Re: [opensource-dev] before opena Jira, APR
Altair Sythos Memo wrote: ... 2010-08-31T21:02:02Z WARNING: ll_apr_warn_status: APR: Too many open files 2010-08-31T21:02:02Z WARNING: open: Attempting to open filename: /home/user/.secondlife/cache/texturecache/texture.entries ... not so sure anyway is a viewer problem of something specific to my linuxbox... is why i'm asking here if somebody else match this kind of crash with latest build This is a genuine problem. Please file it in jira. Any eyes on this would be welcome. It seems to have popped up recently - it may be related to the latest HTTP textures changes, not sure (perhaps leaking file handles, though lsof says we're still somewhat under the default limits). ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
On 1/09/2010 8:28 PM, Tofu Linden wrote: Altair Sythos Memo wrote: ... 2010-08-31T21:02:02Z WARNING: ll_apr_warn_status: APR: Too many open files 2010-08-31T21:02:02Z WARNING: open: Attempting to open filename: /home/user/.secondlife/cache/texturecache/texture.entries ... not so sure anyway is a viewer problem of something specific to my linuxbox... is why i'm asking here if somebody else match this kind of crash with latest build This is a genuine problem. Please file it in jira. Any eyes on this would be welcome. It seems to have popped up recently - it may be related to the latest HTTP textures changes, not sure (perhaps leaking file handles, though lsof says we're still somewhat under the default limits). Hmm. It might not be an actual leak per-se... I've noticed in busy areas that the viewer will often hit a *lot* of parallel HTTP texture fetches. I'm not sure if there's a hard limit there, because my texture console can easily overflow with active texture-fetches. That's... what... 30+ and I'm guessing a minimum of two file-handles each right there (and gut feeling says there's probably closer to 3 involved). If there's no cap on the number of parallel HTTP texture fetches (or the cap is too large), then you'll see more simultaneous fetches for higher-latency users (as an artifact of each HTTP session taking longer to complete), all other things being equal. If that is the case, then it's likely to have a far lower incidence if you're on the continental USA. Altair... you're in southern Europe, right? -- Tateru Nino http://dwellonit.taterunino.net/ ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
On 2010-09-01 7:12, Tateru Nino wrote: Hmm. It might not be an actual leak per-se... I've noticed in busy areas that the viewer will often hit a*lot* of parallel HTTP texture fetches. That's not very good http behavior, but I doubt that we can get it changed until the servers are properly supporting persistent connections. ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
On 1/09/2010 11:24 PM, Oz Linden (Scott Lawrence) wrote: On 2010-09-01 7:12, Tateru Nino wrote: Hmm. It might not be an actual leak per-se... I've noticed in busy areas that the viewer will often hit a*lot* of parallel HTTP texture fetches. That's not very good http behavior, but I doubt that we can get it changed until the servers are properly supporting persistent connections. Indeed. It's not exactly best-practice. Creating a priority list of textures and a configurable concurrent requests cap (default: 16?) would probably be the way to go. -- Tateru Nino http://dwellonit.taterunino.net/ ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
Il giorno 01/set/2010, alle ore 15:36, Tateru Nino tateru.n...@gmail.com ha scritto: On 1/09/2010 11:24 PM, Oz Linden (Scott Lawrence) wrote: On 2010-09-01 7:12, Tateru Nino wrote: Hmm. It might not be an actual leak per-se... I've noticed in busy areas that the viewer will often hit a **lot** of parallel HTTP texture fetches. That's not very good http behavior, but I doubt that we can get it changed until the servers are properly supporting persistent connections. Indeed. It's not exactly best-practice. Creating a priority list of textures and a configurable concurrent requests cap (default: 16?) would probably be the way to go. No, this is a client side problem in file handling, not an HTTP problem... You can parallelize billions of download, the fail (you can see in my logs) is in local filesystem file handling. Maybe there are more locks than suitable, the file/decoder handler must detect the limits and adapt the pipes. As seen in logs i suppose when a cached texture fail (timeout, bad crc for packet loss) the automatic clean try a clear_while_run wasting all openable files. If a http timeout or corrupted cached texture found the SINGLE download or the single fileust be deleted or dropped, not whole cache. If a running viewer have 600 opened tectures and got a timeout now re-open all to clean them, exceding the default 1024 limit I've noticed some grey textures too, i begin to think about the old (patched) bug about decoding fail without retry, the pipe hold the channell opened wasting resources -- Sent by iPhone ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
On 2010-09-01 9:46, Francesco Rabbi wrote: No, this is a client side problem in file handling, not an HTTP problem... You can parallelize billions of download, Whether or not you _can_, you _shouldn't_. The HTTP spec is quite clear on this point. We'd get much better performance than we're getting now if we fixed the servers to support persistent connections; there's a lot of overhead in setting up a new connection - extra round trips plus TCP slow-start. ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
