@@ -521,7 +521,15 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
if (zswap_load(folio)) {
folio_unlock(folio);
- } else if (data_race(sis->flags & SWP_FS_OPS)) {
+ goto finish;
+ }
+
+ /*
+ * We have to read the page from slower devices. Increase zswap protection.
+ */
+ zswap_folio_swapin(folio);
+
+ if (data_race(sis->flags & SWP_FS_OPS)) {
swap_read_folio_fs(folio, plug);
} else if (synchronous) {
swap_read_folio_bdev_sync(folio, sis);
@@ -529,6 +537,7 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
swap_read_folio_bdev_async(folio, sis);
}
+finish:
if (workingset) {
delayacct_thrashing_end(&in_thrashing);
psi_memstall_leave(&pflags);
@@ -698,10 +698,8 @@ struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
/* The page was likely read above, so no need for plugging here */
folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
&page_allocated, false);
- if (unlikely(page_allocated)) {
- zswap_folio_swapin(folio);
+ if (unlikely(page_allocated))
swap_read_folio(folio, NULL);
- }
return folio;
}
@@ -850,10 +848,8 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
/* The folio was likely read above, so no need for plugging here */
folio = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
&page_allocated, false);
- if (unlikely(page_allocated)) {
- zswap_folio_swapin(folio);
+ if (unlikely(page_allocated))
swap_read_folio(folio, NULL);
- }
return folio;
}
Currently, we only increment the swapin counter on pivot pages. This means we are not taking into account pages that also need to be swapped in, but are already taken care of as part of the readahead window. We are also incrementing when the pages are read from the zswap pool, which is inaccurate. This patch rectifies this issue by incrementing whenever we need to perform a non-zswap read. To test this change, I built the kernel under a cgroup with its memory.max set to 2 GB: real: 236.66s user: 4286.06s sys: 652.86s swapins: 81552 For comparison, with just the new second chance algorithm, the build time is as follows: real: 244.85s user: 4327.22s sys: 664.39s swapins: 94663 Without neither: real: 263.89s user: 4318.11s sys: 673.29s swapins: 227300.5 (average over 5 runs) With this change, the kernel CPU time reduces by a further 1.7%, and the real time is reduced by another 3.3%, compared to just the second chance algorithm by itself. The swapins count also reduces by another 13.85%. Combinng the two changes, we reduce the real time by 10.32%, kernel CPU time by 3%, and number of swapins by 64.12%. To gauge the new scheme's ability to offload cold data, I ran another benchmark, in which the kernel was built under a cgroup with memory.max set to 3 GB, but with 0.5 GB worth of cold data allocated before each build (in a shmem file). Under the old scheme: real: 197.18s user: 4365.08s sys: 289.02s zswpwb: 72115.2 Under the new scheme: real: 195.8s user: 4362.25s sys: 290.14s zswpwb: 87277.8 (average over 5 runs) Notice that we actually observe a 21% increase in the number of written back pages - so the new scheme is just as good, if not better at offloading pages from the zswap pool when they are cold. Build time reduces by around 0.7% as a result. Suggested-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Nhat Pham <nphamcs@gmail.com> --- mm/page_io.c | 11 ++++++++++- mm/swap_state.c | 8 ++------ 2 files changed, 12 insertions(+), 7 deletions(-)