-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 On 08/27/2012 09:25 PM, Brandon Allbery wrote: > On Tue, Aug 28, 2012 at 12:20 AM, Yves Dorfsman <y...@zioup.com> > wrote: > >> I for one, totally disagree with your statement, I do not want >> any of my process to be pushed to swap to just buy some buffer >> space. If I have an I/O issue, I'll look into it. This is why I >> set swappiness to zero on Linux, and I sure wish there was a way >> to do that on Windows! >> > > Why exactly do you want to waste RAM on dead code/data? It served > its purpose, it should get out of the way and let something > productive use the RAM.
It can be a real problem for latency-sensitive applications that are cohabiting on a system that's also doing heavy I/O. For instance, IBM's TSM database process (often consuming 75% of the physical memory of the machine for indices) often becomes paged out during heavy backup load because the kernel is trying to free up buffer space for incoming backup data. Of course, what the kernel doesn't know is that the next blob of data is going to require hitting the database process that just got paged out before it can get written to disk or tape. The fix is to set swappiness to 0 so that the database processes stay in memory and are always available to handle transactions. This doesn't have a huge effect on I/O either, because the amount of data that gets backed up always dwarfs the amount of physical memory available in the system, regardless of how much the database processes are using. Skylar -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAlA8SbQACgkQsc4yyULgN4aNxgCgsSlJB1bQ6lXEOwzy98y2wLX8 MGYAoIVZjvaDnvDTYBSCGmBsy9gU5jOU =wF29 -----END PGP SIGNATURE----- _______________________________________________ Tech mailing list Tech@lists.lopsa.org https://lists.lopsa.org/cgi-bin/mailman/listinfo/tech This list provided by the League of Professional System Administrators http://lopsa.org/
