RE: [PATCH v13 22/22] mm: zswap: Batched zswap_compress() with compress batching of large folios.

[Sridhar, Kanchana P]

> -----Original Message-----
> From: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
> Sent: Sunday, December 7, 2025 8:24 PM
> To: Sridhar, Kanchana P <kanchana.p.sridhar@xxxxxxxxx>
> Cc: Yosry Ahmed <yosry.ahmed@xxxxxxxxx>; SeongJae Park <sj@xxxxxxxxxx>;
> linux-kernel@xxxxxxxxxxxxxxx; linux-mm@xxxxxxxxx; hannes@xxxxxxxxxxx;
> nphamcs@xxxxxxxxx; chengming.zhou@xxxxxxxxx;
> usamaarif642@xxxxxxxxx; ryan.roberts@xxxxxxx; 21cnbao@xxxxxxxxx;
> ying.huang@xxxxxxxxxxxxxxxxx; akpm@xxxxxxxxxxxxxxxxxxxx;
> senozhatsky@xxxxxxxxxxxx; kasong@xxxxxxxxxxx; linux-
> crypto@xxxxxxxxxxxxxxx; davem@xxxxxxxxxxxxx; clabbe@xxxxxxxxxxxx;
> ardb@xxxxxxxxxx; ebiggers@xxxxxxxxxx; surenb@xxxxxxxxxx; Accardi,
> Kristen C <kristen.c.accardi@xxxxxxxxx>; Gomes, Vinicius
> <vinicius.gomes@xxxxxxxxx>; Feghali, Wajdi K <wajdi.k.feghali@xxxxxxxxx>;
> Gopal, Vinodh <vinodh.gopal@xxxxxxxxx>
> Subject: Re: [PATCH v13 22/22] mm: zswap: Batched zswap_compress() with
> compress batching of large folios.
> 
> On Mon, Dec 08, 2025 at 04:17:38AM +0000, Sridhar, Kanchana P wrote:
> >
> > I see. So the way my patch-set tries to standardize batching in
> > zswap_compress() is to call it with a batch of 8 pages, regardless of batching
> > or non-batching compressors. In zswap_compress(), I presently iterate
> > through each page in the batch for sequential processing for non-batching
> > compressors whose batch size is 1. For batching compressors, the iteration
> > happens just once: the whole batch is compressed in one call to
> > crypto_acomp_compress().
> 
> Oh I wasn't aware of this.  In that case there is no need for me
> to delay the next step and we can do it straight away.

Sure, makes sense, thanks!

> 
> I had thought that the batch size was to limit the batching size
> to acomp.  But if it's not, perhaps we can remove the batch size
> exposure altogether.  IOW it would only be visible internally to
> the acomp API while the users such as zswap would simply batch
> things in whatever size that suits them.

Yes, I think this can be done. In case zswap sends a batch that is not
an integral multiple of the acomp algorithm's batch-size, we might
have to trade-off one sub-optimal batch (fewer pages than the alg's
batch-size) for a cleaner solution.

Thanks,
Kanchana

> 
> Thanks,
> --
> Email: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
> Home Page: http://gondor.apana.org.au/~herbert/
> PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt