feat(system): 添加系统资源检测功能

- 新增系统资源限制、内核启动参数和内核关键参数检测
- 扩展CPU检测，增加中断统计、软中断、调度器队列和CPU亲和性检测
- 添加内存压力、虚拟内存统计、Slab缓存和大页内存检测
- 增加磁盘延迟、NFS挂载、RAID状态、LVM和磁盘调度算法检测
- 新增不可中断进程、进程文件句柄和网络连接数TOP5检测
- 添加TCP参数、扩展统计、ARP表、路由表和Socket统计检测
- 扩展PowerShell脚本模块映射和国际化

AuxiliaryTool/ScriptTool/服务器监测/check_server_health_modular.ps1

@@ -342,7 +342,15 @@ function Get-ModuleCategory {
     )
 
     switch -Regex ($ModuleName) {
-        "^(0[1-9]|1[0-2])_" { return "系统基础信息" }
+        "^01_" { return "系统基础信息" }
+        "^02_" { return "CPU检测" }
+        "^03_" { return "内存检测" }
+        "^04_" { return "磁盘检测" }
+        "^05_" { return "OOM检测" }
+        "^06_" { return "进程检测" }
+        "^07_" { return "网络检测" }
+        "^11_" { return "计划任务" }
+        "^12_" { return "端口检测" }
         "^(20|21)_" { return "Docker容器" }
         "^2[23]_" { return "MySQL数据库" }
         "^2[45]_" { return "Redis缓存" }
@@ -415,6 +423,92 @@ function Get-DisplayName {
         "CPU_USAGE" = "CPU使用率"
         "MEMORY_USAGE" = "内存使用率"
         "DISK_USAGE" = "磁盘使用率"
+        "ULIMIT_INFO" = "系统资源限制"
+        "KERNEL_CMDLINE" = "内核启动参数"
+        "KERNEL_PARAM_FS_FILE_MAX" = "文件描述符最大值"
+        "KERNEL_PARAM_INOTIFY_MAX_WATCHES" = "inotify最大监听数"
+        "KERNEL_PARAM_SOMAXCONN" = "监听队列最大长度"
+        "KERNEL_PARAM_TCP_TW_REUSE" = "TCP TIME_WAIT重用"
+        "KERNEL_PARAM_TCP_FIN_TIMEOUT" = "TCP FIN超时时间"
+        "CPU_USER" = "CPU用户态使用率"
+        "CPU_SYSTEM" = "CPU系统态使用率"
+        "CPU_PER_CORE" = "各核心CPU使用率"
+        "CPU_TOP10_PROCESSES" = "CPU占用TOP10进程"
+        "CPU_CONTEXT_SWITCHES" = "CPU上下文切换次数"
+        "CPU_INTERRUPTS" = "CPU中断次数"
+        "IRQ_DETAIL" = "中断详情"
+        "SOFTIRQS" = "软中断统计"
+        "SCHEDULER_RUNQUEUE" = "调度器运行队列长度"
+        "CPU_AFFINITY_SAMPLE" = "CPU亲和性示例"
+        "MEMORY_USED" = "已用内存"
+        "MEMORY_FREE" = "空闲内存"
+        "MEMORY_TOTAL" = "总内存"
+        "MEMORY_BUFFERS" = "内存缓冲区"
+        "MEMORY_CACHED" = "内存缓存"
+        "MEMORY_TOP5_PROCESSES" = "内存占用TOP5进程"
+        "MEMORY_PRESSURE_AVG10" = "内存压力(avg10)"
+        "MEMORY_PRESSURE_AVG60" = "内存压力(avg60)"
+        "VM_PGMajFAULT" = "主缺页异常次数"
+        "VM_PSWPIN" = "换入页面数"
+        "VM_PSWPOUT" = "换出页面数"
+        "SLAB_TOTAL" = "Slab缓存总量"
+        "SLAB_RECLAIMABLE" = "可回收Slab缓存"
+        "HUGEPAGES_TOTAL" = "大页总数"
+        "HUGEPAGES_FREE" = "空闲大页数"
+        "HUGEPAGES_SIZE" = "大页大小"
+        "TRANSPARENT_HUGEPAGE" = "透明大页状态"
+        "FD_ALLOCATED" = "已分配文件描述符"
+        "FD_MAXIMUM" = "最大文件描述符"
+        "FD_STATUS" = "文件描述符状态"
+        "LOAD_CORES" = "CPU核心数"
+        "LOAD_RATIO" = "负载与核心数比值"
+        "LOAD_STATUS" = "系统负载状态"
+        "PROCESS_TOP10_CPU" = "CPU占用TOP10进程"
+        "PROCESS_TOP10_MEMORY" = "内存占用TOP10进程"
+        "PROCESS_COUNT" = "进程总数"
+        "PROCESS_LONGEST_RUNNING" = "运行时间最长进程"
+        "ZOMBIE_COUNT" = "僵尸进程数"
+        "ZOMBIE_STATUS" = "僵尸进程状态"
+        "THREAD_STATUS" = "线程状态"
+        "UNINTERRUPTIBLE_COUNT" = "不可中断进程数"
+        "UNINTERRUPTIBLE_PROCESSES" = "不可中断进程详情"
+        "UNINTERRUPTIBLE_STATUS" = "不可中断进程状态"
+        "PROCESS_OPEN_FILES_TOP5" = "打开文件数TOP5进程"
+        "PROCESS_CONNECTIONS_TOP5" = "网络连接数TOP5进程"
+        "TCP_ESTABLISHED" = "ESTABLISHED连接数"
+        "TCP_TIME_WAIT" = "TIME_WAIT连接数"
+        "TCP_TIME_WAIT_STATUS" = "TIME_WAIT连接状态"
+        "TCP_CLOSE_WAIT" = "CLOSE_WAIT连接数"
+        "TCP_CLOSE_WAIT_STATUS" = "CLOSE_WAIT连接状态"
+        "NET_INTERFACE_UP" = "启用网络接口数"
+        "NET_INTERFACE_TOTAL" = "总网络接口数"
+        "NET_INTERFACE_STATUS" = "网络接口状态"
+        "NET_ERRORS" = "网络错误"
+        "NET_ERRORS_STATUS" = "网络错误状态"
+        "NET_TRAFFIC" = "网络流量"
+        "DNS_RESOLUTION" = "DNS解析状态"
+        "NET_HOSTNAME" = "主机名"
+        "NET_GATEWAY" = "默认网关"
+        "NET_GATEWAY_STATUS" = "网关状态"
+        "TCP_EXTENDED_STATS" = "TCP扩展统计"
+        "ARP_ENTRIES" = "ARP表项"
+        "ARP_COUNT" = "ARP条目数"
+        "ROUTES_COUNT" = "路由条目数"
+        "SOCKET_STATS" = "Socket统计"
+        "NET_BANDWIDTH_DETAIL" = "网络带宽详情"
+        "LISTEN_QUEUE_BACKLOG" = "监听队列积压"
+        "GATEWAY_PING_STATUS" = "网关连通性"
+        "CONTAINER_NETWORK_TO_EMQX" = "到EMQX容器网络"
+        "DISK_IO_STATUS" = "磁盘IO状态"
+        "DISK_SMART_STATUS" = "磁盘SMART状态"
+        "DISK_PARTITIONS" = "磁盘分区信息"
+        "DISK_LATENCY" = "磁盘延迟"
+        "REMOTE_MOUNTS" = "远程挂载点"
+        "REMOTE_MOUNTS_COUNT" = "远程挂载数量"
+        "RAID_DEVICES" = "RAID设备"
+        "RAID_STATUS" = "RAID状态"
+        "LVM_VOLUMES" = "LVM卷信息"
+        "DISK_SCHEDULER" = "磁盘调度器"
 
