Re: mysql and system/nice cpu usage

From: Omer Faruk Sen (ofsen_at_enderunix.org)
Date: 10/31/04

  • Next message: Jay Moore: "Re: ACX100 Firmware Licensing" 
    To: Omer Faruk Sen <ofsen@enderunix.org>
Date: Sun, 31 Oct 2004 19:42:39 +0200

    By the way here is my vmstat -m output:

    Memory statistics by bucket size
    Size In Use Free Requests HighWater Couldfree
     16 1057 479 1778721 1280 0
     32 653 1651 2086878 640 19
     64 130358 18122 19867705 320 27489
    128 3120 2032 18073586 160 47472
    256 127456 1472 5097033 80 254
    512 275 245 32349 40 68
     1K 139 353 3956273 20 522307
     2K 27 319 9225 10 6887
     4K 24 1 3179 5 0
     8K 9 0 20 5 0
    16K 10 0 3321 5 0
    64K 1 0 1 5 0
    128K 3 0 11 5 0
    256K 1 0 1 5 0
    512K 6 0 6 5 0

    Memory usage type by bucket size
    Size Type(s)
     16 uc_devlist, nexusdev, devbuf, UFS dirhash, p1003.1b, dummynet,
              routetbl, ether_multi, vnodes, mount, pcb, soname, atexit, accf,
              proc-args, kld, rman, bus, sysctloid, sysctl, temp
     32 atkbddev, devbuf, UFS dirhash, dirrem, mkdir, diradd, freefile,
              freefrag, indirdep, bmsafemap, newblk, tseg_qent, in_multi, routetbl,
              ether_multi, ifaddr, BPF, vnodes, cluster_save buffer, pcb, accf,
              proc-args, sigio, file desc to leader, kld, taskqueue, SWAP,
              eventhandler, bus, sysctloid, sysctl, uidinfo, subproc, pgrp, temp
     64 devbuf, lockf, isadev, UFS dirhash, allocindir, allocdirect, pagedep,
              routetbl, ether_multi, ifaddr, vnodes, vfscache, pcb, proc-args,
              file, rman, eventhandler, bus, sysctloid, subproc, session, temp
    128 devbuf, ZONE, UFS dirhash, freeblks, inodedep, dummynet, routetbl,
              vnodes, mount, vfscache, soname, ttys, zombie, proc-args, dev_t,
              timecounter, kld, bus, cred, temp
    256 devbuf, UFS dirhash, FFS node, newblk, IpFw/IpAcct, dummynet,
              routetbl, ifaddr, vnodes, vfscache, ttys, proc-args, kqueue,
              file desc, bus, subproc, temp
    512 devbuf, UFS dirhash, UFS mount, dummynet, mount, BIO buffer, ptys,
              file desc, msg, ioctlops, bus, temp
     1K uc_devlist, devbuf, dummynet, kqueue, file desc, sem, ioctlops, bus,
              uidinfo, temp
     2K devbuf, UFS mount, ifaddr, BIO buffer, pcb, file desc, bus, temp
     4K memdesc, devbuf, UFS mount, sem, msg, bus, subproc, proc, temp
     8K UFS mount, syncache, dummynet, bus, temp
    16K devbuf, indirdep, shm, msg, bus
    64K pagedep
    128K mbuf, VM pgdata, temp
    256K MSDOSFS mount
    512K UFS ihash, inodedep, vfscache, ISOFS mount, SWAP, temp

