> Von: John Stoffel [john@xxxxxxxxxxx] > Gesendet: Mittwoch, 20. August 2014 01:46 > An: Markus Stockhausen > Cc: linux-raid@xxxxxxxxxxxxxxx > Betreff: Re: [PATCH v2 0/6] raid6: support read-modify-write > > >>>>> "Markus" == Markus Stockhausen <stockhausen@xxxxxxxxxxx> writes: > > Markus> 300 seconds random write with 8 threads > Markus> 3,2TB (10*400GB) RAID6 64K chunk without spare > Markus> group_thread_cnt=4 > > Markus> bsize rmw_level=1 rmw_level=0 rmw_level=1 rmw_level=0 > Markus> skip_copy=1 skip_copy=1 skip_copy=0 skip_copy=0 > Markus> 4K 115 KB/s 141 KB/s 165 KB/s 140 KB/s > Markus> 8K 225 KB/s 275 KB/s 324 KB/s 274 KB/s > Markus> 16K 434 KB/s 536 KB/s 640 KB/s 534 KB/s > Markus> 32K 751 KB/s 1,051 KB/s 1,234 KB/s 1,045 KB/s > Markus> 64K 1,339 KB/s 1,958 KB/s 2,282 KB/s 1,962 KB/s > Markus> 128K 2,673 KB/s 3,862 KB/s 4,113 KB/s 3,898 KB/s > Markus> 256K 7,685 KB/s 7,539 KB/s 7,557 KB/s 7,638 KB/s > Markus> 512K 19,556 KB/s 19,558 KB/s 19,652 KB/s 19,688 Kb/s > > Which is the current 3.16.0 implementation? I can't keep it straight > in my head and you don't clearly specify which set is what we have > now, and which is your patch and it's option(s) in place. Standard of 3.16 in the above numbers is rmw_level=0/skip_copy=0. My patch will be rmw_level=1/skip_copy=0. I just included skip copy as I found it on the mailing list and was interested how rmw plays with stable pages without need for bio page copies. > What type of system did you run this test on? How much CPU/RAM, etc? > Can you should the configuration of the filesystem/MD volume you wrote > too as well? Sorry to be picky here, I'm just trying to see what this > buys us. Were the disks using SATA? IDE? What speed are the disks? It is a single E5630 with 24GB RAM. Although this should not matter as I made direct I/O. My tests wrote directly to /dev/md0 no filesystem in between. Disks are a bunch of 500GB-1TB SATA I/II 7200rpm. Server/Desktop mixed. > Also, how does the SSE2 optimization work? Can it be turned on/off? > And how much speedup does it provide? SSE2 optimization is not an option it is a must. The RAID6 algorithms are choosen on startup. In my case the system chooses the SSE2 implementation. The old patch used the already available implementation of gen_syndrome(). This always overwrote the parity blocks and needed extra spare pages. The discussion result about it was, that md should use an inplace syndrome calculation for the rmw case. Thus I was forced to copy the algorithms to a new xor_syndrome() call. Difference between standard and SSE optimized gen_syndrome is in my case 1-2GB/sec versus 9-10GB/sec (iirc). So it won't make any sense to offer rmw and fall back to a xor_syndrome() calulation with a default implementation that is 5 times slower. To avoid side effects the patch will disable rmw if the choosen existing optimized gen_syndrome() function does not offer a xor_syndrome() "brother". > Otherwise, I don't see any huge improvements with the numbers, and > the only consistent win is the rmw_level=1, skip_copy=0 case. But > even then when the bsize is big enough it's slower than other > options. So is it a win overall? This was the maximum of hardware that I could find in the short time. The original patch post gives better numbers because it used 12 disks. For me reasonable raid6 configurations range from 10-16 disks. So for the upper end the caluclation shows even more potential (but must be proven). >From simple math for 16 disks: - Update one block or one chunk - RCW case: 13 read I/Os + 3 write I/Os - RMW case: 3 read I/Os + 3 write I/Os > John Markus
**************************************************************************** Diese E-Mail enthält vertrauliche und/oder rechtlich geschützte Informationen. Wenn Sie nicht der richtige Adressat sind oder diese E-Mail irrtümlich erhalten haben, informieren Sie bitte sofort den Absender und vernichten Sie diese Mail. Das unerlaubte Kopieren sowie die unbefugte Weitergabe dieser Mail ist nicht gestattet. �ber das Internet versandte E-Mails können unter fremden Namen erstellt oder manipuliert werden. Deshalb ist diese als E-Mail verschickte Nachricht keine rechtsverbindliche Willenserklärung. Collogia Unternehmensberatung AG Ubierring 11 D-50678 Köln Vorstand: Kadir Akin Dr. Michael Höhnerbach Vorsitzender des Aufsichtsrates: Hans Kristian Langva Registergericht: Amtsgericht Köln Registernummer: HRB 52 497 This e-mail may contain confidential and/or privileged information. If you are not the intended recipient (or have received this e-mail in error) please notify the sender immediately and destroy this e-mail. Any unauthorized copying, disclosure or distribution of the material in this e-mail is strictly forbidden. e-mails sent over the internet may have been written under a wrong name or been manipulated. That is why this message sent as an e-mail is not a legally binding declaration of intention. Collogia Unternehmensberatung AG Ubierring 11 D-50678 Köln executive board: Kadir Akin Dr. Michael Höhnerbach President of the supervisory board: Hans Kristian Langva Registry office: district court Cologne Register number: HRB 52 497 ****************************************************************************
