Re: Interesting paper: Contention-Aware Lock Scheduling
От | Ibrar Ahmed |
---|---|
Тема | Re: Interesting paper: Contention-Aware Lock Scheduling |
Дата | |
Msg-id | CALtqXTeEe6cyd2FeDnK_VxMDQsNSpYn3Sycd+WuxyzVJh0VzCA@mail.gmail.com обсуждение исходный текст |
Ответ на | Re: Interesting paper: Contention-Aware Lock Scheduling (Юрий Соколов <funny.falcon@gmail.com>) |
Список | pgsql-hackers |
On Mon, May 7, 2018 at 10:54 PM Юрий Соколов <funny.falcon@gmail.com> wrote:
2018-05-04 23:45 GMT+03:00 AJG <ayden@gera.co.nz>:
>
> Another interesting article from Jan 2018 (Tsinghua University and Microsoft
> Research)
>
> http://madsys.cs.tsinghua.edu.cn/publications/TS2018-liu.pdf
>
> DudeTx: Durable Transactions Made Decoupled
Cite from pdf:
> The key insight of our solution is decoupling a durable transaction into three
> fully asynchronous steps. (1) Perform: execute the transaction on a shadow
> memory, and produce a redo log for the transaction. (2) Persist: flush redo
> logs of transactions to persistent memory in an atomic manner. (3) Reproduce:
> modify original data in persistent memory according to the persisted redo logs.
> It is essential that we never directly write back dirty data from shadow memory
> to persistent memory – all the updates are realized via the logs.
It is exactly the same Amazon did for its Aurora!
Using this decoupling, Aurora provides great replication and failover (by use of
replicated and versioned storage both for logs and for data pages).
regards,
Yura.
Do we still want to see the patch of that paper (http://www.vldb.org/pvldb/vol11/p648-tian.pdf)?
--
Ibrar Ahmed
В списке pgsql-hackers по дате отправления: