Linux – Remove swap completely or set swappiness to 0

1. On hard disks, throughput and seeking is often faster towards the beginning of the disk, because that data is stored closer to the outer area of the disk, which has more sectors per cylinder. Thus, creating the swap at the beginning of the disk might improve performance.

2. For a 2.6 Linux kernel, there is no performance difference between a swap partition and an unfragmented swap file. When a swap partition/file is enabled by swapon, the 2.6 kernel finds which disk blocks the swapfile is stored on, so that when it comes time to swap, it doesn't have to deal with the filesystem at all.

Thus, if the swapfile isn't fragmented, it's exactly as if there were a swap partition at its same location. Or put another way, you'd get identical performance if you used a swap partition raw, or formatted it with a filesystem and then created a swapfile that filled all space, since either way on that disk there is a contiguous region used for swapping, which the kernel uses directly.

So if one creates the swapfile when the filesystem is fresh (thus ensuring it's not fragmented and at the beginning of the volume), performance should be identical to having a swap partition just before the volume. Further, if one created the swapfile say in the middle of the volume, with files on either side, one might get better performance, since there's less seeking to swap.

On Linux, if the swapfile is created unfragmented, and never expanded, it cannot become fragmented, at least with normal filesystems like ext3/4. It will always use the same disk blocks, which are contiguous.

I conclude that about the only benefit of a dedicated swap partition is guaranteed unfragmentation when you need to expand it; if your swap will never be expanded, a file created on a fresh filesystem doesn't require an extra partition.

If info is swapped out to disc and later read back into memory, it will often be left allocated in the swap area until swap space runs low. That means that if the same info needs to be swapped out again later and hasn't changed, the OS can just drop the pages from allocated RAM without needing to write anything to disc saving time.

Swap allocated to stuff that has been read back into memory will be freed either

1. when the relevant pages are no longer needed at all (i.e. are freed by the application)
2. when the relevant pages are changed (so the copy on disc is no longer up to date)
3. the machine runs low on swap space so clears some things that are already in RAM to make room

Look in /proc/meminfo for a line called "SwapCached". This entry counts pages that are found both in RAM and in swap partitions. For instance, picking a small VM at random, the /proc/meminfo virtual file one of my VMs shows:

SwapTotal:        698816 kB
SwapFree:         624520 kB
SwapCached:        17232 kB

indicating that 74268K of swap space is allocated, but that 17232K worth of those pages are also currently mapped into RAM too (so could be deallocated from swap at a moment's notice if the space is needed by something else).

Also there will no doubt be pages sat there that was swapped out ages ago and have never been used again since. The kernel will not reload pages from swap just because there is some free RAM to read it back into as that free RAM might be better used for cache or buffers - pages written to swap are generally only reread when they are next needed.

If you want to clear out what is in swap, as long as you have enough free and/or freeable (i.e. free+cache+buffers (less those parts of the c+b counts that are not freeable RightThisInstant)), just turn it off and back on again with swapoff -a && swapon -a.

Of course you could also have a memory leak somewhere too, but that is not the only explanation for the behaviour you are seeing.