[DRBD-user] Initializing shortcut

Javier Grande updeits at jmworld.es
Thu May 11 09:41:09 CEST 2006

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.

Yes, we have developed a testing couple of servers with vtund, compressed
and unencypted tunnel.
We have try zlib and lzo compression with level 9 and we got very high
speeds even through an Internet link which max throughput was 250KB/s.
Only problem we have had is that at such high speeds, on first sync, we have
a kernel panic at primary node (it never happened with rate limited at 1M on
drbd setup).We think this may be due to kernel compilation stuff as it have
happened only when primary node was a 2.6.15 and never when primary was
We decided to wait until 0.8 was released for production use to restart the

--- Todd Denniston <Todd.Denniston at ssa.crane.navy.mil>
> Lars,
> Would it make sense, in 0.8.x or 0.9.x, that when
> doing a full sync, drbd do a
> minimal look at the data it is sending and handle
> "sparse" (large sequences of
>   0's) data 'efficiently' like tar and cp do, i.e.,
> when drbd notices it is sending 100 4k blocks of
> data, instead of sending 400k
> of 0, send a "drbd_sparse 100" packet to the peer
> which then turns that into
> 0's on the media?

I think that at this point that would be complicated
enough to simply add compression instead.  lzo would
probably be a great fit for this:


but I suspect that this is beyond what the developers
want.  They would probably tell you to use openvpn.
Has anyone ever tried openvpn with drbd without
encryption enabled to see if it can speed things up
(it can use lzo)?


Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around
drbd-user mailing list
drbd-user at lists.linbit.com

More information about the drbd-user mailing list