Re: Dell Perc 5/i Performance issues
On Jun 19, 2010, at 10:31 PM, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 7:56 PM, Scott Long sco...@samsco.org wrote: On Jun 19, 2010, at 5:32 AM, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 4:24 AM, Garrett Cooper yanef...@gmail.com wrote: On Sat, Jun 19, 2010 at 4:21 AM, oizs o...@freemail.hu wrote: Since I tested it on different kind of os's, and with at least 5 testing applications, I don't think that would be the case. On 2010.06.19. 13:17, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 2:58 AM, oizso...@freemail.hu wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) Dumb question: are you sure that the problem that you're seeing isn't in fact inhibited by the application that you're getting `performance' results with? If your applications aren't well suited for your hardware's capabilities, then of course performance will be bad. Furthermore, if the performance applications and your use scenarios are centered around reading, as opposed to writing, there is an option within mficontrol and the mfi(4) interface where you can actually enable read-ahead, instead of writeback (you unfortunately can't enable both scenarios). I realize that this is an artificial improvement in a way, but you should judge whether or not your application will be doing more reading than writing in whatever capacity it's doing... HTH, No, that doesn't help. I wrote the driver, and I have no flipping clue what you're talking about. Nevermind. It was a misunderstanding of what the subcommands... - mfiutil cache .. enable - mfiutil cache .. reads enable - mfiutil cache .. writes enable ... do. -Garrett I'm very late in doing this, but I wanted to publicly apologize to Garrett both for being rude and flippant to him, and for doing so in public. Scott ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
Could you tell me exactly how did you configure your raid? I mean wb/read-ahead/blocksize/stripe etc. Much appreciated. -zsozso On 2010.06.19. 14:26, Svein Skogen (Listmail Account) wrote: On 19.06.2010 11:58, oizs wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. This is from a similar controller running that 8-disk raid5+0 setup: -- CrystalDiskMark 2.2 (C) 2007-2008 hiyohiyo Crystal Dew World : http://crystalmark.info/ -- Sequential Read : 665.383 MB/s Sequential Write : 300.452 MB/s Random Read 512KB : 616.604 MB/s Random Write 512KB : 306.306 MB/s Random Read 4KB : 64.465 MB/s Random Write 4KB :7.646 MB/s Test Size : 100 MB Date : 2010/06/19 14:24:12 You should be looking at number about half of these. I ran the test with adaptive readahead enabled, and write-through for cache (since I run with BBU, I normally use write-back) //Svein ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
I've tried almost everything now. The battery is probably fine: mfiutil show battery mfi0: Battery State: Manufacture Date: 7/25/2009 Serial Number: 3716 Manufacturer: SMP-PA1.9 Model: DLFR463 Chemistry: LION Design Capacity: 1800 mAh Design Voltage: 3700 mV Current Charge: 99% My results: Settings: Raid5: Stripe: 64k mfiutil cache 0 mfi0 volume mfid0 cache settings: I/O caching: writes write caching: write-back read ahead: none drive write cache: default Raid0: Stripe: 64k mfiutil cache 0 mfi0 volume mfid0 cache settings: I/O caching: writes write caching: write-back read ahead: none drive write cache: default Tried to play around with this as well, with almost no difference. Raid5 read: dd if=/dev/mfid0 of=/dev/null bs=10M 1143+0 records in 1143+0 records out 11985223680 bytes transferred in 139.104134 secs (86160083 bytes/sec) write: dd if=/dev/random of=/dev/mfid0 bs=64K 22747+0 records in 22747+0 records out 1490747392 bytes transferred in 23.921103 secs (62319342 bytes/sec) Raid0 read: dd if=/dev/mfid0 of=/dev/null bs=64K 92470+0 records in 92470+0 records out 6060113920 bytes transferred in 47.926007 secs (126447294 bytes/sec) write: dd if=/dev/random of=/dev/mfid0 bs=64K 16441+0 records in 16441+0 records out 1077477376 bytes transferred in 17.232486 secs (62525939 bytes/sec) I'm writing directly to the device so im not sure any slice issues could cause the problems. -zsozso On 2010.06.20. 4:53, Scott Long wrote: Two big things can affect RAID-5 performance: 1. Battery backup. If you don't have a working battery attached to the card, it will turn off the write-back cache, no matter what you do. Check this. If you're unsure, use the mfiutil tool that I added to FreeBSD a few months ago and send me the output. 2. Partition alignment. If you're using classic MBR slices, everything gets misaligned by 63 sectors, making it impossible for the controller to optimize both reads and writes. If the array is used for secondary storage, simply don't use an MBR scheme. If it's used for primary storage, try using GPT instead and setting up your partitions so that they are aligned to large power-of-2 boundaries. Scott On Jun 18, 2010, at 6:27 PM, oizs wrote ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
Does anyone know of a nice how to guide for achieving this? - Original Message - From: Scott Long sco...@samsco.org 2. Partition alignment. If you're using classic MBR slices, everything gets misaligned by 63 sectors, making it impossible for the controller to optimize both reads and writes. If the array is used for secondary storage, simply don't use an MBR scheme. If it's used for primary storage, try using GPT instead and setting up your partitions so that they are aligned to large power-of-2 boundaries. This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmas...@multiplay.co.uk. ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
I just set up a machine with the following GPT scheme: =34 5853511613 mfid0 GPT (2.7T) 34 128 1 freebsd-boot (64K) 162 862 - free - (431K) 1024 2097152 2 freebsd-ufs (1.0G) 2098176 4194304 3 freebsd-swap (2.0G) 6292480 2097152 4 freebsd-ufs (1.0G) 8389632 104857600 5 freebsd-ufs (50G) 113247232 5740264414 6 freebsd-ufs (2.7T) 5853511646 1 - free - (512B) After the first partition, I created a deliberate gap for alignment, reflected in the second line. The third line shows a starting offset of sector 1024, which is 512KB. This should be a good generic start point for most RAID geometries with a stripe size = 512KB. The rest are normal /, swap, /var, /usr and /opt partitions. The single free sector on the final line is probably a calculation error on my part, there's no particular reason for it. The gpart man page has good descriptions on how to create partitions and make the GPT scheme bootable. It's not very automated, you'll need to have a calculator handy, but it works. Scott On Jun 20, 2010, at 12:20 PM, Steven Hartland wrote: Does anyone know of a nice how to guide for achieving this? - Original Message - From: Scott Long sco...@samsco.org 2. Partition alignment. If you're using classic MBR slices, everything gets misaligned by 63 sectors, making it impossible for the controller to optimize both reads and writes. If the array is used for secondary storage, simply don't use an MBR scheme. If it's used for primary storage, try using GPT instead and setting up your partitions so that they are aligned to large power-of-2 boundaries. This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmas...@multiplay.co.uk. ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
/dev/random and /dev/urandom are relatively slow and are not suitable as the source of data for testing modern hard drives' sequential throughput. On my 3GHz dual-core amd63 box both /dev/random and /dev/urandom max out at ~80MB/s while consuming 100% CPU time on one of the processor cores. That would not be enough to saturate single disk with sequential writes. --Artem On Sun, Jun 20, 2010 at 9:51 AM, oizs o...@freemail.hu wrote: I've tried almost everything now. The battery is probably fine: mfiutil show battery mfi0: Battery State: Manufacture Date: 7/25/2009 Serial Number: 3716 Manufacturer: SMP-PA1.9 Model: DLFR463 Chemistry: LION Design Capacity: 1800 mAh Design Voltage: 3700 mV Current Charge: 99% My results: Settings: Raid5: Stripe: 64k mfiutil cache 0 mfi0 volume mfid0 cache settings: I/O caching: writes write caching: write-back read ahead: none drive write cache: default Raid0: Stripe: 64k mfiutil cache 0 mfi0 volume mfid0 cache settings: I/O caching: writes write caching: write-back read ahead: none drive write cache: default Tried to play around with this as well, with almost no difference. Raid5 read: dd if=/dev/mfid0 