         # Redis基础
         "KEY_COUNT" = "Redis键数量"
@@ -960,6 +1054,24 @@ function Get-Threshold {
         "EMQX_CERT_LEVEL" = "<30天"
         "MYSQL_CERT_MIN_DAYS" = "<30天"
         "MYSQL_CERT_LEVEL" = "<30天"
+
+        # ==================== 系统基础信息新增阈值 ====================
+        "TCP_TIME_WAIT_STATUS" = "严重"
+        "TCP_CLOSE_WAIT_STATUS" = "严重"
+        "NET_INTERFACE_STATUS" = "严重"
+        "NET_ERRORS_STATUS" = "警告"
+        "DNS_RESOLUTION" = "警告"
+        "NET_GATEWAY_STATUS" = "警告"
+        "GATEWAY_PING_STATUS" = "异常"
+        "FD_STATUS" = "严重"
+        "LOAD_STATUS" = "严重"
+        "ZOMBIE_STATUS" = "严重"
+        "THREAD_STATUS" = "严重"
+        "UNINTERRUPTIBLE_STATUS" = "严重"
+        "DISK_SMART_STATUS" = "严重"
+        "RAID_STATUS" = "degraded"
+        "MEMORY_PRESSURE_AVG10" = ">1"
+        "VM_PGMajFAULT" = ">100"
     }
 
     if ($thresholds.ContainsKey($Key)) {

AuxiliaryTool/ScriptTool/服务器监测/lib/system/01_system_basic.sh

@@ -114,6 +114,75 @@ check_architecture() {
     output_result "ARCHITECTURE" "$arch"
 }
 
+# 检测系统资源限制
+check_ulimit() {
+    local ulimit_info=""
+    if check_command ulimit; then
+        ulimit_info=$(ulimit -a 2>/dev/null | head -20 | tr '\n' ',' | sed 's/,$//')
+    fi
+    if [ -n "$ulimit_info" ]; then
+        output_result "ULIMIT_INFO" "$ulimit_info"
+    else
+        output_result "ULIMIT_INFO" "无法获取"
+    fi
+}
+
+# 检测内核启动参数
+check_kernel_cmdline() {
+    local cmdline=""
+    if [ -f /proc/cmdline ]; then
+        cmdline=$(cat /proc/cmdline 2>/dev/null | tr ' ' ',')
+        # 截取前200个字符避免过长
+        cmdline=${cmdline:0:200}
+        if [ ${#cmdline} -eq 200 ]; then
+            cmdline="${cmdline}..."
+        fi
+    fi
+    if [ -n "$cmdline" ]; then
+        output_result "KERNEL_CMDLINE" "$cmdline"
+    else
+        output_result "KERNEL_CMDLINE" "无法读取"
+    fi
+}
+
+# 检测内核关键参数
+check_kernel_params() {
+    # 文件描述符限制
+    local file_max=""
+    if [ -f /proc/sys/fs/file-max ]; then
+        file_max=$(cat /proc/sys/fs/file-max 2>/dev/null)
+    fi
+    [ -n "$file_max" ] && output_result "FS_FILE_MAX" "$file_max"
+
+    # inotify监控限制
+    local inotify_max_watches=""
+    if [ -f /proc/sys/fs/inotify/max_user_watches ]; then
+        inotify_max_watches=$(cat /proc/sys/fs/inotify/max_user_watches 2>/dev/null)
+    fi
+    [ -n "$inotify_max_watches" ] && output_result "INOTIFY_MAX_WATCHES" "$inotify_max_watches"
+
+    # TCP连接队列
+    local somaxconn=""
+    if [ -f /proc/sys/net/core/somaxconn ]; then
+        somaxconn=$(cat /proc/sys/net/core/somaxconn 2>/dev/null)
+    fi
+    [ -n "$somaxconn" ] && output_result "NET_SOMAXCONN" "$somaxconn"
+
+    # TCP TIME_WAIT超时
+    local tcp_tw_timeout=""
+    if [ -f /proc/sys/net/ipv4/tcp_fin_timeout ]; then
+        tcp_tw_timeout=$(cat /proc/sys/net/ipv4/tcp_fin_timeout 2>/dev/null)
+    fi
+    [ -n "$tcp_tw_timeout" ] && output_result "TCP_FIN_TIMEOUT" "$tcp_tw_timeout"
+
+    # TCP保活时间
+    local tcp_keepalive_time=""
+    if [ -f /proc/sys/net/ipv4/tcp_keepalive_time ]; then
+        tcp_keepalive_time=$(cat /proc/sys/net/ipv4/tcp_keepalive_time 2>/dev/null)
+    fi
+    [ -n "$tcp_keepalive_time" ] && output_result "TCP_KEEPALIVE_TIME" "$tcp_keepalive_time"
+}
+
 # ==================== 主检测流程 ====================
 main() {
     log_info "开始系统基础信息检测..."
@@ -128,6 +197,9 @@ main() {
     check_memory_total
     check_boot_time
     check_architecture
+    check_ulimit
+    check_kernel_cmdline
+    check_kernel_params
 
     log_info "系统基础信息检测完成"
 }

AuxiliaryTool/ScriptTool/服务器监测/lib/system/02_cpu_check.sh

@@ -105,27 +105,29 @@ check_cpu_per_core() {
     fi
 }
 
-# 检测CPU占用TOP5进程
-check_cpu_top5() {
-    local top5
-    top5=$(ps -eo pid,comm,%cpu,%mem --no-headers 2>/dev/null | sort -k3 -rn | head -5)
+# 检测CPU占用TOP15进程
+check_cpu_top15() {
+    local top15
+    top15=$(ps -eo pid,comm,%cpu --no-headers 2>/dev/null | sort -k3 -rn | head -15)
 
