Charan,
Thank you for sharing. I just took a quick glance. I have a few high-level
questions:
- Can you benchmark this change when you have time? It is interesting to
see:
(1) current logic vs new logic with 1 slot
(2) current logic vs new logic with N slot
repeat the above tests for
- both int
*"I am wondering if your multiple-entrylogs approach is making things
complicated. I have been thinking there can be a simpler approach achieving
the same goal: for example, having a ledger storage comprised of N
interleaved/sorted ledger storages, which they share same LedgerCache, but
having diff
On Fri, Jul 14, 2017 at 6:00 PM, Sijie Guo wrote:
>
>
> On Sat, Jul 15, 2017 at 8:06 AM, Charan Reddy G
> wrote:
>
>> Hey,
>>
>> In InterleavedLedgerStorage, since the initial version of it (
>> https://github.com/apache/bookkeeper/commit/4a94ce1d8184f5f
>> 38def015d80777a8113b96690 and https://
On Sat, Jul 15, 2017 at 8:06 AM, Charan Reddy G
wrote:
> Hey,
>
> In InterleavedLedgerStorage, since the initial version of it (
> https://github.com/apache/bookkeeper/commit/4a94ce1d8184f5f38def015d80777a
> 8113b96690 and https://github.com/apache/bookkeeper/commit/
> d175ada58dcaf78f0a70b0ebebf
Hey,
In InterleavedLedgerStorage, since the initial version of it (
https://github.com/apache/bookkeeper/commit/4a94ce1d8184f5f38def015d80777a8113b96690
and
https://github.com/apache/bookkeeper/commit/d175ada58dcaf78f0a70b0ebebf489255ae67b5f),
addEntry and processEntry methods are synchronized. If
