Re: [PATCH] zram: easy the allocation of zcomp_strm's buffers with 2 pages

[Barry Song]

On Tue, Feb 6, 2024 at 9:55 AM Sergey Senozhatsky
<senozhatsky@xxxxxxxxxxxx> wrote:
>
> On (24/01/29 10:46), Barry Song wrote:
> > On Mon, Jan 15, 2024 at 10:35 AM Sergey Senozhatsky
> > <senozhatsky@xxxxxxxxxxxx> wrote:
> > >
> > > On (24/01/06 15:38), Barry Song wrote:
> > > > On Sat, Jan 6, 2024 at 9:30 AM Sergey Senozhatsky
> > > > <senozhatsky@xxxxxxxxxxxx> wrote:
> > > > >
> > > > > On (24/01/03 13:30), Barry Song wrote:
> > > > > > There is no need to keep zcomp_strm's buffers contiguous physically.
> > > > > > And rarely, 1-order allocation can fail while buddy is seriously
> > > > > > fragmented.
> > > > >
> [..]
> > > Okay, makes sense.
> > > Do you see these problems in real life? I don't recall any reports.
> >
> > i don't have problems with the current zram which supports normal pages only.
> >
> > but  in our out-of-tree code, we have enhanced zram/zsmalloc to support large
> > folios compression/decompression, which will make zram work much better
> > with large anon folios/mTHP things on which Ryan Roberts is working on.
> >
> > I mean, a large folio with for example 16 normal pages can be saved as
> > one object in zram.
> > In millions of phones, we have deployed this approach and seen huge improvement
> > on compression ratio and cpu consumption decrease. in that case, we
> > need a larger
> > per-cpu buffer, and have seen frequent failure on allocation. that
> > inspired me to send
> > this patch in advance.
>
> May I please ask you to resend this patch with updated commit mesasge?
> E.g. mention cpu offlinig/onlining, etc.

I will send v2 to add this information in the commit message. thanks!

>
> [..]
> > > > > I also wonder whether Android uses HW compression, in which case we
> > > > > may need to have physically contig pages. Not to mention TLB shootdowns
> > > > > that virt contig pages add to the picture.
> > > >
> > > > I don't understand how HW compression and TLB shootdown are related as zRAM
> > > > is using a traditional comp API.
> > >
> > > Oh, those are not related. TLB shootdowns are what now will be added to
> > > all compressions/decompressions, so it's sort of extra cost.
> >
> > i am sorry i still don't understand where the tlb shootdowns come
> > from. we don't unmap
> > this per-cpu buffers during compression and decompression, do we ?
> >
> > am i missing something?
>
> No, I guess you are right.

Best regards
Barry