langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-24 04:25:01 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

[Bug] api container memory leak after upgrading to 0.14.0 #7225

New Issue
Closed
opened 2026-02-21 18:19:31 -05:00 by yindo · 4 comments
yindo commented 2026-02-21 18:19:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @shaxiaozz on GitHub (Dec 16, 2024).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

0.14.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Upgrade Dify

cd dify/docker
docker compose down
git pull origin main
docker compose pull
docker compose up -d

✔️ Expected Behavior

The version was successfully upgraded to 0.14.0, and the web UI interface can be opened normally

❌ Actual Behavior

After executing docker compose up -d, the web UI was slow to load. After checking docker stats, I found that the memory usage of the docker-api-1 container had been gradually increasing until all the OS memory was consumed. The host entered a stuck state and was forced to restart. After the restart, this step was repeated, and the memory usage continued to increase. . . .

I observed the logs of docker-api-1 and found no obvious errors, but there were many INFO logs. As follows:

" 200 86313
Preparing database migration...
Database migration skipped
[2024-12-17 02:12:19 +0000] [1] [INFO] Starting gunicorn 23.0.0
[2024-12-17 02:12:19 +0000] [1] [INFO] Listening at: http://0.0.0.0:5001 (1)
[2024-12-17 02:12:19 +0000] [1] [INFO] Using worker: gevent
[2024-12-17 02:12:19 +0000] [37] [INFO] Booting worker with pid: 37
[2024-12-17 02:12:19 +0000] [38] [INFO] Booting worker with pid: 38
[2024-12-17 02:12:19 +0000] [39] [INFO] Booting worker with pid: 39
[2024-12-17 02:12:19 +0000] [40] [INFO] Booting worker with pid: 40
[2024-12-17 02:12:19 +0000] [41] [INFO] Booting worker with pid: 41
[2024-12-17 02:12:19 +0000] [42] [INFO] Booting worker with pid: 42
[2024-12-17 02:12:20 +0000] [43] [INFO] Booting worker with pid: 43
[2024-12-17 02:12:20 +0000] [44] [INFO] Booting worker with pid: 44
[2024-12-17 02:12:20 +0000] [45] [INFO] Booting worker with pid: 45
[2024-12-17 02:12:20 +0000] [46] [INFO] Booting worker with pid: 46
[2024-12-17 02:12:20 +0000] [47] [INFO] Booting worker with pid: 47
[2024-12-17 02:12:20 +0000] [48] [INFO] Booting worker with pid: 48
[2024-12-17 02:12:20 +0000] [49] [INFO] Booting worker with pid: 49
[2024-12-17 02:12:20 +0000] [50] [INFO] Booting worker with pid: 50
[2024-12-17 02:12:20 +0000] [51] [INFO] Booting worker with pid: 51
[2024-12-17 02:12:20 +0000] [52] [INFO] Booting worker with pid: 52
[2024-12-17 02:12:20 +0000] [53] [INFO] Booting worker with pid: 53
[2024-12-17 02:12:20 +0000] [54] [INFO] Booting worker with pid: 54
[2024-12-17 02:12:20 +0000] [55] [INFO] Booting worker with pid: 55
[2024-12-17 02:12:20 +0000] [56] [INFO] Booting worker with pid: 56
[2024-12-17 02:12:20 +0000] [57] [INFO] Booting worker with pid: 57
[2024-12-17 02:12:20 +0000] [58] [INFO] Booting worker with pid: 58
[2024-12-17 02:12:20 +0000] [60] [INFO] Booting worker with pid: 60
[2024-12-17 02:12:20 +0000] [59] [INFO] Booting worker with pid: 59
[2024-12-17 02:12:20 +0000] [61] [INFO] Booting worker with pid: 61
[2024-12-17 02:12:20 +0000] [62] [INFO] Booting worker with pid: 62
[2024-12-17 02:12:20 +0000] [63] [INFO] Booting worker with pid: 63
[2024-12-17 02:12:20 +0000] [64] [INFO] Booting worker with pid: 64
[2024-12-17 02:12:21 +0000] [65] [INFO] Booting worker with pid: 65
[2024-12-17 02:12:21 +0000] [66] [INFO] Booting worker with pid: 66
[2024-12-17 02:12:21 +0000] [67] [INFO] Booting worker with pid: 67
[2024-12-17 02:12:21 +0000] [68] [INFO] Booting worker with pid: 68
[2024-12-17 02:12:21 +0000] [69] [INFO] Booting worker with pid: 69
[2024-12-17 02:12:21 +0000] [70] [INFO] Booting worker with pid: 70
[2024-12-17 02:12:21 +0000] [71] [INFO] Booting worker with pid: 71
