Indeed, if the async blocksize if 16M then the proxy will send out 4 reads
of 16M at once which, unfortuantely, will stress Ceph out. It should send
one of 64M then Ceph will be doing the smallest amount of work per read.
Andy
On Thu, 23 Jul 2020, Wei Yang wrote:
> Just to put a comment here since Raja, Andy and I are using another e-mail thread for discussion because it potentially involves site detailed configuration.
>
> What I see from those configs is that the CEPH block site is 64M (as Raja confirmed), but the CEPH-xrootd gateway using 16M for async IO. The Xcache use 64M for async IO and 16M for pfc.blocksize. So I am suggesting Raja to change all of them to 64M.
>
> regards,
> --
> Wei Yang | [log in to unmask]<mailto:[log in to unmask]> | 650-926-3338(O)
>
> On 7/23/20, 9:23 AM, "Brian P Bockelman" <[log in to unmask]<mailto:[log in to unmask]>> wrote:
>
>
>
>
> --
> You are receiving this because you are subscribed to this thread.
> Reply to this email directly or view it on GitHub:
> https://github.com/xrootd/xrootd/issues/1259#issuecomment-663140433
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
[
{
"@context": "http://schema.org",
"@type": "EmailMessage",
"potentialAction": {
"@type": "ViewAction",
"target": "https://github.com/xrootd/xrootd/issues/1259#issuecomment-663173625",
"url": "https://github.com/xrootd/xrootd/issues/1259#issuecomment-663173625",
"name": "View Issue"
},
"description": "View this Issue on GitHub",
"publisher": {
"@type": "Organization",
"name": "GitHub",
"url": "https://github.com"
}
}
]
Use REPLY-ALL to reply to list
To unsubscribe from the XROOTD-DEV list, click the following link:
https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-DEV&A=1