Article View: comp.sys.sgi.admin
Article #189Re: Return of the Poor NFS performance
From: Jon Peatfield
Date: Tue, 26 Jan 1993 04:11
Date: Tue, 26 Jan 1993 04:11
56 lines
3649 bytes
3649 bytes
Hmm, well this evening having nothing better to do (well I could reinstall perl, xdvi, xfig, gs ghostview, etc like I've been promising for weeks, but this SGI problem really has me hooked ;-), I decided to try playing with one of our SGIs. I'm really new to SGI machines, so I was still learning about them, playing with "inst" etc, and pushing in random CDs and seeign what "inst" made of them. Anyway I put the 4.0.5F maintenance CD in and typed list. Off it popped and gave me a list of stuff, including the 4.0.5E nfs maintenance changes, which it told me were NOT installed. Now this machine was factory installed with 4.0.5F, so I kind of assumed that they had put the 4.0.4E patches in but... I went away and read the manual, and found that "versions" was the command I needed to check what was installed (like pkginfo on Solaris-2 I suppose), and behold only 4.0.1 NFS was installed. Aha! Anyway I then had a crash course in how to boot to the miniroot and installed it from there, (since it refuses to install from inst running normally.) After I reboot and check what is going on (hey why does "inst" in this case build a new kernel for me, but when I installed the 4.0.1 on the other machine it didn't?), I measured the performance as about 37Kbytes/sec which is what I measured on the other SGI all along (doubled the speed.) However, the other SGI is only running the 4.0.1NFS code since I didn't have chance to get round to installing the 4.0.5E patch, and the people on the SGI helpdesk said it didn't matter since I saw the problem on a machine with and without -- well I do now. Does this jog anyone's memory about that level of performance? I'll try installing the 4.0.5E patch on the IP12 tomorrow and see if that performs any better. 37Kbytes/sec isn't TOO bad, I can live with it for a while, but I wouldn't want my sister to marry it. (As her husband probably wouldn't aprove.) I'd also like to appologise for being rude in reply to the reply from the person who suggested that it was a hard/soft mount problem. I'd just spent several hours watching the network and it was very late at night and I was tired and cross. I'm less cross now though it is almost as late. I'll phone SGI's support desk in the morning (well afternoon probably), and see if they have come up with anything. (At lest they are helpful, I've got a problem with one of our other machines and the hardware maintenance people have been sending stuff to the wrong address, and today they sent us a keyboard which generates junk characters as you type as a swap for one with a broken spacebar. I'm not sure which keyboard I'll keep 'til they get us a working one... but I'm not cruel enough to name them.) -- Jon Peatfield (Unix network admin) -- Jon Peatfield, Computer Officer, the DAMTP, University of Cambridge Telephone: (+44 223) 3-37852 Mail: J.S.Peatfield@amtp.cam.ac.uk To be consistent with DNS domain ordering, shouldn't news groups have names like "admin.sun.sys.comp" not "comp.sys.sun.admin" ? EMWTK
Technical Details
Message-ID:
<JP107.93Jan26041130@grus.cus.cam.ac.uk>Path:
arc1-ca.pugleaf.net!sparky!uunet!pipex!pavo.csi.cam.ac.uk!camcus!jp107References:
<JP107.93Jan22121147@grus.cus.cam.ac.uk>Show Full Headers
Complete Article Headers
Newsgroups: comp.sys.sgi.admin Path: arc1-ca.pugleaf.net!sparky!uunet!pipex!pavo.csi.cam.ac.uk!camcus!jp107 From: jp107@cus.cam.ac.uk (Jon Peatfield) Subject: Re: Return of the Poor NFS performance In-Reply-To: jp107@cus.cam.ac.uk's message of Fri, 22 Jan 1993 12:11:53 GMT Message-ID: <JP107.93Jan26041130@grus.cus.cam.ac.uk> Sender: news@infodev.cam.ac.uk (USENET news) Nntp-Posting-Host: grus.cus.cam.ac.uk Organization: U of Cambridge, England References: <JP107.93Jan22121147@grus.cus.cam.ac.uk> Distribution: comp Date: Tue, 26 Jan 1993 04:11:33 GMT Lines: 56