Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
Software RAID 10. Servers are HP DL380 Gen 8s, with 12x4 TB 7200 RPM drives. On 2016-06-01, 3:52 PM, "centos-boun...@centos.org on behalf of m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> wrote: >Kelly Lesperance wrote: >> I did some additional testing - I stopped Kafka on the host, and kicked >> off a disk check, and it ran at the expected speed overnight. I started >> kafka this morning, and the raid check's speed immediately dropped down to >> ~2000K/Sec. >> >> I then enabled the write-back cache on the drives (hdparm -W1 /dev/sd*). >> The raid check is now running between 10K/Sec and 20K/Sec, and has >> been for several hours (it fluctuates, but seems to stay within that >> range). Write-back cache is NOT enabled for the drives on the hosts we >> haven't upgraded yet, but the speeds are similar (I kicked off a raid >> check on one of our CentOS 6 hosts as well, the window seems to be 15 >> - 20K/Sec on that host). > >Perhaps I missed where you answered this: is this software RAID, or >hardware? And I think you said you're upgrading existing boxes? > > mark > >___ >CentOS mailing list >CentOS@centos.org >https://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
I did some additional testing - I stopped Kafka on the host, and kicked off a disk check, and it ran at the expected speed overnight. I started kafka this morning, and the raid check's speed immediately dropped down to ~2000K/Sec. I then enabled the write-back cache on the drives (hdparm -W1 /dev/sd*). The raid check is now running between 10K/Sec and 20K/Sec, and has been for several hours (it fluctuates, but seems to stay within that range). Write-back cache is NOT enabled for the drives on the hosts we haven't upgraded yet, but the speeds are similar (I kicked off a raid check on one of our CentOS 6 hosts as well, the window seems to be 15 - 20K/Sec on that host). Kelly On 2016-05-27, 9:21 AM, "Kelly Lesperance" <klespera...@blackberry.com> wrote: >All of our Kafka clusters are fairly write-heavy. The cluster in question is >our second-heaviest – we haven’t yet upgraded the heaviest, due to the issues >we’ve been experiencing in this one. > >Here is an iostat example from a host within the same cluster, but without the >RAID check running: > >[root@r2k1 ~] # iostat -xdmc 1 10 >Linux 3.10.0-327.13.1.el7.x86_64 (r2k1)05/27/16_x86_64_ >(32 CPU) > >avg-cpu: %user %nice %system %iowait %steal %idle > 8.870.021.280.210.00 89.62 > >Device: rrqm/s wrqm/s r/s w/srMB/swMB/s avgrq-sz >avgqu-sz await r_await w_await svctm %util >sdd 0.02 0.550.15 27.06 0.0311.40 859.89 >1.02 37.40 36.13 37.41 6.86 18.65 >sdf 0.02 0.480.15 26.99 0.0311.40 862.17 >0.155.56 40.945.37 7.27 19.73 >sdk 0.03 0.580.22 27.10 0.0311.40 857.01 >1.60 58.49 36.20 58.67 7.17 19.58 >sdb 0.02 0.520.15 27.43 0.0311.40 848.37 >0.020.78 42.840.55 7.07 19.50 >sdj 0.02 0.550.15 27.11 0.0311.40 858.28 >0.62 22.70 41.97 22.59 7.43 20.27 >sdg 0.03 0.680.22 27.76 0.0311.40 836.98 >0.76 27.10 34.36 27.04 7.33 20.51 >sde 0.03 0.480.22 26.99 0.0311.40 860.43 >0.33 12.07 33.16 11.90 7.34 19.98 >sda 0.03 0.520.22 27.43 0.0311.40 846.65 >0.57 20.48 36.42 20.35 7.34 20.31 >sdh 0.02 0.680.15 27.76 0.0311.40 838.63 >0.47 16.66 40.96 16.53 7.20 20.09 >sdc 0.03 0.550.22 27.06 0.0311.40 858.19 >0.74 27.30 36.96 27.22 7.55 20.58 >sdi 0.03 0.530.22 27.13 0.0311.40 856.04 >1.60 58.50 27.43 58.75 5.21 14.24 >sdl 0.02 0.560.15 27.11 0.0311.40 858.27 >1.12 41.09 27.89 41.16 5.00 13.63 >md127 0.00 0.002.53 