-    if [ -n "$top5" ]; then
-        # 格式化输出
+    if [ -n "$top15" ]; then
+        # 格式化输出，只取前10个避免过长
         local formatted=""
+        local count=0
         while IFS= read -r line; do
-            if [ -n "$line" ]; then
+            if [ -n "$line" ] && [ $count -lt 10 ]; then
                 if [ -n "$formatted" ]; then
                     formatted="${formatted}; ${line}"
                 else
                     formatted="${line}"
                 fi
+                count=$((count + 1))
             fi
-        done <<< "$top5"
+        done <<< "$top15"
 
-        output_result "CPU_TOP5_PROCESSES" "$formatted"
+        output_result "CPU_TOP10_PROCESSES" "$formatted"
     else
-        output_result "CPU_TOP5_PROCESSES" "获取失败"
+        output_result "CPU_TOP10_PROCESSES" "获取失败"
     fi
 }
 
@@ -157,6 +159,56 @@ check_cpu_interrupts() {
     fi
 }
 
+# 检测详细中断统计(/proc/interrupts)
+check_interrupts_detail() {
+    if [ -f /proc/interrupts ]; then
+        # 获取前10个中断的统计
+        local interrupts
+        interrupts=$(head -10 /proc/interrupts 2>/dev/null | grep -v "^$" | tr '\n' ',' | sed 's/,$//')
+        if [ -n "$interrupts" ]; then
+            output_result "IRQ_DETAIL" "$interrupts"
+        fi
+    fi
+}
+
+# 检测软中断统计
+check_softirqs() {
+    if [ -f /proc/softirqs ]; then
+        local softirqs
+        softirqs=$(cat /proc/softirqs 2>/dev/null | tr '\n' ',' | sed 's/,$//')
+        if [ -n "$softirqs" ]; then
+            output_result "SOFTIRQS" "$softirqs"
+        fi
+    fi
+}
+
+# 检测CPU调度器运行队列长度
+check_scheduler_runqueue() {
+    local runqueue
+    runqueue=$(awk '/runnable/ {print $2}' /proc/stat 2>/dev/null)
+
+    if [ -n "$runqueue" ]; then
+        output_result "SCHEDULER_RUNQUEUE" "$runqueue"
+    else
+        output_result "SCHEDULER_RUNQUEUE" "未知"
+    fi
+}
+
+# 检测进程CPU亲和性示例
+check_cpu_affinity() {
+    # 获取init进程的CPU亲和性作为示例
+    local affinity=""
+    if [ -f /proc/1/status ]; then
+        affinity=$(grep "Cpus_allowed_list" /proc/1/status 2>/dev/null | awk '{print $2}')
+    fi
+
+    if [ -n "$affinity" ]; then
+        output_result "CPU_AFFINITY_SAMPLE" "$affinity"
+    else
+        output_result "CPU_AFFINITY_SAMPLE" "未知"
+    fi
+}
+
 # ==================== 主检测流程 ====================
 main() {
     log_info "开始CPU资源检测..."
@@ -164,9 +216,13 @@ main() {
     # 执行各项检测
     check_cpu_usage
     check_cpu_per_core
-    check_cpu_top5
+    check_cpu_top15
     check_cpu_context_switches
     check_cpu_interrupts
+    check_interrupts_detail
+    check_softirqs
+    check_scheduler_runqueue
+    check_cpu_affinity
 
     log_info "CPU资源检测完成"
 }

AuxiliaryTool/ScriptTool/服务器监测/lib/system/03_memory_check.sh

@@ -167,6 +167,77 @@ check_memory_top5() {
     fi
 }
 
+# 检测内存压力
+check_memory_pressure() {
+    if [ -f /proc/pressure/memory ]; then
+        local pressure_info
+        pressure_info=$(cat /proc/pressure/memory 2>/dev/null | head -1)
+        if [ -n "$pressure_info" ]; then
+            # 解析一些关键指标
+            local avg10=$(echo "$pressure_info" | grep -oP 'avg10=\K[\d.]+' || echo "0")
+            local avg60=$(echo "$pressure_info" | grep -oP 'avg60=\K[\d.]+' || echo "0")
+            output_result "MEMORY_PRESSURE_AVG10" "$avg10"
+            output_result "MEMORY_PRESSURE_AVG60" "$avg60"
+        fi
+    else
+        output_result "MEMORY_PRESSURE" "不支持"
+    fi
+}
+
+# 检测虚拟内存统计
+check_vm_stat() {
+    if [ -f /proc/vmstat ]; then
+        # 获取一些关键指标
+        local pgmajfault pswpin pswpout
+        pgmajfault=$(awk '/pgmajfault/ {print $2}' /proc/vmstat 2>/dev/null || echo "0")
+        pswpin=$(awk '/pswpin/ {print $2}' /proc/vmstat 2>/dev/null || echo "0")
+        pswpout=$(awk '/pswpout/ {print $2}' /proc/vmstat 2>/dev/null || echo "0")
+
+        output_result "VM_PGMajFAULT" "$pgmajfault"
+        output_result "VM_PSWPIN" "$pswpin"
+        output_result "VM_PSWPOUT" "$pswpout"
+    fi
+}
+
+# 检测Slab缓存
+check_slab_info() {
+    if [ -f /proc/meminfo ]; then
+        local slab_total slab_reclaimable
+        slab_total=$(awk '/^Slab:/ {print $2}' /proc/meminfo 2>/dev/null)
+        slab_reclaimable=$(awk '/^SReclaimable:/ {print $2}' /proc/meminfo 2>/dev/null)
+
+        if [ -n "$slab_total" ]; then
+            local slab_mb=$(awk "BEGIN {printf \"%.2f\", $slab_total/1024}")
+            output_result "SLAB_TOTAL" "${slab_mb}MB"
+        fi
+
+        if [ -n "$slab_reclaimable" ]; then
+            local reclaimable_mb=$(awk "BEGIN {printf \"%.2f\", $slab_reclaimable/1024}")
+            output_result "SLAB_RECLAIMABLE" "${reclaimable_mb}MB"
+        fi
+    fi
+}
+
+# 检测大页内存
+check_hugepages() {
+    if [ -f /proc/meminfo ]; then
+        local huge_total huge_free huge_size
+        huge_total=$(awk '/^HugePages_Total:/ {print $2}' /proc/meminfo 2>/dev/null)
+        huge_free=$(awk '/^HugePages_Free:/ {print $2}' /proc/meminfo 2>/dev/null)
+        huge_size=$(awk '/^Hugepagesize:/ {print $2}' /proc/meminfo 2>/dev/null)
+
+        output_result "HUGEPAGES_TOTAL" "${huge_total:-0}"
+        output_result "HUGEPAGES_FREE" "${huge_free:-0}"
+        output_result "HUGEPAGES_SIZE" "${huge_size:-未知}"
+
+        # 检查是否启用了透明大页
+        if [ -f /sys/kernel/mm/transparent_hugepage/enabled ]; then
+            local thp_enabled=$(cat /sys/kernel/mm/transparent_hugepage/enabled 2>/dev/null)
+            output_result "TRANSPARENT_HUGEPAGE" "$thp_enabled"
+        fi
+    fi
+}
+
 # ==================== 主检测流程 ====================
 main() {
     log_info "开始内存资源检测..."
@@ -177,6 +248,10 @@ main() {
     check_memory_details
     check_numa
     check_memory_top5
+    check_memory_pressure
+    check_vm_stat
+    check_slab_info
+    check_hugepages
 
