Hi,
I have 3 domU running on a single server.
Domain "clas-0" is exporting a directory to domain "dbn-0"
via NFS.
Both "clas-0" and "dbn-0" has time synchronisation from
another external
server.
Both "clas-0" and "dbn-0" each has HDD file size of 50G.
I can ssh into both "clas-0'' and "dbn-0" normally ;
login response is
acceptable.
Each domU has only a single virtual bridge.
There is only one physical interface in the host machine, ie each domU
virtual interface is bridged into a single interface.
"/var/log/xen/xend.log" file does not indicate any errors.
At time of writing right now, "dbn-0" is creating an Oracle database
instance of 30G.
My problem is that the domain "dbn-0" is creating the oracle instance
very slowly.
I do not know where the problem lies.
Therefore I appreciate your advice on this, or any directions to
identify the bottlenecks.
Thanks.
============================================================================================================================xentop
- 01:18:51 Xen 3.0.3-rc5-8.1.4.el
4 domains: 1 running, 3 blocked, 0 paused, 0 crashed, 0 dying, 0
shutdown
Mem: 8386520k total, 8385632k used, 888k free CPUs: 8 @ 2000MHz
NAME STATE CPU(sec) CPU(%) MEM(k) MEM(%) MAXMEM(k)
MAXMEM(%) VCPUS NETS NETTX(k) NETRX(k) VBDS VBD_OO VBD_RD VBD_WR
SSID
clas0 --b--- 5633 3.0 1063196 12.7 1071516
12.8 1 1 0 0 2 0 0 0 0
VCPUs(sec): 0: 5633s
Net0 RX: 0bytes 0pkts 0err 0drop TX:
0bytes 0pkts 0err 0drop
VBD 5632 [16: 0] OO: 0 RD: 0 WR: 0
VBD 768 [ 3: 0] OO: 0 RD: 0 WR: 0
clas1 --b--- 9801 3.1 1063324 12.7 1071516
12.8 1 1 0 0 1 0 0 0 0
VCPUs(sec): 0: 9801s
Net0 RX: 0bytes 0pkts 0err 0drop TX:
0bytes 0pkts 0err 0drop
VBD 768 [ 3: 0] OO: 0 RD: 0 WR: 0
dbn0 --b--- 8130 3.1 1063196 12.7 1071516
12.8 1 1 0 0 1 0 0 0 0
VCPUs(sec): 0: 8130s
Net0 RX: 0bytes 0pkts 0err 0drop TX:
0bytes 0pkts 0err 0drop
VBD 768 [ 3: 0] OO: 0 RD: 0 WR: 0
Domain-0 -----r 9525 0.9 5101568 60.8 no limit
n/a 8 4 1058702 766852 0 0 0 0 0
VCPUs(sec): 0: 6011s 1: 288s 2: 1002s 3:
658s 4: 213s
5: 203s 6: 807s 7: 339s
Net0 RX: 785256533bytes 1867080pkts 0err 0drop TX:
1084111128bytes 521828pkts 0err 0drop
Net1 RX: 0bytes 0pkts 0err 0drop TX:
0bytes 0pkts 0err 0drop
Net2 RX: 0bytes 0pkts 0err 0drop TX:
0bytes 0pkts 0err 0drop
Net3 RX: 0bytes 0pkts 0err 0drop TX:
0bytes 0pkts 0err 0drop
============================================================================================================================
============================================================================================================================[root@hostmachine
~]# xm vcpu-list
Name ID VCPUs CPU State Time(s) CPU
Affinity
Domain-0 0 0 0 -b- 6013.0 any cpu
Domain-0 0 1 3 -b- 288.6 any cpu
Domain-0 0 2 7 -b- 1002.7 any cpu
Domain-0 0 3 3 -b- 658.6 any cpu
Domain-0 0 4 4 -b- 213.9 any cpu
Domain-0 0 5 2 -b- 203.7 any cpu
Domain-0 0 6 1 -b- 808.0 any cpu
Domain-0 0 7 6 r-- 339.5 any cpu
clas0 13 0 4 -b- 5640.1 any cpu
clas1 7 0 4 -b- 9807.0 any cpu
dbn0 10 0 5 -b- 8134.7 any cpu
============================================================================================================================
_______________________________________________
Xen-users mailing list
Xen-users@lists.xensource.com
http://lists.xensource.com/xen-users
Hi, I have 3 domU running on a single server. Domain "clas-0" is exporting a directory to domain "dbn-0" via NFS. Both "clas-0" and "dbn-0" has time synchronisation from another external server. Both "clas-0" and "dbn-0" each has HDD file size of 50G. I can ssh into both "clas-0'' and "dbn-0" normally ; login response is acceptable. Each domU has only a single virtual bridge. There is only one physical interface in the host machine, ie each domU virtual interface is bridged into a single interface. "/var/log/xen/xend.log" file does not indicate any errors. At time of writing right now, "dbn-0" is creating an Oracle database instance of 30G. My problem is that the domain "dbn-0" is creating the oracle instance very slowly. I do not know where the problem lies. Therefore I appreciate your advice on this, or any directions to identify the bottlenecks. Thanks. ============================================================================================================================ xentop - 01:18:51 Xen 3.0.3-rc5-8.1.4.el 4 domains: 1 running, 3 blocked, 0 paused, 0 crashed, 0 dying, 0 shutdown Mem: 8386520k total, 8385632k used, 888k free CPUs: 8 @ 2000MHz NAME STATE CPU(sec) CPU(%) MEM(k) MEM(%) MAXMEM(k) MAXMEM(%) VCPUS NETS NETTX(k) NETRX(k) VBDS VBD_OO VBD_RD VBD_WR SSID clas0 --b--- 5633 3.0 1063196 12.7 1071516 12.8 1 1 0 0 2 0 0 0 0 VCPUs(sec): 0: 5633s Net0 RX: 0bytes 0pkts 0err 0drop TX: 0bytes 0pkts 0err 0drop VBD 5632 [16: 0] OO: 0 RD: 0 WR: 0 VBD 768 [ 3: 0] OO: 0 RD: 0 WR: 0 clas1 --b--- 9801 3.1 1063324 12.7 1071516 12.8 1 1 0 0 1 0 0 0 0 VCPUs(sec): 0: 9801s Net0 RX: 0bytes 0pkts 0err 0drop TX: 0bytes 0pkts 0err 0drop VBD 768 [ 3: 0] OO: 0 RD: 0 WR: 0 dbn0 --b--- 8130 3.1 1063196 12.7 1071516 12.8 1 1 0 0 1 0 0 0 0 VCPUs(sec): 0: 8130s Net0 RX: 0bytes 0pkts 0err 0drop TX: 0bytes 0pkts 0err 0drop VBD 768 [ 3: 0] OO: 0 RD: 0 WR: 0 Domain-0 -----r 9525 0.9 5101568 60.8 no limit n/a 8 4 1058702 766852 0 0 0 0 0 VCPUs(sec): 0: 6011s 1: 288s 2: 1002s 3: 658s 4: 213s 5: 203s 6: 807s 7: 339s Net0 RX: 785256533bytes 1867080pkts 0err 0drop TX: 1084111128bytes 521828pkts 0err 0drop Net1 RX: 0bytes 0pkts 0err 0drop TX: 0bytes 0pkts 0err 0drop Net2 RX: 0bytes 0pkts 0err 0drop TX: 0bytes 0pkts 0err 0drop Net3 RX: 0bytes 0pkts 0err 0drop TX: 0bytes 0pkts 0err 0drop ============================================================================================================================ ============================================================================================================================ [root@hostmachine ~]# xm vcpu-list Name ID VCPUs CPU State Time(s) CPU Affinity Domain-0 0 0 0 -b- 6013.0 any cpu Domain-0 0 1 3 -b- 288.6 any cpu Domain-0 0 2 7 -b- 1002.7 any cpu Domain-0 0 3 3 -b- 658.6 any cpu Domain-0 0 4 4 -b- 213.9 any cpu Domain-0 0 5 2 -b- 203.7 any cpu Domain-0 0 6 1 -b- 808.0 any cpu Domain-0 0 7 6 r-- 339.5 any cpu clas0 13 0 4 -b- 5640.1 any cpu clas1 7 0 4 -b- 9807.0 any cpu dbn0 10 0 5 -b- 8134.7 any cpu ============================================================================================================================ _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
On Thu, Oct 04, 2007 at 01:27:00AM +0400, karhong.ng@nsn.com wrote:> My problem is that the domain "dbn-0" is creating the oracle instance very > slowly. > I do not know where the problem lies.Applying the patch from http://lists.debian.org/debian-kernel/2007/09/msg00161.html helped me to avoid NFS freezes and speeded NFS up by a factor of 5. See http://bugs.debian.org/440676 for details. JEns _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users