Hi!
> I would advise that you refer to the documentation, what you are asking for
> already exists:
For my tests I had this configuration:
c-plan-ahead 5;
c-delay-target 20;
c-max-rate 35M;
c-min-rate 4M;
# will overrule c-delay-target, but seems to be better
# concerning linearity of the used network bandwith
c-fill-target 18M;
max-buffers 8000;
max-epoch-size 8000;
sndbuf-size 512k;
cram-hmac-alg sha1;
shared-secret "xxxx";
verify-alg md5;
protocol A;
on-congestion pull-ahead;
congestion-fill 2G;
congestion-extents 2000;
And I observed the slowdown of the write as described in my initial post.
Either "pull-ahead" doesn't work, or another configuration interferes with
this setting, or we didn't understand the description or I simply was too
stupid and fooled myself to make the test right.
But I can re-test it.
My goal would be to limit the syncer speed to 300MBit/s AND to keep the
write speed at 130MBit on my local disk and let the peer going out of sync
until the bulk write is done and re-sync does its job.
And yes, I know the data will be inconsistent for this short period.
BR,
Jasmin
_______________________________________________
drbd-user mailing list
[email protected]
http://lists.linbit.com/mailman/listinfo/drbd-user