     log_info "内存资源检测完成"
 }

AuxiliaryTool/ScriptTool/服务器监测/lib/system/04_disk_check.sh

@@ -207,6 +207,89 @@ check_disk_speed() {
     fi
 }
 
+# 检测磁盘延迟统计
+check_disk_latency() {
+    if [ -f /proc/diskstats ]; then
+        # 获取前几个磁盘的延迟信息
+        local disk_latency
+        disk_latency=$(head -5 /proc/diskstats 2>/dev/null | awk '{print $3":"$4":"$7":"$8}' | tr '\n' ',' | sed 's/,$//')
+        if [ -n "$disk_latency" ]; then
+            output_result "DISK_LATENCY" "$disk_latency"
+        fi
+    fi
+}
+
+# 检查网络文件系统挂载
+check_nfs_mounts() {
+    local nfs_mounts
+    nfs_mounts=$(mount | grep -E "(nfs|cifs|smbfs|fuse.sshfs)" 2>/dev/null | awk '{print $1":"$3}' | tr '\n' ',' | sed 's/,$//')
+
+    if [ -n "$nfs_mounts" ]; then
+        output_result "REMOTE_MOUNTS" "$nfs_mounts"
+        output_result "REMOTE_MOUNTS_COUNT" "$(echo "$nfs_mounts" | tr ',' '\n' | wc -l)"
+    else
+        output_result "REMOTE_MOUNTS_COUNT" "0"
+    fi
+}
+
+# 检测RAID状态
+check_raid_status() {
+    if [ -f /proc/mdstat ]; then
+        local mdstat
+        mdstat=$(cat /proc/mdstat 2>/dev/null)
+        if [ -n "$mdstat" ]; then
+            # 检查是否有RAID设备
+            if echo "$mdstat" | grep -q "md"; then
+                local raid_devices
+                raid_devices=$(echo "$mdstat" | grep -oE "md[0-9]+" | tr '\n' ',' | sed 's/,$//')
+                output_result "RAID_DEVICES" "$raid_devices"
+
+                # 检查RAID状态
+                if echo "$mdstat" | grep -q "\[UU+\]"; then
+                    output_result "RAID_STATUS" "正常"
+                elif echo "$mdstat" | grep -q "\[UU\]"; then
+                    output_result "RAID_STATUS" "正常"
+                else
+                    output_result "RAID_STATUS" " degraded"
+                fi
+            else
+                output_result "RAID_STATUS" "无RAID设备"
+            fi
+        else
+            output_result "RAID_STATUS" "无法读取"
+        fi
+    else
+        output_result "RAID_STATUS" "无/proc/mdstat"
+    fi
+}
+
+# 检测LVM状态
+check_lvm_status() {
+    if command -v lvs &> /dev/null; then
+        local lvm_info
+        lvm_info=$(lvs --noheadings --separator ',' -o lv_name,lv_size,lv_attr 2>/dev/null)
+        if [ -n "$lvm_info" ]; then
+            output_result "LVM_VOLUMES" "$lvm_info"
+        fi
+    else
+        output_result "LVM_STATUS" "未安装lvs"
+    fi
+}
+
+# 检测磁盘调度算法
+check_disk_scheduler() {
+    local scheduler=""
+    # 检查第一个块设备的调度器
+    for disk in /sys/block/*; do
+        if [ -d "$disk/queue/scheduler" ]; then
+            local dev_name=$(basename "$disk")
+            scheduler=$(cat "$disk/queue/scheduler" 2>/dev/null | grep -oP '\[[^\]]+\]' | tr -d '[]')
+            output_result "DISK_SCHEDULER_${dev_name}" "$scheduler"
+            break
+        fi
+    done
+}
+
 # ==================== 主检测流程 ====================
 main() {
     log_info "开始磁盘资源检测..."
@@ -217,6 +300,11 @@ main() {
     check_disk_io
     check_disk_smart
     check_disk_partitions
+    check_disk_latency
+    check_nfs_mounts
+    check_raid_status
+    check_lvm_status
+    check_disk_scheduler
     # check_disk_speed  # 可选，比较耗时
 
     log_info "磁盘资源检测完成"

