On Feb19 16:31, William Dauchy wrote: > I would expect at least the same performances in v4.1.x. > What can I do to help debug this issue? I overlooked my config in 4.1.x and find out KASAN and kmemleak were enabled. however I can't reach the results I had on 3.14.x without these debug options. see my updated results on 4.1.x: random-read: (g=0): rw=randread, bs=4K-4K/4K-4K/4K-4K, ioengine=sync, iodepth=1 fio-2.1.11 Starting 1 process Jobs: 1 (f=1): [r(1)] [100.0% done] [7136KB/0KB/0KB /s] [1784/0/0 iops] [eta 00m:00s] random-read: (groupid=0, jobs=1): err= 0: pid=3519: Sat Feb 20 15:44:10 2016 read : io=131072KB, bw=7617.9KB/s, iops=1904, runt= 17206msec clat (usec): min=281, max=2091, avg=517.56, stdev=79.68 lat (usec): min=281, max=2092, avg=517.90, stdev=79.69 clat percentiles (usec): | 1.00th=[ 318], 5.00th=[ 402], 10.00th=[ 422], 20.00th=[ 442], | 30.00th=[ 490], 40.00th=[ 506], 50.00th=[ 516], 60.00th=[ 524], | 70.00th=[ 548], 80.00th=[ 580], 90.00th=[ 612], 95.00th=[ 652], | 99.00th=[ 716], 99.50th=[ 740], 99.90th=[ 772], 99.95th=[ 1208], | 99.99th=[ 1624] bw (KB /s): min= 7080, max= 8128, per=100.00%, avg=7627.53, stdev=343.98 lat (usec) : 500=37.34%, 750=62.32%, 1000=0.28% lat (msec) : 2=0.05%, 4=0.01% cpu : usr=2.05%, sys=14.02%, ctx=65541, majf=0, minf=45 IO depths : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0% submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0% complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0% issued : total=r=32768/w=0/d=0, short=r=0/w=0/d=0 latency : target=0, window=0, percentile=100.00%, depth=1 Run status group 0 (all jobs): READ: io=131072KB, aggrb=7617KB/s, minb=7617KB/s, maxb=7617KB/s, mint=17206msec, maxt=17206msec summary: 3.14: 9348KB/s 4.1: 7617KB/s -- William
Attachment:
signature.asc
Description: PGP signature