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.

Sign up for GitHub

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

Jump to bottom

add some missing timeouts in Distributed #34502

Merged
merged 1 commit into from
Jan 28, 2020
Merged

add some missing timeouts in Distributed #34502

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions stdlib/Distributed/src/cluster.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -569,6 +569,7 @@ end
function create_worker(manager, wconfig)
# only node 1 can add new nodes, since nobody else has the full list of address:port
@assert LPROC.id == 1
timeout = worker_timeout()

# initiate a connect. Does not wait for connection completion in case of TCP.
w = Worker()
Expand Down Expand Up @@ -633,9 +634,14 @@ function create_worker(manager, wconfig)
(notnothing(x.config.ident) in something(wconfig.connect_idents, []))

wlist = filter(filterfunc, PGRP.workers)
waittime = 0
while wconfig.connect_idents !== nothing &&
length(wlist) < length(wconfig.connect_idents)
if waittime >= timeout
error("peer workers did not connect within $timeout seconds")
end
sleep(1.0)
waittime += 1
wlist = filter(filterfunc, PGRP.workers)
end

Expand All @@ -655,7 +661,13 @@ function create_worker(manager, wconfig)
send_msg_now(w, MsgHeader(RRID(0,0), ntfy_oid), join_message)

@async manage(w.manager, w.id, w.config, :register)
# wait for rr_ntfy_join with timeout
timedout = false
@async (sleep($timeout); timedout = true; put!(rr_ntfy_join, 1))
wait(rr_ntfy_join)
if timedout
error("worker did not connect within $timeout seconds")
end
lock(client_refs) do
delete!(PGRP.refs, ntfy_oid)
end
Expand Down