of=/dev/null bs=10M 1143+0 records in 1143+0 records out 11985223680 bytes transferred in 139.104134 secs (86160083 bytes/sec) write: dd if=/dev/random of=/dev/mfid0 bs=64K 22747+0 records in 22747+0 records out 1490747392 bytes transferred in 23.921103 secs (62319342 bytes/sec) Raid0 read: dd if=/dev/mfid0 of=/dev/null bs=64K 92470+0 records in 92470+0 records out 6060113920 bytes transferred in 47.926007 secs (126447294 bytes/sec) write: dd if=/dev/random of=/dev/mfid0 bs=64K 16441+0 records in 16441+0 records out 1077477376 bytes transferred in 17.232486 secs (62525939 bytes/sec) I'm writing directly to the device so im not sure any slice issues could cause the problems. -zsozso On 2010.06.20. 4:53, Scott Long wrote: Two big things can affect RAID-5 performance: 1. Battery backup. If you don't have a working battery attached to the card, it will turn off the write-back cache, no matter what you do. Check this. If you're unsure, use the mfiutil tool that I added to FreeBSD a few months ago and send me the output. 2. Partition alignment. If you're using classic MBR slices, everything gets misaligned by 63 sectors, making it impossible for the controller to optimize both reads and writes. If the array is used for secondary storage, simply don't use an MBR scheme. If it's used for primary storage, try using GPT instead and setting up your partitions so that they are aligned to large power-of-2 boundaries. Scott On Jun 18, 2010, at 6:27 PM, oizs wrote ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
Yeah, there's no value in using the /dev/random devices for testing disk i/o. Use /dev/zero instead. I've known of hardware RAID engines in the past that can recognize certain repeating i/o benchmark patterns and optimize for them, but I have no idea if LSI controllers do this, tho based on your results it's probably safe to say that they don't. Scott On Jun 20, 2010, at 1:09 PM, Artem Belevich wrote: /dev/random and /dev/urandom are relatively slow and are not suitable as the source of data for testing modern hard drives' sequential throughput. On my 3GHz dual-core amd63 box both /dev/random and /dev/urandom max out at ~80MB/s while consuming 100% CPU time on one of the processor cores. That would not be enough to saturate single disk with sequential writes. --Artem On Sun, Jun 20, 2010 at 9:51 AM, oizs o...@freemail.hu wrote: I've tried almost everything now. The battery is probably fine: mfiutil show battery mfi0: Battery State: Manufacture Date: 7/25/2009 Serial Number: 3716 Manufacturer: SMP-PA1.9 Model: DLFR463 Chemistry: LION Design Capacity: 1800 mAh Design Voltage: 3700 mV Current Charge: 99% My results: Settings: Raid5: Stripe: 64k mfiutil cache 0 mfi0 volume mfid0 cache settings: I/O caching: writes write caching: write-back read ahead: none drive write cache: default Raid0: Stripe: 64k mfiutil cache 0 mfi0 volume mfid0 cache settings: I/O caching: writes write caching: write-back read ahead: none drive write cache: default Tried to play around with this as well, with almost no difference. Raid5 read: dd if=/dev/mfid0 of=/dev/null bs=10M 1143+0 records in 1143+0 records out 11985223680 bytes transferred in 139.104134 secs (86160083 bytes/sec) write: dd if=/dev/random of=/dev/mfid0 bs=64K 22747+0 records in 22747+0 records out 1490747392 bytes transferred in 23.921103 secs (62319342 bytes/sec) Raid0 read: dd if=/dev/mfid0 of=/dev/null bs=64K 92470+0 records in 92470+0 records out 6060113920 bytes transferred in 47.926007 secs (126447294 bytes/sec) write: dd if=/dev/random of=/dev/mfid0 bs=64K 16441+0 records in 16441+0 records out 1077477376 bytes transferred in 17.232486 secs (62525939 bytes/sec) I'm writing directly to the device so im not sure any slice issues could cause the problems. -zsozso On 2010.06.20. 4:53, Scott Long wrote: Two big things can affect RAID-5 performance: 1. Battery backup. If you don't have a working battery attached to the card, it will turn off the write-back cache, no matter what you do. Check this. If you're unsure, use the mfiutil tool that I added to FreeBSD a few months ago and send me the output. 