On 2/09/2010 12:20 AM, Oz Linden (Scott Lawrence) wrote: On 2010-09-01 9:46, Francesco Rabbi wrote: No, this is a client side problem in file handling, not an HTTP problem... You can parallelize billions of download, Whether or not you _can_, you _shouldn't_. The HTTP spec is quite clear on this point. RFC2616 makes for great reading, and the *majority* of it is superbly thought through. I spent years with a copy close-to-hand at all times. We'd get much better performance than we're getting now if we fixed the servers to support persistent connections; there's a lot of overhead in setting up a new connection - extra round trips plus TCP slow-start. Concur. However, persistent connections (and possibly pipelining) will pretty much mean that you'll need to make sure you're maintaining a priority-queue of textures to fetch. Otherwise it will *feel* slower to the end-user even if it is actually faster in total fetch-and-render time. I've been down this road before. -- Tateru Nino http://dwellonit.taterunino.net/ ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
On 2010-09-01 10:36, Tateru Nino wrote: On 2/09/2010 12:20 AM, Oz Linden (Scott Lawrence) wrote: On 2010-09-01 9:46, Francesco Rabbi wrote: No, this is a client side problem in file handling, not an HTTP problem... You can parallelize billions of download, Whether or not you _can_, you _shouldn't_. The HTTP spec is quite clear on this point. RFC2616 makes for great reading, and the *majority* of it is superbly thought through. I spent years with a copy close-to-hand at all times. We'd get much better performance than we're getting now if we fixed the servers to support persistent connections; there's a lot of overhead in setting up a new connection - extra round trips plus TCP slow-start. Concur. However, persistent connections (and possibly pipelining) will pretty much mean that you'll need to make sure you're maintaining a priority-queue of textures to fetch. Otherwise it will *feel* slower to the end-user even if it is actually faster in total fetch-and-render time. I've been down this road before. Correct, but that's also something we should improve anyway - doing a better job of prioritizing which textures are loaded and in what order could make things _seem_ faster, even if the total time was the same. Doing both that and the connection handling together would be a big win (file under Faster). ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
Il giorno 01/set/2010, alle ore 16:47, Oz Linden (Scott Lawrence) o...@lindenlab.com ha scritto: Correct, but that's also something we should improve anyway - doing a better job of prioritizing which textures are loaded and in what order could make things _seem_ faster, even if the total time was the same. Doing both that and the connection handling together would be a big win (file under Faster). May be usefull do something like old windlight... The area visible by avatar (cam or mouselook) should be splitted in slices and textures should be downloaded starting from closest slice 16 textures each 512Kbps of inbound network speed (client setup). A system for fallback on single texture if corrupted or timed out will be great... -- Sent by iPhone ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
Re: [opensource-dev] before opena Jira, APR
On Wed, 01 Sep 2010 11:28:42 +0100 Tofu Linden t...@lindenlab.com wrote: Altair Sythos Memo wrote: ... 2010-08-31T21:02:02Z WARNING: ll_apr_warn_status: APR: Too many open files 2010-08-31T21:02:02Z WARNING: open: Attempting to open filename: /home/user/.secondlife/cache/texturecache/texture.entries ... not so sure anyway is a viewer problem of something specific to my linuxbox... is why i'm asking here if somebody else match this kind of crash with latest build This is a genuine problem. Please file it in jira. Any eyes on this would be welcome. It seems to have popped up recently - it may be related to the latest HTTP textures changes, not sure (perhaps leaking file handles, though lsof says we're still somewhat under the default limits). http://jira.secondlife.com/browse/VWR-22757 added info, but i thyink lsof isn't right tools, if on an empty sim (1 texture: the gorund) of if i'm in a city fullfit of textures lsof report about same numbers. is there a debug info to activate to read files opened by HTTP handler? ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges
[opensource-dev] before opena Jira, APR
got a lot of crashes on a linux 32 system [cut] 2010-08-31T21:02:02Z INFO: purgeAllTextures: Deleting files in directory: /home/user/.secondlife/cache/texturecache/f 2010-08-31T21:02:02Z WARNING: ll_apr_warn_status: APR: Too many open files 2010-08-31T21:02:02Z WARNING: open: Attempting to open filename: /home/user/.secondlife/cache/texturecache/texture.entries 2010-08-31T21:02:02Z INFO: purgeAllTextures: The entire texture cache is cleared. 2010-08-31T21:02:02Z WARNING: ll_apr_warn_status: APR: Too many open files 2010-08-31T21:02:02Z WARNING: open: Attempting to open filename: /home/user/.secondlife/cache/texturecache/texture.entries 2010-08-31T21:02:02Z WARNING: write: apr mFile is removed by somebody else. Can not write. 2010-08-31T21:02:02Z WARNING: clearCorruptedCache: the texture cache is corrupted, need to be cleared. 2010-08-31T21:02:02Z INFO: purgeAllTextures: Deleting files in directory: /home/user/.secondlife/cache/texturecache/0 [/cut] all this repeated some times, then viewer crash badly double checked limits on my user, none reasonable related to number of files opened or sort off... build Second Life 2.1.2 (208719) Aug 30 2010 09:18:15 (Second Life Development) not so sure anyway is a viewer problem of something specific to my linuxbox... is why i'm asking here if somebody else match this kind of crash with latest build ___ Policies and (un)subscribe information available here: http://wiki.secondlife.com/wiki/OpenSource-Dev Please read the policies before posting to keep unmoderated posting privileges