You are not logged in.
When copying to my Raid 5 in Arch, it copies about a gigabyte in samba and then it dies for all intents and purposes.I assume thats the cache. The load average goes above 20, idk what it's waiting for.
Linux Titan 6.11.2-arch1-1 #1 SMP PREEMPT_DYNAMIC Fri, 04 Oct 2024 21:51:11 +0000 x86_64 GNU/LinuxIostat -
Device r/s rkB/s rrqm/s %rrqm r_await rareq-sz w/s wkB/s wrqm/s %wrqm w_await wareq-sz d/s dkB/s drqm/s %drqm d_await dareq-sz f/s f_await aqu-sz %util
loop20 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 100.00
loop21 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
loop22 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
md127 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 100.00800kb/s??!
[culex@Titan share]$ fio --name=writefile --ioengine=libaio --rw=write --bs=1M --size=1G --numjobs=1 --runtime=30 --time_based --direct=1
writefile: (g=0): rw=write, bs=(R) 1024KiB-1024KiB, (W) 1024KiB-1024KiB, (T) 1024KiB-1024KiB, ioengine=libaio, iodepth=1
fio-3.37
Starting 1 process
writefile: Laying out IO file (1 file / 1024MiB)
Jobs: 1 (f=1): [W(1)][2.3%][eta 22m:13s]
writefile: (groupid=0, jobs=1): err= 0: pid=10174: Mon Oct 7 23:11:58 2024
write: IOPS=0, BW=781KiB/s (800kB/s)(25.0MiB/32765msec); 0 zone resets
slat (usec): min=162, max=29141, avg=1356.42, stdev=5788.61
clat (usec): min=1473, max=32672k, avg=1309198.25, stdev=6533901.21
lat (usec): min=1652, max=32672k, avg=1310554.67, stdev=6533664.34
clat percentiles (usec):
| 1.00th=[ 1467], 5.00th=[ 1614], 10.00th=[ 1614],
| 20.00th=[ 1647], 30.00th=[ 1680], 40.00th=[ 1762],
| 50.00th=[ 1893], 60.00th=[ 1909], 70.00th=[ 1975],
| 80.00th=[ 2008], 90.00th=[ 2147], 95.00th=[ 16188],
| 99.00th=[17112761], 99.50th=[17112761], 99.90th=[17112761],
| 99.95th=[17112761], 99.99th=[17112761]
bw ( KiB/s): min=49152, max=49152, per=100.00%, avg=49152.00, stdev= 0.00, samples=1
iops : min= 48, max= 48, avg=48.00, stdev= 0.00, samples=1
lat (msec) : 2=76.00%, 4=16.00%, 20=4.00%, >=2000=4.00%
cpu : usr=0.02%, sys=0.00%, ctx=29, majf=0, minf=11
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 rwts: total=0,25,0,0 short=0,0,0,0 dropped=0,0,0,0
latency : target=0, window=0, percentile=100.00%, depth=1
Run status group 0 (all jobs):
WRITE: bw=781KiB/s (800kB/s), 781KiB/s-781KiB/s (800kB/s-800kB/s), io=25.0MiB (26.2MB), run=32765-32765msec
Disk stats (read/write):
dm-1: ios=0/24, sectors=0/49152, merge=0/0, ticks=0/80, in_queue=80, util=99.89%, aggrios=0/141, aggsectors=0/52128, aggrmerge=0/0, aggrticks=0/3148260, aggrin_queue=3148260, aggrutil=99.70%
md127: ios=0/141, sectors=0/52128, merge=0/0, ticks=0/3148260, in_queue=3148260, util=99.70%, aggrios=38/3282, aggsectors=309/26251, aggrmerge=0/0, aggrticks=12/32824, aggrin_queue=65493, aggrutil=99.77%
loop21: ios=44/3277, sectors=352/26209, merge=0/0, ticks=15/32874, in_queue=65594, util=99.77%
loop22: ios=72/3249, sectors=576/25985, merge=0/0, ticks=21/32741, in_queue=65343, util=99.40%
loop20: ios=0/3321, sectors=0/26561, merge=0/0, ticks=0/32858, in_queue=65543, util=99.71%When I hook up my old box to the same RAID using Ubuntu it transfers 39.0MB/s according to fio.
Device r/s rkB/s rrqm/s %rrqm r_await rareq-sz w/s wkB/s wrqm/s %wrqm w_await wareq-sz d/s dkB/s drqm/s %drqm d_await dareq-sz f/s f_await aqu-sz %util
loop20 0.00 0.00 0.00 0.00 0.00 0.00 1368.00 5472.00 0.00 0.00 1.52 4.00 0.00 0.00 0.00 0.00 0.00 0.00 4.00 109.00 2.52 51.20
loop21 0.00 0.00 0.00 0.00 0.00 0.00 1366.00 5464.00 0.00 0.00 0.34 4.00 0.00 0.00 0.00 0.00 0.00 0.00 2.00 35.50 0.54 14.00
loop22 0.00 0.00 0.00 0.00 0.00 0.00 1376.00 5504.00 0.00 0.00 5.59 4.00 0.00 0.00 0.00 0.00 0.00 0.00 6.00 193.17 8.85 122.00
md127 0.00 0.00 0.00 0.00 0.00 0.00 14.00 10796.00 0.00 0.00 534.29 771.14 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 7.48 132.80I'm uncertain how to diagnose what's causing this. When I do a sync_action check on Ubuntu or Arch, the speed is the same.I tried both kernels 6.8.7 and 6.11.2.
edit: I suspect it might be the AX88179A
[culex@Titan share]$ iperf -c 192.168.1.11
------------------------------------------------------------
Client connecting to 192.168.1.11, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[ 1] local 192.168.1.210 port 59160 connected with 192.168.1.11 port 5001
[ ID] Interval Transfer Bandwidth
[ 1] 0.0000-10.3027 sec 14.1 MBytes 11.5 Mbits/sec
[culex@Titan share]$ iperf -c 192.168.1.11
------------------------------------------------------------
Client connecting to 192.168.1.11, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[ 1] local 192.168.1.210 port 58666 connected with 192.168.1.11 port 5001
[ ID] Interval Transfer Bandwidth
[ 1] 0.0000-10.0522 sec 420 MBytes 351 Mbits/sec
Client connecting to 192.168.1.13, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[ 1] local 192.168.1.210 port 56552 connected with 192.168.1.13 port 5001
[ ID] Interval Transfer Bandwidth
[ 1] 0.0000-10.2295 sec 14.0 MBytes 11.5 Mbits/sec
[culex@Titan share]$ iperf -c 192.168.1.13
------------------------------------------------------------
Client connecting to 192.168.1.13, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[ 1] local 192.168.1.210 port 60200 connected with 192.168.1.13 port 5001
[ ID] Interval Transfer Bandwidth
[ 1] 0.0000-10.0309 sec 419 MBytes 351 Mbits/secupdate: I switched from the AX88179A driver to cdc_ncm and no more issue.
Last edited by FireCulex (2024-10-11 09:02:54)
Offline