2. Partition alignment. If you're using classic MBR slices, everything gets misaligned by 63 sectors, making it impossible for the controller to optimize both reads and writes. If the array is used for secondary storage, simply don't use an MBR scheme. If it's used for primary storage, try using GPT instead and setting up your partitions so that they are aligned to large power-of-2 boundaries. Scott On Jun 18, 2010, at 6:27 PM, oizs wrote ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Mon, Jun 21, 2010 at 4:50 AM, Scott Long sco...@samsco.org wrote: I just set up a machine with the following GPT scheme: = 34 5853511613 mfid0 GPT (2.7T) 34 128 1 freebsd-boot (64K) 162 862 - free - (431K) 1024 2097152 2 freebsd-ufs (1.0G) 2098176 4194304 3 freebsd-swap (2.0G) 6292480 2097152 4 freebsd-ufs (1.0G) 8389632 104857600 5 freebsd-ufs (50G) 113247232 5740264414 6 freebsd-ufs (2.7T) 5853511646 1 - free - (512B) After the first partition, I created a deliberate gap for alignment, reflected in the second line. The third line shows a starting offset of sector 1024, which is 512KB. This should be a good generic start point for most RAID geometries with a stripe size = 512KB. The rest are normal /, swap, /var, /usr and /opt partitions. The single free sector on the final line is probably a calculation error on my part, there's no particular reason for it. The gpart man page has good descriptions on how to create partitions and make the GPT scheme bootable. It's not very automated, you'll need to have a calculator handy, but it works. I scripted this as part of our custom installer - it uses the same 1MB offset that Vista/Win7 do which should align for anything with a = 1MB stripe size: # Device to partition diskdev=/dev/da0 # First partition offset in 512-byte sectors. This should be aligned with # any RAID stripe size for maximum performance. 2048 aligns the partition # start boundary at the 1MiB, consistent with Vista/Windows 7. This should # match all common stripe sizes such as 64kb, 128kb and 256kb. root_offset=2048 # Boot partition offset. This sits just before our first root partition and # stores the boot loader which is used to load the OS. boot_offset=2032 # Initialise the disk with a GPT partition table gpart create -s gpt $diskdev # # System disk partitioning layout # gpart add -l boot -t freebsd-boot -s 16 -b $boot_offset $diskdev # boot p1 gpart add -l root -t freebsd-ufs -s 2G -b $root_offset $diskdev # /p2 gpart add -l swap -t freebsd-swap -s 4G $diskdev # swap p3 gpart add -l var -t freebsd-ufs -s 4G $diskdev # /var p4 gpart add -l usr -t freebsd-ufs$diskdev # /usr p5 # Install the gpt boot code (pmbr into the PMBR, gptboot into our boot partition p1) gpart bootcode -b /boot/pmbr -p /boot/gptboot -i 1 $diskdev # Make the first partition active # (required for older BIOSes to boot from the GPT PMBR) echo 'a 1' | fdisk -f - $diskdev gpart is smart enough to figure out most of the math for you these days... -- Antony ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Sat, 19 Jun 2010, oizs wrote: Date: Sat, 19 Jun 2010 02:27:05 +0200 From: oizs o...@freemail.hu To: freebsd-current@freebsd.org Subject: Re: Dell Perc 5/i Performance issues Im using the Samsung F3 disks, which can do 140MB/s sequentially. I have tried different raids raid0 will do just as bad as raid5. I even tried one disk which performed as expected 100MB/s+ reads and writes so I'm not sure anymore what could be the problem. Maybe the controller hates samsung disks? I have a 8-disk Samsung F1/F3 mixed setup under FreeBSD-current: (fs)(root) mfiutil show drives mfi0 Physical Drives: ( 932G) ONLINE SAMSUNG HD103UJ 1118 serial=S13PJDWS500394 SATA slot 0 ( 932G) ONLINE SAMSUNG HD103UJ 1118 serial=S13PJDWS500033 SATA slot 1 ( 932G) ONLINE SAMSUNG HD103UJ 1113 serial=S13PJDWQC28106 SATA slot 2 ( 932G) ONLINE SAMSUNG HD103UJ 1113 serial=S13PJDWQC28108 SATA slot 3 ( 932G) ONLINE SAMSUNG HD103UJ 1104 serial=S13PJ1EPB00232 SATA slot 4 ( 932G) ONLINE ST31000340AS SD1A serial=9QJ18R8B SATA slot 5 ( 932G) ONLINE SAMSUNG HD103UJ 1104 serial=S13PJ1EPB00066 SATA slot 6 ( 932G) ONLINE SAMSUNG HD103UJ 1104 serial=S13PJ1EPB00602 SATA slot 7 The disks are organized as JBOD disks. Later on they form one ZFS pool: config: NAME STATE READ WRITE CKSUM xONLINE 0 0 0 mirror ONLINE 0 0 0 mfid0p4 ONLINE 0 0 0 mfid1p4 ONLINE 0 0 0 mirror ONLINE 0 0 0 mfid2p4 ONLINE 0 0 0 mfid3p4 ONLINE 0 0 0 mirror ONLINE 0 0 0 mfid4p4 ONLINE 0 0 0 mfid5p4 ONLINE 0 0 0 mirror ONLINE 0 0 0 mfid6p4 ONLINE 0 0 0 mfid7p4 ONLINE 0 0 0 ada0p3 ONLINE 0 0 0 (ada0 is there because mfid6 had some unreadable blocks lately) I get ~370MiB/s writing performance using `iozone -s10g -r1m`. While my samsung disks are problematic in the area of reliability (I get occasional parity mismatches or read errors), performance is good. Have you enabled the disk caches as well? Something like: MegaCli -LdSetProp Cached -LALL -a0 MegaCli -LdSetProp NORA -LALL -a0 MegaCli -LdSetProp WB -LALL -a0 MegaCli -LdSetProp -EnDskCache -LALL -a0 (Only if having a USV of course) Dunno if there is a mfiutil equivalent though. Bye/2 --- Michael Reifenberger mich...@reifenberger.com http://www.Reifenberger.com ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On 19 June 2010 11:17, Michael Reifenberger m...@reifenberger.com wrote: Have you enabled the disk caches as well? Something like: MegaCli -LdSetProp Cached -LALL -a0 MegaCli -LdSetProp NORA -LALL -a0 MegaCli -LdSetProp WB -LALL -a0 MegaCli -LdSetProp -EnDskCache -LALL -a0 (Only if having a USV of course) Dunno if there is a mfiutil equivalent though. Hi. That would be: mfiutil cache mfid0 enable mfiutil cache mfid0 read-ahead none mfiutil cache mfid0 write-back mfiutil cache mfid0 write-cache enable -- wbr, pluknet ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) //Svein -- +---+--- /\ |Svein Skogen | sv...@d80.iso100.no \ / |Solberg Østli 9| PGP Key: 0xE5E76831 X|2020 Skedsmokorset | sv...@jernhuset.no / \ |Norway | PGP Key: 0xCE96CE13 | | sv...@stillbilde.net ascii | | PGP Key: 0x58CD33B6 ribbon |System Admin | svein-listm...@stillbilde.net Campaign|stillbilde.net | PGP Key: 0x22D494A4 +---+--- |msn messenger: | Mobile Phone: +47 907 03 575 |sv...@jernhuset.no | RIPE handle:SS16503-RIPE +---+--- If you really are in a hurry, mail me at svein-mob...@stillbilde.net This mailbox goes directly to my cellphone and is checked even when I'm not in front of my computer. Picture Gallery: https://gallery.stillbilde.net/v/svein/ signature.asc Description: OpenPGP digital signature
Re: Dell Perc 5/i Performance issues
I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. -zsozso On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) //Svein ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Sat, Jun 19, 2010 at 2:58 AM, oizs o...@freemail.hu wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) Dumb question: are you sure that the problem that you're seeing isn't in fact inhibited by the application that you're getting `performance' results with? HTH, -Garrett ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
Since I tested it on different kind of os's, and with at least 5 testing applications, I don't think that would be the case. -zsozso On 2010.06.19. 13:17, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 2:58 AM, oizso...@freemail.hu wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) Dumb question: are you sure that the problem that you're seeing isn't in fact inhibited by the application that you're getting `performance' results with? HTH, -Garrett ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Sat, Jun 19, 2010 at 4:21 AM, oizs o...@freemail.hu wrote: Since I tested it on different kind of os's, and with at least 5 testing applications, I don't think that would be the case. On 2010.06.19. 13:17, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 2:58 AM, oizso...@freemail.hu wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) Dumb question: are you sure that the problem that you're seeing isn't in fact inhibited by the application that you're getting `performance' results with? If your applications aren't well suited for your hardware's capabilities, then of course performance will be bad. -Garrett ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Sat, Jun 19, 2010 at 4:24 AM, Garrett Cooper yanef...@gmail.com wrote: On Sat, Jun 19, 2010 at 4:21 AM, oizs o...@freemail.hu wrote: Since I tested it on different kind of os's, and with at least 5 testing applications, I don't think that would be the case. On 2010.06.19. 13:17, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 2:58 AM, oizso...