iamqq23ue commented on issue #3536:
URL: https://github.com/apache/rocketmq/issues/3536#issuecomment-984246713
What you said makes sense. The main reason is that RocketMQ has bugs, and
messages will be lost when storage fails or cluster performance will be
severely degraded. The probability of RAID card failure is much greater than
that of centralized storage
------------------ 原始邮件 ------------------
发件人:
"apache/rocketmq"
***@***.***>;
发送时间: 2021年12月2日(星期四) 上午10:54
***@***.***>;
***@***.******@***.***>;
主题: Re: [apache/rocketmq] Can RocketMQ use centralized storage to
ensure syncflush? (Issue #3536)
This is equivalent to the separation of storage and calculation. Of course,
the computing node will be well maintained, but in essence it just transfers
the maintenance work to the storage node. But the structure of separation of
storage and computing is of course also beneficial, at least it is more
decoupled and flexible, and overall maintenance will reduce the problems caused
by coupling.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
Triage notifications on the go with GitHub Mobile for iOS or Android.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
