Large amount of data at a time,an error occurred

Issues Dgraph
1

@omar hello
dgraph version: v21.03.1

Last Friday, I wrote a large amount of data to the alpha1 of a 3-host 6-node cluster. Today, when I query a large amount of data at a time,an error occurred：
rpc error: code = Unavailable desc = Gateway Timeout: HTTP status code 504; transport: received the unexpected content-type \"text/html\"

top - 11:47:41 up 26 days, 19:50,  2 users,  load average: 0.56, 0.42, 0.29
Tasks: 270 total,   2 running, 268 sleeping,   0 stopped,   0 zombie
%Cpu(s):  0.3 us,  0.1 sy,  0.0 ni, 99.5 id,  0.0 wa,  0.0 hi,  0.0 si,  0.0 st
KiB Mem : 32778692 total,  4438416 free,  2872316 used, 25467960 buff/cache
KiB Swap:  4194300 total,  3961600 free,   232700 used. 28732164 avail Mem

  PID USER      PR  NI    VIRT    RES    SHR S  %CPU %MEM     TIME+ COMMAND
18888 root      20   0  109.7g  22.7g  21.7g S   5.6 72.6   2019:14 /usr/local/bin/dgraph alpha --my=alpha1:7080 --zero=zero1:5080,zero2:5081,+
18896 root      20   0 2704708 108548  10396 S   4.0  0.3 219:38.57 /usr/local/bin/dgraph zero --my=zero1:5080 --replicas 3 --raft=idx=1

alpha1 logs:

I0721 03:51:03.797797      16 log.go:34] 3 is starting a new election at term 46
I0721 03:51:03.797817      16 log.go:34] 3 became pre-candidate at term 46
I0721 03:51:03.797822      16 log.go:34] 3 received MsgPreVoteResp from 3 at term 46
I0721 03:51:03.797833      16 log.go:34] 3 [logterm: 45, index: 136898478] sent MsgPreVote request to 1 at term 46
I0721 03:51:03.797841      16 log.go:34] 3 [logterm: 45, index: 136898478] sent MsgPreVote request to 2 at term 46

zero1 logs:

W0721 03:52:46.500966      19 node.go:420] Unable to send message to peer: 0x2. Error: Unhealthy connection
I0721 03:52:48.512000      19 log.go:34] 1 [logterm: 12, index: 111096064, vote: 1] rejected MsgPreVote from 2 [logterm: 12, index: 109412368] at term 12
I0721 03:52:50.812006      19 log.go:34] 1 [logterm: 12, index: 111096064, vote: 1] rejected MsgPreVote from 2 [logterm: 12, index: 109412368] at term 12
I0721 03:52:53.112904      19 log.go:34] 1 [logterm: 12, index: 111096064, vote: 1] rejected MsgPreVote from 2 [logterm: 12, index: 109412368] at term 12
I0721 03:52:55.412621      19 log.go:34] 1 [logterm: 12, index: 111096064, vote: 1] rejected MsgPreVote from 2 [logterm: 12, index: 109412368] at term 12
2

How didi you query for it?

3 
{
	find(func: type(fileOwner), first: 100, offset: 200) {
			uid
    ...
  }
}

Similar to this, as long as it is not a single data query, the result cannot be queried。
I used this query statement to query on the web side, and the web side crashed directly。

4

That doesn’t look large. Are you doing something else? what are your machine stats?