161.84 0.3668.39 856.56 >0.000.000.000.00 0.00 0.00 > >avg-cpu: %user %nice %system %iowait %steal %idle > 13.110.001.821.070.00 84.01 > >Device: rrqm/s wrqm/s r/s w/srMB/swMB/s avgrq-sz >avgqu-sz await r_await w_await svctm %util >sdd 0.00 0.000.00 81.00 0.0038.48 972.95 >51.00 219.060.00 219.06 6.37 51.60 >sdf 0.00 1.000.00 73.00 0.0033.70 945.33 >55.02 235.860.00 235.86 7.12 52.00 >sdk 0.00 1.000.00 56.00 0.0025.70 939.73 >60.45 223.790.00 223.79 9.29 52.00 >sdb 0.00 2.000.00 70.00 0.0034.48 1008.70 >58.88 292.810.00 292.81 7.37 51.60 >sdj 0.00 3.000.00 62.00 0.0029.87 986.60 >59.32 243.480.00 243.48 8.26 51.20 >sdg 0.00 1.000.00 49.00 0.0023.43 979.45 >60.37 234.980.00 234.98 10.53 51.60 >sde 0.00 1.000.00 61.00 0.0027.95 938.38 >58.17 239.570.00 239.57 8.52 52.00 >sda 0.00 2.000.00 56.00 0.0027.48 1004.88 >56.27 202.880.00 202.88 9.27 51.90 >sdh 0.00 1.000.00 70.00 0.0033.57 982.19 >59.00 277.840.00 277.84 7.43 52.00 >sdc 0.00 0.000.00 64.00 0.0030.06 961.89 >58.20 268.300.00 268.30 8.08 51.70 >sdi 0.00 3.000.00 116.00 0.0055.62 981.94 >44.54 199.720.00 199.72 4.56 52.90 >sdl 0.00 1.000.00 128.00 0.0060
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
0.00 0.000.00 535.00 0.00 248.42 950.95 0.000.000.000.00 0.00 0.00 avg-cpu: %user %nice %system %iowait %steal %idle 11.080.001.410.000.00 87.51 Device: rrqm/s wrqm/s r/s w/srMB/swMB/s avgrq-sz avgqu-sz await r_await w_await svctm %util sdd 0.00 5.000.00 42.00 0.00 0.3818.55 2.25 53.520.00 53.52 4.93 20.70 sdf 0.00 0.000.00 35.00 0.00 0.2112.43 1.62 46.170.00 46.17 5.29 18.50 sdk 0.0023.000.00 42.00 0.00 0.4421.40 1.99 47.290.00 47.29 4.64 19.50 sdb 0.00 9.000.00 58.00 0.00 0.3412.02 2.77 47.780.00 47.78 4.12 23.90 sdj 0.00 1.000.00 39.00 0.00 0.2412.79 1.79 45.970.00 45.97 5.21 20.30 sdg 0.0011.000.00 66.00 0.00 0.4012.45 3.60 54.470.00 54.47 3.42 22.60 sde 0.00 0.000.00 35.00 0.00 0.2112.43 2.13 61.000.00 61.00 8.89 31.10 sda 0.00 9.000.00 58.00 0.00 0.3412.02 2.48 42.810.00 42.81 3.71 21.50 sdh 0.0011.000.00 66.00 0.00 0.4012.45 4.81 72.830.00 72.83 3.80 25.10 sdc 0.00 5.000.00 43.00 0.00 0.8841.93 1.99 63.810.00 63.81 5.00 21.50 sdi 0.00 1.000.00 39.00 0.00 0.2412.79 1.31 33.690.00 33.69 4.03 15.70 sdl 0.0023.000.00 42.00 0.00 0.4421.40 1.23 29.330.00 29.33 3.71 15.60 md127 0.00 0.000.00 313.00 0.00 2.0113.14 0.000.000.000.00 0.00 0.00 avg-cpu: %user %nice %system %iowait %steal %idle 16.160.031.660.000.00 82.15 Device: rrqm/s wrqm/s r/s w/srMB/swMB/s avgrq-sz avgqu-sz await r_await w_await svctm %util sdd 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdf 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdk 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdb 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdj 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdg 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sde 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sda 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdh 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdc 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdi 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 sdl 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 md127 0.00 0.000.000.00 0.00 0.00 0.00 0.000.000.000.00 0.00 0.00 On 2016-05-26, 11:50 PM, "centos-boun...@centos.org on behalf of Gordon Messmer" <centos-boun...@centos.org on behalf of gordon.mess...