11-03-2011
Poor Disk performance on ZFS
Hello,
we have a machine with Solaris Express 11, 2 LSI 9211 8i SAS 2 controllers (multipath to disks), multiport backplane, 16 Seagate Cheetah 15K RPM disks.
Each disk has a sequential performance of 220/230 MB/s and in fact if I do a
dd if=/dev/zero of=/dev/rdsk/<diskID_1> bs=1024k count=16384
writing 16 GB of sequential 0 goes at that speed (iostat confirms that, with load in round robin on the 2 controllers and 100% disk utilization)
If I now create a simple zpool made up of 1 single disk (the same disk as above) with zpool create tank <diskID_1>
and then issue a
dd if=/dev/zero of=/Tank/test bs=1024k count=16384
iostat shows a disk performance of less than 20 MB/s (1/10 !!!!!!!) with disk utilization around 96% (also zpool iostat shows similar figures)
I tried to set also checksum=off but it does not change anything.
Zpool is created with default values (compress=off, dedup=off, stripe 128k).
Of course if I turn compression on and dedup on everthing changes, but this is a "trick" and works because file are all zeros.
I tried to change the max_vdev_pending to 1, to 64 (default is 10) and nothing changes.
Anyone has a clue of what is going on ?
9 More Discussions You Might Find Interesting
1. UNIX for Advanced & Expert Users
Hi you all, I have a BIG performance problem on an Sun E3500, the scenario is described below:
I have several users (30) accessing via samba to the E3500 using an application built on Visual Foxpro from their Windows PC , the problem is that the first guy that logs in demands 30% of the E3500... (2 Replies)
Discussion started by: alex blanco
2 Replies
2. Filesystems, Disks and Memory
Hello,
i have a a1000 connected to an e6500. There's a raid 10 (12 disks) on the a1000.
If i do a
dd if=/dev/zero of=/mnt/1 bs=1024k count=1000
and then look at iostat it tells me there's a kw/s of 25000.
But if i do a
dd of=/dev/zero if=/mnt/1 bs=1024k count=1000
then i see only a... (1 Reply)
Discussion started by: mbrenner
1 Replies
3. UNIX for Dummies Questions & Answers
Hello,
I'm running a script on AIX to process lines in a file. I need to enclose the second column in quotation marks and write each line to a new file. I've come up with the following:
#!/bin/ksh
filename=$1
exec >> $filename.new
cat $filename | while read LINE
do
echo $LINE | awk... (2 Replies)
Discussion started by: scooter53080
2 Replies
4. UNIX for Advanced & Expert Users
Hello all
We just built a storage cluster for our new xenserver farm. Using 3ware 9650SE raid controllers with 8 x 1TB WD sata disks in a raid 5, 256KB stripe size.
While making first performance test on the local storage server using dd (which simulates the read/write access to the disk... (1 Reply)
Discussion started by: roli8200
1 Replies
5. Solaris
Hello guys,
I have two servers performing the same disk operations. I believe one server is having a disk's impending failure however I have no hard evidence to prove it. This is a pair of Netra 210's with 2 drives in a hardware raid mirror (LSI raid controller). While performing intensive... (4 Replies)
Discussion started by: s ladd
4 Replies
6. AIX
Hi,
I am new registered user here in this UNIX forums.
I am a new system administrator for AIX 6.1. One of our servers performs poorly every time our application (FINACLE) runs many processes/instances. (see below for topas snapshot)
I use NMON or Topas to monitor the server utilization. I... (9 Replies)
Discussion started by: guzzelle
9 Replies
7. Solaris
Hi
We have an M3000 single physical processor and 8gb of memory running Solaris 10. This system runs two Oracle Databases one on Oracle 9i and One on Oracle 10g.
As soon as the Oracle 10g database starts we see an immediate drop in system performance, for example opening an ssh session can... (6 Replies)
Discussion started by: gregsih
6 Replies
8. AIX
Hi Everyone,
I have been struggling for few days with iSCSI and thought I could get some help on the forum...
fresh install of AIX7.1 TL4 on Power 710, The rootvg relies on 3 SAS disks in RAID 0, 32GB Memory
The lpar Profile is using all of the managed system's resources.
I have connected... (11 Replies)
Discussion started by: frenchy59
11 Replies
9. Windows & DOS: Issues & Discussions
Just a quick note for macOS users.
I just installed (and removed) Parallels Desktop 15 Edition on my MacPro (2013) with 64GB memory and 12-cores, which is running the latest version of macOS Catalina as of this post. The reason for this install was to test some RIGOL test gear software which... (6 Replies)
Discussion started by: Neo
6 Replies
LEARN ABOUT HPUX
vxsplitlines
vxsplitlines(1M) vxsplitlines(1M)
NAME
vxsplitlines - show disks with conflicting configuration copies in a cluster
SYNOPSIS
vxsplitlines [-g diskgroup] [-c daname]
DESCRIPTION
If you import portions of a disk group on different systems, this can lead to conflicting configuration copies on the disks of the disk
group.
If the configuration information in a disk group is ambiguous, it may not be possible for Veritas Volume Manager to determine which config-
uration copy is most up-to-date. (This is usually termed a serial split brain (SSB) condition when it occurs in a cluster.) You cannot
import a disk group in this state unless you specify which disk's configuration copy to use.
You can use the vxsplitlines command to see which disks in a disk group have conflicting configuration copies, and use this information
together with your knowledge of the history of the disk groups' usage to determine which configuration copy is most valid.
The output from vxsplitlines displays the vxdg commands that you can run to import the disk group using the available configuration copies.
The -o selectcp option of the vxdg import command is used to select the configuration copy to use for the import.
OPTIONS
-c daname Display the SSB IDs for each disk that are stored in the configuration copy on the disk specified by its disk access name.
Note: Although the SSB IDs for some disks may match, this does not necessarily mean that those disks' configuration copies have
recorded all the configuration changes. When viewed from some other configuration copies, the SSB IDs of the same disks may not
match.
-g diskgroup
Specifies the disk group. If a disk group is not specified, the default disk group is used as determined from the rules on the
vxdg(1M) manual page.
EXAMPLES
Display the disks on each side of the split in the disk group newdg:
vxsplitlines -g newdg
Display the SSB IDs stored in the configuration copy on disk c2t4d0:
vxsplitlines -g newdg -c c2t4d0
NOTES
The vxsplitlines is primarily intended to be used with private disk groups, but it also works with shared disk groups.
The version number of the disk group must be 110 or greater.
SEE ALSO
vxdg(1M)
Veritas Volume Manager Administrator's Guide
VxVM 5.0.31.1 24 Mar 2008 vxsplitlines(1M)