Re: [Maria-developers] [Maria-discuss] Known limitation with TokuDB in Read Free Replication & parallel replication ?

Hello Kristian, I am working on a second variant of the kill query design that will only kill the pending lock request if any for the thd being killed. The previous design had a problem when killing the query that triggered the wait for call On Aug 15, 2016 7:26 PM, "Rich Prohaska" <prohaska7@gmail.com> wrote: Hello Kristian, I have a prototype of the TokuFT code that will cause ALL lock waiters to call their killed callback here: https://github.com/ prohaska7/tokuft/tree/kill_lockers On Mon, Aug 15, 2016 at 11:51 AM, Rich Prohaska <prohaska7@gmail.com> wrote:

Hello Kristian, I have tokudb kill query working with parallel replication. Needed to attach the mysql thd pointer to each lock request, and use the thd as a key into the pending lock requests to find the one being used by a particular thd. Once found, this lock request is immediately completed with a lock timeout result. Also needed to rearrange the lock wait for code so that the callback is called when not holding any tokudb locks. This solves 1 or 10 parallel replication stalls with tokudb. The remainder require the tokudb lock timer to pop. The problem is that the parallel replicator attempts to kill the query for a mysql slave thread that is waiting for a prior txn to complete. This does not have any effect on tokudb. The workaround for now is to use an extremely small tokudb lock timeout so that the stalls are short. On Tue, Aug 16, 2016 at 9:59 PM, Rich Prohaska <prohaska7@gmail.com> wrote:

Rich Prohaska <prohaska7@gmail.com> writes:
Ok, sounds great!
Hm, that sounds like a problem with the parallel replication code. It should be normal that a thread needs to be killed in "waiting for prior txn", and it should work. I will look into this. Is your latest kill query code on github? Thanks, - Kristian.
participants (2)
-
Kristian Nielsen
-
Rich Prohaska