On Mon, 7 Apr 2008, Hugh Dickins wrote:Looks like that one of the issues here is that swap_writepage() does not perform enough reclaim? If it would free more pages then __scsi_get_command would still have pages to allocate and not drain the reserves. Mempool_alloc()s use of the gfp_mask here suggests that it can potentially drain all reserves and exhaust all available "slots" (partial slabs). Thus it may regularly force any other user of the slab to hit the slow path and potentially trigger reclaim. Could be a bit unfair. --
| Linus Torvalds | Linux 2.6.27-rc8 |
| Greg Kroah-Hartman | [PATCH 001/196] Chinese: Add the known_regression URI to the HOWTO |
| Mark Lord | Re: Linux 2.6.24-rc7 |
| Andi Kleen | Re: [PATCH] Version 3 (2.6.23-rc8) Smack: Simplified Mandatory Access Control Kernel |
git: | |
| Alex Riesen | Re: First cut at git port to Cygwin |
| Sverre Rabbelier | Git vs Monotone |
| Stephen R. van den Berg | [RFC] origin link for cherry-pick and revert |
| Len Brown | fatal: unable to create '.git/index': File exists |
| Richard Stallman | Real men don't attack straw men |
| GVG GVG | ssh_exchange_identification: Connection closed by remote host |
| Chris | Prolific USB-Serial Controller |
| Karl Sjödahl - dunceor | Re: Routerboard 532 Bounty |
| KOSAKI Motohiro | [bug?] tg3: Failed to load firmware "tigon/tg3_tso.bin" |
| Linus Torvalds | Re: [GIT]: Networking |
| Denys Fedoryshchenko | packetloss, on e1000e worse than r8169? |
| Ilpo Järvinen | Re: [bug] stuck localhost TCP connections, v2.6.26-rc3+ |