@gmail.com> wrote: >On 05/25/2016 09:54 AM, Kelly Lesperance wrote: >> What we're seeing is that when the weekly raid-check script executes, >> performance nose dives, and I/O wait skyrockets. The raid check starts out >> fairly fast (2K/sec - the limit that's been set), but then quickly drops >> down to about 4000K/Sec. dev.raid.speed sysctls are at the defaults: > >It looks like some pretty heavy writes are going on at the time. I'm not >sure what you mean by "nose dives", but I'd expect *some* performance >impact of running a read-intensive process like a RAID check at the same >time you're running a write-intensive process. > >Do the same write-heavy processes run on the other clusters, where you >aren't seeing performance issues? > >> avg-cpu: %user %nice %system %iowait %steal %idle >> 9.240.001.32 20.020.00 69.42 >> >> Device:tpskB_read/skB_wrtn/skB_readkB_wrtn >>
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
sdf 0.00 0.00 16.006.00 1.00 0.0295.27 0.146.594.06 13.33 6.55 14.40 sdg 0.00 0.00 16.00 29.00 1.00 0.1150.56 0.316.800.44 10.31 4.82 21.70 sdb 0.00 0.008.00 16.00 0.50 0.0648.08 0.24 10.170.62 14.94 6.75 16.20 md127 0.00 0.000.00 89.00 0.00 0.36 8.24 0.000.000.000.00 0.00 0.00 avg-cpu: %user %nice %system %iowait %steal %idle 35.500.037.430.000.00 57.04 Device: rrqm/s wrqm/s r/s w/srMB/swMB/s avgrq-sz avgqu-sz await r_await w_await svctm %util sdi 74.00 0.00 21.007.00 5.94 1.53 546.00 0.47 16.71 17.57 14.14 4.89 13.70 sdk 70.00 0.00 26.00 10.00 6.00 1.41 421.56 0.41 10.94 11.738.90 4.33 15.60 sdc 77.00 0.00 11.009.00 5.50 1.57 723.60 0.64 32.00 42.64 19.00 10.65 21.30 sdd 77.00 0.00 11.009.00 5.50 1.57 723.60 1.19 59.60 96.36 14.67 12.10 24.20 sda 71.00 1.00 24.00 11.00 5.94 1.53 437.09 0.51 14.46 14.38 14.64 5.09 17.80 sdj 74.00 0.00 21.007.00 5.94 1.53 546.00 0.58 20.79 20.57 21.43 7.04 19.70 sdl 70.00 0.00 26.00 11.00 6.00 1.91 437.84 0.39 10.54 11.049.36 4.32 16.00 sdh 77.00 0.00 11.007.00 5.50 1.52 798.67 0.43 24.17 33.829.00 6.61 11.90 sde 77.00 0.00 11.006.00 5.50 1.52 845.18 0.58 34.24 36.91 29.33 13.71 23.30 sdf 77.00 0.00 11.006.00 5.50 1.52 845.18 0.60 35.35 45.36 17.00 10.06 17.10 sdg 77.00 0.00 11.008.00 5.50 1.52 757.05 0.43 22.95 32.00 10.50 6.89 13.10 sdb 71.00 1.00 24.00 11.00 5.94 1.53 437.09 0.60 17.14 13.67 24.73 9.03 31.60 md127 0.00 0.000.00 52.00 0.00 9.57 376.96 0.000.000.000.00 0.00 0.00 avg-cpu: %user %nice %system %iowait %steal %idle 27.060.036.000.000.00 66.91 Device: rrqm/s wrqm/s r/s w/srMB/swMB/s avgrq-sz avgqu-sz await r_await w_await svctm %util sdi 14.00 0.00 10.009.00 1.50 4.06 599.58 0.136.842.60 11.56 6.63 12.60 sdk 14.00 0.00 10.00 10.00 1.50 5.00 665.60 0.137.052.50 11.60 6.35 12.70 sdc 14.00 0.00 11.00 10.00 1.56 4.01 543.24 0.157.331.00 14.30 7.24 15.20 sdd 14.00 0.00 11.00 10.00 1.56 4.01 543.24 0.157.141.00 13.90 7.05 14.80 sda 14.00 0.00 11.00 10.00 1.56 4.20 561.52 0.125.380.91 10.30 5.43 11.40 sdj 14.00 0.00 10.009.00 1.50 4.06 599.58 0.26 13.683.60 24.89 13.47 25.60 sdl 14.00 0.00 10.009.00 1.50 4.50 646.74 0.136.631.30 12.56 6.47 12.30 sdh 13.00 0.00 11.009.00 1.50 4.00 563.60 0.115.701.18 11.22 5.55 11.10 sde 14.00 0.00 10.008.00 1.50 4.00 625.78 0.094.781.109.38 4.67 8.40 sdf 14.00 0.00 10.008.00 1.50 4.00 625.78 0.148.064.00 13.12 7.17 12.90 sdg 13.00 0.00 11.009.00 1.50 4.00 563.60 0.147.001.91 13.22 6.80 13.60 sdb 14.00 0.00 11.00 10.00 1.56 4.20 561.52 0.177.671.73 14.20 7.71 16.20 md127 0.00 0.000.00 56.00 0.0025.27 924.14 0.000.000.000.00 0.00 0.00 On 2016-05-25, 5:43 PM, "centos-boun...@centos.org on behalf of cpol...@surewest.net" <centos-boun...@centos.org on behalf of cpol...@surewest.net> wrote: >On 2016-05-25 19:13, Kelly Lesperance wrote: >> Hdparm didn’t get far: >> >> [root@r1k1 ~] # hdparm -tT /dev/sda >> >> /dev/sda: >> Timing cached reads: Alarm clock >> [root@r1k1 ~] # > >Hi Kelly, > >Try running 'iostat -xdmc 1'. Look for a single drive that has >substantially greater await than ~10msec. If all the drives >except one are taking 6-8msec, but one is very much more, you've >got a drive that drags down the whole array's performance. > >Ignore the very first output from the command - it's an >average of the disk subsystem since boot. > >Pos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
I should rephrase that – some parts of HP are helping us, but the team I opened the case with isn’t being very helpful. On 2016-05-25, 4:29 PM, "Kelly Lesperance" <klespera...@blackberry.com> wrote: >Already done – they’re not being very helpful, as we don’t have a support >contract, just standard warranty. > >On 2016-05-25, 4:27 PM, "centos-boun...@centos.org on behalf of >m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> >wrote: > >>Kelly Lesperance wrote: >>> LSI/Avago’s web pages don’t have any downloads for the SAS2308, so I think >>> I’m out of luck wrt MegaRAID. >>> >>> Bounced the node, confirmed MPT Firmware 15.10.09.00-IT. >>> HP Driver is v 15.10.04.00. >>> >>> Both are the latest from HP. >>> >>> Unsure why, but the module itself reports version 20.100.00.00: >>> >>> [root@r1k1 sys] # cat module/mpt2sas/version >>> 20.100.00.00 >> >>Suggestion: if these are new, they're under warranty, and it's a hardware >>issue. Call HP tech support and open a ticket with them - they might have >>an answer. >> >> mark >> >>___ >>CentOS mailing list >>CentOS@centos.org >>https://lists.centos.org/mailman/listinfo/centos > ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
Already done – they’re not being very helpful, as we don’t have a support contract, just standard warranty. On 2016-05-25, 4:27 PM, "centos-boun...@centos.org on behalf of m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> wrote: >Kelly Lesperance wrote: >> LSI/Avago’s web pages don’t have any downloads for the SAS2308, so I think >> I’m out of luck wrt MegaRAID. >> >> Bounced the node, confirmed MPT Firmware 15.10.09.00-IT. >> HP Driver is v 15.10.04.00. >> >> Both are the latest from HP. >> >> Unsure why, but the module itself reports version 20.100.00.00: >> >> [root@r1k1 sys] # cat module/mpt2sas/version >> 20.100.00.00 > >Suggestion: if these are new, they're under warranty, and it's a hardware >issue. Call HP tech support and open a ticket with them - they might have >an answer. > > mark > >___ >CentOS mailing list >CentOS@centos.org >https://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
LSI/Avago’s web pages don’t have any downloads for the SAS2308, so I think I’m out of luck wrt MegaRAID. Bounced the node, confirmed MPT Firmware 15.10.09.00-IT. HP Driver is v 15.10.04.00. Both are the latest from HP. Unsure why, but the module itself reports version 20.100.00.00: [root@r1k1 sys] # cat module/mpt2sas/version 20.100.00.00 On 2016-05-25, 3:20 PM, "centos-boun...