HAST slowness ?
Mike Tancsa
mike at sentex.net
Thu Jul 31 21:20:46 UTC 2014
I am trying to setup my first HAST setup and for some reason, traffic
sync seems to be really slow. If I do something simple like
#dd if=/dev/zero of=/hastvirt/test count=2000 bs=1024k
on the primary box, traffic on the secondary never gets much beyond a
Mb/s ?!?!
iperf and netrate show I can pretty well saturate across the link. There
are no errors and the underlying NICs are both at gigabit with no other
traffic. Everything seems happy, just very slow to sync. Any idea where
to start debugging ?
# ifstat -b -i vlan5
vlan5
Kbps in Kbps out
840.40 621.14
825.26 622.40
768.74 577.49
12772.84 1099.10
976.68 729.80
856.61 645.19
751.33 561.07
854.44 637.67
1087.46 811.47
798.61 600.51
837.40 624.65
957.50 719.61
945.90 697.86
756.10 573.92
869.78 649.61
935.69 706.42
784.65 588.13
835.90 627.21
1050.15 772.38
772.70 580.70
795.23 589.38
869.19 660.23
899.00 679.72
837.06 619.58
809.34 607.60
981.75 735.31
875.33 657.42
842.79 627.45
931.13 694.73
# ifconfig vlan5
vlan5: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
options=303<RXCSUM,TXCSUM,TSO4,TSO6>
ether 00:1e:67:84:c8:ca
inet 1.1.1.2 netmask 0xfffffff8 broadcast 1.1.1.7
inet6 fe80::21e:67ff:fe84:c8ca%vlan5 prefixlen 64 scopeid 0x4
nd6 options=29<PERFORMNUD,IFDISABLED,AUTO_LINKLOCAL>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
vlan: 5 parent interface: igb0
# hastctl status
Name Status Role Components
disk1 complete secondary /dev/ada0p4 1.1.1.1
disk2 complete secondary /dev/ada1p4 1.1.1.1
# hastctl list
disk1:
role: secondary
provname: disk1
localpath: /dev/ada0p4
extentsize: 2097152 (2.0MB)
keepdirty: 0
remoteaddr: 1.1.1.1
replication: memsync
status: complete
workerpid: 888
dirty: 0 (0B)
statistics:
reads: 0
writes: 40529
deletes: 12
flushes: 22
activemap updates: 0
local errors: read: 0, write: 0, delete: 12, flush: 0
queues: local: 0, send: 0, recv: 0, done: 0, idle: 255
disk2:
role: secondary
provname: disk2
localpath: /dev/ada1p4
extentsize: 2097152 (2.0MB)
keepdirty: 0
remoteaddr: 1.1.1.1
replication: memsync
status: complete
workerpid: 889
dirty: 0 (0B)
statistics:
reads: 0
writes: 40529
deletes: 12
flushes: 22
activemap updates: 0
local errors: read: 0, write: 0, delete: 12, flush: 0
queues: local: 0, send: 0, recv: 0, done: 0, idle: 255
---Mike
--
-------------------
Mike Tancsa, tel +1 519 651 3400
Sentex Communications, mike at sentex.net
Providing Internet services since 1994 www.sentex.net
Cambridge, Ontario Canada http://www.tancsa.com/
More information about the freebsd-fs
mailing list