daniel at digsys.bg
Fri Jun 3 15:32:21 UTC 2011
Decided to apply the patch proposed in -current by Mikolaj Golub:
This apparently fixed my issue as well. Running without checksums for a
full bonnie++ run (~100GB write/rewrite) produced no disconnects, no
stalls and generated up to 280MB/sec (4 drives in stripped zpool).
Interestingly, the hast devices write latency as observed by gstat was
I believe this fix should be committed.
Here are the accumulated netstat -s from both hosts, for comparison with
previous runs. Retransmits etc are much less.
Before applying the patch I verified there are no network problems.
Created 1TB file from /dev/random on the first host. Copied over to the
second host with ftp. Transfer speed was low, at 80MB/sec -- ftp would
utilize one CPU core 100% at the receiving node. Then calculated md5
checksums on both sides, matched.
More information about the freebsd-stable