@centos.org on behalf of m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> wrote: >John R Pierce wrote: >> On 5/25/2016 11:44 AM, Kelly Lesperance wrote: >>> The HBA is an HP H220. >> >> OH.its a very good idea to verify the driver is at the same revision >> level as the firmware.not 100% sure how you do this under CentOS, my >> H220 system is running FreeBSD, and is at revision P20, both firmware >> and driver. HP's firmware, at least what I could find, was a fairly >> old P14 or something, so I had to re-flash mine with 'generic' LSI >> firmware, this isn't exactly a recommended thing to do, but its sure >> working fine for me. > >Not sure if dmidecode will tell you, but you might see if you can run >smartctl -i > >Also, you could either, on boot, go into the card's firmware interface, >and that'll tell you, somewhere, what the firmware version is. Not sure if >MegaRAID will work with this card - if it does, you really want it..even >though it has an actively user-hostile interface. > > mark > >___ >CentOS mailing list >CentOS@centos.org >https://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
I installed the latest firmware and driver (mpt2sas) from HP on one system. The driver is v20, it appears the firmware may be 15, though: [ 11.128979] mpt2sas version 20.100.00.00 loaded [ 11.513836] mpt2sas0: LSISAS2308: FWVersion(15.10.09.00), ChipRevision(0x05), BiosVersion(07.39.00.00) On 2016-05-25, 3:01 PM, "centos-boun...@centos.org on behalf of John R Pierce" <centos-boun...@centos.org on behalf of pie...@hogranch.com> wrote: >On 5/25/2016 11:44 AM, Kelly Lesperance wrote: >> The HBA is an HP H220. > > >OH.its a very good idea to verify the driver is at the same revision >level as the firmware.not 100% sure how you do this under CentOS, my >H220 system is running FreeBSD, and is at revision P20, both firmware >and driver. HP's firmware, at least what I could find, was a fairly >old P14 or something, so I had to re-flash mine with 'generic' LSI >firmware, this isn't exactly a recommended thing to do, but its sure >working fine for me. > > > > >-- >john r pierce, recycling bits in santa cruz > >___ >CentOS mailing list >CentOS@centos.org >https://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
Hdparm didn’t get far: [root@r1k1 ~] # hdparm -tT /dev/sda /dev/sda: Timing cached reads: Alarm clock [root@r1k1 ~] # On 2016-05-25, 2:44 PM, "Kelly Lesperance" <klespera...@blackberry.com> wrote: >The HBA is an HP H220. > >We haven’t really benchmarked individual drives – all 12 drives are utilized >in one RAID-10 array, I’m unsure how we would test individual drives without >breaking the array. > >Trying ‘hdparm -tT /dev/sda’ now – it’s been running for 25 minutes so far… > >Kelly > >On 2016-05-25, 2:12 PM, "centos-boun...@centos.org on behalf of Dennis >Jacobfeuerborn" <centos-boun...@centos.org on behalf of denni...@conversis.de> >wrote: > >>What is the HBA the drives are attached to? >>Have you done a quick benchmark on a single disk to check if this is a >>raid problem or further down the stack? >> >>Regards, >> Dennis >> >>On 25.05.2016 19:26, Kelly Lesperance wrote: >>> [merging] >>> >>> The HBA the drives are attached to has no configuration that I’m aware of. >>> We would have had to accidentally change 23 of them ☺ >>> >>> Thanks, >>> >>> Kelly >>> >>> On 2016-05-25, 1:25 PM, "Kelly Lesperance" <klespera...@blackberry.com> >>> wrote: >>> >>>> They are: >>>> >>>> [root@r1k1 ~] # hdparm -I /dev/sda >>>> >>>> /dev/sda: >>>> >>>> ATA device, with non-removable media >>>>Model Number: MB4000GCWDC >>>>Serial Number: S1Z06RW9 >>>>Firmware Revision: HPGD >>>>Transport: Serial, SATA Rev 3.0 >>>> >>>> Thanks, >>>> >>>> Kelly >>> >>> >>> On 2016-05-25, 1:23 PM, "centos-boun...@centos.org on behalf of >>> m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> >>> wrote: >>> >>>> Kelly Lesperance wrote: >>>>> I’ve posted this on the forums at >>>>> https://www.centos.org/forums/viewtopic.php?f=47=57926=244614#p244614 >>>>> - posting to the list in the hopes of getting more eyeballs on it. >>>>> >>>>> We have a cluster of 23 HP DL380p Gen8 hosts running Kafka. Basic specs: >>>>> >>>>> 2x E5-2650 >>>>> 128 GB RAM >>>>> 12 x 4 TB 7200 RPM SATA drives connected to an HP H220 HBA >>>>> Dual port 10 GB NIC >>>>> >>>>> The drives are configured as one large RAID-10 volume with mdadm, >>>>> filesystem is XFS. The OS is not installed on the drive - we PXE boot a >>>>> CentOS image we've built with minimal packages installed, and do the OS >>>>> configuration via puppet. Originally, the hosts were running CentOS 6.5, >>>>> with Kafka 0.8.1, without issue. We recently upgraded to CentOS 7.2 and >>>>> Kafka 0.9, and that's when the trouble started. >>>> >>>> One more stupid question: could the configuration of the card for how the >>>> drives are accessed been accidentally changed? >>>> >>>> mark >>>> >>>> ___ >>>> CentOS mailing list >>>> CentOS@centos.org >>>> https://lists.centos.org/mailman/listinfo/centos >>> >>> ___ >>> CentOS mailing list >>> CentOS@centos.org >>> https://lists.centos.org/mailman/listinfo/centos >>> >> >>___ >>CentOS mailing list >>CentOS@centos.org >>https://lists.centos.org/mailman/listinfo/centos > ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
The HBA is an HP H220. We haven’t really benchmarked individual drives – all 12 drives are utilized in one RAID-10 array, I’m unsure how we would test individual drives without breaking the array. Trying ‘hdparm -tT /dev/sda’ now – it’s been running for 25 minutes so far… Kelly On 2016-05-25, 2:12 PM, "centos-boun...@centos.org on behalf of Dennis Jacobfeuerborn" <centos-boun...@centos.org on behalf of denni...@conversis.de> wrote: >What is the HBA the drives are attached to? >Have you done a quick benchmark on a single disk to check if this is a >raid problem or further down the stack? > >Regards, > Dennis > >On 25.05.2016 19:26, Kelly Lesperance wrote: >> [merging] >> >> The HBA the drives are attached to has no configuration that I’m aware of. >> We would have had to accidentally change 23 of them ☺ >> >> Thanks, >> >> Kelly >> >> On 2016-05-25, 1:25 PM, "Kelly Lesperance" <klespera...@blackberry.com> >> wrote: >> >>> They are: >>> >>> [root@r1k1 ~] # hdparm -I /dev/sda >>> >>> /dev/sda: >>> >>> ATA device, with non-removable media >>> Model Number: MB4000GCWDC >>> Serial Number: S1Z06RW9 >>> Firmware Revision: HPGD >>> Transport: Serial, SATA Rev 3.0 >>> >>> Thanks, >>> >>> Kelly >> >> >> On 2016-05-25, 1:23 PM, "centos-boun...@centos.org on behalf of >> m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> >> wrote: >> >>> Kelly Lesperance wrote: >>>> I’ve posted this on the forums at >>>> https://www.centos.org/forums/viewtopic.php?f=47=57926=244614#p244614 >>>> - posting to the list in the hopes of getting more eyeballs on it. >>>> >>>> We have a cluster of 23 HP DL380p Gen8 hosts running Kafka. Basic specs: >>>> >>>> 2x E5-2650 >>>> 128 GB RAM >>>> 12 x 4 TB 7200 RPM SATA drives connected to an HP H220 HBA >>>> Dual port 10 GB NIC >>>> >>>> The drives are configured as one large RAID-10 volume with mdadm, >>>> filesystem is XFS. The OS is not installed on the drive - we PXE boot a >>>> CentOS image we've built with minimal packages installed, and do the OS >>>> configuration via puppet. Originally, the hosts were running CentOS 6.5, >>>> with Kafka 0.8.1, without issue. We recently upgraded to CentOS 7.2 and >>>> Kafka 0.9, and that's when the trouble started. >>> >>> One more stupid question: could the configuration of the card for how the >>> drives are accessed been accidentally changed? >>> >>> mark >>> >>> ___ >>> CentOS mailing list >>> CentOS@centos.org >>> https://lists.centos.org/mailman/listinfo/centos >> >> ___ >> CentOS mailing list >> CentOS@centos.org >> https://lists.centos.org/mailman/listinfo/centos >> > >___ >CentOS mailing list >CentOS@centos.org >https://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
