Re: /proc/sys/vm/swappiness == 0 makes OOM killer go beserk



On 1/13/06, Jim MacBaine <jmacbaine@xxxxxxxxx> wrote:
> On 1/13/06, Ram Gupta <ram.gupta5@xxxxxxxxx> wrote:
> It _would_ be ok if swappiness == 0 would mean that the kernel will
> not swap at all. That's not the case. Even without an excessive use of
> tmpfs the kernel found ~250 MB of unused memory which it swapped out
> during the last days with swappiness == 0.
>
> Regards,
> Jim
>

I correct myself. swappiness == 0 does not mean that kernel will not try to
swap at all but this value decreases the swapping.
swap_tendency = mapped_ratio / 2 + distress + vm_swappiness;

swap_tendency depends on swappiness and affects the memory reclaimation.

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



Relevant Pages

  • swapping and the value of /proc/sys/vm/swappiness
    ... cache, and the data rates for the dd's. ... The benchmark was repeated for swappiness values of 0, 20, 40, ... What is unexpected is that the amount of swap space used at a particular ... whereas Kernel 2.6.9-rc1-mm3 swapped out 10 GB. ...
    (Linux-Kernel)
  • Re: why swap at all?
    ... then yes the autoregulated swappiness patch should help. ... swap discussion centres around 2 different arguments. ... desktop users will feel the former and not really notice the latter. ... Yet you know that if you set your swappiness to 0 mozilla will load ...
    (Linux-Kernel)
  • Re: OOM killer gripe (was Re: What still uses the block layer?)
    ... so much unless you do want the kernel to actually use it all, ... I tend to lower "swappiness" and when that happens all sorts of stuff goes ... Software suspend used to say says it can't free enough memory if I ... never triggered before hard deadlock. ...
    (Linux-Kernel)
  • Re: 2.6.0-test9 - poor swap performance on low end machines
    ... >> Well I was considering adding the swap pressure to this algorithm but I ... It wont be as aggressive as setting the swappiness ... > The test compile started in a similar way to the compile when using your ... detriment of other tasks that are on the runqueue and still need ram. ...
    (Linux-Kernel)
  • Re: swapping and the value of /proc/sys/vm/swappiness
    ... So for this one testcase it is being beneficial. ... decreasing the "swappiness" value does not seem to make much of a difference: ... Kernel Version 2.6.8.1-mm4: ... send the line "unsubscribe linux-kernel" in ...
    (Linux-Kernel)