共计 7934 个字符,预计需要花费 20 分钟才能阅读完成。
Skywalking 是一款分布式追踪利用,具体介绍能够参考 skywalking。
最近公司的一个 Php 利用在 Skywalking 后盾查不到数据了:
登录到某台服务器上发现注册不上,启动时就报错了:
先来整顿下 Skywalking php 的整个流程,php 扩大在系统启动时注册利用和实例,而后在每次申请拦挡相干调用,将相干调用状况保留下来;注册相干代码在 skywalking.c 的 module_init 中:
static void module_init() {
application_instance = -100000;
application_id = -100000;
int i = 0;
do {application_id = serviceRegister(SKYWALKING_G(grpc), SKYWALKING_G(app_code));
if(application_id == -100000) {sleep(1);
}
i++;
} while (application_id == -100000 && i <= 1);
if (application_id == -100000) {
sky_close = 1;
return;
}
char *ipv4s = _get_current_machine_ip();
char hostname[100] = {0};
if (gethostname(hostname, sizeof(hostname)) < 0) {strcpy(hostname, "");
}
char *l_millisecond = get_millisecond();
long millisecond = zend_atol(l_millisecond, strlen(l_millisecond));
efree(l_millisecond);
i = 0;
do {application_instance = serviceInstanceRegister(SKYWALKING_G(grpc), application_id, millisecond, SKY_OS_NAME,
hostname, getpid(),
ipv4s);
if(application_instance == -100000) {sleep(2);
}
i++;
} while (application_instance == -100000 && i <= 5);
if (application_instance == -100000) {
sky_close = 1;
php_error(E_WARNING, "skywalking: register service error");
return;
}
php_error(E_WARNING, "skywalking: register service success");
}
能够看到,注册利用是调用 serviceRegister 函数注册,而后调用 serviceInstanceRegister 来注册实例的,后者会调用 GreeterClient::serviceInstanceRegister 以下函数实现注册:
int serviceInstanceRegister(int applicationid, long registertime, char *osname, char *hostname, int processno,
char *ipv4s) {
ServiceInstances request;
ServiceInstance *s = request.add_instances();
if (uuid == NULL) {std::string uuid_str = boost::uuids::to_string(boost_uuid);
uuid = (char *) malloc(uuid_str.size() + 1);
bzero(uuid, uuid_str.size() + 1);
strncpy(uuid, uuid_str.c_str(), uuid_str.size() + 1);
}
s->set_serviceid(applicationid);
s->set_instanceuuid(std::string(uuid));
s->set_time(registertime);
KeyStringValuePair *os = s->add_properties();
KeyStringValuePair *host = s->add_properties();
KeyStringValuePair *process = s->add_properties();
KeyStringValuePair *ipv4 = s->add_properties();
KeyStringValuePair *language = s->add_properties();
os->set_key("os_name");
os->set_value(osname);
host->set_key("host_name");
host->set_value(hostname);
process->set_key("process_no");
process->set_value(std::to_string(processno));
ipv4->set_key("ipv4");
ipv4->set_value(ipv4s);
language->set_key("language");
language->set_value("php");
ServiceInstanceRegisterMapping reply;
ClientContext context;
Status status = stub_->doServiceInstanceRegister(&context, request, &reply);
if (status.ok()) {for (int i = 0; i < reply.serviceinstances_size(); i++) {const KeyIntValuePair &kv = reply.serviceinstances(i);
// std::cout << "Register Instance:"<< std::endl;
// std::cout << kv.key() << ":" << kv.value() << std::endl;
if (kv.key() == uuid) {return kv.value();
}
}
}
return -100000;
}
通过 gdb 的断点,发现注册利用是胜利的,注册实例失败了,而后在 GreeterClient::serviceInstanceRegister 加上相应的日志:
Status status = stub_->doServiceInstanceRegister(&context, request, &reply);
if (status.ok()) {std::cout << "size:" << reply.serviceinstances_size() << std::endl;
for (int i = 0; i < reply.serviceinstances_size(); i++) {const KeyIntValuePair &kv = reply.serviceinstances(i);
std::cout << "Register Instance:"<< std::endl;
std::cout << kv.key() << ":" << kv.value() << std::endl;
if (kv.key() == uuid) {return kv.value();
}
}
}else{printf("instance register error");
}
这里也把 UUID 打印进去了,发现响应里每次都是空的,所以导致失败。
客户端曾经没有线索了,只好从服务端动手,因为服务端是 Java 实现的,不大不便调试,因而在本地搭了个环境想调试下,哪知服务端跑起来了,Php 客户端死活编译不上,因为 Skywalking 依赖 protobuf、grpc 等组件,这些组件之间有版本依赖关系的,官网文档也没有阐明,一时陷入困境。
因之前服务端保护的同学走了,只好本人硬着头皮看代码,发现注册入口代码在 RegisterServiceHandler::doServiceInstanceRegister 中:
@Override
public void doServiceInstanceRegister(ServiceInstances request,
StreamObserver<ServiceInstanceRegisterMapping> responseObserver) {ServiceInstanceRegisterMapping.Builder builder = ServiceInstanceRegisterMapping.newBuilder();
request.getInstancesList().forEach(instance -> {ServiceInventory serviceInventory = serviceInventoryCache.get(instance.getServiceId());
JsonObject instanceProperties = new JsonObject();
List<String> ipv4s = new ArrayList<>();
for (KeyStringValuePair property : instance.getPropertiesList()) {String key = property.getKey();
switch (key) {
case HOST_NAME:
instanceProperties.addProperty(HOST_NAME, property.getValue());
break;
case OS_NAME:
instanceProperties.addProperty(OS_NAME, property.getValue());
break;
case LANGUAGE:
instanceProperties.addProperty(LANGUAGE, property.getValue());
break;
case "ipv4":
ipv4s.add(property.getValue());
break;
case PROCESS_NO:
instanceProperties.addProperty(PROCESS_NO, property.getValue());
break;
}
}
instanceProperties.addProperty(IPV4S, ServiceInstanceInventory.PropertyUtil.ipv4sSerialize(ipv4s));
String instanceName = serviceInventory.getName();
if (instanceProperties.has(PROCESS_NO)) {instanceName += "-pid:" + instanceProperties.get(PROCESS_NO).getAsString();}
if (instanceProperties.has(HOST_NAME)) {instanceName += "@" + instanceProperties.get(HOST_NAME).getAsString();}
int serviceInstanceId = serviceInstanceInventoryRegister.getOrCreate(instance.getServiceId(), instanceName, instance.getInstanceUUID(), instance.getTime(), instanceProperties);
if (serviceInstanceId != Const.NONE) {logger.info("register service instance id={} [UUID:{}]", serviceInstanceId, instance.getInstanceUUID());
builder.addServiceInstances(KeyIntValuePair.newBuilder().setKey(instance.getInstanceUUID()).setValue(serviceInstanceId));
}
});
responseObserver.onNext(builder.build());
responseObserver.onCompleted();}
要害是这行代码来生成实例 id 的:
int serviceInstanceId = serviceInstanceInventoryRegister.getOrCreate(instance.getServiceId(), instanceName, instance.getInstanceUUID(), instance.getTime(), instanceProperties);
再跟进去:
@Override public int getOrCreate(int serviceId, String serviceInstanceName, String uuid, long registerTime,
JsonObject properties) {if (logger.isDebugEnabled()) {logger.debug("Get or create service instance by service instance name, service id: {}, service instance name: {},uuid: {}, registerTime: {}", serviceId, serviceInstanceName, uuid, registerTime);
}
int serviceInstanceId = getServiceInstanceInventoryCache().getServiceInstanceId(serviceId, uuid);
if (serviceInstanceId == Const.NONE) {ServiceInstanceInventory serviceInstanceInventory = new ServiceInstanceInventory();
serviceInstanceInventory.setServiceId(serviceId);
serviceInstanceInventory.setName(serviceInstanceName);
serviceInstanceInventory.setInstanceUUID(uuid);
serviceInstanceInventory.setIsAddress(BooleanUtils.FALSE);
serviceInstanceInventory.setAddressId(Const.NONE);
serviceInstanceInventory.setRegisterTime(registerTime);
serviceInstanceInventory.setHeartbeatTime(registerTime);
serviceInstanceInventory.setProperties(properties);
InventoryStreamProcessor.getInstance().in(serviceInstanceInventory);
}
return serviceInstanceId;
}
这里的逻辑就比拟清晰了,先从缓存中拿实例 ID:
getServiceInstanceInventoryCache().getServiceInstanceId(serviceId, uuid);
拿不到则退出后台任务解决生成 ID。
再跟进 getServiceInstanceId 办法,
Integer serviceInstanceId = serviceInstanceNameCache.getIfPresent(ServiceInstanceInventory.buildId(serviceId, uuid));
if (Objects.isNull(serviceInstanceId) || serviceInstanceId == Const.NONE) {serviceInstanceId = getCacheDAO().getServiceInstanceId(serviceId, uuid);
if (serviceId != Const.NONE) {serviceInstanceNameCache.put(ServiceInstanceInventory.buildId(serviceId, uuid), serviceInstanceId);
}
}
return serviceInstanceId;
从缓存中拿不到则从 DAO 中拿,
GetResponse response = getClient().get(ServiceInstanceInventory.INDEX_NAME, id);
if (response.isExists()) {return (int)response.getSource().getOrDefault(RegisterSource.SEQUENCE, 0);
} else {return Const.NONE;}
后者从 ES 索引 service_instance_inventory 去拿。
为了证实上述逻辑无误,从 ES 中读取数据试下,果然实例 ID 都注册在 ES 外面:
再从客户端证实下,既然实例 ID 是写入 ES 的,那么用以前的 ID 必定是能注册胜利的,因而批改客户端代码,将 UUID 写死注册试下:
int serviceInstanceRegister(int applicationid, long registertime, char *osname, char *hostname, int processno,
char *ipv4s) {
ServiceInstances request;
ServiceInstance *s = request.add_instances();
uuid= "7e22c317-e2e2-4f81-a53d-fe011013e0a3";
// 省略无关代码
马上注册胜利了:
7e22c317-e2e2-4f81-a53d-fe011013e0a3
size:1
Register Instance:
7e22c317-e2e2-4f81-a53d-fe011013e0a3: 3386041
PHP Warning: skywalking: register service success in Unknown on line 0
PHP Warning: skywalking: hook redis handler success in Unknown on line 0
PHP Warning: skywalking: hook session handler success in Unknown on line 0
再回到这个问题,起因曾经晓得了,如何解决呢,有两个方法:
1、加大注册时等待时间,如期待到 100 秒;
2、记录最近一次注册胜利的 UUID 并且长久化,下次启动时间接用上次的;
因为 2 波及到改代码,因而先用计划 1 解决问题。
Skywalking Php 二:代码剖析
故障演练利器之 ChaosBlade 介绍
寰球智能 DNS 解析实际
一次线上 Mysql 死锁剖析