Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
On Wed, 05 Mar 2008 at 11:13:14PM -0500, Talpey, Thomas wrote: At 08:20 AM 3/3/2008, Pawel Dziekonski wrote: both nfs server and client have Mellanox MT25204 HCAs. tests were done by connecting them port to port (without switch) with DDR cable. reported link was 20Gbps. What kernel base is your client running also? (uname -a) There are some known issues with cached write throughput over NFS above 1Gb, that we may be able to work around but it's kernel-dependent. currently I have a Flextronix switch that reports itself as MT47396 Infiniscale-III Mellanox Technologies. Looking at your results from earlier this month, it's not at all clear that the nfs/rdma run was actually using nfs/rdma. The speeds and cpu loads were very similar to the ethernet results. Can we take this offline and look into it more? All on the client, I'll be interested in the exact mount command you ran, the output of cat /proc/mounts, the contents of dmesg/kernel logs after a run, and the output of nfsstat. Hi, thanks for answering. I can not provide any details now. I will repeat whole setup and benchmarks ASAP. Pawel -- Pawel Dziekonski [EMAIL PROTECTED] Wroclaw Centre for Networking Supercomputing, HPC Department Politechnika Wr., pl. Grunwaldzki 9, bud. D2/101, 50-377 Wroclaw, POLAND phone: +48 71 3202043, fax: +48 71 3225797, http://www.wcss.wroc.pl ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
At 08:20 AM 3/3/2008, Pawel Dziekonski wrote: both nfs server and client have Mellanox MT25204 HCAs. tests were done by connecting them port to port (without switch) with DDR cable. reported link was 20Gbps. What kernel base is your client running also? (uname -a) There are some known issues with cached write throughput over NFS above 1Gb, that we may be able to work around but it's kernel-dependent. currently I have a Flextronix switch that reports itself as MT47396 Infiniscale-III Mellanox Technologies. Looking at your results from earlier this month, it's not at all clear that the nfs/rdma run was actually using nfs/rdma. The speeds and cpu loads were very similar to the ethernet results. Can we take this offline and look into it more? All on the client, I'll be interested in the exact mount command you ran, the output of cat /proc/mounts, the contents of dmesg/kernel logs after a run, and the output of nfsstat. Tom. ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
On Sun, 02 Mar 2008 at 06:48:11PM -0600, Tom Tucker wrote: On Fri, 2008-02-29 at 09:29 +0100, Sebastian Schmitzdorff wrote: hi pawel, I was wondering if you have achieved better nfs rdma benchmark results by now? Pawel: What is your network hardware setup? hi, both nfs server and client have Mellanox MT25204 HCAs. tests were done by connecting them port to port (without switch) with DDR cable. reported link was 20Gbps. currently I have a Flextronix switch that reports itself as MT47396 Infiniscale-III Mellanox Technologies. cheers, P -- Pawel Dziekonski [EMAIL PROTECTED] Wroclaw Centre for Networking Supercomputing, HPC Department Politechnika Wr., pl. Grunwaldzki 9, bud. D2/101, 50-377 Wroclaw, POLAND phone: +48 71 3202043, fax: +48 71 3225797, http://www.wcss.wroc.pl ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
