Re: Further reduction of bufmgr lock contention
От | Simon Riggs |
---|---|
Тема | Re: Further reduction of bufmgr lock contention |
Дата | |
Msg-id | 1145658480.3112.108.camel@localhost.localdomain обсуждение исходный текст |
Ответ на | Re: Further reduction of bufmgr lock contention (Tom Lane <tgl@sss.pgh.pa.us>) |
Ответы |
Re: Further reduction of bufmgr lock contention
Re: Further reduction of bufmgr lock contention |
Список | pgsql-hackers |
On Fri, 2006-04-21 at 17:38 -0400, Tom Lane wrote: > Simon Riggs <simon@2ndquadrant.com> writes: > > The earlier lmgr lock partitioning had a hard-coded number of > > partitions, which was sensible because of the reduced likelihood of > > effectiveness beyond a certain number of partitions. That doesn't follow > > here since the BufMappingLock contention will vary with the size of > > shared_buffers and with the number of CPUs in use (for a given > > workload). I'd like to see the partitioning calculated at server startup > > either directly from shared_buffers or via a parameter. We may not be > > restricted to only using a hash function as we were with lmgr, perhaps > > using a simple range partitioning. > > I don't think any of that follows; and a large number of partitions is > risky because it increases the probability of exhausting shared memory > (due to transient variations in the actual size of the hashtables for > different partitions). lmgr partitioning uses either 4 or 16, restricted by the hash function, for various reasons. I see no similar restriction on using a hash function here - we could equally well use range partitioning. That relieves the restriction on the number of partitions, allowing us either more or less partitions, according to need. We can place a limit on that if you see a problem - at what level do you see a problem? -- Simon Riggs EnterpriseDB http://www.enterprisedb.com/
В списке pgsql-hackers по дате отправления: