Tom Lane wrote:

Anyway, I've committed your patch with some changes.


BTW, I noticed a lot of concern in the Intel app notes about reserving
64 or even 128 bytes for each spinlock to avoid cache line conflicts.
That seems excessive to me (we use a lot of spinlocks for buffers), but
perhaps it is worth looking into.

This recommendation usually ignored in the Linux kernel. A few very hot spinlocks have an exclusive cacheline, but most don't.

Is there an easy way find out which LWLock is contended?

Not from oprofile output, as far as I can think. I've suspected for
some time that the BufMgrLock is a major bottleneck, but have no proof.

I'll try to write a patch that dumps the LWLock usage and ask mark to run it.


---------------------------(end of broadcast)--------------------------- TIP 4: Don't 'kill -9' the postmaster

Reply via email to