[2024-12-17 02:12:21 +0000] [72] [INFO] Booting worker with pid: 72
[2024-12-17 02:12:21 +0000] [73] [INFO] Booting worker with pid: 73
[2024-12-17 02:12:21 +0000] [74] [INFO] Booting worker with pid: 74
[2024-12-17 02:12:21 +0000] [75] [INFO] Booting worker with pid: 75
[2024-12-17 02:12:21 +0000] [76] [INFO] Booting worker with pid: 76
[2024-12-17 02:12:21 +0000] [77] [INFO] Booting worker with pid: 77
[2024-12-17 02:12:21 +0000] [78] [INFO] Booting worker with pid: 78
[2024-12-17 02:12:21 +0000] [79] [INFO] Booting worker with pid: 79
[2024-12-17 02:12:21 +0000] [80] [INFO] Booting worker with pid: 80
[2024-12-17 02:12:21 +0000] [81] [INFO] Booting worker with pid: 81
[2024-12-17 02:12:21 +0000] [82] [INFO] Booting worker with pid: 82
[2024-12-17 02:12:21 +0000] [84] [INFO] Booting worker with pid: 84
[2024-12-17 02:12:22 +0000] [83] [INFO] Booting worker with pid: 83
[2024-12-17 02:12:22 +0000] [85] [INFO] Booting worker with pid: 85
[2024-12-17 02:12:22 +0000] [86] [INFO] Booting worker with pid: 86
[2024-12-17 02:12:22 +0000] [87] [INFO] Booting worker with pid: 87
[2024-12-17 02:12:22 +0000] [88] [INFO] Booting worker with pid: 88
[2024-12-17 02:12:22 +0000] [89] [INFO] Booting worker with pid: 89
[2024-12-17 02:12:22 +0000] [90] [INFO] Booting worker with pid: 90
[2024-12-17 02:12:22 +0000] [92] [INFO] Booting worker with pid: 92
[2024-12-17 02:12:22 +0000] [91] [INFO] Booting worker with pid: 91
[2024-12-17 02:12:22 +0000] [93] [INFO] Booting worker with pid: 93
[2024-12-17 02:12:22 +0000] [94] [INFO] Booting worker with pid: 94
[2024-12-17 02:12:22 +0000] [95] [INFO] Booting worker with pid: 95
[2024-12-17 02:12:22 +0000] [96] [INFO] Booting worker with pid: 96
[2024-12-17 02:12:22 +0000] [97] [INFO] Booting worker with pid: 97
[2024-12-17 02:12:22 +0000] [98] [INFO] Booting worker with pid: 98
[2024-12-17 02:12:22 +0000] [99] [INFO] Booting worker with pid: 99
[2024-12-17 02:12:22 +0000] [100] [INFO] Booting worker with pid: 100
[2024-12-17 02:12:22 +0000] [102] [INFO] Booting worker with pid: 102
[2024-12-17 02:12:22 +0000] [103] [INFO] Booting worker with pid: 103
[2024-12-17 02:12:22 +0000] [101] [INFO] Booting worker with pid: 101
[2024-12-17 02:12:22 +0000] [104] [INFO] Booting worker with pid: 104
[2024-12-17 02:12:22 +0000] [105] [INFO] Booting worker with pid: 105
[2024-12-17 02:12:22 +0000] [106] [INFO] Booting worker with pid: 106
[2024-12-17 02:12:22 +0000] [107] [INFO] Booting worker with pid: 107
[2024-12-17 02:12:23 +0000] [108] [INFO] Booting worker with pid: 108
[2024-12-17 02:12:23 +0000] [109] [INFO] Booting worker with pid: 109
[2024-12-17 02:12:23 +0000] [110] [INFO] Booting worker with pid: 110
[2024-12-17 02:12:23 +0000] [111] [INFO] Booting worker with pid: 111
[2024-12-17 02:12:23 +0000] [112] [INFO] Booting worker with pid: 112
[2024-12-17 02:12:23 +0000] [113] [INFO] Booting worker with pid: 113
[2024-12-17 02:12:23 +0000] [114] [INFO] Booting worker with pid: 114
[2024-12-17 02:12:23 +0000] [115] [INFO] Booting worker with pid: 115
[2024-12-17 02:12:23 +0000] [116] [INFO] Booting worker with pid: 116
[2024-12-17 02:12:23 +0000] [118] [INFO] Booting worker with pid: 118
[2024-12-17 02:12:23 +0000] [117] [INFO] Booting worker with pid: 117
[2024-12-17 02:12:23 +0000] [119] [INFO] Booting worker with pid: 119
[2024-12-17 02:12:23 +0000] [120] [INFO] Booting worker with pid: 120
[2024-12-17 02:12:23 +0000] [121] [INFO] Booting worker with pid: 121
[2024-12-17 02:12:23 +0000] [122] [INFO] Booting worker with pid: 122
[2024-12-17 02:12:24 +0000] [124] [INFO] Booting worker with pid: 124
[2024-12-17 02:12:24 +0000] [123] [INFO] Booting worker with pid: 123
[2024-12-17 02:12:24 +0000] [125] [INFO] Booting worker with pid: 125
[2024-12-17 02:12:24 +0000] [126] [INFO] Booting worker with pid: 126
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.

