Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Test this options
net {
max-buffers 8000;
max-epoch-size 8000;
max-buffers 16000;
max-epoch-size 16000;
unplug-watermark 16;
unplug-watermark 16000;
}
disk {
no-disk-barrier;
no-disk-flushes;
}
syncer {
al-extents 3389;
}
El 04/01/16 a las 17:48, Ricardo Branco escribió:
> I have an odd situation with resync.
>
> Resync seems to always be limited to max 40MB/s, if I am doing both of
> my resources at the same time then both are at 40MB/s (total 80M), but
> never goes above this.
> If I copy a 20G file which is on drbd then the sync speed to the other
> server reaches 800GB/s, doing a dd gives similar results around 1GB/s.
> Does not matter what param I tweek i can not get the sync speed to be
> above 40MB/s.
> To test that cachecade is not getting in the way I have disabled it
> for tests but nothing changed.
>
> This server has been running 8.4.3 up to recently, now 8.4.6.
> Before the upgrade I am sure when I did a sync I saw much higher
> resync rates.
>
> The server setup is:
> 16x 3TB SAS 7.2k RAID 6 on LSI Megaraid 9271-4i (FBWC + CacheCade)
> 10G Ethernet direct link between servers
>
>
> Config:
> resource d0 {
> options {
> cpu-mask ""; # default
> on-no-data-accessible io-error; # default
> }
> net {
> protocol C; # default
> timeout 60; # 1/10 seconds, default
> max-epoch-size 2048; # default
> max-buffers 2048; # default
> unplug-watermark 128; # default
> connect-int 10; # seconds, default
> ping-int 10; # seconds, default
> sndbuf-size 0; # bytes, default
> rcvbuf-size 0; # bytes, default
> ko-count 7; # default
> allow-two-primaries no; # default
> cram-hmac-alg ""; # default
> shared-secret ""; # default
> after-sb-0pri disconnect; # default
> after-sb-1pri disconnect; # default
> after-sb-2pri disconnect; # default
> always-asbp no; # default
> rr-conflict disconnect; # default
> ping-timeout 5; # 1/10 seconds, default
> data-integrity-alg ""; # default
> tcp-cork yes; # default
> on-congestion block; # default
> congestion-fill 0s; # bytes, default
> congestion-extents 1237; # default
> csums-alg ""; # default
> csums-after-crash-only no; # default
> verify-alg "crc32c";
> use-rle yes; # default
> socket-check-timeout 0; # default
> }
> _remote_host {
> address ipv4 192.168.10.1:7789;
> }
> _this_host {
> address ipv4 192.168.10.2:7789;
> volume 0 {
> device minor 1;
> disk "/dev/vg_raid1/drbd0";
> meta-disk internal;
> disk {
> size 0s; # bytes, default
> max-bio-bvecs 0; # default
> on-io-error detach; # default
> fencing resource-only;
> disk-barrier no; # default
> disk-flushes no;
> disk-drain yes; # default
> md-flushes yes; # default
> resync-rate 512000k; # bytes/second
> resync-after -1; # default
> al-extents 1237; # default
> al-updates yes; # default
> c-plan-ahead 0; # 1/10 seconds
> c-delay-target 10; # 1/10 seconds, default
> c-fill-target 100s; # bytes, default
> c-max-rate 102400k; # bytes/second, default
> c-min-rate 250k; # bytes/second, default
> disk-timeout 0; # 1/10 seconds, default
> read-balancing prefer-local; # default
> }
> }
> }
> }
>
> 0: cs:SyncTarget ro:Secondary/Primary ds:Inconsistent/UpToDate C r-----
> ns:0 nr:262361424 dw:325178528 dr:0 al:0 bm:0 lo:0 pe:0 ua:0 ap:0
> ep:1 wo:d oos:11362364
> [==>.................] sync'ed: 15.5% (11096/13116)M
> finish: 0:05:15 speed: 35,944 (31,844) want: 512,000 K/sec
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.linbit.com/pipermail/drbd-user/attachments/20160105/5916e0d2/attachment.htm>