No shipment notification, but Newegg just charged my credit card a few minutes ago.Did anyone who pre-ordered with Newegg actually have theirs ship today?
No shipment notification, but Newegg just charged my credit card a few minutes ago.Did anyone who pre-ordered with Newegg actually have theirs ship today?
pg_test_fsync resultjournal-test: (g=0): rw=write, bs=4K-4K/4K-4K/4K-4K, ioengine=libaio, iodepth=1
fio-2.2.10
Starting 1 process
Jobs: 1 (f=1): [W(1)] [100.0% done] [0KB/382.2MB/0KB /s] [0/97.8K/0 iops] [eta 00m:00s]
journal-test: (groupid=0, jobs=1): err= 0: pid=7783: Sun Oct 29 19:52:19 2017
write: io=11106MB, bw=379062KB/s, iops=94765, runt= 30001msec
slat (usec): min=0, max=46, avg= 1.04, stdev= 0.48
clat (usec): min=0, max=95, avg= 9.14, stdev= 3.65
lat (usec): min=8, max=96, avg=10.23, stdev= 3.75
clat percentiles (usec):
| 1.00th=[ 8], 5.00th=[ 8], 10.00th=[ 8], 20.00th=[ 8],
| 30.00th=[ 8], 40.00th=[ 8], 50.00th=[ 9], 60.00th=[ 9],
| 70.00th=[ 9], 80.00th=[ 9], 90.00th=[ 10], 95.00th=[ 12],
| 99.00th=[ 15], 99.50th=[ 46], 99.90th=[ 49], 99.95th=[ 50],
| 99.99th=[ 53]
bw (KB /s): min=231592, max=404816, per=99.95%, avg=378883.80, stdev=40305.43
lat (usec) : 2=0.01%, 4=0.01%, 10=87.60%, 20=11.46%, 50=0.88%
lat (usec) : 100=0.06%
cpu : usr=5.92%, sys=20.57%, ctx=2843044, majf=0, minf=15
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=0/w=2843058/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
latency : target=0, window=0, percentile=100.00%, depth=1
Run status group 0 (all jobs):
WRITE: io=11106MB, aggrb=379061KB/s, minb=379061KB/s, maxb=379061KB/s, mint=30001msec, maxt=30001msec
Disk stats (read/write):
nvme1n1: ios=42/2833887, merge=0/0, ticks=0/22988, in_queue=22928, util=76.46%
5 seconds per test
O_DIRECT supported on this platform for open_datasync and open_sync.
Compare file sync methods using one 8kB write:
(in wal_sync_method preference order, except fdatasync is Linux's default)
open_datasync 34082.670 ops/sec 29 usecs/op
fdatasync 32653.145 ops/sec 31 usecs/op
fsync 29887.415 ops/sec 33 usecs/op
fsync_writethrough n/a
open_sync 31385.443 ops/sec 32 usecs/op
Compare file sync methods using two 8kB writes:
(in wal_sync_method preference order, except fdatasync is Linux's default)
open_datasync 22007.384 ops/sec 45 usecs/op
fdatasync 24656.267 ops/sec 41 usecs/op
fsync 26058.545 ops/sec 38 usecs/op
fsync_writethrough n/a
open_sync 20995.057 ops/sec 48 usecs/op
Compare open_sync with different write sizes:
(This is designed to compare the cost of writing 16kB in different write
open_sync sizes.)
1 * 16kB open_sync write 27767.367 ops/sec 36 usecs/op
2 * 8kB open_sync writes 19522.926 ops/sec 51 usecs/op
4 * 4kB open_sync writes 10317.340 ops/sec 97 usecs/op
8 * 2kB open_sync writes 3880.826 ops/sec 258 usecs/op
16 * 1kB open_sync writes 1889.986 ops/sec 529 usecs/op
Test if fsync on non-write file descriptor is honored:
(If the times are similar, fsync() can sync data written on a different
descriptor.)
write, fsync, close 30976.020 ops/sec 32 usecs/op
write, close, fsync 31613.255 ops/sec 32 usecs/op
Non-sync'ed 8kB writes:
write 589719.610 ops/sec 2 usecs/op
sadly I've never seen the pg_test_fsync results on P4800x. what really interests me is the performance gap between 900p and P4800x.Blimey! 34082 iops in pg_test_fsync is just friggin insane!!! Thats 35 times!!!! more than Samsung SM961
I live in Shanghai, bought mine from taobao.com.@lni where did you get one from?
I feel like I should just fly to Zurich with a few.Best price in switzerland is about 670$ for the 280GB and not even in stock. :-(
So much for Newegg's "notify when in stock" feature. Thanks for the heads up.Ordered a 280gb from newEgg today, fingers crossed it comes next week Said in-stock, we'll see
Sadly Limit was only 1
I guess thats pretty much true for most of us. Definetly for me tooPS: ServeTheHome is definitely dangerous to my finances.