On Fri, 2008-02-29 at 09:29 +0100, Sebastian Schmitzdorff wrote: hi pawel, I was wondering if you have achieved better nfs rdma benchmark results by now? Pawel: What is your network hardware setup? Thanks, Tom regards Sebastian Pawel Dziekonski schrieb: hi, the saga continues. ;) very basic benchmarks and surprising (at least for me) results - it look's like reading is much slower than writing and NFS/RDMA is twice slower in reading than classic NFS. :o results below - comments appreciated! regards, Pawel both nfs server and client have 8-cores, 16 GB RAM, Mellanox DDR HCAs (MT25204) connected port-port (no switch). local_hdd - 2 sata2 disks in soft-raid0, nfs_ipoeth - classic nfs over ethernet, nfs_ipoib - classic nfs over IPoIB, nfs_rdma - NFS/RDMA. simple write of 36GB file with dd (both machines have 16GB RAM): /usr/bin/time -p dd if=/dev/zero of=/mnt/qqq bs=1M count=36000 local_hddsys 54.52user 0.04real 254.59 nfs_ipoibsys 36.35user 0.00real 266.63 nfs_rdma sys 39.03user 0.02real 323.77 nfs_ipoeth sys 34.21user 0.01real 375.24 remount /mnt to clear cache and read a file from nfs share and write it to /dev/: /usr/bin/time -p dd if=/mnt/qqq of=/scratch/qqq bs=1M nfs_ipoib sys 59.04user 0.02real 571.57 nfs_ipoeth sys 58.92user 0.02real 606.61 nfs_rdmasys 62.57user 0.03real 1296.36 results from bonnie++: Version 1.03c --Sequential Write -- --Sequential Read -- --Random- -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks-- MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP local_hdd 35G:128k 93353 12 58329 6 143293 7 243.6 1 local_hdd 35G:256k 92283 11 58189 6 144202 8 172.2 2 local_hdd 35G:512k 93879 12 57715 6 144167 8 128.2 4 local_hdd 35G:1024k 93075 12 58637 6 144172 8 95.3 7 nfs_ipoeth 35G:128k 91325 7 31848 464299 4 170.2 1 nfs_ipoeth 35G:256k 90668 7 32036 564542 4 163.2 2 nfs_ipoeth 35G:512k 93348 7 31757 564454 4 85.7 3 nfs_ipoet 35G:1024k 91283 7 31869 564241 5 51.7 4 nfs_ipoib 35G:128k 91733 7 36641 565839 4 178.4 2 nfs_ipoib 35G:256k 92453 7 36567 666682 4 166.9 3 nfs_ipoib 35G:512k 91157 7 37660 666318 4 86.8 3 nfs_ipoib 35G:1024k 92111 7 35786 666277 5 53.3 4 nfs_rdma 35G:128k 91152 8 29942 532147 2 187.0 1 nfs_rdma 35G:256k 89772 7 30560 534587 2 158.4 3 nfs_rdma 35G:512k 91290 7 29698 534277 2 60.9 2 nfs_rdma 35G:1024k 91336 8 29052 531742 2 41.5 3 --Sequential Create-- Random Create -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete-- files:max:min/sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP local_hdd16 10587 36 + +++ 8674 29 10727 35 + +++ 7015 28 local_hdd16 11372 41 + +++ 8490 29 11192 43 + +++ 6881 27 local_hdd16 10789 35 + +++ 8520 29 11468 46 + +++ 6651 24 local_hdd16 10841 40 + +++ 8443 28 11162 41 + +++ 6441 22 nfs_ipoeth 16 3753 7 13390 12 3795 7 3773 8 22181 16 3635 7 nfs_ipoeth 16 3762 8 12358 7 3713 8 3753 7 20448 13 3632 6 nfs_ipoeth 16 3834 7 12697 6 3729 8 3725 9 22807 11 3673 7 nfs_ipoeth 16 3729 8 14260 10 3774 7 3744 7 25285 14 3688 7 nfs_ipoib16 6803 17 + +++ 6843 15 6820 14 + +++ 5834 11 nfs_ipoib16 6587 16 + +++ 4959 9 6832 14 + +++ 5608 12 nfs_ipoib16 6820 18 + +++ 6636 15 6479 15 + +++ 5679 13 nfs_ipoib16 6475 14 + +++ 6435 14 5543 11 + +++ 5431 11 nfs_rdma 16 7014 15 + +++ 6714 10 7001 14 + +++ 5683 8 nfs_rdma 16 7038 13 + +++ 6713 12 6956 11 + +++ 5488 8 nfs_rdma 16 7058 12 + +++ 6797 11 6989 14 + +++ 5761 9 nfs_rdma 16 7201 13 + +++ 6821 12 7072 15 + +++ 5609 9 ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit
Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
hi pawel, I was wondering if you have achieved better nfs rdma benchmark results by now? regards Sebastian Pawel Dziekonski schrieb: hi, the saga continues. ;) very basic benchmarks and surprising (at least for me) results - it look's like reading is much slower than writing and NFS/RDMA is twice slower in reading than classic NFS. :o results below - comments appreciated! regards, Pawel both nfs server and client have 8-cores, 16 GB RAM, Mellanox DDR HCAs (MT25204) connected port-port (no switch). local_hdd - 2 sata2 disks in soft-raid0, nfs_ipoeth - classic nfs over ethernet, nfs_ipoib - classic nfs over IPoIB, nfs_rdma - NFS/RDMA. simple write of 36GB file with dd (both machines have 16GB RAM): /usr/bin/time -p dd if=/dev/zero of=/mnt/qqq bs=1M count=36000 local_hddsys 54.52user 0.04real 254.59 nfs_ipoibsys 36.35user 0.00real 266.63 nfs_rdma sys 39.03user 0.02real 323.77 nfs_ipoeth sys 34.21user 0.01real 375.24 remount /mnt to clear cache and read a file from nfs share and write it to /dev/: /usr/bin/time -p dd if=/mnt/qqq of=/scratch/qqq bs=1M nfs_ipoib sys 59.04user 0.02real 571.57 nfs_ipoeth sys 58.92user 0.02real 606.61 nfs_rdmasys 62.57user 0.03real 1296.36 results from bonnie++: Version 1.03c --Sequential Write -- --Sequential Read -- --Random- -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks-- MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP local_hdd 35G:128k 93353 12 58329 6 143293 7 243.6 1 local_hdd 35G:256k 92283 11 58189 6 144202 8 172.2 2 local_hdd 35G:512k 93879 12 57715 6 144167 8 128.2 4 local_hdd 35G:1024k 93075 12 58637 6 144172 8 95.3 7 nfs_ipoeth 35G:128k 91325 7 31848 464299 4 170.2 1 nfs_ipoeth 35G:256k 90668 7 32036 564542 4 163.2 2 nfs_ipoeth 35G:512k 93348 7 31757 564454 4 85.7 3 nfs_ipoet 35G:1024k 91283 7 31869 564241 5 51.7 4 nfs_ipoib 35G:128k 91733 7 36641 565839 4 178.4 2 nfs_ipoib 35G:256k 92453 7 36567 666682 4 166.9 3 nfs_ipoib 35G:512k 91157 7 37660 666318 4 86.8 3 nfs_ipoib 35G:1024k 92111 7 35786 666277 5 53.3 4 nfs_rdma 35G:128k 91152 8 29942 532147 2 187.0 1 nfs_rdma 35G:256k 89772 7 30560 534587 2 158.4 3 nfs_rdma 35G:512k 91290 7 29698 534277 2 60.9 2 nfs_rdma 35G:1024k 91336 8 29052 531742 2 41.5 3 --Sequential Create-- Random Create -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete-- files:max:min/sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP local_hdd16 10587 36 + +++ 8674 29 10727 35 + +++ 7015 28 local_hdd16 11372 41 + +++ 8490 29 11192 43 + +++ 6881 27 local_hdd16 10789 35 + +++ 8520 29 11468 46 + +++ 6651 24 local_hdd16 10841 40 + +++ 8443 28 11162 41 + +++ 6441 22 nfs_ipoeth 16 3753 7 13390 12 3795 7 3773 8 22181 16 3635 7 nfs_ipoeth 16 3762 8 12358 7 3713 8 3753 7 