Re: [PATCH] mm: Add Kcompressd for accelerated memory compression

[Barry Song <21cnbao@gmail.com>]

On Wed, May 7, 2025 at 1:50 PM Zi Yan <ziy@nvidia.com> wrote:
>
> On 6 May 2025, at 21:12, Harry Yoo wrote:
>
> > On Wed, Apr 30, 2025 at 04:26:41PM +0800, Qun-Wei Lin wrote:
> >> This patch series introduces a new mechanism called kcompressd to
> >> improve the efficiency of memory reclaiming in the operating system.
> >>
> >> Problem:
> >>   In the current system, the kswapd thread is responsible for both scanning
> >>   the LRU pages and handling memory compression tasks (such as those
> >>   involving ZSWAP/ZRAM, if enabled). This combined responsibility can lead
> >>   to significant performance bottlenecks, especially under high memory
> >>   pressure. The kswapd thread becomes a single point of contention, causing
> >>   delays in memory reclaiming and overall system performance degradation.
> >>
> >> Solution:
> >>   Introduced kcompressd to handle asynchronous compression during memory
> >>   reclaim, improving efficiency by offloading compression tasks from
> >>   kswapd. This allows kswapd to focus on its primary task of page reclaim
> >>   without being burdened by the additional overhead of compression.
> >>
> >> In our handheld devices, we found that applying this mechanism under high
> >> memory pressure scenarios can increase the rate of pgsteal_anon per second
> >> by over 260% compared to the situation with only kswapd. Additionally, we
> >> observed a reduction of over 50% in page allocation stall occurrences,
> >> further demonstrating the effectiveness of kcompressd in alleviating memory
> >> pressure and improving system responsiveness.
> >>
> >> Co-developed-by: Barry Song <21cnbao@gmail.com>
> >> Signed-off-by: Barry Song <21cnbao@gmail.com>
> >> Signed-off-by: Qun-Wei Lin <qun-wei.lin@mediatek.com>
> >> Reference: Re: [PATCH 0/2] Improve Zram by separating compression context from kswapd - Barry Song
> >>           https://lore.kernel.org/lkml/20250313093005.13998-1-21cnbao@gmail.com/
> >> ---
> >
> > +Cc Zi Yan, who might be interested in writing a framework (or improving
> > the existing one, padata) for parallelizing jobs (e.g. migration/compression)
>
> Thanks.
>
> I am currently looking into padata [1] to perform multithreaded page migration
> copy job. But based on this patch, it seems that kcompressed is just an additional
> kernel thread of executing zswap_store(). Is there any need for performing
> compression with multiple threads?

The current focus is on enabling kswapd to perform asynchronous compression,
which can significantly reduce direct reclaim and allocstall events.
Therefore, the work begins with supporting a single thread. Supporting
multiple threads might be possible in the future, but it could be difficult
to control—especially on busy phones—since it consumes more power and may
interfere with other threads impacting user experience.

>
> BTW, I also notice that zswap IAA compress batching patchset[2] is using
> hardware accelerator (Intel Analytics Accelerator) to speed up zswap.
> I wonder if the handheld devices have similar hardware to get a similar benefit.

Usually, the answer is no. We use zRAM and CPU, but this patch aims to provide
a common capability that can be shared by both zRAM and zswap.

