gregs@umbc5.umbc.edu (Greg Sylvain) (09/13/89)
Hi, I hope you people can clear something else up for me. Earlier this year/late last year I was told that hp-ux workstations can't have a local swap disk. Know I believe the person that told us this may of been refering to 6.2 (or there abouts), but were running 6.5, and I've seen several references saying that 6.5 can have a local swap disk, what do you think? Also, I'm administering a cluster of 4 hp 340s (two monos 4MB ea., and two color 8 MB ea.). I think this might be the problem right here, but anyway. The root server has a high speed HP-IB, but is even slower than my workstation, that has a regular HP-IB. My workstation is only a cluser of 2, each of wich has 8 MB but still, there is an incredible slowdown on the bigger cluster. Is there anything else I can reconfigure to speed up the bigger cluster. (It's been reconfigured for about 120MB swap space). Any clue??? Thanks alot, greg
nre@otter.hpl.hp.com (Nigel Evans) (09/13/89)
You should be able to put local swap on a discless client with HPUX 6.2 (I'm running 6.2 discless with local swap). I think you can do it with HPUX as far back as 6.0. As far as performance is concerned on discless, the worst slowdowns I have seen are when someone trys running X11 without much memory. X11 on a 4 Meg 340 is asking for trouble. You will be swapping (across the net) before the application does anything. This swapping will kill the performance of the 4 Meg machines, and could have a knock on effect to the 8 Meg machines (since the file server will be busy doing swap operations). Solutions: 1. Go back to X10. 2. Put 12 Meggs in each 340. If you ain't running X11 then it could be your applications chewing up memory/file access. As far as tuning the system is concerned, increasing the size of the file buffers on the server may help a bit. It wont help much if your main problem is intensive swapping though. Kevin Jones. kev%hpcpbla%otter.lb.hp.co.uk@hpl.hp.co.uk
jack@hpindda.HP.COM (Jack Repenning) (09/14/89)
> I've seen several references saying that 6.5 can have a local swap > disk, what do you think? You can have local swap (although you can't have local filesystems). This has been true since the very beginning of Diskless (6.0). However, local swap is not necessarily a performance gain! This is because the difference between fast disks and slow disks is greater than the difference between local swapping and remote swapping. Since the faster disks are generally bigger, it's more economical to share them (by putting them on the server) - and not many single workstations really need 304Mb of swap space, anyway. There are (at least) two ways you can gain performance by adding local swap. First, local swap on any client will probably help the rootserver (even if the client gets slower). Second, if there's so much swapping going on, that swap requests are being queued up at the server, then local swap might help. A simple intuitive test of this would be, is your cluster too slow when only one workstation is in use, or only when two or three are used concurrently? All of this assumes that you really are paging and swapping enough for that to be your major performance concern, of course. You might want to use /usr/contrib/bin/monitor's "k" screen, to verify that your workstations are really using significantly more swap space than their (physical memory - kernel size). You can also use the "g" screen to see what demands you're putting on the disk bandwidth. What can you reconfigure? Well first, gut everything you don't need from the kernels: client and server. Second, play with the configuration variables, to reduce tables as much as possible. "As much as possible," you'll have to discover for yourself - it depends on what you do with the workstations. Here are the tunings I've installed in my cluster. They work for us, but of course your needs may be entirely different. (We do a lot of X, mostly X11, mostly mail reading, editing, HP TeamWork - compiles are run on S800 systems.) The server tunings, in particular, are for a 16M server. If you have less memory, you'll want to pull back "nbuf" considerably. (But do tweak it up from the default: it's an important tuning to improve filesystem access from the clients.) * CONFIGURABLE PARAMETERS: * * Tunings for X workstations * (Assumptions: one X user, maxo-piggo; maybe a few visitors * from elsewhere, not using much the main user isn't) maxuprc 64 maxusers 5 nproc (20+MAXUPRC+((MAXUSERS-1)*8)+(NGCSP)) ntext (20+MAXUPRC+(NGCSP)) * * Tunings for cluster server only nbuf 512 ngcsp (4*NUM_CNODES) num_cnodes 10 server_node 1 ------------------------------------------------------------- Jack Repenning - Information Networks Division, Hewlett Packard Corporation uucp: ... {allegra,decvax,ihnp4,ucbvax} !hplabs!hpda!jack or: ... jack@hpda.hp.com HPDesk: Jack REPENNING /HP6600/UX USMail: 43LN; 19420 Homestead Ave; Cupertino, CA 95014 Phone: 408/447-3380 HPTelnet: 1-447-3380 ------------------------------------------------------------- Disclaimer: These opinions are not necessarily those of my employer. In fact, my manager doesn't know I'm . . . Oh shoot! Here he comes! Quick! Pop up that window with code in it! Bye!
rodc@hpfcmgw.HP.COM (Rod Cerkoney) (09/17/89)
Yes you can have a local SWAP disk on a diskless node. Add the proper entries to you cnode dfile to configure swap space and edit your /etc/clusterconf to reflect the change. See your Sys Admin manual for details on each. As for node/network performance you will have to understand where the bottle neck is. If you applications are doing a lot of file i/o then this may be a performance bottle neck. Or, if your running large applications that require alot of text and data space you could be overtaxing the virtual memory system. If so the local swap may help. Hope this helps. RWC.