<div dir="ltr">Hi.<div><br></div><div>Ok, df was incorrect because one of servers went into <defunct> (zombie) state, and df waits until the software done writing or releases writing handles.</div><div><br></div><div>
I'm giving GlusterFS a 3rd try, but these issues are very critical:</div><div><br></div><div>1) 0 size files</div><div>2) AFR losts some of the files - after a day of running there is a mismatch between the one server and the second one</div>
<div>3) Possible memory leak</div><div>4) Server going to defunct state</div><div><br></div><div><br></div><div>Any idea how it would be the best to diagnose and advance with these issues?</div><div><br></div><div>Thanks!</div>
<div><br><div class="gmail_quote">2009/3/31 Stas Oskin <span dir="ltr"><<a href="mailto:stas.oskin@gmail.com">stas.oskin@gmail.com</a>></span><br><blockquote class="gmail_quote" style="margin:0 .8ex;border-left:1px #ccc solid;border-right:1px #ccc solid;padding-left:1ex;padding-right:1ex">
<div dir="rtl"><div dir="ltr">Hi.</div><div dir="ltr"><br></div><div dir="ltr">I'm receiving very strange results with AFR:</div><div dir="ltr"><br></div><div dir="ltr">Client:</div><div dir="ltr"><br></div><div dir="ltr">
df -h: </div><div dir="ltr">Filesystem Size Used Avail Use% Mounted on</div><div dir="ltr">glusterfs 31G 28G 1020M 97% /mnt/media</div><div dir="ltr"><br></div><div dir="ltr">du -sh for mounted directory:</div>
<div dir="ltr">1007M (ompletely different)</div><div dir="ltr"><br></div><div dir="ltr"><br></div><div dir="ltr">Server 1:</div><div dir="ltr">df -h:</div><div dir="ltr">Filesystem Size Used Avail Use% Mounted on</div>
<div dir="ltr">/dev/hda4 31G 28G 1021M 97% /media</div><div dir="ltr"><br></div><div dir="ltr">du -sh for exported directory:</div><div dir="ltr">1007M (completely different here too!)</div><div dir="ltr">
<br></div><div dir="ltr"><br></div><div dir="ltr">Server 2:</div><div dir="ltr">Filesystem Size Used Avail Use% Mounted on</div><div dir="ltr">/dev/hda4 31G 1.1G 28G 4% /media</div><div dir="ltr">
<br></div><div dir="ltr">du -sh for exported directory:</div><div dir="ltr">920M</div><div dir="ltr"><br></div><div dir="ltr"><br></div><div dir="ltr">1) It's just like the AFR completely broken.</div><div dir="ltr">
2) What's more strange, that the server 1 has completely different stats for 2 commands - first time that I see it.</div>
<div dir="ltr">3) This happened after the disk space on GlusterFS got completely full.</div><div dir="ltr"><br></div><div dir="ltr"><br></div><div dir="ltr">I also have some files with 0 sizes, so the other mentioned problem exist too. The used version is 2RC7.</div>
<div dir="ltr"><br></div><div dir="ltr">How can these issues be tracked down? They are very serious, and basically influent the whole cluster reliability.</div><div dir="ltr"><br></div><div dir="ltr">Regards.</div></div>
</blockquote></div></div></div>