20448 13 3632 6 nfs_ipoeth 16 3834 7 12697 6 3729 8 3725 9 22807 11 3673 7 nfs_ipoeth 16 3729 8 14260 10 3774 7 3744 7 25285 14 3688 7 nfs_ipoib16 6803 17 + +++ 6843 15 6820 14 + +++ 5834 11 nfs_ipoib16 6587 16 + +++ 4959 9 6832 14 + +++ 5608 12 nfs_ipoib16 6820 18 + +++ 6636 15 6479 15 + +++ 5679 13 nfs_ipoib16 6475 14 + +++ 6435 14 5543 11 + +++ 5431 11 nfs_rdma 16 7014 15 + +++ 6714 10 7001 14 + +++ 5683 8 nfs_rdma 16 7038 13 + +++ 6713 12 6956 11 + +++ 5488 8 nfs_rdma 16 7058 12 + +++ 6797 11 6989 14 + +++ 5761 9 nfs_rdma 16 7201 13 + +++ 6821 12 7072 15 + +++ 5609 9 -- Hamburgnet, Geschäftsführer Sebastian Schmitzdorff http://www.hamburgnet.de Kottwitzstrasse 49 D-20253 Hamburg fon: 040 / 736 72 322 fax: 040 / 736 72 321 ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
On Fri, 29 Feb 2008 at 09:29:21AM +0100, Sebastian Schmitzdorff wrote: hi pawel, I was wondering if you have achieved better nfs rdma benchmark results by now? no :( -- Pawel Dziekonski [EMAIL PROTECTED] Wroclaw Centre for Networking Supercomputing, HPC Department Politechnika Wr., pl. Grunwaldzki 9, bud. D2/101, 50-377 Wroclaw, POLAND phone: +48 71 3202043, fax: +48 71 3225797, http://www.wcss.wroc.pl ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
hi, the saga continues. ;) very basic benchmarks and surprising (at least for me) results - it look's like reading is much slower than writing and NFS/RDMA is twice slower in reading than classic NFS. :o results below - comments appreciated! regards, Pawel both nfs server and client have 8-cores, 16 GB RAM, Mellanox DDR HCAs (MT25204) connected port-port (no switch). local_hdd - 2 sata2 disks in soft-raid0, nfs_ipoeth - classic nfs over ethernet, nfs_ipoib - classic nfs over IPoIB, nfs_rdma - NFS/RDMA. simple write of 36GB file with dd (both machines have 16GB RAM): /usr/bin/time -p dd if=/dev/zero of=/mnt/qqq bs=1M count=36000 local_hddsys 54.52user 0.04real 254.59 nfs_ipoibsys 36.35user 0.00real 266.63 nfs_rdma sys 39.03user 0.02real 323.77 nfs_ipoeth sys 34.21user 0.01real 375.24 remount /mnt to clear cache and read a file from nfs share and write it to /dev/: /usr/bin/time -p dd if=/mnt/qqq of=/scratch/qqq bs=1M nfs_ipoib sys 59.04user 0.02real 571.57 nfs_ipoeth sys 58.92user 0.02real 606.61 nfs_rdmasys 62.57user 0.03real 1296.36 results from bonnie++: Version 1.03c --Sequential Write -- --Sequential Read -- --Random- -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks-- MachineSize K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP local_hdd 35G:128k 93353 12 58329 6 143293 7 243.6 1 local_hdd 35G:256k 92283 11 58189 6 144202 8 172.2 2 local_hdd 35G:512k 93879 12 57715 6 144167 8 128.2 4 local_hdd 35G:1024k 93075 12 58637 6 144172 8 95.3 7 nfs_ipoeth 35G:128k 91325 7 31848 464299 4 170.2 1 nfs_ipoeth 35G:256k 90668 7 32036 564542 4 163.2 2 nfs_ipoeth 35G:512k 93348 7 31757 564454 4 85.7 3 nfs_ipoet 35G:1024k 91283 7 31869 564241 5 51.7 4 nfs_ipoib 35G:128k 91733 7 36641 565839 4 178.4 2 nfs_ipoib 35G:256k 92453 7 36567 666682 4 166.9 3 nfs_ipoib 35G:512k 91157 7 37660 666318 4 86.8 3 nfs_ipoib 35G:1024k 92111 7 35786 666277 5 53.3 4 nfs_rdma 35G:128k 91152 8 