@freemail.hu wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) Dumb question: are you sure that the problem that you're seeing isn't in fact inhibited by the application that you're getting `performance' results with? If your applications aren't well suited for your hardware's capabilities, then of course performance will be bad. Furthermore, if the performance applications and your use scenarios are centered around reading, as opposed to writing, there is an option within mficontrol and the mfi(4) interface where you can actually enable read-ahead, instead of writeback (you unfortunately can't enable both scenarios). I realize that this is an artificial improvement in a way, but you should judge whether or not your application will be doing more reading than writing in whatever capacity it's doing... HTH, -Garrett ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Sat, 19 Jun 2010, pluknet wrote: ... MegaCli -LdSetProp Cached -LALL -a0 MegaCli -LdSetProp NORA -LALL -a0 MegaCli -LdSetProp WB -LALL -a0 MegaCli -LdSetProp -EnDskCache -LALL -a0 (Only if having a USV of course) Dunno if there is a mfiutil equivalent though. Hi. That would be: mfiutil cache mfid0 enable mfiutil cache mfid0 read-ahead none mfiutil cache mfid0 write-back mfiutil cache mfid0 write-cache enable Thanks! Bye/2 --- Michael Reifenberger mich...@reifenberger.com http://www.Reifenberger.com ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On 19.06.2010 11:58, oizs wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. This is from a similar controller running that 8-disk raid5+0 setup: -- CrystalDiskMark 2.2 (C) 2007-2008 hiyohiyo Crystal Dew World : http://crystalmark.info/ -- Sequential Read : 665.383 MB/s Sequential Write : 300.452 MB/s Random Read 512KB : 616.604 MB/s Random Write 512KB : 306.306 MB/s Random Read 4KB : 64.465 MB/s Random Write 4KB :7.646 MB/s Test Size : 100 MB Date : 2010/06/19 14:24:12 You should be looking at number about half of these. I ran the test with adaptive readahead enabled, and write-through for cache (since I run with BBU, I normally use write-back) //Svein -- +---+--- /\ |Svein Skogen | sv...@d80.iso100.no \ / |Solberg Østli 9| PGP Key: 0xE5E76831 X|2020 Skedsmokorset | sv...@jernhuset.no / \ |Norway | PGP Key: 0xCE96CE13 | | sv...@stillbilde.net ascii | | PGP Key: 0x58CD33B6 ribbon |System Admin | svein-listm...@stillbilde.net Campaign|stillbilde.net | PGP Key: 0x22D494A4 +---+--- |msn messenger: | Mobile Phone: +47 907 03 575 |sv...@jernhuset.no | RIPE handle:SS16503-RIPE +---+--- If you really are in a hurry, mail me at svein-mob...@stillbilde.net This mailbox goes directly to my cellphone and is checked even when I'm not in front of my computer. Picture Gallery: https://gallery.stillbilde.net/v/svein/ signature.asc Description: OpenPGP digital signature
Re: Dell Perc 5/i Performance issues
Two big things can affect RAID-5 performance: 1. Battery backup. If you don't have a working battery attached to the card, it will turn off the write-back cache, no matter what you do. Check this. If you're unsure, use the mfiutil tool that I added to FreeBSD a few months ago and send me the output. 2. Partition alignment. If you're using classic MBR slices, everything gets misaligned by 63 sectors, making it impossible for the controller to optimize both reads and writes. If the array is used for secondary storage, simply don't use an MBR scheme. If it's used for primary storage, try using GPT instead and setting up your partitions so that they are aligned to large power-of-2 boundaries. Scott On Jun 18, 2010, at 6:27 PM, oizs wrote: Im using the Samsung F3 disks, which can do 140MB/s sequentially. I have tried different raids raid0 will do just as bad as raid5. I even tried one disk which performed as expected 100MB/s+ reads and writes so I'm not sure anymore what could be the problem. Maybe the controller hates samsung disks? -zsozso On 2010.06.19. 0:21, krad wrote: On 18 June 2010 10:08, oizso...@freemail.hu wrote: I've seen people with the same configuration doing 160MB/s writes and 250MB/s+ reads with raid5 so I still think something isn't right. And using raid10 with 4 disks is a rather large waste of capacity. -zsozso On 2010.06.18. 