Group: Member
Post Group: Newbie
Posts: 1
Status:
|
NVME best virtual machine performance.
I'm using the Intel (R) Xeon (R) CPU E3-1270 v6 @ 3.80GHz node
NVME SAMSUNG 980 EVO PRO
driver=virtio io = native cache=none
Code But the speed in gives out only on vps
[root @ alex ~] # fio --randrepeat = 1 --ioengine = libaio --direct = 1 --gtod_reduce = 1 --name = test --filename = testio --bs = 4k --iodepth = 64 - size = 4G --readwrite = randread
test: (g = 0): rw = randread, bs = (R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine = libaio, iodepth = 64
fio-3.7
Starting 1 process
Jobs: 1 (f = 1): [r (1)] [100.0%] [r = 560MiB / s, w = 0KiB / s] [r = 143k, w = 0 IOPS] [eta 00m: 00s]
test: (groupid = 0, jobs = 1): err = 0: pid = 1012: Tue Nov 30 05:22:05 2021
read: IOPS = 142k, BW = 556MiB / s (583MB / s) (4096MiB / 7363msec)
bw (KiB / s): min = 528728, max = 576520, per = 99.71%, avg = 567975.50, stdev = 12652.63, samples = 14
iops: min = 132182, max = 144130, avg = 141993.86, stdev = 3163.15, samples = 14
cpu: usr = 20.69%, sys = 54.28%, ctx = 20394, majf = 0, minf = 95
IO depths: 1 = 0.1%, 2 = 0.1%, 4 = 0.1%, 8 = 0.1%, 16 = 0.1%, 32 = 0.1%,> = 64 = 100.0%
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 = 0.1%,> = 64 = 0.0%
issued rwts: total = 1,048576,0,0,0 short = 0,0,0,0 dropped = 0,0,0,0
latency: target = 0, window = 0, percentile = 100.00%, depth = 64
Run status group 0 (all jobs):
READ: bw = 556MiB / s (583MB / s), 556MiB / s-556MiB / s (583MB / s-583MB / s), io = 4096MiB (4295MB), run = 7363-7363msec
Disk stats (read / write):
vda: ios = 994246/39, merge = 0/26, ticks = 345099/3, in_queue = 345102, util = 98.66%
And the speed on the node
Code [root @ kvm-nd500 kvm] # fio --randrepeat = 1 --ioengine = libaio --direct = 1 --gtod_reduce = 1 --name = test --filename = testio --bs = 4k --iodepth = 64 --size = 4G --readwrite = randread
test: (g = 0): rw = randread, bs = (R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine = libaio, iodepth = 64
fio-3.7
Starting 1 process
test: Laying out IO file (1 file / 4096MiB)
Jobs: 1 (f = 1): [r (1)] [100.0%] [r = 1325MiB / s, w = 0KiB / s] [r = 339k, w = 0 IOPS] [eta 00m: 00s]
test: (groupid = 0, jobs = 1): err = 0: pid = 28119: Tue Nov 30 15:23:25 2021
read: IOPS = 336k, BW = 1311MiB / s (1374MB / s) (4096MiB / 3125msec)
bw (MiB / s): min = 1253, max = 1327, per = 100.00%, avg = 1312.22, stdev = 29.06, samples = 6
iops: min = 320806, max = 339920, avg = 335927.33, stdev = 7438.83, samples = 6
cpu: usr = 38.32%, sys = 61.59%, ctx = 373, majf = 0, minf = 93
IO depths: 1 = 0.1%, 2 = 0.1%, 4 = 0.1%, 8 = 0.1%, 16 = 0.1%, 32 = 0.1%,> = 64 = 100.0%
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 = 0.1%,> = 64 = 0.0%
issued rwts: total = 1,048576,0,0,0 short = 0,0,0,0 dropped = 0,0,0,0
latency: target = 0, window = 0, percentile = 100.00%, depth = 64
Run status group 0 (all jobs):
READ: bw = 1311MiB / s (1374MB / s), 1311MiB / s-1311MiB / s (1374MB / s-1374MB / s), io = 4096MiB (4295MB), run = 3125-3125msec
Disk stats (read / write):
nvme0n1: ios = 1034074/0, merge = 0/0, ticks = 58610/0, in_queue = 58610, util = 96.92%
How to increase the speed of NVME in virtual machines?
|