[merging] The HBA the drives are attached to has no configuration that I’m aware of. We would have had to accidentally change 23 of them ☺ Thanks, Kelly On 2016-05-25, 1:25 PM, "Kelly Lesperance" <klespera...@blackberry.com> wrote: >They are: > >[root@r1k1 ~] # hdparm -I /dev/sda > >/dev/sda: > >ATA device, with non-removable media > Model Number: MB4000GCWDC > Serial Number: S1Z06RW9 > Firmware Revision: HPGD > Transport: Serial, SATA Rev 3.0 > >Thanks, > >Kelly On 2016-05-25, 1:23 PM, "centos-boun...@centos.org on behalf of m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> wrote: >Kelly Lesperance wrote: >> I’ve posted this on the forums at >> https://www.centos.org/forums/viewtopic.php?f=47=57926=244614#p244614 >> - posting to the list in the hopes of getting more eyeballs on it. >> >> We have a cluster of 23 HP DL380p Gen8 hosts running Kafka. Basic specs: >> >> 2x E5-2650 >> 128 GB RAM >> 12 x 4 TB 7200 RPM SATA drives connected to an HP H220 HBA >> Dual port 10 GB NIC >> >> The drives are configured as one large RAID-10 volume with mdadm, >> filesystem is XFS. The OS is not installed on the drive - we PXE boot a >> CentOS image we've built with minimal packages installed, and do the OS >> configuration via puppet. Originally, the hosts were running CentOS 6.5, >> with Kafka 0.8.1, without issue. We recently upgraded to CentOS 7.2 and >> Kafka 0.9, and that's when the trouble started. > >One more stupid question: could the configuration of the card for how the >drives are accessed been accidentally changed? > > mark > >___ >CentOS mailing list >CentOS@centos.org >https://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
Re: [CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
They are: [root@r1k1 ~] # hdparm -I /dev/sda /dev/sda: ATA device, with non-removable media Model Number: MB4000GCWDC Serial Number: S1Z06RW9 Firmware Revision: HPGD Transport: Serial, SATA Rev 3.0 Thanks, Kelly On 2016-05-25, 1:21 PM, "centos-boun...@centos.org on behalf of m.r...@5-cent.us" <centos-boun...@centos.org on behalf of m.r...@5-cent.us> wrote: >Kelly Lesperance wrote: >> I’ve posted this on the forums at >> https://www.centos.org/forums/viewtopic.php?f=47=57926=244614#p244614 >> - posting to the list in the hopes of getting more eyeballs on it. >> >> We have a cluster of 23 HP DL380p Gen8 hosts running Kafka. Basic specs: >> >> 2x E5-2650 >> 128 GB RAM >> 12 x 4 TB 7200 RPM SATA drives connected to an HP H220 HBA >> Dual port 10 GB NIC >> >> The drives are configured as one large RAID-10 volume with mdadm, >> filesystem is XFS. The OS is not installed on the drive - we PXE boot a >> CentOS image we've built with minimal packages installed, and do the OS >> configuration via puppet. Originally, the hosts were running CentOS 6.5, >> with Kafka 0.8.1, without issue. We recently upgraded to CentOS 7.2 and >> Kafka 0.9, and that's when the trouble started. > >Really stupid question: are the drives in that the ones that came with the >unit? > > mark, who, a few years ago, found serious issues with green drives in a > server > >___ >CentOS mailing list >CentOS@centos.org >https://lists.centos.org/mailman/listinfo/centos ___ CentOS mailing list CentOS@centos.org https://lists.centos.org/mailman/listinfo/centos
