On Tue, 12 May 2020 17:29:36 -0400 Johannes Weiner <hannes@xxxxxxxxxxx> wrote: > > ... > > Solution > > This patch fixes the aging inversion described above on > !CONFIG_HIGHMEM systems, without reintroducing the problems associated > with excessive shrinker LRU rotations, by keeping populated inodes off > the shrinker LRUs entirely. > > Currently, inodes are kept off the shrinker LRU as long as they have > an elevated i_count, indicating an active user. Unfortunately, the > page cache cannot simply hold an i_count reference, because unlink() > *should* result in the inode being dropped and its cache invalidated. > > Instead, this patch makes iput_final() consult the state of the page > cache and punt the LRU linking to the VM if the inode is still > populated; the VM in turn checks the inode state when it depopulates > the page cache, and adds the inode to the LRU if necessary. > > This is not unlike what we do for dirty inodes, which are moved off > the LRU permanently until writeback completion puts them back on (iff > still unused). We can reuse the same code -- inode_add_lru() - here. > > This is also not unlike page reclaim, where the lower VM layer has to > negotiate state with the higher VFS layer. Follow existing precedence > and handle the inversion as much as possible on the VM side: > > - introduce an I_PAGES flag that the VM maintains under the i_lock, so > that any inode code holding that lock can check the page cache state > without having to lock and inspect the struct address_space Maintaining the same info in two places is a hassle. Is this optimization worthwhile? > - introduce inode_pages_set() and inode_pages_clear() to maintain the > inode LRU state from the VM side, then update all cache mutators to > use them when populating the first cache entry or clearing the last > > With this, the concept of "inodesteal" - where the inode shrinker > drops page cache - is relegated to CONFIG_HIGHMEM systems only. The VM > is in charge of the cache, the shrinker in charge of struct inode. How tested is this on highmem machines? > Footnotes > > - For debuggability, add vmstat counters that track the number of > times a new cache entry pulls a previously unused inode off the LRU > (pginoderescue), as well as how many times existing cache deferred > an LRU addition. Keep the pginodesteal/kswapd_inodesteal counters > for backwards compatibility, but they'll just show 0 now. > > - Fix /proc/sys/vm/drop_caches to drop shadow entries from the page > cache. Not doing so has always been a bit strange, but since most > people drop cache and metadata cache together, the inode shrinker > would have taken care of them before - no more, so do it VM-side. > > ... > > 14 files changed, 208 insertions(+), 34 deletions(-) Patch is surprisingly large.
