[DRBD-user] Large block IO bottleneck
Leroy van Logchem
leroy.vanlogchem at wldelft.nl
Thu Jan 4 09:58:10 CET 2007
>>>> Hi there I am using DRBD 0.7.21 with iSCSI Enterprise
> The 32k are a rather arbitrary value we have chosen in DRBD. Such a limit
> is needed for some of the algorithms in the area of the two primary
> nodes, write conflict detection code.
> If you really want you can change that define (HT_SHIFT), but probably
> the positive effects are out-numbered by negative effects (more collision
> in hash tables etc...)
I was hoping to analyse the difference by patching the source but the
is only used in the 8.x code. What would need changing to try 32K BIO's
in the 0.7.x code?
More information about the drbd-user