1:55, Chuck Swiger wrote: On Jun 17, 2010, at 4:50 PM, oizs wrote: I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) Switch to using RAID-10 rather than RAID-5. It's normal for RAID-5 to have worse write performance than that of a single drive. Regards, ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org what are your drives though? Are they SATA green/eco type drives or proper SAS enterprise ones ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Jun 19, 2010, at 5:32 AM, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 4:24 AM, Garrett Cooper yanef...@gmail.com wrote: On Sat, Jun 19, 2010 at 4:21 AM, oizs o...@freemail.hu wrote: Since I tested it on different kind of os's, and with at least 5 testing applications, I don't think that would be the case. On 2010.06.19. 13:17, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 2:58 AM, oizso...@freemail.hu wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) Dumb question: are you sure that the problem that you're seeing isn't in fact inhibited by the application that you're getting `performance' results with? If your applications aren't well suited for your hardware's capabilities, then of course performance will be bad. Furthermore, if the performance applications and your use scenarios are centered around reading, as opposed to writing, there is an option within mficontrol and the mfi(4) interface where you can actually enable read-ahead, instead of writeback (you unfortunately can't enable both scenarios). I realize that this is an artificial improvement in a way, but you should judge whether or not your application will be doing more reading than writing in whatever capacity it's doing... HTH, No, that doesn't help. I wrote the driver, and I have no flipping clue what you're talking about. Scott ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Sat, Jun 19, 2010 at 7:56 PM, Scott Long sco...@samsco.org wrote: On Jun 19, 2010, at 5:32 AM, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 4:24 AM, Garrett Cooper yanef...@gmail.com wrote: On Sat, Jun 19, 2010 at 4:21 AM, oizs o...@freemail.hu wrote: Since I tested it on different kind of os's, and with at least 5 testing applications, I don't think that would be the case. On 2010.06.19. 13:17, Garrett Cooper wrote: On Sat, Jun 19, 2010 at 2:58 AM, oizso...@freemail.hu wrote: I tried almost everything raid 0 1 5 10 with all kind of stripes 32/64/128 and settings direct io/cached/read-ahead/wt/wb/disk-cache but nothing seems to work. I changed the card to another dell perc 5 which had an older firmware. Tried 4 kind of motherboards even tried changing the os to linux and windows xp/7. In windows I got some funny results 1.3MB/s with write-back and 150MB/s reads with 5 disks in raid0. I just wanted to have a hw raid with no problems since the motherboard 88sx7042 and bsd did not like eachother. On 2010.06.19. 11:07, Svein Skogen (Listmail Account) wrote: On 18.06.2010 01:50, oizs wrote: Hi, I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) As far as I know this controller should be as fast as on other systems. (Freebsd.org mx1 has one of these cards.) I'm hoping somebody on the list reads this and helps because I can't afford to buy another card. I've lost track of what actual boards Dell has OEMized to make the various PERCs, but if I remember somewhat correctly, the PERC5 is basically an LSI Megaraid SAS 8308elp with different labels and firmware? If so, I've got that exact controller (minus the dell labels and firmware) in my primary storage box here, and yes, you SHOULD be able to get more performance out of it. What's your strip sizes and logical disk layout? (I've got the same board running on 8x 1T5 Seagates in RAID5+0, and that setup easily pulls 5 times the values you're seeing, and by all logic you should see about half of what I'm seeing) Dumb question: are you sure that the problem that you're seeing isn't in fact inhibited by the application that you're getting `performance' results with? If your applications aren't well suited for your hardware's capabilities, then of course performance will be bad. Furthermore, if the performance applications and your use scenarios are centered around reading, as opposed to writing, there is an option within mficontrol and the mfi(4) interface where you can actually enable read-ahead, instead of writeback (you unfortunately can't enable both scenarios). I realize that this is an artificial improvement in a way, but you should judge whether or not your application will be doing more reading than writing in whatever capacity it's doing... HTH, No, that doesn't help. I wrote the driver, and I have no flipping clue what you're talking about. Nevermind. It was a misunderstanding of what the subcommands... - mfiutil cache .. enable - mfiutil cache .. reads enable - mfiutil cache .. writes enable ... do. -Garrett ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