AuxiliaryTool/ScriptTool/服务器监测/lib/system/06_process_check.sh

@@ -211,6 +211,67 @@ check_longest_running() {
     fi
 }
 
+# 检测D状态不可中断睡眠进程
+check uninterruptible_processes() {
+    local d_count=0
+    local d_processes=""
+
+    # 统计D状态进程
+    d_processes=$(ps -eo stat,pid,comm --no-headers 2>/dev/null | grep " D" | head -10)
+    d_count=$(echo "$d_processes" | wc -l)
+
+    if [ -n "$d_processes" ]; then
+        d_processes=$(echo "$d_processes" | tr '\n' ',' | sed 's/,$//')
+    fi
+
+    output_result "UNINTERRUPTIBLE_COUNT" "$d_count"
+
+    if [ -n "$d_processes" ]; then
+        output_result "UNINTERRUPTIBLE_PROCESSES" "$d_processes"
+    fi
+
+    if [ "$d_count" -gt 5 ]; then
+        output_result "UNINTERRUPTIBLE_STATUS" "严重"
+    elif [ "$d_count" -gt 0 ]; then
+        output_result "UNINTERRUPTIBLE_STATUS" "警告"
+    else
+        output_result "UNINTERRUPTIBLE_STATUS" "正常"
+    fi
+}
+
+# 按进程统计打开文件数TOP5
+check_process_open_files_top5() {
+    if command -v lsof &> /dev/null; then
+        local top5
+        top5=$(lsof 2>/dev/null | awk '{print $2}' | sort | uniq -c | sort -rn | head -5)
+
+        if [ -n "$top5" ]; then
+            output_result "PROCESS_OPEN_FILES_TOP5" "$top5"
+        else
+            output_result "PROCESS_OPEN_FILES_TOP5" "无数据"
+        fi
+    else
+        output_result "PROCESS_OPEN_FILES_TOP5" "lsof不可用"
+    fi
+}
+
+# 按进程统计网络连接数TOP5
+check_process_connections_top5() {
+    if command -v ss &> /dev/null; then
+        local top5
+        # 获取各进程的网络连接数
+        top5=$(ss -ntp 2>/dev/null | awk '{print $7}' | sort | uniq -c | sort -rn | head -5 | grep -v "PID")
+
+        if [ -n "$top5" ]; then
+            output_result "PROCESS_CONNECTIONS_TOP5" "$top5"
+        else
+            output_result "PROCESS_CONNECTIONS_TOP5" "无数据"
+        fi
+    else
+        output_result "PROCESS_CONNECTIONS_TOP5" "ss不可用"
+    fi
+}
+
 # ==================== 主检测流程 ====================
 main() {
     log_info "开始进程状态检测..."
@@ -224,6 +285,9 @@ main() {
     check_process_top_cpu
     check_process_top_memory
     check_longest_running
+    check_uninterruptible_processes
+    check_process_open_files_top5
+    check_process_connections_top5
 
