Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Profile picture
JumpyRaven4
Moderator
6 Questions, 36 Answers
  Active since 18 May 2023
  Last activity 3 months ago

Reputation

0

Badges 1

35 × Eureka!
0 Votes
0 Answers
357 Views
0 Votes 0 Answers 357 Views
Hi Guys, been using clearml-serving for several years now and recently upgraded to the new version of the app server and clearml-serving. However, when deplo...
3 months ago
0 Votes
4 Answers
402 Views
0 Votes 4 Answers 402 Views
3 months ago
0 Votes
26 Answers
1K Views
0 Votes 26 Answers 1K Views
one year ago
0 Votes
11 Answers
1K Views
0 Votes 11 Answers 1K Views
one year ago
0 Votes
15 Answers
2K Views
0 Votes 15 Answers 2K Views
Hi Guys, we are running clearml-serving on a kube cluster on AWS and we have noticed that we are getting some 502 errors once in a while that we can't seem t...
one year ago
0 Votes
4 Answers
2K Views
0 Votes 4 Answers 2K Views
Hi Guys, I have a question regarding Model tracking. I have pipelines that use Xgboost through the scikit-learn api to perform: - Feature selection through n...
2 years ago
0 Hi Guys, We Are Running Clearml-Serving On A Kube Cluster On Aws And We Have Noticed That We Are Getting Some 502 Errors Once In A While That We Can'T Seem To Trace Back.

Hi Martin,

  • Actually we are using ALB with a 30 seconds timeout
  • we do not have GPUs instances
  • docker version 1.3.0
one year ago
0 Hi Guys, We Are Running Clearml-Serving On A Kube Cluster On Aws And We Have Noticed That We Are Getting Some 502 Errors Once In A While That We Can'T Seem To Trace Back.

ACtually the request are never registered to the gunicorn app, and the ALB log show that there is no response from the target "-".

one year ago
0 Hi Guys, We Are Running Clearml-Serving On A Kube Cluster On Aws And We Have Noticed That We Are Getting Some 502 Errors Once In A While That We Can'T Seem To Trace Back.

we have tried both and got the same issue (gunicorn vs uvcorn).
No I meant creating a

@router.post(
    "/sleep",
    tags=["temp"],
    response_description="Return HTTP Status Code 200 (OK)",
    status_code=status.HTTP_200_OK,
    response_model=TestResponse,
)
# def here instead of async def
def post_sleep(time_sleep: float) -> TestResponse:
    """ """
    time.sleep(time_sleep)
    return TestResponse(status="OK")
one year ago
0 Hi Guys, We Are Running Clearml-Serving On A Kube Cluster On Aws And We Have Noticed That We Are Getting Some 502 Errors Once In A While That We Can'T Seem To Trace Back.

alright, so actually we noticed that the problem disappears if we use only sync requests. Meaning if I create a sleep endpoint that is async we get the 502 but if it's sync we don't

one year ago
one year ago
0 Hi Guys, We Are Running Clearml-Serving On A Kube Cluster On Aws And We Have Noticed That We Are Getting Some 502 Errors Once In A While That We Can'T Seem To Trace Back.

that's a fair point. Actually we have switched from using siege because we believe it is causing the issues and are using Locust now instead. We have been running for days at the same rate and don't see any errors being reported...

one year ago
0 Hi Guys, We Are Running Clearml-Serving On A Kube Cluster On Aws And We Have Noticed That We Are Getting Some 502 Errors Once In A While That We Can'T Seem To Trace Back.

yeah I don't know I think we are probably just trying to fit to high a throughput for that box but it's weird that the packet just get dropped i would have assumed the response time should degrade and requests be queued.

one year ago
0 Hi Guys, I Have Been Running The Clearml-Serving For A While Now And I Realize That From Time To Time After A Couple Of Hours The Serving Task (Control Plane) That Is Configured Through The Cli Goes Into Status Abort. This Happens Even Though All The Pods

ok so I haven't looked at the latest changes after the sync this morning but the ones we put in yesterday seems to have fixed the issue, the service is still running this morning at least.

one year ago
0 Hi Guys, I Feel Like I'M Missing Something Regarding The Way I Should Be Cloning Tasks. I Have Tasks Templates That I Want To Be Able To Clone And Dynamically Change The Package Requirements Required To Run The Said Task. I Have Tried Most Of What I Coul

This being said, now I'm running into another issue that this seems to be "erasing" all the packages that had been set in the base task I'm cloning from. I can't find a method that would return these packages so that I could add to it?

one year ago
Show more results compactanswers