Whenever the shrink_cache wakes up after a laundered page in unlocked, it should move that page to the end of inactive list so that the page can be freed immediately and shrink_cache dosen't have to wait for complete list scan before freeing this page. The patch is created against standard redhat 7.1 distribution 2.4.16 kernel. Let me know if I need to create it for a different kernel release. Regards Amol (See attached file: vmscan.c-2.4.16)
Attachment:
vmscan.c-2.4.16
Description: Binary data
- Prev by Date: RE: 1gb RAM + 1gb SWAP + make -j bzImage = OOM
- Next by Date: [PATCH] More loop/BIO breakage (ll_rw_blk.c:1359)
- Previous by thread: [patch] mini-lowlatency
- Next by thread: [PATCH] More loop/BIO breakage (ll_rw_blk.c:1359)
- Indexes:[Main][Thread]