     log_info "进程状态检测完成"
 }

AuxiliaryTool/ScriptTool/服务器监测/lib/system/07_network_check.sh

@@ -215,6 +215,146 @@ check_network_config() {
     fi
 }
 
+# 检测TCP参数配置
+check_tcp_params() {
+    # 检查关键TCP参数
+    local tcp_tw_reuse=""
+    local tcp_tw_recycle=""
+    local tcp_fin_timeout=""
+
+    if [ -f /proc/sys/net/ipv4/tcp_tw_reuse ]; then
+        tcp_tw_reuse=$(cat /proc/sys/net/ipv4/tcp_tw_reuse 2>/dev/null)
+    fi
+    if [ -f /proc/sys/net/ipv4/tcp_tw_recycle ]; then
+        tcp_tw_recycle=$(cat /proc/sys/net/ipv4/tcp_tw_recycle 2>/dev/null)
+    fi
+    if [ -f /proc/sys/net/ipv4/tcp_fin_timeout ]; then
+        tcp_fin_timeout=$(cat /proc/sys/net/ipv4/tcp_fin_timeout 2>/dev/null)
+    fi
+
+    [ -n "$tcp_tw_reuse" ] && output_result "TCP_TW_REUSE" "$tcp_tw_reuse"
+    [ -n "$tcp_tw_recycle" ] && output_result "TCP_TW_RECYCLE" "$tcp_tw_recycle"
+    [ -n "$tcp_fin_timeout" ] && output_result "TCP_FIN_TIMEOUT_PARAM" "$tcp_fin_timeout"
+}
+
+# 检测TCP扩展统计
+check_tcp_extended_stats() {
+    if [ -f /proc/net/snmp ]; then
+        # 获取TCP扩展统计
+        local tcp_stats=""
+        tcp_stats=$(cat /proc/net/snmp 2>/dev/null | grep "^Tcp:" | head -1)
+        if [ -n "$tcp_stats" ]; then
+            output_result "TCP_EXT_STATS" "$(echo "$tcp_stats" | cut -c1-200)"  # 截取前200字符
+        fi
+    fi
+}
+
+# 检测ARP表
+check_arp_table() {
+    local arp_count=""
+    local arp_entries=""
+
+    if command -v ip &> /dev/null; then
+        arp_entries=$(ip neigh show 2>/dev/null | grep -v "FAILED" | head -10 | tr '\n' ',' | sed 's/,$//')
+        arp_count=$(ip neigh show 2>/dev/null | grep -v "FAILED" | wc -l)
+    fi
+
+    [ -n "$arp_entries" ] && output_result "ARP_ENTRIES" "$arp_entries"
+    [ -n "$arp_count" ] && output_result "ARP_COUNT" "$arp_count"
+}
+
+# 检测路由表
+check_routing_table() {
+    if command -v ip &> /dev/null; then
+        local route_count=""
+        route_count=$(ip route show 2>/dev/null | wc -l)
+        output_result "ROUTES_COUNT" "$route_count"
+    fi
+}
+
+# 检测Socket统计
+check_socket_stats() {
+    if [ -f /proc/net/sockstat ]; then
+        local sockstat
+        sockstat=$(cat /proc/net/sockstat 2>/dev/null | tr '\n' ',' | sed 's/,$//')
+        if [ -n "$sockstat" ]; then
+            output_result "SOCKET_STATS" "$sockstat"
+        fi
+    fi
+}
+
+# 检测网络带宽统计详情
+check_network_bandwidth() {
+    if [ -f /proc/net/dev ]; then
+        # 获取主要网络接口的带宽统计
+        local bandwidth_info=""
+        bandwidth_info=$(tail -n +3 /proc/net/dev | head -3 | awk '{print $1":"$2":"$10}' | tr '\n' ',' | sed 's/,$//')
+
+        if [ -n "$bandwidth_info" ]; then
+            output_result "NET_BANDWIDTH_DETAIL" "$bandwidth_info"
+        fi
+    fi
+}
+
+# 检测监听队列积压
+check_listen_queue() {
+    if command -v ss &> /dev/null; then
+        # 检查监听队列积压情况
+        local queue_full=""
+        queue_full=$(ss -lnt 2>/dev/null | awk '{print $6}' | grep -v "0" | head -5)
+
+        if [ -n "$queue_full" ]; then
+            output_result "LISTEN_QUEUE_BACKLOG" "$queue_full"
+        else
+            output_result "LISTEN_QUEUE_BACKLOG" "正常"
+        fi
+    else
+        output_result "LISTEN_QUEUE_BACKLOG" "ss不可用"
+    fi
+}
+
+# 检测网关连通性
+check_gateway_connectivity() {
+    local gateway=""
+    local ping_status="未测试"
+
+    # 获取默认网关
+    if command -v ip &> /dev/null; then
+        gateway=$(ip route | grep default | awk '{print $3}' | head -1)
+    elif command -v route &> /dev/null; then
+        gateway=$(route -n | grep "^0.0.0.0" | awk '{print $2}' | head -1)
+    fi
+
+    if [ -n "$gateway" ] && command -v ping &> /dev/null; then
+        # ping网关3次，每次超时1秒
+        if ping -c 3 -W 1 "$gateway" &>/dev/null; then
+            ping_status="正常"
+        else
+            ping_status="异常"
+        fi
+    fi
+
+    output_result "GATEWAY_PING_STATUS" "$ping_status"
+}
+
+# 检测容器间网络连通性
+check_container_network() {
+    # 检查Docker容器间网络连通性
+    if command -v docker &> /dev/null; then
+        # ping uemqx容器
+        local uemqx_ip=""
+        uemqx_ip=$(docker inspect --format='{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' uemqx 2>/dev/null | head -1)
+
+        if [ -n "$uemqx_ip" ] && command -v ping &> /dev/null; then
+            if ping -c 1 -W 1 "$uemqx_ip" &>/dev/null; then
+                output_result "CONTAINER_NETWORK_TO_EMQX" "正常"
+            else
+                output_result "CONTAINER_NETWORK_TO_EMQX" "异常"
+            fi
+        fi
+    fi
+}
+
 # ==================== 主检测流程 ====================
 main() {
     log_info "开始网络连接检测..."
@@ -227,6 +367,15 @@ main() {
     check_network_traffic
     check_dns_resolution
     check_network_config
+    check_tcp_params
+    check_tcp_extended_stats
+    check_arp_table
+    check_routing_table
+    check_socket_stats
+    check_network_bandwidth
+    check_listen_queue
+    check_gateway_connectivity
+    check_container_network
 
     log_info "网络连接检测完成"
 }