29942 532147 2 187.0 1 nfs_rdma 35G:256k 89772 7 30560 534587 2 158.4 3 nfs_rdma 35G:512k 91290 7 29698 534277 2 60.9 2 nfs_rdma 35G:1024k 91336 8 29052 531742 2 41.5 3 --Sequential Create-- Random Create -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete-- files:max:min/sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP local_hdd16 10587 36 + +++ 8674 29 10727 35 + +++ 7015 28 local_hdd16 11372 41 + +++ 8490 29 11192 43 + +++ 6881 27 local_hdd16 10789 35 + +++ 8520 29 11468 46 + +++ 6651 24 local_hdd16 10841 40 + +++ 8443 28 11162 41 + +++ 6441 22 nfs_ipoeth 16 3753 7 13390 12 3795 7 3773 8 22181 16 3635 7 nfs_ipoeth 16 3762 8 12358 7 3713 8 3753 7 20448 13 3632 6 nfs_ipoeth 16 3834 7 12697 6 3729 8 3725 9 22807 11 3673 7 nfs_ipoeth 16 3729 8 14260 10 3774 7 3744 7 25285 14 3688 7 nfs_ipoib16 6803 17 + +++ 6843 15 6820 14 + +++ 5834 11 nfs_ipoib16 6587 16 + +++ 4959 9 6832 14 + +++ 5608 12 nfs_ipoib16 6820 18 + +++ 6636 15 6479 15 + +++ 5679 13 nfs_ipoib16 6475 14 + +++ 6435 14 5543 11 + +++ 5431 11 nfs_rdma 16 7014 15 + +++ 6714 10 7001 14 + +++ 5683 8 nfs_rdma 16 7038 13 + +++ 6713 12 6956 11 + +++ 5488 8 nfs_rdma 16 7058 12 + +++ 6797 11 6989 14 + +++ 5761 9 nfs_rdma 16 7201 13 + +++ 6821 12 7072 15 + +++ 5609 9 -- Pawel Dziekonski [EMAIL PROTECTED] Wroclaw Centre for Networking Supercomputing, HPC Department Politechnika Wr., pl. Grunwaldzki 9, bud. D2/101, 50-377 Wroclaw, POLAND phone: +48 71 3202043, fax: +48 71 3225797, http://www.wcss.wroc.pl ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Re: [nfs-rdma-devel] [ofa-general] Status of NFS-RDMA ? (fwd)
On Wed, 06 Feb 2008 at 11:54:51AM -0600, Tom Tucker wrote: Pawel: On Wed, 2008-02-06 at 12:19 -0500, James Lentini wrote: -- Forwarded message -- cat /proc/fs/nfsd/portlist # cat /proc/fs/nfsd/portlist tcp 0.0.0.0, port=2049 udp 0.0.0.0, port=2049 From the output of the portlist file, I can tell that you have a patch that I have since removed from the tree. The syntax for creating a listener with this patch is different from James' README. The syntax with that patch is as follows: echo rdma 2 0.0.0.0 2050 /proc/fs/nfsd/portlist and it works!!! server: # echo rdma 2 0.0.0.0 2050 /proc/fs/nfsd/portlist # cat /proc/fs/nfsd/portlist rdma 0.0.0.0, port=2050 tcp 0.0.0.0, port=2049 udp 0.0.0.0, port=2049 client: # mount.nfs 10.2.2.1:/scratch /mnt -i -o rdma,port=2050 -v mount.nfs: timeout set for Wed Feb 6 19:30:18 2008 mount.nfs: text-based options: 'rdma,port=2050,addr=10.2.2.1' 10.2.2.1:/scratch on /mnt type nfs (rdma,port=2050) # ls -la /mnt total 28 drwxr-xr-x 3 root root 4096 Feb 6 12:39 ./ drwxr-xr-x 24 root root 4096 Feb 6 13:33 ../ drwx-- 2 root root 16384 Jan 25 16:29 lost+found/ -rw-r--r-- 1 root root 0 Feb 6 12:39 qqq thanks!! I'm going to start performance tests now - I will report results. cheers, P -- Pawel Dziekonski [EMAIL PROTECTED] Wroclaw Centre for Networking Supercomputing, HPC Department Politechnika Wr., pl. Grunwaldzki 9, bud. D2/101, 50-377 Wroclaw, POLAND phone: +48 71 3202043, fax: +48 71 3225797, http://www.wcss.wroc.pl ___ general mailing list general@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general