Currently, I have rolled back to the previous version through git checkout 0.13.2 When I perform the upgrade operation again, this problem will recur stably~

Are there any other ideas or methods for troubleshooting? Can you guide me? Thank you~

Originally created by @shaxiaozz on GitHub (Dec 16, 2024). ### Self Checks - [X] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [X] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [X] Please do not modify this template :) and fill in all the required fields. ### Dify version 0.14.0 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce ***Upgrade Dify*** ``` cd dify/docker docker compose down git pull origin main docker compose pull docker compose up -d ``` ### ✔️ Expected Behavior The version was successfully upgraded to 0.14.0, and the web UI interface can be opened normally ### ❌ Actual Behavior After executing ```docker compose up -d```, the web UI was slow to load. After checking docker stats, I found that the memory usage of the ```docker-api-1``` container had been gradually increasing until all the OS memory was consumed. The host entered a stuck state and was forced to restart. After the restart, this step was repeated, and the memory usage continued to increase. . . . I observed the logs of ```docker-api-1``` and found no obvious errors, but there were many INFO logs. As follows: ``` " 200 86313 Preparing database migration... Database migration skipped [2024-12-17 02:12:19 +0000] [1] [INFO] Starting gunicorn 23.0.0 [2024-12-17 02:12:19 +0000] [1] [INFO] Listening at: http://0.0.0.0:5001 (1) [2024-12-17 02:12:19 +0000] [1] [INFO] Using worker: gevent [2024-12-17 02:12:19 +0000] [37] [INFO] Booting worker with pid: 37 [2024-12-17 02:12:19 +0000] [38] [INFO] Booting worker with pid: 38 [2024-12-17 02:12:19 +0000] [39] [INFO] Booting worker with pid: 39 [2024-12-17 02:12:19 +0000] [40] [INFO] Booting worker with pid: 40 [2024-12-17 02:12:19 +0000] [41] [INFO] Booting worker with pid: 41 [2024-12-17 02:12:19 +0000] [42] [INFO] Booting worker with pid: 42 [2024-12-17 02:12:20 +0000] [43] [INFO] Booting worker with pid: 43 [2024-12-17 02:12:20 +0000] [44] [INFO] Booting worker with pid: 44 [2024-12-17 02:12:20 +0000] [45] [INFO] Booting worker with pid: 45 [2024-12-17 02:12:20 +0000] [46] [INFO] Booting worker with pid: 46 [2024-12-17 02:12:20 +0000] [47] [INFO] Booting worker with pid: 47 [2024-12-17 02:12:20 +0000] [48] [INFO] Booting worker with pid: 48 [2024-12-17 02:12:20 +0000] [49] [INFO] Booting worker with pid: 49 [2024-12-17 02:12:20 +0000] [50] [INFO] Booting worker with pid: 50 [2024-12-17 02:12:20 +0000] [51] [INFO] Booting worker with pid: 51 [2024-12-17 02:12:20 +0000] [52] [INFO] Booting worker with pid: 52 [2024-12-17 02:12:20 +0000] [53] [INFO] Booting worker with pid: 53 [2024-12-17 02:12:20 +0000] [54] [INFO] Booting worker with pid: 54 [2024-12-17 02:12:20 +0000] [55] [INFO] Booting worker with pid: 55 [2024-12-17 02:12:20 +0000] [56] [INFO] Booting worker with pid: 56 [2024-12-17 02:12:20 +0000] [57] [INFO] Booting worker with pid: 57 [2024-12-17 02:12:20 +0000] [58] [INFO] Booting worker with pid: 58 [2024-12-17 02:12:20 +0000] [60] [INFO] Booting worker with pid: 60 [2024-12-17 02:12:20 +0000] [59] [INFO] Booting worker with pid: 59 [2024-12-17 02:12:20 +0000] [61] [INFO] Booting worker with pid: 61 [2024-12-17 02:12:20 +0000] [62] [INFO] Booting worker with pid: 62 [2024-12-17 02:12:20 +0000] [63] [INFO] Booting worker with pid: 63 [2024-12-17 02:12:20 +0000] [64] [INFO] Booting worker with pid: 64 [2024-12-17 02:12:21 +0000] [65] [INFO] Booting worker with pid: 65 [2024-12-17 02:12:21 +0000] [66] [INFO] Booting worker with pid: 66 [2024-12-17 02:12:21 +0000] [67] [INFO] Booting worker with pid: 67 [2024-12-17 02:12:21 +0000] [68] [INFO] Booting worker with pid: 68 [2024-12-17 02:12:21 +0000] [69] [INFO] Booting worker with pid: 69 [2024-12-17 02:12:21 +0000] [70] [INFO] Booting worker with pid: 70 [2024-12-17 02:12:21 +0000] [71] [INFO] Booting worker with pid: 71 [2024-12-17 02:12:21 +0000] [72] [INFO] Booting worker with pid: 72 [2024-12-17 02:12:21 +0000] [73] [INFO] Booting worker with pid: 73 [2024-12-17 02:12:21 +0000] [74] [INFO] Booting worker with pid: 74 [2024-12-17 02:12:21 +0000] [75] [INFO] Booting worker with pid: 75 [2024-12-17 02:12:21 +0000] [76] [INFO] Booting worker with pid: 76 [2024-12-17 02:12:21 +0000] [77] [INFO] Booting worker with pid: 77 [2024-12-17 02:12:21 +0000] [78] [INFO] Booting worker with pid: 78 [2024-12-17 02:12:21 +0000] [79] [INFO] Booting worker with pid: 79 [2024-12-17 02:12:21 +0000] [80] [INFO] Booting worker with pid: 80 [2024-12-17 02:12:21 +0000] [81] [INFO] Booting worker with pid: 81 [2024-12-17 02:12:21 +0000] [82] [INFO] Booting worker with pid: 82 [2024-12-17 02:12:21 +0000] [84] [INFO] Booting worker with pid: 84 [2024-12-17 02:12:22 +0000] [83] [INFO] Booting worker with pid: 83 [2024-12-17 02:12:22 +0000] [85] [INFO] Booting worker with pid: 85 [2024-12-17 02:12:22 +0000] [86] [INFO] Booting worker with pid: 86 [2024-12-17 02:12:22 +0000] [87] [INFO] Booting worker with pid: 87 [2024-12-17 02:12:22 +0000] [88] [INFO] Booting worker with pid: 88 [2024-12-17 02:12:22 +0000] [89] [INFO] Booting worker with pid: 89 [2024-12-17 02:12:22 +0000] [90] [INFO] Booting worker with pid: 90 [2024-12-17 02:12:22 +0000] [92] [INFO] Booting worker with pid: 92 [2024-12-17 02:12:22 +0000] [91] [INFO] Booting worker with pid: 91 [2024-12-17 02:12:22 +0000] [93] [INFO] Booting worker with pid: 93 [2024-12-17 02:12:22 +0000] [94] [INFO] Booting worker with pid: 94 [2024-12-17 02:12:22 +0000] [95] [INFO] Booting worker with pid: 95 [2024-12-17 02:12:22 +0000] [96] [INFO] Booting worker with pid: 96 [2024-12-17 02:12:22 +0000] [97] [INFO] Booting worker with pid: 97 [2024-12-17 02:12:22 +0000] [98] [INFO] Booting worker with pid: 98 [2024-12-17 02:12:22 +0000] [99] [INFO] Booting worker with pid: 99 [2024-12-17 02:12:22 +0000] [100] [INFO] Booting worker with pid: 100 [2024-12-17 02:12:22 +0000] [102] [INFO] Booting worker with pid: 102 [2024-12-17 02:12:22 +0000] [103] [INFO] Booting worker with pid: 103 [2024-12-17 02:12:22 +0000] [101] [INFO] Booting worker with pid: 101 [2024-12-17 02:12:22 +0000] [104] [INFO] Booting worker with pid: 104 [2024-12-17 02:12:22 +0000] [105] [INFO] Booting worker with pid: 105 [2024-12-17 02:12:22 +0000] [106] [INFO] Booting worker with pid: 106 [2024-12-17 02:12:22 +0000] [107] [INFO] Booting worker with pid: 107 [2024-12-17 02:12:23 +0000] [108] [INFO] Booting worker with pid: 108 [2024-12-17 02:12:23 +0000] [109] [INFO] Booting worker with pid: 109 [2024-12-17 02:12:23 +0000] [110] [INFO] Booting worker with pid: 110 [2024-12-17 02:12:23 +0000] [111] [INFO] Booting worker with pid: 111 [2024-12-17 02:12:23 +0000] [112] [INFO] Booting worker with pid: 112 [2024-12-17 02:12:23 +0000] [113] [INFO] Booting worker with pid: 113 [2024-12-17 02:12:23 +0000] [114] [INFO] Booting worker with pid: 114 [2024-12-17 02:12:23 +0000] [115] [INFO] Booting worker with pid: 115 [2024-12-17 02:12:23 +0000] [116] [INFO] Booting worker with pid: 116 [2024-12-17 02:12:23 +0000] [118] [INFO] Booting worker with pid: 118 [2024-12-17 02:12:23 +0000] [117] [INFO] Booting worker with pid: 117 [2024-12-17 02:12:23 +0000] [119] [INFO] Booting worker with pid: 119 [2024-12-17 02:12:23 +0000] [120] [INFO] Booting worker with pid: 120 [2024-12-17 02:12:23 +0000] [121] [INFO] Booting worker with pid: 121 [2024-12-17 02:12:23 +0000] [122] [INFO] Booting worker with pid: 122 [2024-12-17 02:12:24 +0000] [124] [INFO] Booting worker with pid: 124 [2024-12-17 02:12:24 +0000] [123] [INFO] Booting worker with pid: 123 [2024-12-17 02:12:24 +0000] [125] [INFO] Booting worker with pid: 125 [2024-12-17 02:12:24 +0000] [126] [INFO] Booting worker with pid: 126 None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. ``` Currently, I have rolled back to the previous version through ```git checkout 0.13.2``` When I perform the upgrade operation again, this problem will recur stably~ Are there any other ideas or methods for troubleshooting? Can you guide me? Thank you~
yindo added the 🐞 bug🤔 cant-reproduce labels 2026-02-21 18:19:31 -05:00
yindo closed this issue 2026-02-21 18:19:32 -05:00
yindo commented 2026-02-21 18:19:32 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Dec 16, 2024):

