Content-Type: multipart/mixed; boundary="===============0629438660393517051==" MIME-Version: 1.0 From: kernel test robot To: lkp@lists.01.org Subject: Re: [futex] 8019ad13ef: will-it-scale.per_process_ops -97.8% regression Date: Mon, 09 Mar 2020 16:26:49 +0800 Message-ID: <20200309082649.GT5972@shao2-debian> In-Reply-To: <87h7yy90ve.fsf@nanos.tec.linutronix.de> List-Id: --===============0629438660393517051== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On Sun, Mar 08, 2020 at 07:07:17PM +0100, Thomas Gleixner wrote: > Linus Torvalds writes: > = > > [ Just a re-send without html crud that makes all the lists unhappy. > > I'm still on the road, the flight I was supposed to be on yesterday > > got cancelled.. ] > > > > I do note that the futex hashing seems to be broken by that commit. Or > > at least it's questionable. It keeps hashing on "both.word", and > > doesn't use the u64 field at all for hashing. > > > > Maybe I'm mis-reading it - I didn't apply the patch, I just looked at > > the patch and my source base separately. > > > > But the 98% regression sure says something went wrong ;) > = > Right you are. The pointer needs to be the starting point as it moved > ahead of word, which means it starts at word and hashes word and > offset and an extra u32 beyond the end of the key. > = > Thanks, > = > tglx > ---- > diff --git a/kernel/futex.c b/kernel/futex.c > index e14f7cd45dbd..9f3251349f65 100644 > --- a/kernel/futex.c > +++ b/kernel/futex.c > @@ -385,8 +385,8 @@ static inline int hb_waiters_pending(struct futex_has= h_bucket *hb) > */ > static struct futex_hash_bucket *hash_futex(union futex_key *key) > { > - u32 hash =3D jhash2((u32*)&key->both.word, > - (sizeof(key->both.word)+sizeof(key->both.ptr))/4, > + u32 hash =3D jhash2((u32*)&key->both.ptr, > + (sizeof(key->both.ptr) + sizeof(key->both.word)) / 4, > key->both.offset); > return &futex_queues[hash & (futex_hashsize - 1)]; > } Hi Thomas, I have tested the above patch, and the patch can fix the regression. commit: v5.6-rc4 8019ad13ef ("futex: Fix inode life-time issue") 8eb641cbc3 ("the fix patch") v5.6-rc4 8019ad13ef7f64be44d4f892af 8eb641cbc397e3bbea2a9974e0 t= estcase/testparams/testbox ---------------- -------------------------- -------------------------- -= -------------------------- %stddev change %stddev change %stddev \ | \ | \ = 1083510 -98% 23904 1078868 w= ill-it-scale/performance-process-100%-futex2-ucode=3D0x2000065/lkp-skl-fpga= 01 1083510 -98% 23904 1078868 G= EO-MEAN will-it-scale.per_process_ops Best Regards, Rong Chen --===============0629438660393517051==--