Re: very slow sync
"Peter T. Breuer" <[email protected]>
| Newsgroups | gmane.linux.enbd.general |
|---|---|
| Message-ID | <[email protected]> |
"Also sprach Hegedus Gabor:" > 2005-02-01, k keltez_ssel 16:35-kor Peter T. Breuer ezt _rta: > > The sync speed is really up to raid1, not anyone else. I expect you > > have not asked raid1 to go any faster than that. Look in > > /proc/sys/dev/raid! > hygy@uml-rg-fw2:~$ cat /proc/sys/dev/raid/speed_limit_max > 100000 > hygy@uml-rg-fw2:~$ cat /proc/sys/dev/raid/speed_limit_min > 100 Then that's probably your problem! You might want to change that. > > None of that means very much to me :-(. What does enbd say? Show the > > output from nbdinfo. > hygy@uml-rg-fw2:~$ cat /proc/nbdinfo > Device a: Open > [a] State: signed, rw, enabled, validated, plug, acct, last error 0, > lives 0, bp 0 You haven't turned on merge requests ... > [a] Queued: +0R/0W curr (check 0R/0W) +248R/1024W max > [a] Buffersize: 262144 (sectors=512, blocks=512) > [a] Blocksize: 512 (log=9) And the blocksize is tiny! What? How? That's most unusual. Are you running xfs or something? > [a] Size: 512000KB > [a] Blocks: 0 > [a] Sockets: 4 (+) (+) (+) (*) > [a] Requested: 1.9644M (496K) (491K) (511K) (511K) 1.030MR/955.4KW max 8 > [a] Despatched: 1.9644M (496K) (491K) (511K) (511K) 1.030MR/955.4KW md5 > 10.5KW (26 eq, 10.4K ne, 0 dn) > [a] Errored: 0 (0) (0) (0) (0) 0+0 > [a] Pending: 0 (0) (0) (0) (0) 0R/0W+0R/0W > [a] B/s now: 0 (0R+0W) > [a] B/s ave: 242K (127KR+141KW) > [a] B/s max: 6.06M (6.06MR+4.16MW) > [a] Spectrum: 80%2 19%8 Yes, well, all the requests coming through are for 1KB or 4KB. I'm not sure how you chose 512B as blocksize. I'd simply turn on merge_requests, rather than change it, since I'm sure you have a good reason! Maybe set it to about 128. Peter