The issue you're experiencing with memory leaks in the Dify API container after upgrading to version 0.14.0 might be related to several factors. Here are some steps and considerations to help troubleshoot and potentially resolve the problem:

  1. Check Worker Configuration: The number of workers in the API container is determined by the SERVER_WORKER_AMOUNT environment variable, which defaults to CPU cores x 2 + 1. Ensure that this configuration is appropriate for your system's resources. You might want to manually set this variable to a lower number to see if it helps manage memory usage better [1].

  2. Dependencies: The logs indicate that PyTorch, TensorFlow, or Flax are not found. Ensure these dependencies are correctly installed in your Docker environment, as their absence might affect the application's performance and memory usage [2][3][4].

  3. Docker Configuration Changes: Version 0.14.0 introduced changes in Docker configurations, such as the addition of a certbot container and management of environment variables through a .env file. Ensure that your .env file is correctly configured and that these changes are not affecting your setup [5].

  4. Monitoring and Logs: Since the logs do not show obvious errors, consider using additional monitoring tools to track memory usage over time. Tools like docker stats can provide real-time insights into container resource usage.

  5. Rollback and Test: As you've already rolled back to version 0.13.2, try incrementally applying changes from version 0.14.0 to identify which specific change might be causing the issue.

  6. Community and Updates: Keep an eye on the Dify repository for any updates or patches related to this issue, as other users might have reported similar problems.

These steps should help you narrow down the cause of the memory leak and find a suitable solution.

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other

@dosubot[bot] commented on GitHub (Dec 16, 2024): <!-- Answer --> The issue you're experiencing with memory leaks in the Dify API container after upgrading to version 0.14.0 might be related to several factors. Here are some steps and considerations to help troubleshoot and potentially resolve the problem: 1. **Check Worker Configuration**: The number of workers in the API container is determined by the `SERVER_WORKER_AMOUNT` environment variable, which defaults to `CPU cores x 2 + 1`. Ensure that this configuration is appropriate for your system's resources. You might want to manually set this variable to a lower number to see if it helps manage memory usage better <sup>[[1]](https://github.com/langgenius/dify-docs/blob/main/jp/getting-started/install-self-hosted/environments.md)</sup>. 2. **Dependencies**: The logs indicate that PyTorch, TensorFlow, or Flax are not found. Ensure these dependencies are correctly installed in your Docker environment, as their absence might affect the application's performance and memory usage <sup>[[2]](https://github.com/langgenius/dify/issues/11688)</sup><sup>[[3]](https://github.com/langgenius/dify-docs/blob/main/jp/getting-started/install-self-hosted/faq.md)</sup><sup>[[4]](https://github.com/langgenius/dify-docs/blob/main/en/getting-started/install-self-hosted/faqs.md)</sup>. 3. **Docker Configuration Changes**: Version 0.14.0 introduced changes in Docker configurations, such as the addition of a `certbot` container and management of environment variables through a `.env` file. Ensure that your `.env` file is correctly configured and that these changes are not affecting your setup <sup>[[5]](https://github.com/langgenius/dify/blob/main/docker/README.md)</sup>. 4. **Monitoring and Logs**: Since the logs do not show obvious errors, consider using additional monitoring tools to track memory usage over time. Tools like `docker stats` can provide real-time insights into container resource usage. 5. **Rollback and Test**: As you've already rolled back to version 0.13.2, try incrementally applying changes from version 0.14.0 to identify which specific change might be causing the issue. 6. **Community and Updates**: Keep an eye on the Dify repository for any updates or patches related to this issue, as other users might have reported similar problems. These steps should help you narrow down the cause of the memory leak and find a suitable solution. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/85844be7-6a78-476c-b91a-82a86c17918a?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/85844be7-6a78-476c-b91a-82a86c17918a?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/85844be7-6a78-476c-b91a-82a86c17918a?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/85844be7-6a78-476c-b91a-82a86c17918a?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/85844be7-6a78-476c-b91a-82a86c17918a?feedback_type=hallucination) | [Other](https://app.dosu.dev/response-feedback/85844be7-6a78-476c-b91a-82a86c17918a?feedback_type=other)</sup>
yindo commented 2026-02-21 18:19:32 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Dec 17, 2024):

Actually this is hard to reproduce, seems we didn't get enough reports regarding this issue.

@crazywoola commented on GitHub (Dec 17, 2024): Actually this is hard to reproduce, seems we didn't get enough reports regarding this issue.
yindo commented 2026-02-21 18:19:32 -05:00
Author
Owner
Copy Link
Copy Source

@shaxiaozz commented on GitHub (Dec 17, 2024):

@crazywoola Thanks for your reply~
I made another attempt yesterday.
I went to the warehouse to re-pull the latest dify code, put it in another directory on the host, and then restarted dify. I found that it could be started, and I observed that the memory did not increase continuously.

Because we have a habit of tarring the volume data in the docker directory every time we upgrade.

I don't know what happened, I am very confused~

@shaxiaozz commented on GitHub (Dec 17, 2024): @crazywoola Thanks for your reply~ I made another attempt yesterday. I went to the warehouse to re-pull the latest dify code, put it in another directory on the host, and then restarted dify. I found that it could be started, and I observed that the memory did not increase continuously. Because we have a habit of tarring the volume data in the docker directory every time we upgrade. I don't know what happened, I am very confused~
yindo commented 2026-02-21 18:19:32 -05:00
Author
Owner
Copy Link
Copy Source

@lichao4Java commented on GitHub (Apr 3, 2025):

https://github.com/langgenius/dify/issues/17384#issuecomment-2775165109

The problem still exists in 1.1.3, how did you solve it?

@lichao4Java commented on GitHub (Apr 3, 2025): https://github.com/langgenius/dify/issues/17384#issuecomment-2775165109 The problem still exists in 1.1.3, how did you solve it?
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug 🤔 cant-reproduce
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#7225
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?