From mboxrd@z Thu Jan 1 00:00:00 1970 From: Laurent Riffard Subject: Re: 2.6.16-rc6-mm2: slow writes on reiser4. Date: Wed, 22 Mar 2006 19:51:46 +0100 Message-ID: <44219CC2.3060405@free.fr> References: <44206D3C.7050504@free.fr> <4420FFA2.1090908@namesys.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="------------060605090101080903030608" Return-path: list-help: list-unsubscribe: list-post: Errors-To: flx@namesys.com In-Reply-To: <4420FFA2.1090908@namesys.com> List-Id: To: Hans Reiser Cc: reiserfs-list@namesys.com, vs , Alexander Zarochentcev --------------060605090101080903030608 Content-Type: text/plain; charset="iso-8859-15" Content-Transfer-Encoding: quoted-printable Le 22.03.2006 08:41, Hans Reiser a =E9crit : > Laurent Riffard wrote: >=20 >=20 >>Hello, >> >>Writing big files is very slow on reiser4 now.=20 >> >>"dd if=3D/dev/zero of=3Dtoto bs=3D1k count=3D102400; sync" >> >=20 > try bs=3D4M, and tell me what happens. also try an empty fs, and an fs > that is equally full to reiserfs. Note that reiserfs in your test is > 68% full vs. 90% full for V4. It may be that we need to port some of > the block allocation optimizations from V3 to V4 (Jeff's work) to help > with 90% full filesystems. Thanks for doing this. Real users always > teach me a lot when they test things differently from how I did. >=20 > Hans Hello Hans, Yesterday, I realized that my tests were not fair. So I did some further tests trying to have the same situation for 3 different FS (reiserfs/ext2/reiser4) and I sent the result to the list, but this mail never reached the list. I have resent it. As per your request, I tried to replay my dd test on my 90% full reiser4 FS, using a 4M block size. Here are the results: --------------------- > Desktop$ cd ~/kernel >=20 > kernel$ rm toto > rm: d=E9truire fichier r=E9gulier `toto'? o >=20 > kernel$ df . > Sys. de fich. Tail. Occ. Disp. %Occ. Mont=E9 sur > /dev/hda8 925M 748M 177M 81% /home/laurent/kernel >=20 > kernel$ grep /dev/hda8 /rpoc/mounts > grep: /rpoc/mounts: Aucun fichier ou r=E9pertoire de ce type >=20 > kernel$ grep /dev/hda8 /proc/mounts > /dev/hda8 /home/laurent/kernel reiser4 rw,nosuid,nodev,atom_max_size=3D0x= 7e0c,atom_max_age=3D0x249f0,atom_min_size=3D0x100,atom_max_flushers=3D0x1,c= bk_cache_slots=3D0x10 0 0 >=20 > kernel$ sync; time dd if=3D/dev/zero of=3Dtoto bs=3D4M count=3D25; time = sync > 25+0 enregistrements lus. > 25+0 enregistrements =E9crits. > 0.00user 2.89system 0:17.18elapsed 16%CPU (0avgtext+0avgdata 0maxresident= )k > 0inputs+0outputs (0major+252minor)pagefaults 0swaps > 0.00user 0.00system 2:19.91elapsed 0%CPU (0avgtext+0avgdata 0maxresident)k > 0inputs+0outputs (0major+191minor)pagefaults 0swaps >=20 > kernel$ sync; time dd if=3D/dev/zero of=3Dtoto bs=3D4M count=3D25; time s= ync > 25+0 enregistrements lus. > 25+0 enregistrements =E9crits. > 0.00user 2.96system 1:16.42elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k > 0inputs+0outputs (0major+252minor)pagefaults 0swaps > 0.00user 0.00system 0:08.70elapsed 0%CPU (0avgtext+0avgdata 0maxresident)k > 0inputs+0outputs (0major+190minor)pagefaults 0swaps --------------------- I tried to run an "iostat 10" simultaneously with dd+sync. I attached the output. Hope this helps. ~~ laurent --------------060605090101080903030608 Content-Type: text/plain; name="typescript" Content-Transfer-Encoding: 8bit Content-Disposition: inline; filename="typescript" Le script a d���but��� sur mer 22 mar 2006 19:12:56 CET Desktop$ cd ~/kernel kernel$ kernel$ sleep 15 && echo SYNC && sync && echo DD && time dd if=/dev/zero of=toto bs=4M count=25 && echo SYNC && time sync && echo END & [1] 4657 kernel$ iostat -t 10 /dev/hda8 Linux 2.6.16-rc6-mm2 (antares.localdomain) 22.03.2006 Heure: 19:13:32 avg-cpu: %user %nice %system %iowait %idle 5,01 0,02 11,07 4,45 79,46 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 5,34 0,27 217,58 1297 1026592 Heure: 19:13:42 avg-cpu: %user %nice %system %iowait %idle 0,10 0,00 0,20 0,20 99,50 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 0,00 0,00 0,00 0 0 SYNC DD Heure: 19:13:52 avg-cpu: %user %nice %system %iowait %idle 1,50 0,00 79,32 8,29 10,89 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 20,38 3,20 1202,00 32 12032 Heure: 19:14:02 avg-cpu: %user %nice %system %iowait %idle 2,30 0,00 81,08 16,62 0,00 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 33,53 0,00 1398,20 0 13968 Heure: 19:14:12 avg-cpu: %user %nice %system %iowait %idle 1,90 0,00 88,51 9,59 0,00 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 25,27 0,00 893,51 0 8944 Heure: 19:14:22 avg-cpu: %user %nice %system %iowait %idle 3,19 0,00 85,63 11,18 0,00 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 27,35 0,00 1288,62 0 12912 Heure: 19:14:32 avg-cpu: %user %nice %system %iowait %idle 0,80 0,00 90,01 9,19 0,00 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 25,17 0,00 800,00 0 8008 Heure: 19:14:42 avg-cpu: %user %nice %system %iowait %idle 0,30 0,00 74,93 24,78 0,00 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 54,35 0,00 3138,46 0 31416 Heure: 19:14:52 avg-cpu: %user %nice %system %iowait %idle 0,20 0,00 81,62 18,18 0,00 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 50,75 0,00 1324,28 0 13256 Heure: 19:15:02 avg-cpu: %user %nice %system %iowait %idle 0,60 0,00 71,60 27,80 0,00 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 76,30 0,00 2363,20 0 23632 Heure: 19:15:12 avg-cpu: %user %nice %system %iowait %idle 1,10 0,00 29,77 68,93 0,20 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 123,78 0,00 3275,12 0 32784 25+0 enregistrements lus. 25+0 enregistrements ���crits. 0.00user 2.94system 1:29.83elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+252minor)pagefaults 0swaps SYNC Heure: 19:15:22 avg-cpu: %user %nice %system %iowait %idle 2,90 0,00 76,60 19,10 1,40 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 55,10 0,80 1435,20 8 14352 0.00user 0.00system 0:17.41elapsed 0%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+190minor)pagefaults 0swaps END Heure: 19:15:32 avg-cpu: %user %nice %system %iowait %idle 0,10 0,00 31,73 42,14 26,03 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 94,19 0,00 3402,60 0 33992 Heure: 19:15:42 avg-cpu: %user %nice %system %iowait %idle 0,10 0,00 0,00 0,10 99,80 Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn hda8 0,00 0,00 0,00 0 0 ^C [1]+ Done sleep 15 && echo SYNC && sync && echo DD && time dd if=/dev/zero of=toto bs=4M count=25 && echo SYNC && time sync && echo END kernel$ exit Script compl���t��� sur mer 22 mar 2006 19:15:46 CET --------------060605090101080903030608--