Duke Posted April 28, 2011 Posted April 28, 2011 VMWare was reporting the following averages before and after the switch (taken from the same time period on seperate days) Were you running any specific reproducible tests to get these figures? If possible I'd like to test them on my SAN to get an idea of the figures I'm getting. Were you monitoring the Disk or the Virtual Disk stats in VMware? Thanks, Chris
andy0789 Posted April 28, 2011 Posted April 28, 2011 I was looking at both Datastore and Virtual Disk, the one I documented below is for the datastore. Both showed improvement, mostly with write latency. In my environment I have two of the 1GbE interfaces on the 7110 using LACP over 2 interconnected Cisco 3750 switches. These two interfaces are dedicated to VLAN 11 for our ESX servers to use NFS or iSCSI. When I created a LUN on the 7110 I enabled the "write cache" feature. I think if you start with a datastore using NFS, put load on it, specifically writes and see what your latency is, then switch to iSCSI with "write cache" enabled on the 7110 LUN and compair the two. If you are like me, you will see the write latency drop. 1
andy0789 Posted May 10, 2011 Posted May 10, 2011 Continuing on with the 7110 Performance, I have attached a link to a report of my I/O operations per second. I am still stumped as to why my iSCSI, NFS, and SMB operations remain low but the Disk I/O is always around 2000 ops/sec. What are the disks doing? Is it due to the raid level (Double Parity Raid)? Any insight would be appreciated. http://www.asgsolvesit.com/images/SUN7110Perf.jpg
john Posted May 10, 2011 Posted May 10, 2011 (edited) I've been having a chat with Oracle Support over a good number of issues and we were looking at performance and the disk pool setup and the rule of thumb seems to be that the Protocol I/O should be 4x that of the Disk I/O if the Disk I/O is higher than Protocol I/O then the disk pool isn't setup efficently, this is very key on the 7110 as its got a small number of spindles to spread it across and very limited memory. My 7110 is suffering now from the poor performance issue, but my 7120 which has bags more ram and a Flash Accelerator card is much better and the I/O is the other way around. As you can see from the graphs below (which I sent to Oracle to look at and confirm about the 4x rule) I have marked up the 7110 and 7120 on them and have only shown SMB, however both are doing NFS as well. As that shows the 7120 is working optimally in terms of Disk VS Protcol I/O (as confirmed by Oracle Support today when I sent them images to them) and the 7110 is under a great deal of strain. They are the analytics for those options for 1 week as obviously on SMB it peaks and troughs usually during the day. Edited May 10, 2011 by john
Hanson Posted October 25, 2011 Posted October 25, 2011 (edited) sun storage 7110 have a problem when user only open shared folder graphs smb operations shows that he generate about 3k ops per sec graphs by type of operations show that operations is NtTransact what could it be? Edited October 25, 2011 by Hanson
Duke Posted October 26, 2011 Posted October 26, 2011 sun storage 7110 have a problem when user only open shared folder graphs smb operations shows that he generate about 3k ops per sec graphs by type of operations show that operations is NtTransact what could it be? What firmware release are you on? I hit a similar NtTransact bug on one of the older firmware releases. Firstly, restart the SMB service. It shouldn't take long to go down and come back up but warn people there will be short outage. If you SMB usage drops off then this is probably it, even if SMB starts to grow again. There is a binary patch available for older releases: The binary fix for 6991334 on the 2010.08.17.1.0,1-0.0 release of the firmware contains two files. These files must not be installed on an appliance running any release other than 2010.08.17.1.0,1-0.0 (2010Q3.1) However you'd be better off just using the latest release which includes it. Looks on the bright-side, my 7410 hit 92,100 SMB IOPS while I had this bug. Chris
Hanson Posted October 26, 2011 Posted October 26, 2011 Thanks, current version 2010.08.17.1.1.1-1.16 but have available 2 new update (haven't time to install it, think it's time to do this) restart SMB doesn't help, it's first that i done. and one question not for this problem 7110 have CPU 1 RAM 8gb disk 13 in Double parity RAID How many Disk IO a limit for it ?
Duke Posted October 26, 2011 Posted October 26, 2011 (edited) Thanks, current version 2010.08.17.1.1.1-1.16 but have available 2 new update (haven't time to install it, think it's time to do this) restart SMB doesn't help, it's first that i done. I think that bug affected up to 2010.08.17.1.0,1-0.0 and the release after that, so it could still well be that bug. Applying updates is definitely the first route to go and Oracle will ask you to do that anyway probably. Have you contacted Oracle support about this problem? Over in the UK their support has been great so far. 7110 have CPU 1 RAM 8gb disk 13 in Double parity RAID How many Disk IO a limit for it ? There's not so much an IO limit, as it depends on what types of files you're writing (random, sequential, large files, small files). A 7110 with 8GB RAM and no SSDs in RAID-DP isn't going to be amazing I'm afraid. Chris Edited October 26, 2011 by Duke 1
Hanson Posted October 28, 2011 Posted October 28, 2011 one more question i can install latest 2010.Q3.4.2 or previous (2.0, 2.1, 3.1, 4.0, 4.1) need to install too?
kmount Posted October 28, 2011 Posted October 28, 2011 2010.Q3.4.2 requires you to be running 2010.Q3.2.1. You'll need to upgrade to that first from where you are. Software Updates - Fishworks - wikis.sun.com The release notes show you which versions to follow through. 1
Hanson Posted November 7, 2011 Posted November 7, 2011 yes, update software remove problem with SMB add 8gb RAM to 7110 and have a question in Maintenace => hardware show 16Gb memory Why in Status on diagram memory unused memory only 300 mb, where the othe free memory ?
Duke Posted November 7, 2011 Posted November 7, 2011 How much RAM is recognised when you go to Maintenance > Hardware? http://www.hardenhuish.wilts.sch.uk/avatar%5Cs7410_ram.png I've got 16GB but if I add up the numbers on that chart on my box I get 20.86GB, so I assume there's either some kind of memory overcommitment thing going on or it maybe includes memory from elsewhere. As yours adds up to 9.06GB I'd suggest it's still only using 8GB RAM?
Hanson Posted November 7, 2011 Posted November 7, 2011 in hardware i saw 16gb in both 7110 but chart in first storage show 9.25 on second 14.2
Duke Posted November 7, 2011 Posted November 7, 2011 14GB sounds closer to being okay. The box uses some RAM for caching so maybe it's still loading data into it (although that doesn't make much sense, it should show as free like you said). Give it a day and then see how it looks?
john Posted November 7, 2011 Posted November 7, 2011 Maybe the box has some intelligence over RAM perhaps and is blocking its use? Although when I discussed adding more ram, apart from the its not supported etc there was no reason the people I was speaking to said it wouldn't work for in the box assuming it was right and balanced across the CPUs as expected etc... You followed the guidelines for the original Sun server that the 7110 was based on in terms of the pairing as there is a hot swap spare slot I believe on these boxes 1
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now