Re: [PATCH 1/5] mm/zswap: reuse dstmem when decompress

[Chris Li <chrisl@kernel.org>]

On Tue, Dec 12, 2023 at 8:18 PM Chengming Zhou
<zhouchengming@bytedance.com> wrote:
>
> In the !zpool_can_sleep_mapped() case such as zsmalloc, we need to first
> copy the entry->handle memory to a temporary memory, which is allocated
> using kmalloc.
>
> Obviously we can reuse the per-compressor dstmem to avoid allocating
> every time, since it's percpu-compressor and protected in mutex.

You are trading more memory for faster speed.
Per-cpu data structure does not come free. It is expensive in terms of
memory on a big server with a lot of CPU. Think more than a few
hundred CPU. On the big servers, we might want to disable this
optimization to save a few MB RAM, depending on the gain of this
optimization.
Do we have any benchmark suggesting how much CPU overhead or latency
this per-CPU page buys us, compared to using kmalloc?

Chris

>
> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
> Reviewed-by: Nhat Pham <nphamcs@gmail.com>
> ---
>  mm/zswap.c | 29 +++++++++--------------------
>  1 file changed, 9 insertions(+), 20 deletions(-)
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 7ee54a3d8281..edb8b45ed5a1 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -1772,9 +1772,9 @@ bool zswap_load(struct folio *folio)
>         struct zswap_entry *entry;
>         struct scatterlist input, output;
>         struct crypto_acomp_ctx *acomp_ctx;
> -       u8 *src, *dst, *tmp;
> +       unsigned int dlen = PAGE_SIZE;
> +       u8 *src, *dst;
>         struct zpool *zpool;
> -       unsigned int dlen;
>         bool ret;
>
>         VM_WARN_ON_ONCE(!folio_test_locked(folio));
> @@ -1796,27 +1796,18 @@ bool zswap_load(struct folio *folio)
>                 goto stats;
>         }
>
> -       zpool = zswap_find_zpool(entry);
> -       if (!zpool_can_sleep_mapped(zpool)) {
> -               tmp = kmalloc(entry->length, GFP_KERNEL);
> -               if (!tmp) {
> -                       ret = false;
> -                       goto freeentry;
> -               }
> -       }
> -
>         /* decompress */
> -       dlen = PAGE_SIZE;
> -       src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
> +       acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
> +       mutex_lock(acomp_ctx->mutex);
>
> +       zpool = zswap_find_zpool(entry);
> +       src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
>         if (!zpool_can_sleep_mapped(zpool)) {
> -               memcpy(tmp, src, entry->length);
> -               src = tmp;
> +               memcpy(acomp_ctx->dstmem, src, entry->length);
> +               src = acomp_ctx->dstmem;
>                 zpool_unmap_handle(zpool, entry->handle);
>         }
>
> -       acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
> -       mutex_lock(acomp_ctx->mutex);
>         sg_init_one(&input, src, entry->length);
>         sg_init_table(&output, 1);
>         sg_set_page(&output, page, PAGE_SIZE, 0);
> @@ -1827,15 +1818,13 @@ bool zswap_load(struct folio *folio)
>
>         if (zpool_can_sleep_mapped(zpool))
>                 zpool_unmap_handle(zpool, entry->handle);
> -       else
> -               kfree(tmp);
>
>         ret = true;
>  stats:
>         count_vm_event(ZSWPIN);
>         if (entry->objcg)
>                 count_objcg_event(entry->objcg, ZSWPIN);
> -freeentry:
> +
>         spin_lock(&tree->lock);
>         if (ret && zswap_exclusive_loads_enabled) {
>                 zswap_invalidate_entry(tree, entry);
>
> --
> b4 0.10.1