lkml.org 
[lkml]   [2006]   [Aug]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [take13 1/3] kevent: Core files.
    On Thu, Aug 24, 2006 at 11:58:59PM -0700, Andrew Morton (akpm@osdl.org) wrote:
    > > > > kmalloc is really slow actually - it always shows somewhere on top
    > > > > in profiles and brings noticeble overhead
    > > >
    > > > It shouldn't. Please describe the workload and send the profiles.
    > >
    > > epoll based trivial server (accept + sendfile for the same file, about
    > > 4k), httperf with big amount of simulateneous connections. 3c59x NIC
    > > (with e1000 there were no ioreads and netif_rx).
    > > __alloc_skb calls kmem_cache_alloc() and ___kmalloc().
    > >
    > > 16158 1.3681 ioread16
    > > 8073 0.6835 ioread32
    > > 3485 0.2951 irq_entries_start
    > > 3018 0.2555 _spin_lock
    > > 2103 0.1781 tcp_v4_rcv
    > > 1503 0.1273 sysenter_past_esp
    > > 1492 0.1263 netif_rx
    > > 1459 0.1235 skb_copy_bits
    > > 1422 0.1204 _spin_lock_irqsave
    > > 1145 0.0969 ip_route_input
    > > 983 0.0832 kmem_cache_free
    > > 964 0.0816 __alloc_skb
    > > 926 0.0784 common_interrupt
    > > 891 0.0754 __do_IRQ
    > > 846 0.0716 _read_lock
    > > 826 0.0699 __netif_rx_schedule
    > > 806 0.0682 __kmalloc
    > > 767 0.0649 do_tcp_sendpages
    > > 747 0.0632 __copy_to_user_ll
    > > 744 0.0630 pskb_expand_head
    > >
    >
    > That doesn't look too bad.
    >
    > What's that as a percentage of total user+system time?

    With e1000 allocations take more time than actual TCP processing, so it
    rised some suspicious for me (especially in bulk transfer).
    Total time is about 7 times more than system one, user time is much less
    than system one (about 20 times less, but test duration was not too
    long, so it can vary).

    I do not say it is bad, but it is noticeble and should be eliminated
    if there are no requirements to have it.

    --
    Evgeniy Polyakov
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2006-08-25 09:25    [W:0.024 / U:220.260 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site