Displaying 6 results from an estimated 6 matches for "203s".
Did you mean:
203
2019 Apr 11
3
nbdkit, VDDK, extents, readahead, etc
...8 bits/s
Without noextents (ie. rely on qemu-img skipping sparse bits):
elapsed time: 237.41 s
read: 833 ops, 1734345216 bytes, 5.84423e+07 bits/s
extents: 70 ops, 135654246400 bytes, 4.57114e+09 bits/s
Note if you deduct 120 seconds (see point (1) above) from these times
then it goes from 203s -> 117s, about a 40% saving. We can likely do
better by having > 32 bit requests and qemu not using
NBD_CMD_FLAG_REQ_ONE.
(4) We can also add nbdkit-readahead-filter in both cases to see if
that helps or not:
With noextents and readahead:
elapsed time: 325.358 s
read: 265 ops, 1717986...
2019 Apr 12
2
Re: nbdkit, VDDK, extents, readahead, etc
...parse bits):
> >
> > elapsed time: 237.41 s
> > read: 833 ops, 1734345216 bytes, 5.84423e+07 bits/s
> > extents: 70 ops, 135654246400 bytes, 4.57114e+09 bits/s
> >
> >Note if you deduct 120 seconds (see point (1) above) from these times
> >then it goes from 203s -> 117s, about a 40% saving. We can likely do
> >better by having > 32 bit requests and qemu not using
> >NBD_CMD_FLAG_REQ_ONE.
> >
> How did you run qemu-img?
The full command was:
LD_LIBRARY_PATH=vmware-vix-disklib-distrib/lib64 \
./nbdkit -r -U - vddk file="[da...
2019 Apr 15
1
Re: nbdkit, VDDK, extents, readahead, etc
...time: 237.41 s
> >>> read: 833 ops, 1734345216 bytes, 5.84423e+07 bits/s
> >>> extents: 70 ops, 135654246400 bytes, 4.57114e+09 bits/s
> >>>
> >>>Note if you deduct 120 seconds (see point (1) above) from these times
> >>>then it goes from 203s -> 117s, about a 40% saving. We can likely do
> >>>better by having > 32 bit requests and qemu not using
> >>>NBD_CMD_FLAG_REQ_ONE.
> >>>
> >>How did you run qemu-img?
> >
> >The full command was:
> >
> >LD_LIBRARY_PATH=vmw...
2019 Apr 15
0
Re: nbdkit, VDDK, extents, readahead, etc
...gt;> > elapsed time: 237.41 s
>> > read: 833 ops, 1734345216 bytes, 5.84423e+07 bits/s
>> > extents: 70 ops, 135654246400 bytes, 4.57114e+09 bits/s
>> >
>> >Note if you deduct 120 seconds (see point (1) above) from these times
>> >then it goes from 203s -> 117s, about a 40% saving. We can likely do
>> >better by having > 32 bit requests and qemu not using
>> >NBD_CMD_FLAG_REQ_ONE.
>> >
>> How did you run qemu-img?
>
>The full command was:
>
>LD_LIBRARY_PATH=vmware-vix-disklib-distrib/lib64 \
>...
2019 Apr 12
0
Re: nbdkit, VDDK, extents, readahead, etc
...(ie. rely on qemu-img skipping sparse bits):
>
> elapsed time: 237.41 s
> read: 833 ops, 1734345216 bytes, 5.84423e+07 bits/s
> extents: 70 ops, 135654246400 bytes, 4.57114e+09 bits/s
>
>Note if you deduct 120 seconds (see point (1) above) from these times
>then it goes from 203s -> 117s, about a 40% saving. We can likely do
>better by having > 32 bit requests and qemu not using
>NBD_CMD_FLAG_REQ_ONE.
>
How did you run qemu-img? I think on slow CPU and fast disk this might be even
bigger difference if qemu-img can write whatever it gets and not searching fo...
2014 May 13
0
Samba 4.1 id->user mapping slow (using winbind)
...SEEK_SET, start=37196,
len=1}) = 0
fcntl(11, F_SETLKW, {type=F_RDLCK, whence=SEEK_SET, start=6032,
len=1}) = 0
fcntl(11, F_SETLKW, {type=F_UNLCK, whence=SEEK_SET, start=6032,
len=1}) = 0
writev(44,
[{"\5\0\2\3\20\0\0\0P\0\20\0\273])\1\30\0\0\0\0\0\0\0h\345\213\f\334\203s\223"...,
80}], 1) = 80
epoll_wait(9, {{EPOLLIN, {u32=1836735552, u64=140507396856896}}}, 1,
30000) = 1
readv(44, [{"\5\0\0\3\20\0\0\0P\0", 10}], 1) = 10
readv(44,
[{"\20\0\274])\1\26\0\0\0\0\0\24\0008\3412\232u\322\322\253\245I\10k\344\312\312B\22\307&quo...