I've seen people with the same configuration doing 160MB/s writes and 250MB/s+ reads with raid5 so I still think something isn't right. And using raid10 with 4 disks is a rather large waste of capacity. -zsozso On 2010.06.18. 1:55, Chuck Swiger wrote: On Jun 17, 2010, at 4:50 PM, oizs wrote: I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) Switch to using RAID-10 rather than RAID-5. It's normal for RAID-5 to have worse write performance than that of a single drive. Regards, ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Jun 18, 2010, at 2:08 AM, oizs wrote: I've seen people with the same configuration doing 160MB/s writes and 250MB/s+ reads with raid5 so I still think something isn't right. How is that being measured? And using raid10 with 4 disks is a rather large waste of capacity. If you value performance and reliability more than cost, RAID-10 is a better choice. If you value cost more than performance, RAID-5 is what you use. See: http://lists.freebsd.org/pipermail/freebsd-questions/2006-March/116122.html Regards, -- -Chuck ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On 18 June 2010 10:08, oizs o...@freemail.hu wrote: I've seen people with the same configuration doing 160MB/s writes and 250MB/s+ reads with raid5 so I still think something isn't right. And using raid10 with 4 disks is a rather large waste of capacity. -zsozso On 2010.06.18. 1:55, Chuck Swiger wrote: On Jun 17, 2010, at 4:50 PM, oizs wrote: I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) Switch to using RAID-10 rather than RAID-5. It's normal for RAID-5 to have worse write performance than that of a single drive. Regards, ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org what are your drives though? Are they SATA green/eco type drives or proper SAS enterprise ones ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
Im using the Samsung F3 disks, which can do 140MB/s sequentially. I have tried different raids raid0 will do just as bad as raid5. I even tried one disk which performed as expected 100MB/s+ reads and writes so I'm not sure anymore what could be the problem. Maybe the controller hates samsung disks? -zsozso On 2010.06.19. 0:21, krad wrote: On 18 June 2010 10:08, oizso...@freemail.hu wrote: I've seen people with the same configuration doing 160MB/s writes and 250MB/s+ reads with raid5 so I still think something isn't right. And using raid10 with 4 disks is a rather large waste of capacity. -zsozso On 2010.06.18. 1:55, Chuck Swiger wrote: On Jun 17, 2010, at 4:50 PM, oizs wrote: I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) Switch to using RAID-10 rather than RAID-5. It's normal for RAID-5 to have worse write performance than that of a single drive. Regards, ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org what are your drives though? Are they SATA green/eco type drives or proper SAS enterprise ones ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
Re: Dell Perc 5/i Performance issues
On Jun 17, 2010, at 4:50 PM, oizs wrote: I've bought a Dell Perc 5/i because I couldn't make the onboard marvell 88sx7042 work with 8.0/8.1 or current, but as lucky as I am, the best I can do with 4x1.5tb samsung in raid5 is 60MB/s writes and 90MB/s reads, with bbu/write-back/adaptive-read-ahead. I was expecting at least twice of that, and I'm not sure what can I do to get that speed. (I've read man 7 tuning with no success) Switch to using RAID-10 rather than RAID-5. It's normal for RAID-5 to have worse write performance than that of a single drive. Regards, -- -Chuck ___ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to freebsd-current-unsubscr...@freebsd.org
