【每周SDV用例】netperf客户端测试失败之后，之后无法再连接服务端测试

【环境信息】
openeulerversion=openEuler-20.03-LTS-SP1
compiletime=2020-12-22-09-16-12
gccversion=7.3.0-20190804.35.oe1
kernelversion=4.19.90-2012.4.0.0053.oe1
openjdkversion=1.8.0.272.b10-4.oe1
[root@openEuler ~]# rpm -q dpdk
dpdk-19.11-33.oe1.aarch64
[root@openEuler ~]# rpm -q gazelle
gazelle-1.0.2-29.aarch64

**【问题复现步骤】**，请描述具体的操作步骤
1.带gazelle启动netserver
LD_PRELOAD=/usr/lib64/liblstack.so GAZELLE_BIND_PROCNAME=netserver netserver -p 12865 -D -f -L 124.88.97.85

```
dpdk_args=["--socket-mem", "1024,0,0,0", "--huge-dir", "/mnt/hugepages-lstack", "--proc-type", "primary", "--legacy-mem", "--map-perfect"]

stack_thread_mode="run-to-wakeup"

use_ltran=0
kni_switch=0

low_power_mode=0
 
#needed mbuf count = tcp_conn_count * mbuf_count_per_conn
tcp_conn_count=1500
mbuf_count_per_conn=138

# send ring size, default is 32, max is 2048
send_ring_size = 32

#protocol stack thread per loop params
#read data form protocol stack into recv_ring
read_connect_number = 4
#process rpc msg number
rpc_number = 4
#read nic pkts number
nic_read_number = 128

nic_rxqueue_size = 4096
nic_txqueue_size = 2048

#each cpu core start a protocol stack thread.
num_cpus="10"

#app worker thread bind to numa in epoll/poll.
app_bind_numa=1
#app main thread affinity set by dpdk.
main_thread_affinity=0

host_addr="124.88.97.85"
mask_addr="255.255.0.0"
gateway_addr="124.88.0.1"
devices="52:54:00:1f:9a:2e"

#0: use rss rule
#1: use tcp tuple rule to specify packet to nic queue
tuple_filter=0

#tuple_filter=1, below cfg valid
num_process=1
process_numa="0,1"
process_idx=0

#tuple_filer=0, below cfg valid
listen_shadow=1

#vlan mode; only support -1~4094, -1 is disabled
nic_vlan_mode=-1

#bond mode; only support bond 4 or 6 mode ,-1 is disabled
bond_mode=-1
#bond slave mac, separated by ; , only support 2 slave mac
#bond_slave_mac="aa:bb:cc:dd:ee:ff;gg:hh:ii:jj:kk:ll"
udp_enable=1
nonblock_mode=0

```
2.启动客户端（测试超过最大包长的包）
netperf -H 124.88.97.85 -L 124.88.27.181 -p 12865 -t UDP_RR -l 5 -- -r 65508 -O MIN_LATENCY,MAX_LATENCY,MEAN_LATENCY,P99_LATENCY,STDDEV_LATENCY,THROUGHPUT,THROUGHPUT_UNITS

3.之后再在客户端测试正常包长
netperf -H 124.88.97.85 -L 124.88.27.181 -p 12865 -t UDP_RR -l 5 -- -r 64 -O MIN_LATENCY,MAX_LATENCY,MEAN_LATENCY,P99_LATENCY,STDDEV_LATENCY,THROUGHPUT,THROUGHPUT_UNITS

**【实际结果】**，请描述出问题的结果和影响
只要netperf出现报错，之后再连接服务端就无法再测试

初步分析：内核是一段时间收不到包或者收包错误，就退回到select状态，等新的包和事件；但是gazelle select超时，recv超时都没有导致一直处于收包状态

openEuler/gazelle

内容风险标识

评论 (5)

openEuler/gazelle .gitee-modal { width: 500px !important; }

内容风险标识