Hi dev,
I pushed a PR https://github.com/apache/pulsar/pull/20822 to fix the infinite
unloading. Please help review this PR. Thanks!
Thanks,
Kai
On 2023/07/09 23:40:03 PengHui Li wrote:
> Hi Heesung,
>
> For 2.10, I would like to suggest fixing the issue instead of cherry-picking
> the PR. The
Hi Heesung,
For 2.10, I would like to suggest fixing the issue instead of cherry-picking
the PR. The problem that https://github.com/apache/pulsar/pull/388 had
resolved will happen again if `loadBalancerDistributeBundlesEvenlyEnabled`
is disabled. We should try to remove the configuration in the f
Hi dev,
I think we also need to consider the namespace anit-affinity-group logic
too. These logics seem to do similar things.
https://pulsar.apache.org/docs/3.0.x/administration-load-balance/#distribute-anti-affinity-namespaces-across-failure-domains
PengHui
We got three biding votes here. Do yo
> `removeMostServicingBrokersForNamespace ` is introduced by [1] to
solve the problem that when all bundles in a particular namespace
belong to 1 or few machines, customers owning that namespace will be
heavily impacted if that broker goes down. Of course, this PR caused
the infinite unloading issu
+1
Enrico
Il Dom 2 Lug 2023, 06:19 Hang Chen ha scritto:
> +1 for cherry-picking it to branch-2.10. We have a flag to control
> whether to enable or disable it.
>
> `removeMostServicingBrokersForNamespace ` is introduced by [1] to
> solve the problem that when all bundles in a particular namesp
+1 for cherry-picking it to branch-2.10. We have a flag to control
whether to enable or disable it.
`removeMostServicingBrokersForNamespace ` is introduced by [1] to
solve the problem that when all bundles in a particular namespace
belong to 1 or few machines, customers owning that namespace will
+1 for cherry-pick to branch-2.10 since users don't have a workaround
for this issue, and the change is well-understand, low risk.
I agree with making it false for the next major version release by default.
Thanks,
Penghui
On Sat, Jul 1, 2023 at 9:26 AM Heesung Sohn
wrote:
> Hi dev,
>
> I real
Hi dev,
I realized that `removeMostServicingBrokersForNamespace` func in the broker
selection logic can cause infinite unloading.
Suppose an overloaded broker unloaded a bundle and only has the minimum
number of bundles(in that namespace) among brokers. In that case, the
selection logic (`removeM
