[openresty][systemtap][docker]执行./ngx-sample-lua-bt -p 32469 --luajit20 -t 5 &gt; tmp.bt报错ERROR: Build-id mismatch [man error::buildid]

[openresty][systemtap][docker]执行./ngx-sample-lua-bt -p 32469 --luajit20 -t 5 > tmp.bt报错ERROR: Build-id mismatch [man error::buildid]

kekys0123

环境：

宿主机版本

[root@85-aliyun-core]# uname -r

3.10.0-514.26.2.el7.x86_64

[root@85-aliyun-core]# lsb_release -a

LSB Version: :core-4.1-amd64:core-4.1-noarch

Distributor ID: CentOS

Description: CentOS Linux release 7.5.1804 (Core)

Release: 7.5.1804

Codename: Core

[root@85-aliyun-core]#

docker kernel信息：

[root@85-132-83-aliyun-core util]# uname -r

3.10.0-514.26.2.el7.x86_64

[root@85-132-83-aliyun-core util]# lsb_release

LSB Version: :core-4.1-amd64:core-4.1-noarch:cxx-4.1-amd64:cxx-4.1-noarch:desktop-4.1-amd64:desktop-4.1-noarch:languages-4.1-amd64:languages-4.1-noarch:printing-4.1-amd64:printing-4.1-noarch

[root@85-132-83-aliyun-core util]# lsb_release -a

LSB Version: :core-4.1-amd64:core-4.1-noarch:cxx-4.1-amd64:cxx-4.1-noarch:desktop-4.1-amd64:desktop-4.1-noarch:languages-4.1-amd64:languages-4.1-noarch:printing-4.1-amd64:printing-4.1-noarch

Distributor ID: CentOS

Description: CentOS Linux release 7.5.1804 (Core)

Release: 7.5.1804

Codename: Core

docker 安装的rpm

[root@85-132-83-aliyun-core util]# rpm -qa | fgrep -i -e kernel | sort

kernel-3.10.0-514.26.2.el7.x86_64

kernel-debug-devel-3.10.0-514.26.2.el7.x86_64

kernel-debuginfo-3.10.0-514.26.2.el7.x86_64

kernel-debuginfo-common-x86_64-3.10.0-514.26.2.el7.x86_64

kernel-devel-3.10.0-514.26.2.el7.x86_64

kernel-headers-3.10.0-514.26.2.el7.x86_64

kernel-tools-3.10.0-514.26.2.el7.x86_64

kernel-tools-debuginfo-3.10.0-514.26.2.el7.x86_64

kernel-tools-libs-3.10.0-514.26.2.el7.x86_64

[root@85-132-83-aliyun-core util]#

1.启动docker --使用--pid=host --privileged 参数

docker run -it --name flamegraph --net=host --pid=host --privileged -v /lib/modules/3.10.0-514.26.2.el7.x86_64:/lib/modules/3.10.0-514.26.2.el7.x86_64 -v /data1/RUF_video_recom:/home -d centos7-ruf-flamegraph:v2

2.查看systemtap安装执行

[root@85aliyun-core systemtap]# stap -v -e 'probe vfs.read {printf("read performed\n"); exit()}'

Pass 1: parsed user script and 471 library scripts using 137320virt/41268res/3444shr/37864data kb, in 370usr/30sys/399real ms.

WARNING: cannot find module nfs debuginfo: No DWARF information found [man warning::debuginfo]

WARNING: cannot find module sunrpc debuginfo: No DWARF information found [man warning::debuginfo]

WARNING: cannot find module nfs debuginfo: No DWARF information found [man warning::debuginfo]

Pass 2: analyzed script: 1 probe, 1 function, 7 embeds, 0 globals using 268616virt/173448res/6420shr/167060data kb, in 2580usr/770sys/6016real ms.

Pass 3: translated to C into "/tmp/stapyrnOvH/stap_cdfdd457c52f576127197101d57e23cf_2721_src.c" using 268616virt/173688res/6660shr/167060data kb, in 10usr/0sys/6real ms.

Pass 4: compiled C into "stap_cdfdd457c52f576127197101d57e23cf_2721.ko" in 8750usr/2090sys/11239real ms.

Pass 5: starting run.

read performed

Pass 5: run completed in 10usr/60sys/427real ms.

执行成功

3. 抓取pid：报错

./ngx-sample-lua-bt -p 16139 --luajit20 -t 10

WARNING: Tracing 16140 16142 16143 16144 16145 16146 16147 16148 16149 16150 16151 16153 16154 16155 16156 16157 (/usr/local/openresty/nginx/sbin/nginx) for LuaJIT 2.0...