[CentOS] Slow RAID Check/high %iowait during check after updgrade from CentOS 6.5 -> CentOS 7.2
704 7680 sdl 26.00 704.00 7680.00 704 7680 md127 92.00 0.00 46596.00 0 46596 avg-cpu: %user %nice %system %iowait %steal %idle 14.24 0.00 2.22 19.89 0.00 63.65 Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn sda 33.00 1024.00 7244.00 1024 7244 sdb 33.00 1024.00 7244.00 1024 7244 sdc 31.00 1024.00 7668.00 1024 7668 sdd 31.00 1024.00 7668.00 1024 7668 sdf 31.00 1024.00 7680.00 1024 7680 sdg 26.00 768.00 6672.00 768 6672 sdh 26.00 768.00 6672.00 768 6672 sde 31.00 1024.00 7680.00 1024 7680 sdj 21.00 512.00 6656.00 512 6656 sdi 21.00 512.00 6656.00 512 6656 sdk 27.00 832.00 7168.00 832 7168 sdl 27.00 832.00 7168.00 832 7168 md127 88.00 0.00 43088.00 0 43088 avg-cpu: %user %nice %system %iowait %steal %idle 8.02 0.13 1.42 23.90 0.00 66.53 Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn sda 30.00 1024.00 7168.00 1024 7168 sdb 30.00 1024.00 7168.00 1024 7168 sdc 29.00 960.00 7168.00 960 7168 sdd 29.00 960.00 7168.00 960 7168 sdf 23.00 512.00 7668.00 512 7668 sdg 28.00 768.00 7680.00 768 7680 sdh 28.00 768.00 7680.00 768 7680 sde 23.00 512.00 7668.00 512 7668 sdj 30.00 1024.00 6672.00 1024 6672 sdi 30.00 1024.00 6672.00 1024 6672 sdk 30.00 1024.00 7168.00 1024 7168 sdl 30.00 1024.00 7168.00 1024 7168 md127 87.00 0.00 43524.00 0 43524 Details of the array: [root@r1k1] # cat /proc/mdstat Personalities : [raid10] md127 : active raid10 sdf[5] sdi[8] sdh[7] sdk[10] sdb[1] sdj[9] sdc[2] sdd[3] sdl[11] sde[13] sdg[12] sda[0] 23441323008 blocks super 1.2 512K chunks 2 near-copies [12/12] [] [==>..] check = 30.8% (7237496960/23441323008) finish=62944.5min speed=4290K/sec unused devices: [root@r1k1] # mdadm --detail /dev/md127 /dev/md127: Version : 1.2 Creation Time : Thu Sep 18 09:57:57 2014 Raid Level : raid10 Array Size : 23441323008 (22355.39 GiB 24003.91 GB) Used Dev Size : 3906887168 (3725.90 GiB 4000.65 GB) Raid Devices : 12 Total Devices : 12 Persistence : Superblock is persistent Update Time : Tue May 24 15:32:56 2016 State : active, checking Active Devices : 12 Working Devices : 12 Failed Devices : 0 Spare Devices : 0 Layout : near=2 Chunk Size : 512K Check Status : 30% complete Name : localhost:kafka UUID : b6b98e3e:65ee06c3:3599d781:98908041 Events : 2459193 Number Major Minor RaidDevice State 0 8 0 0 active sync set-A /dev/sda 1 8 16 1 active sync set-B /dev/sdb 2 8 32 2 active sync set-A /dev/sdc 3 8 48 3 active sync set-B /dev/sdd 13 8 64 4 active sync set-A /dev/sde 5 8 80 5 active sync set-B /dev/sdf 12 8 96 6 active sync set-A /dev/sdg 7 8 112 7 active sync set-B /dev/sdh 8 8 128 8 active sync set-A /dev/sdi 9 8 144 9 active sync set-B /dev/sdj 10 8 160 10 active sync set-A /dev/sdk 11 8 176 11 active sync set-B /dev/sdl We've tried changing the I/O scheduler, queue_depth, queue_type, read-ahead, etc, but nothing has helped. We've also upgraded all of the firmware, and installed HP's mpt2sas driver. We have 4 other Kafka clusters, however they're HP DL180 G6 servers. We completed the same CentOS 6.5 -> 7.2/Kafka 0.8 -> 0.9 upgrade on those clusters, and there has been no impact to their performance. We've been banging our heads against the wall for a few weeks now, really hoping someone from the community can point us in the right direction. Thanks, Kelly Lesperance ___ CentOS mailing li