tgtd tuning, poor performance at low throughput

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi folks,

I'm having high machine load on the tgtd side, and would like to ask
for help tuning.

background on hardware:
I have a 10 disk sw-raid10 array setup with mdadm on CentOS 6, 2
(dual)x6core E5-2620 0 @ 2.00GHz, 32GB ram target machine, dedicated
gigabit interfaces multipathed, and jumbo frames mtu 9000 between my
target/switch/initiators.

I plan to use this for KVM storage.  Local IO performance tested with
bonnie++ is ~ 250MB/sec for random writes, with minimal CPU load
during the test.

However after I introduced tgtd and iscsi into the mix, even at speeds
of ~10MB/sec coming from the initiators, my target machine load is
very high 10-15.  The load seems to be due to tgtd.

Can someone please help me tune tgtd? Thanks in advance!

target.conf:

default-driver iscsi
<target iqn.2014-01.com.foo.us1.storage1:vmstorage>
    backing-store /dev/md2
    initiator-address 192.168.84.29  #kvm5
    initiator-address 192.168.85.29  #kvm5
    initiator-address 192.168.84.78  #kvm6
    initiator-address 192.168.85.78  #kvm6
    initiator-address 192.168.84.76  #kvm7
    initiator-address 192.168.85.76  #kvm7
    write-cache off
</target>


iscsi initiator side:


[aamerik@kvm5 ~]$ iscsiadm -m session -P 3
iSCSI Transport Class version 2.0-870
version 6.2.0-873.10.el6
Target: iqn.2014-01.com.foo.us1.storage1:vmstorage
Current Portal: 192.168.84.77:3260,1
Persistent Portal: 192.168.84.77:3260,1
**********
Interface:
**********
Iface Name: default
Iface Transport: tcp
Iface Initiatorname: iqn.1994-05.com.redhat:65274b4cae8e
Iface IPaddress: 192.168.84.29
Iface HWaddress: <empty>
Iface Netdev: <empty>
SID: 1
iSCSI Connection State: Unknown
iSCSI Session State: LOGGED_IN
Internal iscsid Session State: Unknown
*********
Timeouts:
*********
Recovery Timeout: 120
Target Reset Timeout: 30
LUN Reset Timeout: 30
Abort Timeout: 15
*****
CHAP:
*****
username: <empty>
password: ********
username_in: <empty>
password_in: ********
************************
Negotiated iSCSI params:
************************
HeaderDigest: None
DataDigest: None
MaxRecvDataSegmentLength: 262144
MaxXmitDataSegmentLength: 8192
FirstBurstLength: 65536
MaxBurstLength: 262144
ImmediateData: Yes
InitialR2T: Yes
MaxOutstandingR2T: 1
************************
Attached SCSI devices:
************************
Host Number: 7 State: running
scsi7 Channel 00 Id 0 Lun: 0
scsi7 Channel 00 Id 0 Lun: 1
Attached scsi disk sdb State: running
Current Portal: 192.168.85.77:3260,1
Persistent Portal: 192.168.85.77:3260,1
**********
Interface:
**********
Iface Name: default
Iface Transport: tcp
Iface Initiatorname: iqn.1994-05.com.redhat:65274b4cae8e
Iface IPaddress: 192.168.85.29
Iface HWaddress: <empty>
Iface Netdev: <empty>
SID: 2
iSCSI Connection State: Unknown
iSCSI Session State: LOGGED_IN
Internal iscsid Session State: Unknown
*********
Timeouts:
*********
Recovery Timeout: 120
Target Reset Timeout: 30
LUN Reset Timeout: 30
Abort Timeout: 15
*****
CHAP:
*****
username: <empty>
password: ********
username_in: <empty>
password_in: ********
************************
Negotiated iSCSI params:
************************
HeaderDigest: None
DataDigest: None
MaxRecvDataSegmentLength: 262144
MaxXmitDataSegmentLength: 8192
FirstBurstLength: 65536
MaxBurstLength: 262144
ImmediateData: Yes
InitialR2T: Yes
MaxOutstandingR2T: 1
************************
Attached SCSI devices:
************************
Host Number: 8 State: running
scsi8 Channel 00 Id 0 Lun: 0
scsi8 Channel 00 Id 0 Lun: 1
Attached scsi disk sdc State: running

-- 
Alexey Amerik
--
To unsubscribe from this list: send the line "unsubscribe stgt" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux SCSI]     [Linux RAID]     [Linux Clusters]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]

  Powered by Linux