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/nginx/sbin/nginx" byte 0 (0x75 vs 0x94) address 0x400284 rc 0

WARNING: task_finder inode-uprobes callback for task 17106 failed: 1

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/nginx/sbin/nginx" byte 0 (0x75 vs 0x94) address 0x400284 rc 0

WARNING: task_finder inode-uprobes callback for task 17110 failed: 1

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/nginx/sbin/nginx" byte 0 (0x75 vs 0x94) address 0x400284 rc 0

WARNING: task_finder inode-uprobes callback for task 17116 failed: 1

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/luajit/lib/libluajit-5.1.so.2.1.0" byte 0 (0xc2 vs 0x08) address 0x7f1576bb0210 rc 0

WARNING: task_finder mmap inode-uprobes callback for task 17110 failed: 1

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/luajit/lib/libluajit-5.1.so.2.1.0" byte 0 (0xc2 vs 0x08) address 0x7f1576bb0210 rc 0

WARNING: task_finder mmap inode-uprobes callback for task 17106 failed: 1

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/luajit/lib/libluajit-5.1.so.2.1.0" byte 0 (0xc2 vs 0x08) address 0x7f1576bb0210 rc 0

WARNING: task_finder mmap inode-uprobes callback for task 17116 failed: 1

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/nginx/sbin/nginx" byte 0 (0x75 vs 0x94) address 0x400284 rc 0

WARNING: task_finder inode-uprobes callback for task 17119 failed: 1

ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/luajit/lib/libluajit-5.1.so.2.1.0" byte 0 (0xc2 vs 0x08) address 0x7f1576bb0210 rc 0

WARNING: task_finder mmap inode-uprobes callback for task 17119 failed: 1

WARNING: /usr/bin/staprun exited with status: 1

yichun

Hello!
On Mon, Nov 12, 2018 at 11:13 PM _Xiangqian C <keky...@gmail.com> wrote:
>
> 3. 抓取pid：报错
> ./ngx-sample-lua-bt -p 16139 --luajit20 -t 10
> WARNING: Tracing 16140 16142 16143 16144 16145 16146 16147 16148 16149 16150 16151 16153 16154 16155 16156 16157 (/usr/local/openresty/nginx/sbin/nginx) for LuaJIT 2.0...
> ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/nginx/sbin/nginx" byte 0 (0x75 vs 0x94) address 0x400284 rc 0
> WARNING: task_finder inode-uprobes callback for task 17106 failed: 1

Docker 虚机有自己的 Linux namespace，有自己的一整套系统库（像 glibc 这样的），所以不能直接这么
probe。我们的 OpenResty Trace 商业平台会提供对 Docker 虚机的原生支持，同时 Docker
虚机本身也不必用特权模式运行，Docker 虚机里也不必安装任何软件。

Regards,
Yichun

kekys0123

现实情况是生产环境就是部署在centos 的docker中，我需要模拟生产环境，部署火焰图。（您说的 OpenResty Trace 商业平台会提供对 Docker 虚机的原生支持可以辛苦给下链接吗）

万幸，通过摸索目前已经搭建了一个稳定版本的火焰图的docker镜像，至于ERROR: Build-id mismatch [man error::buildid]的错误，我发现导致的原因应该是ngx-sample-lua-bt -p 16139 --luajit20 的参数--luajit20, 我编译的openresty 使用的是luajit-2.1.0版本，两者并不能很好的支持，所以我降级使用luajit-2.0.5 release版本后，已经可以正常使用了，至于为什么--luajit20 不能支持luajit-2.1.0版本，目前还没有时间去看ngx-sample-lua-bt的源码，只是通过猜测（WARNING:probe process("/usr/local/openresty/luajit/lib/libluajit-5.1.so.2.1.0").function("lua_yield@/home/RUF_relate/ngx_openresty_woo_1.11.2.5/build/LuaJIT-2.1-20170808/src/lj_api.c:1178") inode-offset 000000000001ec80 registration error (rc -524)

）

在 2018年11月16日，上午9:12，Yichun Zhang <yi...@openresty.com> 写道：

Hello!
On Mon, Nov 12, 2018 at 11:13 PM _Xiangqian C <keky...@gmail.com> wrote:

3. 抓取pid：报错
./ngx-sample-lua-bt -p 16139 --luajit20 -t 10
WARNING: Tracing 16140 16142 16143 16144 16145 16146 16147 16148 16149 16150 16151 16153 16154 16155 16156 16157 (/usr/local/openresty/nginx/sbin/nginx) for LuaJIT 2.0...
ERROR: Build-id mismatch [man error::buildid]: "/usr/local/openresty/nginx/sbin/nginx" byte 0 (0x75 vs 0x94) address 0x400284 rc 0
WARNING: task_finder inode-uprobes callback for task 17106 failed: 1

Docker 虚机有自己的 Linux namespace，有自己的一整套系统库（像 glibc 这样的），所以不能直接这么
probe。我们的 OpenResty Trace 商业平台会提供对 Docker 虚机的原生支持，同时 Docker
虚机本身也不必用特权模式运行，Docker 虚机里也不必安装任何软件。

Regards,
Yichun

--
--