>
>
> [1] https://docs.kernel.org/core-api/padata.html
> [2] https://lore.kernel.org/linux-crypto/20250303084724.6490-1-kanchana.p.sridhar@intel.com/
> >
> >>  include/linux/mmzone.h |  6 ++++
> >>  mm/mm_init.c           |  1 +
> >>  mm/page_io.c           | 71 ++++++++++++++++++++++++++++++++++++++++++
> >>  mm/swap.h              |  6 ++++
> >>  mm/vmscan.c            | 25 +++++++++++++++
> >>  5 files changed, 109 insertions(+)
> >>
> >> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> >> index 6ccec1bf2896..93c9195a54ae 100644
> >> --- a/include/linux/mmzone.h
> >> +++ b/include/linux/mmzone.h
> >> @@ -23,6 +23,7 @@
> >>  #include <linux/page-flags.h>
> >>  #include <linux/local_lock.h>
> >>  #include <linux/zswap.h>
> >> +#include <linux/kfifo.h>
> >>  #include <asm/page.h>
> >>
> >>  /* Free memory management - zoned buddy allocator.  */
> >> @@ -1398,6 +1399,11 @@ typedef struct pglist_data {
> >>
> >>      int kswapd_failures;            /* Number of 'reclaimed == 0' runs */
> >>
> >> +#define KCOMPRESS_FIFO_SIZE 256
> >> +    wait_queue_head_t kcompressd_wait;
> >> +    struct task_struct *kcompressd;
> >> +    struct kfifo kcompress_fifo;
> >> +
> >>  #ifdef CONFIG_COMPACTION
> >>      int kcompactd_max_order;
> >>      enum zone_type kcompactd_highest_zoneidx;
> >> diff --git a/mm/mm_init.c b/mm/mm_init.c
> >> index 9659689b8ace..49bae1dd4584 100644
> >> --- a/mm/mm_init.c
> >> +++ b/mm/mm_init.c
> >> @@ -1410,6 +1410,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
> >>      pgdat_init_kcompactd(pgdat);
> >>
> >>      init_waitqueue_head(&pgdat->kswapd_wait);
> >> +    init_waitqueue_head(&pgdat->kcompressd_wait);
> >>      init_waitqueue_head(&pgdat->pfmemalloc_wait);
> >>
> >>      for (i = 0; i < NR_VMSCAN_THROTTLE; i++)
> >> diff --git a/mm/page_io.c b/mm/page_io.c
> >> index 4bce19df557b..d85deb494a6a 100644
> >> --- a/mm/page_io.c
> >> +++ b/mm/page_io.c
> >> @@ -233,6 +233,38 @@ static void swap_zeromap_folio_clear(struct folio *folio)
> >>      }
> >>  }
> >>
> >> +static bool swap_sched_async_compress(struct folio *folio)
> >> +{
> >> +    struct swap_info_struct *sis = swp_swap_info(folio->swap);
> >> +    int nid = numa_node_id();
> >> +    pg_data_t *pgdat = NODE_DATA(nid);
> >> +
> >> +    if (unlikely(!pgdat->kcompressd))
> >> +            return false;
> >> +
> >> +    if (!current_is_kswapd())
> >> +            return false;
> >> +
> >> +    if (!folio_test_anon(folio))
> >> +            return false;
> >> +    /*
> >> +     * This case needs to synchronously return AOP_WRITEPAGE_ACTIVATE
> >> +     */
> >> +    if (!mem_cgroup_zswap_writeback_enabled(folio_memcg(folio)))
> >> +            return false;
> >> +
> >> +    sis = swp_swap_info(folio->swap);
> >> +    if (zswap_is_enabled() || data_race(sis->flags & SWP_SYNCHRONOUS_IO)) {
> >> +            if (kfifo_avail(&pgdat->kcompress_fifo) >= sizeof(folio) &&
> >> +                    kfifo_in(&pgdat->kcompress_fifo, &folio, sizeof(folio))) {
> >> +                    wake_up_interruptible(&pgdat->kcompressd_wait);
> >> +                    return true;
> >> +            }
> >> +    }
> >> +
> >> +    return false;
> >> +}
> >> +
> >>  /*
> >>   * We may have stale swap cache pages in memory: notice
> >>   * them here and get rid of the unnecessary final write.
> >> @@ -275,6 +307,15 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
> >>               */
> >>              swap_zeromap_folio_clear(folio);
> >>      }
> >> +
> >> +    /*
> >> +     * Compression within zswap and zram might block rmap, unmap
> >> +     * of both file and anon pages, try to do compression async
> >> +     * if possible
> >> +     */
> >> +    if (swap_sched_async_compress(folio))
> >> +            return 0;
> >> +
> >>      if (zswap_store(folio)) {
> >>              count_mthp_stat(folio_order(folio), MTHP_STAT_ZSWPOUT);
> >>              folio_unlock(folio);
> >> @@ -289,6 +330,36 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
> >>      return 0;
> >>  }
> >>
> >> +int kcompressd(void *p)
> >> +{
> >> +    pg_data_t *pgdat = (pg_data_t *)p;
> >> +    struct folio *folio;
> >> +    struct writeback_control wbc = {
> >> +            .sync_mode = WB_SYNC_NONE,
> >> +            .nr_to_write = SWAP_CLUSTER_MAX,
> >> +            .range_start = 0,
> >> +            .range_end = LLONG_MAX,
> >> +            .for_reclaim = 1,
> >> +    };
> >> +
> >> +    while (!kthread_should_stop()) {
> >> +            wait_event_interruptible(pgdat->kcompressd_wait,
> >> +                            !kfifo_is_empty(&pgdat->kcompress_fifo));
> >> +
> >> +            while (!kfifo_is_empty(&pgdat->kcompress_fifo)) {
> >> +                    if (kfifo_out(&pgdat->kcompress_fifo, &folio, sizeof(folio))) {
> >> +                            if (zswap_store(folio)) {
> >> +                                    count_mthp_stat(folio_order(folio), MTHP_STAT_ZSWPOUT);
> >> +                                    folio_unlock(folio);
> >> +                                    continue;
> >> +                            }
> >> +                            __swap_writepage(folio, &wbc);
> >> +                    }
> >> +            }
> >> +    }
> >> +    return 0;
> >> +}
> >> +
> >>  static inline void count_swpout_vm_event(struct folio *folio)
> >>  {
> >>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> >> diff --git a/mm/swap.h b/mm/swap.h
> >> index 6f4a3f927edb..3579da413dc2 100644
> >> --- a/mm/swap.h
> >> +++ b/mm/swap.h
> >> @@ -22,6 +22,7 @@ static inline void swap_read_unplug(struct swap_iocb *plug)
> >>  void swap_write_unplug(struct swap_iocb *sio);
> >>  int swap_writepage(struct page *page, struct writeback_control *wbc);
> >>  void __swap_writepage(struct folio *folio, struct writeback_control *wbc);
> >> +int kcompressd(void *p);
> >>
> >>  /* linux/mm/swap_state.c */
> >>  /* One swap address space for each 64M swap space */
> >> @@ -199,6 +200,11 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
> >>      return 0;
> >>  }
> >>
> >> +static inline int kcompressd(void *p)
> >> +{
> >> +    return 0;
> >> +}
> >> +
> >>  #endif /* CONFIG_SWAP */
> >>
> >>  #endif /* _MM_SWAP_H */
> >> diff --git a/mm/vmscan.c b/mm/vmscan.c
> >> index 3783e45bfc92..2d7b9167bfd6 100644
> >> --- a/mm/vmscan.c
> >> +++ b/mm/vmscan.c
> >> @@ -7420,6 +7420,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
> >>  void __meminit kswapd_run(int nid)
> >>  {
> >>      pg_data_t *pgdat = NODE_DATA(nid);
> >> +    int ret;
> >>
> >>      pgdat_kswapd_lock(pgdat);
> >>      if (!pgdat->kswapd) {
> >> @@ -7433,7 +7434,26 @@ void __meminit kswapd_run(int nid)
> >>              } else {
> >>                      wake_up_process(pgdat->kswapd);
> >>              }
> >> +            ret = kfifo_alloc(&pgdat->kcompress_fifo,
> >> +                            KCOMPRESS_FIFO_SIZE * sizeof(struct folio *),
> >> +                            GFP_KERNEL);
> >> +            if (ret) {
> >> +                    pr_err("%s: fail to kfifo_alloc\n", __func__);
> >> +                    goto out;
> >> +            }
> >> +
> >> +            pgdat->kcompressd = kthread_create_on_node(kcompressd, pgdat, nid,
> >> +                            "kcompressd%d", nid);
> >> +            if (IS_ERR(pgdat->kcompressd)) {
> >> +                    pr_err("Failed to start kcompressd on node %d，ret=%ld\n",
> >> +                                    nid, PTR_ERR(pgdat->kcompressd));
> >> +                    pgdat->kcompressd = NULL;
> >> +                    kfifo_free(&pgdat->kcompress_fifo);
> >> +            } else {
> >> +                    wake_up_process(pgdat->kcompressd);
> >> +            }
> >>      }
> >> +out:
> >>      pgdat_kswapd_unlock(pgdat);
> >>  }
> >>
> >> @@ -7452,6 +7472,11 @@ void __meminit kswapd_stop(int nid)
> >>              kthread_stop(kswapd);
> >>              pgdat->kswapd = NULL;
> >>      }
> >> +    if (pgdat->kcompressd) {
> >> +            kthread_stop(pgdat->kcompressd);
> >> +            pgdat->kcompressd = NULL;
> >> +            kfifo_free(&pgdat->kcompress_fifo);
> >> +    }
> >>      pgdat_kswapd_unlock(pgdat);
> >>  }
> >>
> >> --
> >> 2.45.2
> >>
> >>
> >
> > --
> > Cheers,
> > Harry / Hyeonggon
>
>
> --
> Best Regards,
> Yan, Zi

Thanks
Barry