Hi,
here is the result of iozone:
Iozone: Performance Test of File I/O
Version $Revision: 3.429 $
Compiled for 64 bit mode.
Build: linux-AMD64
Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
Al Slater, Scott Rhine, Mike Wisner, Ken Goss
Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
Randy Dunlap, Mark Montague, Dan Million, Gavin Brebner,
Jean-Marc Zucconi, Jeff Blomberg, Benny Halevy, Dave Boone,
Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root,
Fabrice Bacchella, Zhenghua Xue, Qin Li, Darren Sawyer,
Vangel Bojaxhi, Ben England, Vikentsi Lapa.
Run began: Tue Jan 26 09:22:08 2016
Excel chart generation enabled
Record Size 4 kB
File size set to 102400 kB
Command line used: iozone -R -l 5 -u 5 -r 4k -s 100m -F /data/f1 /data/f2
/data/f3 /data/f4 /data/f5
Output is in kBytes/sec
Time Resolution = 0.000001 seconds.
Processor cache size set to 1024 kBytes.
Processor cache line size set to 32 bytes.
File stride size set to 17 * record size.
Min process = 5
Max process = 5
Throughput test with 5 processes
Each process writes a 102400 kByte file in 4 kByte records
Children see throughput for 5 initial writers = 1505927.47 kB/sec
Parent sees throughput for 5 initial writers = 148906.70 kB/sec
Min throughput per process = 201997.91 kB/sec
Max throughput per process = 380595.62 kB/sec
Avg throughput per process = 301185.49 kB/sec
Min xfer = 53260.00 kB
Children see throughput for 5 rewriters = 2165373.12 kB/sec
Parent sees throughput for 5 rewriters = 164745.92 kB/sec
Min throughput per process = 293634.97 kB/sec
Max throughput per process = 578844.50 kB/sec
Avg throughput per process = 433074.62 kB/sec
Min xfer = 51996.00 kB
Children see throughput for 5 readers = 4239675.44 kB/sec
Parent sees throughput for 5 readers = 3913493.02 kB/sec
Min throughput per process = 550723.50 kB/sec
Max throughput per process = 1217377.75 kB/sec
Avg throughput per process = 847935.09 kB/sec
Min xfer = 46296.00 kB
Children see throughput for 5 re-readers = 4115558.53 kB/sec
Parent sees throughput for 5 re-readers = 3895954.18 kB/sec
Min throughput per process = 406504.81 kB/sec
Max throughput per process = 1236357.38 kB/sec
Avg throughput per process = 823111.71 kB/sec
Min xfer = 33180.00 kB
Children see throughput for 5 reverse readers = 3035094.88 kB/sec
Parent sees throughput for 5 reverse readers = 2955261.71 kB/sec
Min throughput per process = 345686.91 kB/sec
Max throughput per process = 783863.56 kB/sec
Avg throughput per process = 607018.97 kB/sec
Min xfer = 45156.00 kB
Children see throughput for 5 stride readers = 2729678.81 kB/sec
Parent sees throughput for 5 stride readers = 2635553.53 kB/sec
Min throughput per process = 387056.06 kB/sec
Max throughput per process = 726215.44 kB/sec
Avg throughput per process = 545935.76 kB/sec
Min xfer = 53928.00 kB
Children see throughput for 5 random readers = 2741175.25 kB/sec
Parent sees throughput for 5 random readers = 2695067.68 kB/sec
Min throughput per process = 335544.44 kB/sec
Max throughput per process = 731835.81 kB/sec
Avg throughput per process = 548235.05 kB/sec
Min xfer = 46936.00 kB
Children see throughput for 5 mixed workload = 2339391.75 kB/sec
Parent sees throughput for 5 mixed workload = 308170.67 kB/sec
Min throughput per process = 363991.88 kB/sec
Max throughput per process = 781703.56 kB/sec
Avg throughput per process = 467878.35 kB/sec
Min xfer = 47672.00 kB
Children see throughput for 5 random writers = 1562589.19 kB/sec
Parent sees throughput for 5 random writers = 110574.52 kB/sec
Min throughput per process = 225203.20 kB/sec
Max throughput per process = 451381.59 kB/sec
Avg throughput per process = 312517.84 kB/sec
Min xfer = 52292.00 kB
Children see throughput for 5 pwrite writers = 1230276.08 kB/sec
Parent sees throughput for 5 pwrite writers = 151892.70 kB/sec
Min throughput per process = 162737.70 kB/sec
Max throughput per process = 314977.12 kB/sec
Avg throughput per process = 246055.22 kB/sec
Min xfer = 52892.00 kB
Children see throughput for 5 pread readers = 3645236.03 kB/sec
Parent sees throughput for 5 pread readers = 3002540.75 kB/sec
Min throughput per process = 481141.28 kB/sec
Max throughput per process = 1091392.88 kB/sec
Avg throughput per process = 729047.21 kB/sec
Min xfer = 45168.00 kB
Children see throughput for 5 fwriters = 1953463.41 kB/sec
Parent sees throughput for 5 fwriters = 147409.36 kB/sec
Min throughput per process = 334873.59 kB/sec
Max throughput per process = 483180.59 kB/sec
Avg throughput per process = 390692.68 kB/sec
Min xfer = 102400.00 kB
Children see throughput for 5 freaders = 4402325.88 kB/sec
Parent sees throughput for 5 freaders = 3287470.61 kB/sec
Min throughput per process = 663789.25 kB/sec
Max throughput per process = 1099585.38 kB/sec
Avg throughput per process = 880465.18 kB/sec
Min xfer = 102400.00 kB
"Throughput report Y-axis is type of test X-axis is number of
processes"
"Record size = 4 kBytes "
"Output is in kBytes/sec"
" Initial write " 1505927.47
" Rewrite " 2165373.12
" Read " 4239675.44
" Re-read " 4115558.53
" Reverse Read " 3035094.88
" Stride read " 2729678.81
" Random read " 2741175.25
" Mixed workload " 2339391.75
" Random write " 1562589.19
" Pwrite " 1230276.08
" Pread " 3645236.03
" Fwrite " 1953463.41
" Fread " 4402325.88
iozone test complete.
I don't know why samba is long to open the roaming profile sometimes
Pierre
2016-01-25 17:59 GMT+01:00 Reindl Harald <h.reindl at thelounge.net>:
>
>
> Am 25.01.2016 um 17:49 schrieb BRIEC, Pierre:
>
>> I have several VMs running on Xenserver 6.5
>> I have 2 samba servers (1 DC & 1 Fileserver). They are both running
Debian
>> Linux 8.2 Jessie.
>> I'm using the samba debian package (4.1.17)
>> My VM has 8G RAM and 4 vCPU
>>
>> How can i test if the performances are quite good or not? with
>> reading/writing
>>
>
> https://www.google.com/search?q=samba+performance+test
> http://www.pcmag.com/article2/0,2817,2266909,00.asp
>
> Could I have better performance with the latest samba release?
>>
>
> wrong question - if you can saturate your network with Samba in the
> installed version there is no better performance to gain
>
> normally one looks at the current results and then asks if it could become
> better and even if it could in theory how much noticeable it would be for
> the workload
>
>
> --
> To unsubscribe from this list go to the following URL and read the
> instructions: https://lists.samba.org/mailman/options/samba
>
--