Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

版本5.11 性能优化问题 #724

Open
niceneo opened this issue Oct 9, 2024 · 3 comments
Open

版本5.11 性能优化问题 #724

niceneo opened this issue Oct 9, 2024 · 3 comments

Comments

@niceneo
Copy link

niceneo commented Oct 9, 2024

文件上传偶尔出现延迟超过5秒,无规律

部署:
上传:
group组内,2台在主机房,1台在同城备机房,ping延迟5ms以内,带宽无瓶颈

下载:
代理到主机房2台storage的nginx上

atop检查,ioutil 达到100%
IMG20241009100351

  1. 硬件厂商排查磁盘写IO不慢, 尝试更换过容量更大的cache卡,调整CPU高性能模式,问题没有解决

  2. 抓包分析,是与 Issues 【fastdfs性能测试间歇性卡顿问题 fastdfs性能测试间歇性卡顿问题 #241】压测类似,在客户端发送完最后一个数据报文后,到storage 返回存储文件信息时,耗时长。

  3. 请教下还有啥办法可以协助定位问题?

  4. 参数是否还可以优化
    storage参数:
    disabled=false
    group_name=g4
    bind_addr=
    client_bind=true
    port=23000
    connect_timeout=30
    network_timeout=60
    heart_beat_interval=30
    stat_report_interval=60
    base_path=/data/fastdfs_storage
    max_connections=65535
    buff_size = 256KB
    accept_threads=2
    work_threads=2
    disk_rw_separated = true
    disk_reader_threads = 2
    disk_writer_threads = 2
    sync_wait_msec=50
    sync_interval=0
    sync_start_time=00:00
    sync_end_time=23:59
    write_mark_file_freq=500
    store_path_count=1
    store_path0=/data/store/M00
    subdir_count_per_path=256
    tracker_server=192.168.1.100:22122
    log_level=info
    run_by_group=
    run_by_user=
    allow_hosts=*
    file_distribute_path_mode=0
    file_distribute_rotate_count=100
    fsync_after_written_bytes=0
    sync_log_buff_interval=10
    sync_binlog_buff_interval=10
    sync_stat_file_interval=300
    thread_stack_size=1024KB
    upload_priority=10
    if_alias_prefix=
    check_file_duplicate=0
    file_signature_method=hash
    key_namespace=FastDFS
    keep_alive=0
    use_access_log = true
    rotate_access_log = true
    access_log_rotate_time=00:00
    rotate_error_log = true
    error_log_rotate_time=00:00
    rotate_access_log_size = 1GB
    rotate_error_log_size = 1GB
    log_file_keep_days = 15
    file_sync_skip_invalid_record=false
    use_connection_pool = false
    connection_pool_max_idle_time = 3600

@happyfish100
Copy link
Owner

版本太低了,建议升级到最新版本。

@niceneo
Copy link
Author

niceneo commented Oct 22, 2024

版本太低了,建议升级到最新版本。

之前是5.11版本,集群升级到6.12版本,java客户端还是旧版本,连接不上集群,
recv body length: 40 is not correct, expect length: 70

对java 客户端版本升级到最新1.3版本后,是可以使用新集群,但是旧 5.11集群连接不上了
recv body length: 70 is not correct, expect length: 40

这样的话,生产还有平滑升级JAVA客户端和fastdfs的集群方案吗?

@happyfish100
Copy link
Owner

需要server端和client SDK同步升级。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants