> On Mon, 29 Jun 2009, NightBird wrote: > > > > I checked the output of iostat. svc_t is between 5 > and 50, depending on when data is flushed to the disk > (CIFS write pattern). %b is between 10 and 50. > > %w is always 0. > > Example: > > device r/s w/s kr/s kw/s wait actv svc_t > %w %b > sd27 31.5 127.0 935.9 616.7 0.0 11.9 75.2 > 0 66 > d28 5.0 0.0 320.0 0.0 0.0 0.1 18.0 > 0 9 > > This tells me disks are busy but I do not know what > they are doing? > > are they spending time seeking, writting or > reading? > > It looks like your sd27 is being pounded with write > iops. It is close > to its limit. > > Can you post complete iostat output? Since you have > so many disks, > (which may not always be involved in the same stripe) > you may need to > have iostat average over a long period of time such > as 30 or 60 > seconds in order to see a less responsive disk. > Disks could be less > esponsive for many reasons, including vibrations in > their operating > environment. > > Also see Jeff Bonwick's "diskqual.sh" as described at > > http://www.mail-archive.com/zfs-disc...@opensolaris.or > g/msg15384.html > which is good at helping to find pokey disks. A > slightly modified > version is included below. > > Bob > -- > Bob Friesenhahn > bfrie...@simple.dallas.tx.us, > http://www.simplesystems.org/users/bfriesen/ > GraphicsMagick Maintainer, > http://www.GraphicsMagick.org/
I will run the script when the server is idle as recommended and report back. Here is the full iostat output (30sec). c9t40d0 seems to have a consistently higher svc_t time. r/s w/s kr/s kw/s wait actv wsvc_t asvc_t %w %b device 0.0 2.6 2.1 11.0 0.0 0.0 0.0 6.5 0 1 c8t0d0 0.1 2.6 0.4 11.0 0.0 0.0 0.0 5.1 0 0 c8t1d0 6.0 6.2 380.1 147.8 0.0 0.3 0.0 23.6 0 13 c9t8d0 6.2 6.5 390.8 147.9 0.0 0.3 0.0 21.9 0 13 c9t9d0 6.3 6.2 386.1 147.6 0.0 0.3 0.0 26.7 0 12 c9t10d0 6.7 6.2 413.5 147.8 0.0 0.3 0.0 21.9 0 14 c9t11d0 6.1 5.7 371.1 147.6 0.0 0.3 0.0 21.2 0 11 c9t12d0 6.7 5.9 407.3 147.6 0.0 0.3 0.0 21.4 0 13 c9t13d0 5.7 6.3 347.6 147.7 0.0 0.3 0.0 22.4 0 12 c9t14d0 7.0 5.9 426.5 147.5 0.0 0.3 0.0 20.6 0 13 c9t15d0 6.6 6.1 405.0 147.6 0.0 0.3 0.0 21.1 0 12 c9t16d0 6.6 6.2 405.2 147.7 0.0 0.3 0.0 21.1 0 12 c9t17d0 7.1 6.3 432.9 147.8 0.0 0.3 0.0 20.9 0 14 c9t18d0 6.7 6.5 411.6 147.9 0.0 0.3 0.0 23.6 0 13 c9t19d0 6.4 6.4 390.3 148.1 0.0 0.3 0.0 21.7 0 13 c9t20d0 6.9 6.9 424.4 147.9 0.0 0.3 0.0 19.8 0 13 c9t21d0 6.2 6.9 375.3 148.1 0.0 0.3 0.0 20.2 0 12 c9t22d0 5.7 6.8 349.5 147.9 0.0 0.3 0.0 20.9 0 12 c9t23d0 6.2 6.6 377.5 147.9 0.0 0.3 0.0 20.6 0 11 c9t24d0 5.4 6.7 328.2 147.9 0.0 0.2 0.0 20.7 0 11 c9t25d0 6.7 6.7 407.3 148.0 0.0 0.3 0.0 19.8 0 12 c9t26d0 6.5 6.9 396.7 148.1 0.0 0.3 0.0 20.4 0 13 c9t27d0 6.4 6.6 390.4 147.9 0.0 0.3 0.0 21.3 0 13 c9t28d0 6.8 6.3 416.0 147.6 0.0 0.4 0.0 26.8 0 13 c9t29d0 6.8 6.3 413.9 147.8 0.0 0.3 0.0 23.5 0 13 c9t30d0 7.5 33.5 446.9 312.0 0.0 1.8 0.0 45.0 0 18 c9t31d0 8.2 33.6 491.7 312.0 0.0 2.1 0.0 51.1 0 21 c9t32d0 7.0 34.3 414.9 312.3 0.0 1.9 0.0 47.0 0 20 c9t33d0 7.6 34.1 463.4 312.2 0.0 2.1 0.0 51.2 0 21 c9t34d0 7.9 33.5 474.4 312.0 0.0 2.2 0.0 52.9 0 21 c9t35d0 8.2 33.2 496.0 311.7 0.0 2.4 0.0 59.1 0 23 c9t36d0 8.0 33.2 481.0 311.9 0.0 2.0 0.0 48.8 0 21 c9t37d0 7.8 33.4 469.9 311.9 0.0 2.3 0.0 56.4 0 20 c9t38d0 8.5 34.1 518.7 312.4 0.0 2.3 0.0 54.3 0 22 c9t39d0 8.4 32.9 510.5 311.8 0.0 2.9 0.0 70.6 0 27 c9t40d0 8.2 34.3 501.5 312.4 0.0 2.3 0.0 55.1 0 24 c9t41d0 8.1 34.3 491.1 312.5 0.0 2.3 0.0 55.4 0 21 c9t42d0 8.5 34.3 510.9 312.7 0.0 2.3 0.0 53.3 0 23 c9t43d0 7.5 34.3 453.1 312.6 0.0 2.3 0.0 54.4 0 20 c9t44d0 7.0 33.7 420.9 312.1 0.0 2.3 0.0 55.7 0 19 c9t45d0 7.0 34.2 420.9 312.4 0.0 2.3 0.0 55.2 0 20 c9t46d0 7.9 35.1 474.6 312.5 0.0 2.1 0.0 49.1 0 22 c9t47d0 8.1 35.0 487.4 312.8 0.0 2.3 0.0 52.8 0 22 c9t48d0 8.1 34.2 491.3 312.2 0.0 2.1 0.0 50.2 0 20 c9t49d0 7.2 34.6 429.4 312.5 0.0 2.1 0.0 51.3 0 20 c9t50d0 7.6 35.2 459.3 312.6 0.0 2.3 0.0 54.1 0 21 c9t51d0 7.7 35.0 463.5 312.6 0.0 2.1 0.0 49.2 0 21 c9t52d0 7.4 35.1 442.6 312.8 0.0 2.1 0.0 48.8 0 21 c9t53d0 -- This message posted from opensolaris.org _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss