_tcp.c

@@ -132,6 +132,7 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk)
 	struct iscsi_conn *conn;
 	struct iscsi_tcp_conn *tcp_conn;
 	read_descriptor_t rd_desc;
+	int current_cpu;
 
 	read_lock_bh(&sk->sk_callback_lock);
 	conn = sk->sk_user_data;
@@ -141,6 +142,13 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk)
 	}
 	tcp_conn = conn->dd_data;
 
+	/* 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;
+	}
+
 	/*
 	 * Use rd_desc to pass 'conn' to iscsi_tcp_recv.
 	 * We set count to 1 because we want the network layer to

drivers/scsi/libiscsi.c

@@ -90,9 +90,15 @@ inline void iscsi_conn_queue_work(struct iscsi_conn *conn)
 {
 	struct Scsi_Host *shost = conn->session->host;
 	struct iscsi_host *ihost = shost_priv(shost);
+	int intimate_cpu = conn->intimate_cpu;
 
-	if (ihost->workq)
+	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);
+	}
 }
 EXPORT_SYMBOL_GPL(iscsi_conn_queue_work);
 
@@ -2682,7 +2688,9 @@ struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht,
 	if (xmit_can_sleep) {
 		snprintf(ihost->workq_name, sizeof(ihost->workq_name),
 			"iscsi_q_%d", shost->host_no);
-		ihost->workq = create_singlethread_workqueue(ihost->workq_name);
+		/* this kind of workqueue only support single work */
+		ihost->workq = alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM |
+						__WQ_DYNAMIC, ihost->workq_name);
 		if (!ihost->workq)
 			goto free_host;
 	}
@@ -2959,6 +2967,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
 	conn->id = conn_idx;
 	conn->exp_statsn = 0;
 	conn->tmf_state = TMF_INITIAL;
+	conn->intimate_cpu = -1;
 
 	timer_setup(&conn->transport_timer, iscsi_check_transport_timeouts, 0);