Use multiple Dask schedulers
We're using Dask to distribute the computation tasks to multiple servers. There is 1 dask-scheduler and 5 dask-worker servers. My question is: is there a way so that multiple dask-schedulers can be used? I'm asking this because single dask-scheduler can't avoid single point of failure, and sometimes, if the requests are in a very high volume, the single-scheduler could be a bottleneck of the performance.
Thanks!
dask dask-distributed
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
add a comment |
We're using Dask to distribute the computation tasks to multiple servers. There is 1 dask-scheduler and 5 dask-worker servers. My question is: is there a way so that multiple dask-schedulers can be used? I'm asking this because single dask-scheduler can't avoid single point of failure, and sometimes, if the requests are in a very high volume, the single-scheduler could be a bottleneck of the performance.
Thanks!
dask dask-distributed
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
add a comment |
We're using Dask to distribute the computation tasks to multiple servers. There is 1 dask-scheduler and 5 dask-worker servers. My question is: is there a way so that multiple dask-schedulers can be used? I'm asking this because single dask-scheduler can't avoid single point of failure, and sometimes, if the requests are in a very high volume, the single-scheduler could be a bottleneck of the performance.
Thanks!
dask dask-distributed
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
We're using Dask to distribute the computation tasks to multiple servers. There is 1 dask-scheduler and 5 dask-worker servers. My question is: is there a way so that multiple dask-schedulers can be used? I'm asking this because single dask-scheduler can't avoid single point of failure, and sometimes, if the requests are in a very high volume, the single-scheduler could be a bottleneck of the performance.
Thanks!
dask dask-distributed
dask dask-distributed
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
asked Nov 13 '18 at 20:49
Aaron ChuAaron Chu
1
1
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
A dask cluster runs with a single scheduler, and overhead due to assigning tasks can indeed be a bottleneck in some circumstances.
To answer your specific question, yes you can connect to separate schedulers from the same python process/session, if you wish: each call to Client() can point to a different address. Whether that is useful for some sort of load balancing is hard to say - the clusters will not know about each other and not share any resources.
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53289283%2fuse-multiple-dask-schedulers%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
A dask cluster runs with a single scheduler, and overhead due to assigning tasks can indeed be a bottleneck in some circumstances.
To answer your specific question, yes you can connect to separate schedulers from the same python process/session, if you wish: each call to Client() can point to a different address. Whether that is useful for some sort of load balancing is hard to say - the clusters will not know about each other and not share any resources.
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
add a comment |
A dask cluster runs with a single scheduler, and overhead due to assigning tasks can indeed be a bottleneck in some circumstances.
To answer your specific question, yes you can connect to separate schedulers from the same python process/session, if you wish: each call to Client() can point to a different address. Whether that is useful for some sort of load balancing is hard to say - the clusters will not know about each other and not share any resources.
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
add a comment |
A dask cluster runs with a single scheduler, and overhead due to assigning tasks can indeed be a bottleneck in some circumstances.
To answer your specific question, yes you can connect to separate schedulers from the same python process/session, if you wish: each call to Client() can point to a different address. Whether that is useful for some sort of load balancing is hard to say - the clusters will not know about each other and not share any resources.
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
A dask cluster runs with a single scheduler, and overhead due to assigning tasks can indeed be a bottleneck in some circumstances.
To answer your specific question, yes you can connect to separate schedulers from the same python process/session, if you wish: each call to Client() can point to a different address. Whether that is useful for some sort of load balancing is hard to say - the clusters will not know about each other and not share any resources.
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
answered Nov 18 '18 at 17:37
mdurantmdurant
10.2k11436
10.2k11436
add a comment |
add a comment |
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53289283%2fuse-multiple-dask-schedulers%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