    Memory statistics by type Type Kern
           Type InUse MemUse HighUse Limit Requests Limit Limit Size(s)
        atkbddev 2 1K 1K102400K 2 0 0 32
      uc_devlist 16 2K 2K102400K 16 0 0 16,1K
        nexusdev 3 1K 1K102400K 3 0 0 16
         memdesc 1 4K 4K102400K 1 0 0 4K
            mbuf 1 88K 88K102400K 1 0 0 128K
          devbuf 769 344K 504K102400K 2852 0 0
    16,32,64,128,256,512,1K,2K,4K,16K
           lockf 54 4K 11K102400K 1007915 0 0 64
          isadev 12 1K 1K102400K 12 0 0 64
            ZONE 14 2K 2K102400K 14 0 0 128
       VM pgdata 1 128K 128K102400K 1 0 0 128K
     UFS dirhash 657 131K 257K102400K 2610 0 0
    16,32,64,128,256,512
       UFS mount 18 47K 47K102400K 18 0 0 512,2K,4K,8K
       UFS ihash 1 512K 512K102400K 1 0 0 512K
        FFS node121493 30374K 30374K102400K 4335964 0 0 256
          dirrem 3 1K 2K102400K 278448 0 0 32
           mkdir 0 0K 1K102400K 8 0 0 32
          diradd 2 1K 2K102400K 280239 0 0 32
        freefile 1 1K 1K102400K 260385 0 0 32
        freeblks 3 1K 37K102400K 202522 0 0 128
        freefrag 2 1K 3K102400K 63040 0 0 32
      allocindir 5 1K 1381K102400K 176591 0 0 64
        indirdep 1 1K 49K102400K 4779 0 0 32,16K
     allocdirect 3 1K 36K102400K 343645 0 0 64
       bmsafemap 4 1K 1K102400K 14877 0 0 32
          newblk 1 1K 1K102400K 520237 0 0 32,256
        inodedep 9 513K 551K102400K 266268 0 0 128,512K
         pagedep 4 65K 65K102400K 9089 0 0 64,64K
        p1003.1b 1 1K 1K102400K 1 0 0 16
        syncache 1 8K 8K102400K 1 0 0 8K
       tseg_qent 1 1K 2K102400K 4567 0 0 32
     IpFw/IpAcct 7 2K 2K102400K 7 0 0 256
        dummynet 1050 141K 163K102400K 12415712 0 0
    16,128,256,512,1K,8K
        in_multi 3 1K 1K102400K 3 0 0 32
        routetbl 292 41K 501K102400K 222847 0 0
    16,32,64,128,256
     ether_multi 12 1K 1K102400K 12 0 0 16,32,64
          ifaddr 27 7K 7K102400K 27 0 0 32,64,256,2K
             BPF 4 1K 1K102400K 4 0 0 32
    MSDOSFS mount 1 256K 256K102400K 1 0 0 256K
          vnodes 46 6K 6K102400K 365 0 0
    16,32,64,128,256
           mount 7 4K 4K102400K 9 0 0 16,128,512
    cluster_save buffer 0 0K 1K102400K 268971 0 0 32
        vfscache129506 9144K 9316K102400K 4601963 0 0
    64,128,256,512K
      BIO buffer 6 12K 648K102400K 8208 0 0 512,2K
             pcb 17 5K 5K102400K 9740 0 0 16,32,64,2K
          soname 4 1K 22K102400K 2288534 0 0 16,128
          atexit 1 1K 1K102400K 1 0 0 16
            accf 4 1K 1K102400K 4 0 0 16,32
            ptys 2 1K 1K102400K 2 0 0 512
            ttys 409 53K 53K102400K 1072 0 0 128,256
          zombie 0 0K 22K102400K 241389 0 0 128
       proc-args 61 4K 6K102400K 90306 0 0
    16,32,64,128,256
          kqueue 2 2K 23K102400K 6090 0 0 256,1K
           sigio 1 1K 1K102400K 35 0 0 32
            file 575 36K 90K102400K 13594151 0 0 64
             shm 1 12K 12K102400K 1 0 0 16K
    file desc to leader 1 1K 1K102400K 3 0 0 32
       file desc 301 81K 176K102400K 100750 0 0 256,512,1K,2K
           dev_t 827 104K 104K102400K 827 0 0 128
     timecounter 10 2K 2K102400K 10 0 0 128
             kld 4 1K 1K102400K 35 0 0 16,32,128
     ISOFS mount 1 512K 512K102400K 1 0 0 512K
             sem 3 6K 6K102400K 3 0 0 1K,4K
             msg 4 25K 25K102400K 4 0 0 512,4K,16K
            rman 65 4K 4K102400K 423 0 0 16,64
        ioctlops 0 0K 1K102400K 17 0 0 512,1K
       taskqueue 2 1K 1K102400K 2 0 0 32
            SWAP 2 1097K 1097K102400K 2 0 0 32,512K
    eventhandler 16 1K 1K102400K 16 0 0 32,64
             bus 446 61K 65K102400K 1155 0 0
    16,32,64,128,256,512,1K,2K,4K,8K,16K
       sysctloid 67 3K 3K102400K 67 0 0 16,32,64
          sysctl 0 0K 1K102400K 5747 0 0 16,32
         uidinfo 16 2K 2K102400K 2537 0 0 32,1K
            cred 133 17K 41K102400K 3283634 0 0 128
         subproc 404 27K 46K102400K 314732 0 0 32,64,256,4K
            proc 2 8K 8K102400K 2 0 0 4K
         session 23 2K 2K102400K 5382 0 0 64
            pgrp 28 1K 2K102400K 5573 0 0 32
            temp 5663 1760K 2009K102400K 5663826 0 0
    16,32,64,128,256,512,1K,2K,4K,8K,128K,512K

    Memory Totals: In Use Free Requests
                   45649K 2932K 50908309

     

    Omer Faruk Sen writes:

    > Hi
    >
    >
    > The oid you are talking about is not valid in FreeBSD-4. Maybe you are
    > talking about FreeBSD-5 sysctl oids? But it does worth to try but I am not
    > sure which oid it is in FreeBSD 4..
    >
    > REGARDS
    >
    > PS: I have found vm.kvm_size. I think it is the one that corresponds in
    > your email?
    >
    > TM4525@aol.com writes:
    >
    >> In a message dated 10/31/04 11:03:12 AM Eastern Standard Time,
    >> ofsen@enderunix.org writes:
    >>> but never come across with a problem like that. I am thinking to use
    >>> Zend Optimizer. Maybe that helps me ..
    >>>
    >>> If that doesn't help I was thinking to run sql on a seperate machine.
    >>
    >> You might try tuning kern.vm.kmem.size if thats not in the tuning
    >> suggestions.
    >> The OS tends to allocate way more memory than needed for the kernel if
    >> you have a lot of memory in the system; you probably don't need more than
    >> 100M or so unless you're running bgp or something unusual. Once you start
    >> swapping with mysql and php you're dead.
    >>
    >> Moving to another system can help, but be aware that if your network is
    >> busy it can add some "different" inefficiencies. If you do go to a
    >> separate
    >> system connect it with a dedicated NIC if possible, to alleviate network
    >> backup. If you have a multiple bus machine, moving your NIC to a separate
    >> bus from the HDD can significantly increase performance. When you have
    >> the NIC and HDD on the same bus, heavy network traffic can cause disk
    >> operations to back up and substantially slow database applications. Make
    >> sure the busses are really separate (and not cascaded), otherwise it
    >> won't
    >> help.
    >>
    >> Also if you're on a 32bit bus machine you'll have a lot more contention
    >> than
    >> with a pci-x bus. Most people think that if you have enough bus then it
    >> doesnt matter, but thats dead wrong. Bus contention between devices is a
    >> major performance factor.
    >
    >
    >
    > -----------------------
    > Omer Faruk Sen
    > http://www.EnderUNIX.ORG
    > Software Development Team @ Turkey
    > http://www.Faruk.NET
    > For Public key: http://www.enderunix.org/ofsen/ofsen.asc
    > ********************************************************
    >
    >
    > First Turkish FreeBSD book is out! Go check it.
    > Duydunuz mu! Turkiye'nin ilk FreeBSD kitabi cikti.
    > http://www.acikkod.com/freebsd.php
    >
    >
    > _______________________________________________
    > freebsd-questions@freebsd.org mailing list
    > http://lists.freebsd.org/mailman/listinfo/freebsd-questions
    > To unsubscribe, send any mail to
    > "freebsd-questions-unsubscribe@freebsd.org"
     

     -----------------------
    Omer Faruk Sen
    http://www.EnderUNIX.ORG
    Software Development Team @ Turkey
    http://www.Faruk.NET
    For Public key: http://www.enderunix.org/ofsen/ofsen.asc
    ********************************************************

    First Turkish FreeBSD book is out! Go check it.
    Duydunuz mu! Turkiye'nin ilk FreeBSD kitabi cikti.
    http://www.acikkod.com/freebsd.php

    _______________________________________________
    freebsd-questions@freebsd.org mailing list
    http://lists.freebsd.org/mailman/listinfo/freebsd-questions
    To unsubscribe, send any mail to "freebsd-questions-unsubscribe@freebsd.org"

  • Next message: Jay Moore: "Re: ACX100 Firmware Licensing"